The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)research.However,the high computational demands of most SR techniques hinder ...The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)research.However,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction performance.These methods commonly use standard convolutions,which increase the convolutional operation cost of the model.In this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this problem.Specifically,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image reconstruction.Additionally,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature representations.Inspired by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an image.MFFB can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature information.As the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.展开更多
Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has...Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.展开更多
Digital in-line holographic microscopy(DIHM)is a widely used interference technique for real-time reconstruction of living cells’morphological information with large space-bandwidth product and compact setup.However,...Digital in-line holographic microscopy(DIHM)is a widely used interference technique for real-time reconstruction of living cells’morphological information with large space-bandwidth product and compact setup.However,the need for a larger pixel size of detector to improve imaging photosensitivity,field-of-view,and signal-to-noise ratio often leads to the loss of sub-pixel information and limited pixel resolution.Additionally,the twin-image appearing in the reconstruction severely degrades the quality of the reconstructed image.The deep learning(DL)approach has emerged as a powerful tool for phase retrieval in DIHM,effectively addressing these challenges.However,most DL-based strategies are datadriven or end-to-end net approaches,suffering from excessive data dependency and limited generalization ability.Herein,a novel multi-prior physics-enhanced neural network with pixel super-resolution(MPPN-PSR)for phase retrieval of DIHM is proposed.It encapsulates the physical model prior,sparsity prior and deep image prior in an untrained deep neural network.The effectiveness and feasibility of MPPN-PSR are demonstrated by comparing it with other traditional and learning-based phase retrieval methods.With the capabilities of pixel super-resolution,twin-image elimination and high-throughput jointly from a single-shot intensity measurement,the proposed DIHM approach is expected to be widely adopted in biomedical workflow and industrial measurement.展开更多
In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural cavities.However,in clini...In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural cavities.However,in clinical operating environments,endoscopic images often suffer from challenges such as low texture,uneven illumination,and non-rigid structures,which affect feature observation and extraction.This can severely impact surgical navigation or clinical diagnosis due to missing feature points in endoscopic images,leading to treatment and postoperative recovery issues for patients.To address these challenges,this paper introduces,for the first time,a Cross-Channel Multi-Modal Adaptive Spatial Feature Fusion(ASFF)module based on the lightweight architecture of EfficientViT.Additionally,a novel lightweight feature extraction and matching network based on attention mechanism is proposed.This network dynamically adjusts attention weights for cross-modal information from grayscale images and optical flow images through a dual-branch Siamese network.It extracts static and dynamic information features ranging from low-level to high-level,and from local to global,ensuring robust feature extraction across different widths,noise levels,and blur scenarios.Global and local matching are performed through a multi-level cascaded attention mechanism,with cross-channel attention introduced to simultaneously extract low-level and high-level features.Extensive ablation experiments and comparative studies are conducted on the HyperKvasir,EAD,M2caiSeg,CVC-ClinicDB,and UCL synthetic datasets.Experimental results demonstrate that the proposed network improves upon the baseline EfficientViT-B3 model by 75.4%in accuracy(Acc),while also enhancing runtime performance and storage efficiency.When compared with the complex DenseDescriptor feature extraction network,the difference in Acc is less than 7.22%,and IoU calculation results on specific datasets outperform complex dense models.Furthermore,this method increases the F1 score by 33.2%and accelerates runtime by 70.2%.It is noteworthy that the speed of CMMCAN surpasses that of comparative lightweight models,with feature extraction and matching performance comparable to existing complex models but with faster speed and higher cost-effectiveness.展开更多
Objective:To explore the implementation of gastrointestinal endoscopy technology and endoscopic narrow-band imaging(NBI)in the early screening of gastric cancer and to observe and study their application effects.Metho...Objective:To explore the implementation of gastrointestinal endoscopy technology and endoscopic narrow-band imaging(NBI)in the early screening of gastric cancer and to observe and study their application effects.Methods:During the period from March 2023 to August 2023,312 patients who received gastroscopy in the Kunming Guandu District People’s Hospital were selected,and they underwent both conventional gastroscopy and endoscopic NBI,with clinicopathological tissue biopsy serving as the gold standard.The application value for early screening of gastric cancer was observed and analyzed.Results:The scoring data showed that the clarity of gastric mucosal glandular tube structure,microvascular structure clarity,and lesion contour scoring data of conventional gastroscopy were lower than those of the NBI technology(P<0.05).The screening rate of pathological biopsy in 312 patients was 18.59%(58 cases).Conventional gastroscopy showed a screening rate of 11.53%(36 cases),while NBI technology examined a screening rate of 17.63%(55 cases),and the two-by-two comparison of the screening rate data of the three groups was not statistically significant(P>0.05).The sensitivity,specificity,accuracy,positive predictive value,and negative predictive value of conventional gastroscopy appeared to be lower than those of NBI technology(P<0.05).Conclusion:In the early screening of gastric cancer,endoscopic NBI technology can be applied to patients.Compared with conventional gastroscopy,it provides a clearer visualization of the structure of the gastric mucosal glandular structure and microvascular structure,with a certain screening rate.Additionally,its sensitivity,specificity,accuracy,positive predictive value,and negative predictive value are higher,demonstrating outstanding effectiveness.展开更多
Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,w...Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.展开更多
Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the r...Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the rapid progress in convolutional neural networks(CNNs)has achieved superior performance in the area of medical image super-resolution.However,the traditional CNN approaches use interpolation techniques as a preprocessing stage to enlarge low-resolution magnetic resonance(MR)images,adding extra noise in the models and more memory consumption.Furthermore,conventional deep CNN approaches used layers in series-wise connection to create the deeper mode,because this later end layer cannot receive complete information and work as a dead layer.In this paper,we propose Inception-ResNet-based Network for MRI Image Super-Resolution known as IRMRIS.In our proposed approach,a bicubic interpolation is replaced with a deconvolution layer to learn the upsampling filters.Furthermore,a residual skip connection with the Inception block is used to reconstruct a high-resolution output image from a low-quality input image.Quantitative and qualitative evaluations of the proposed method are supported through extensive experiments in reconstructing sharper and clean texture details as compared to the state-of-the-art methods.展开更多
Automatic segmentation of early esophagus cancer(EEC)in gastrointestinal endoscopy(GIE)images is a critical and challenging task in clinical settings,which relies primarily on labor-intensive and time-consuming routin...Automatic segmentation of early esophagus cancer(EEC)in gastrointestinal endoscopy(GIE)images is a critical and challenging task in clinical settings,which relies primarily on labor-intensive and time-consuming routines.EEC has often been diagnosed at the late stage since early signs of cancer are not obvious,resulting in low survival rates.This work proposes a deep learning approach based on the U-Net++method to segment EEC in GIE images.A total of 2690 GIE images collected from 617 patients at the Digestive Endoscopy Center,West China Hospital of Sichuan University,China,have been utilized.The experimental result shows that our proposed method achieved promising results.Furthermore,the comparison has been made between the proposed and other U-Net-related methods using the same dataset.The mean and standard deviation(SD)of the dice similarity coefficient(DSC),intersection over union(IoU),precision(Pre),and recall(Rec)achieved by the proposed framework were DSC(%)=94.62±0.02,IoU(%)=90.99±0.04,Pre(%)=94.61±0.04,and Rec(%)=95.00±0.02,respectively,outperforming the others.The proposed method has the potential to be applied in EEC automatic diagnoses.展开更多
BACKGROUND It has been confirmed that three-dimensional(3D)imaging allows easier identification of bile duct anatomy and intraoperative guidance of endoscopic retrograde cholangiopancreatography(ERCP),which reduces th...BACKGROUND It has been confirmed that three-dimensional(3D)imaging allows easier identification of bile duct anatomy and intraoperative guidance of endoscopic retrograde cholangiopancreatography(ERCP),which reduces the radiation dose and procedure time with improved safety.However,current 3D biliary imaging does not have good real-time fusion with intraoperative imaging,a process meant to overcome the influence of intraoperative respiratory motion and guide navigation.The present study explored the feasibility of real-time continuous image-guided ERCP.AIM To explore the feasibility of real-time continuous image-guided ERCP.METHODS We selected 23D-printed abdominal biliary tract models with different structures to simulate different patients.The ERCP environment was simulated for the biliary phantom experiment to create a navigation system,which was further tested in patients.In addition,based on the estimation of the patient’s respiratory motion,preoperative 3D biliary imaging from computed tomography of 18 patients with cholelithiasis was registered and fused in real-time with 2D fluoroscopic sequence generated by the C-arm unit during ERCP.RESULTS Continuous image-guided ERCP was applied in the biliary phantom with a registration error of 0.46 mm±0.13 mm and a tracking error of 0.64 mm±0.24mm.After estimating the respiratory motion,3D/2D registration accurately transformed preoperative 3D biliary images to each image in the X-ray image sequence in real-time in 18 patients,with an average fusion rate of 88%.CONCLUSION Continuous image-guided ERCP may be an effective approach to assist the operator and reduce the use of X-ray and contrast agents.展开更多
Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural netwo...Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural network based on a generative adversarial network(GAN).The generator employs a U-Net-based network,which integrates Dense Net for the downsampling component.The proposed method has excellent properties,for example,the network model is trained with several different datasets of biological structures;the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging;and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets.In addition,experimental results showed that the method improved the resolution of caveolin-coated pits(CCPs)structures from 264 nm to 138 nm,a 1.91-fold increase,and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.展开更多
Blast furnace(BF)burden surface contains the most abundant,intuitive and credible smelting information and acquiring high-definition and high-brightness optical images of which is essential to realize precise material...Blast furnace(BF)burden surface contains the most abundant,intuitive and credible smelting information and acquiring high-definition and high-brightness optical images of which is essential to realize precise material charging control,optimize gas flow distribution and improve ironmaking efficiency.It has been challengeable to obtain high-quality optical burden surface images under high-temperature,high-dust,and extremelydim(less than 0.001 Lux)environment.Based on a novel endoscopic sensing detection idea,a reverse telephoto structure starlight imaging system with large field of view and large aperture is designed.Combined with a water-air dual cooling intelligent self-maintenance protection device and the imaging system,a starlight high-temperature industrial endoscope is developed to obtain clear optical burden surface images stably under the harsh environment.Based on an endoscope imaging area model,a material flow trajectory model and a gas-dust coupling distribution model,an optimal installation position and posture configuration method for the endoscope is proposed,which maximizes the effective imaging area and ensures large-area,safe and stable imaging of the device in a confined space.Industrial experiments and applications indicate that the proposed method obtains clear and reliable large-area optical burden surface images and reveals new BF conditions,providing key data support for green iron smelting.展开更多
This editorial elaborates on the current and future applications of linear endoscopic ultrasound(EUS),a substantial diagnostic and therapeutic modality for various anatomical regions.The scope of endosonographic asses...This editorial elaborates on the current and future applications of linear endoscopic ultrasound(EUS),a substantial diagnostic and therapeutic modality for various anatomical regions.The scope of endosonographic assessment is broad and,among other factors,allows for the evaluation of the mediastinal anatomy and related pathologies,such as mediastinal lymphadenopathy and the staging of central malignant lung lesions.Moreover,EUS assessment has proven more accurate in detecting small lesions missed by standard imaging examinations,such as computed tomography or magnetic resonance imaging.We focus on its current uses in the mediastinum,including lung and esophageal cancer staging,as well as evaluating mediastinal lymphadenopathy and submucosal lesions.The editorial also explores future perspectives of EUS in mediastinal examination,including ultrasound-guided therapies,artificial intelligence integration,advancements in mediastinal modalities,and improved diagnostic approaches for various mediastinal lesions.展开更多
BACKGROUND Conventional magnifying endoscopy with narrow-band imaging(NBI)observation of the gastric body mucosa shows dominant patterns in relation to the regular arrangement of collecting venules,subepithelial capil...BACKGROUND Conventional magnifying endoscopy with narrow-band imaging(NBI)observation of the gastric body mucosa shows dominant patterns in relation to the regular arrangement of collecting venules,subepithelial capillary network,and gastric pits.AIM To evaluate the effectiveness of a new one-dual(near)focus,NBI mode in the assessment of the microscopic features of gastric body mucosa compared to conventional magnification.METHODS During 2021 and 2022,68 patients underwent proximal gastrointestinal endoscopy using magnification endoscopic modalities subsequently applying acetic acid(AA).The GIF-190HQ series NBI system with dual focus capability was used for the investigation of gastric mucosa.At the time of the endoscopy,the gastric body mucosa of all enrolled patients was photographed using the white light endoscopy(WLE),near focus(NF),NF-NBI,AA-NF,and AA-NF-NBI modes.RESULTS The WLE,NF and NF-NBI endoscopic modes for all patients(204 images)were classified in the same order into three groups.Two images from each patient for the AA-NF and AA-NF-NBI endoscopic modes were classified in the same order.According to all three observers who completed the work independently,NF magnification was significantly superior to WLE(P<0.01),and the NF-NBI mode was significantly superior to NF magnification(P<0.01).After applying AA,the three observers confirmed that AA-NF-NBI was significantly superior to AA-NF(P<0.01).Interobserver kappa values for WLE were 0.609,0.704,and 0.598,respectively and were 0.600,0.721,and 0.637,respectively,for NF magnification.For the NF-NBI mode,the values were 0.378,0.471,and 0.553,respectively.For AA-NF,they were 0.453,0.603,and 0.480,respectively,and for AA-NF-NBI,they were 0.643,0.506,and 0.354,respectively.CONCLUSION When investigating gastric mucosa in microscopic detail,NF-NBI was the most powerful endoscopic mode for assessing regular arrangement of collecting venules,subepithelial capillary network,and gastric pits among the five endoscopic modalities investigated in this study.AA-NF-NBI was the most powerful endoscopic mode for analyzing crypt opening and intervening part.展开更多
AIM:To develop a fuzzy classification method to score the texture features of pancreatic cancer in endoscopic ultrasonography(EUS)images and evaluate its utility in making prognosis judgments for patients with unresec...AIM:To develop a fuzzy classification method to score the texture features of pancreatic cancer in endoscopic ultrasonography(EUS)images and evaluate its utility in making prognosis judgments for patients with unresectable pancreatic cancer treated by EUS-guided interstitial brachytherapy.METHODS:EUS images from our retrospective database were analyzed.The regions of interest were drawn,and texture features were extracted,selected,and scored with a fuzzy classification method using a C++program.Then,patients with unresectable pancreatic cancer were enrolled to receive EUS-guided iodine 125 radioactive seed implantation.Their fuzzy classification scores,tumor volumes,and carbohydrate antigen 199(CA199)levels before and after the brachytherapy were recorded.The association between the changes in these parameters and overall survival was analyzed statistically.RESULTS:EUS images of 153 patients with pancreatic cancer and 63 non-cancer patients were analyzed.A total of 25 consecutive patients were enrolled,and they tolerated the brachytherapy well without any complications.There was a correlation between the change in the fuzzy classification score and overall survival(Spearman test,r=0.616,P=0.001),whereas no correlation was found to be significant between the change in tumor volume(P=0.663),CA199 level(P=0.659),and overall survival.There were 15 patients with a decrease in their fuzzy classification score after brachytherapy,whereas the fuzzy classification score increased in another 10 patients.There was a significant difference in overall survival between the two groups(67 d vs 151 d,P=0.001),but not in the change of tumor volume and CA199 level.CONCLUSION:Using the fuzzy classification method to analyze EUS images of pancreatic cancer is feasible,and the method can be used to make prognosis judgments for patients with unresectable pancreatic cancer treated by interstitial brachytherapy.展开更多
AIM: To compare the diagnostic yield of heterotopic gastric mucosa (HGM) in the cervical esophagus with conventional imaging (CI) and narrow-band imaging (NBI).
A super-resolution reconstruction approach of (SVD) technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. F...A super-resolution reconstruction approach of (SVD) technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function (PSF) matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar (SAR) images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio (SNR). Five versions of SVD algorithms, namely 1 ) using all singular values, 2) using the top 80% singular values, 3) using the top 50% singular values, 4) using the top 20% singular values and 5) using singular values s such that S2≥/max(s2)/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/(rinSNR)1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.展开更多
Single image super resolution(SISR)is an important research content in the field of computer vision and image processing.With the rapid development of deep neural networks,different image super-resolution models have ...Single image super resolution(SISR)is an important research content in the field of computer vision and image processing.With the rapid development of deep neural networks,different image super-resolution models have emerged.Compared to some traditional SISR methods,deep learning-based methods can complete the super-resolution tasks through a single image.In addition,compared with the SISR methods using traditional convolutional neural networks,SISR based on generative adversarial networks(GAN)has achieved the most advanced visual performance.In this review,we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics.Then,we review the improved network structures and loss functions of GAN-based perceptual SISR.Subsequently,the advantages and disadvantages of different networks are analyzed by multiple comparative experiments.Finally,we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.展开更多
Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent...Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images.This paper presents a color super-resolution reconstruction method combining the L2/3 sparse regularization model with color channel constraints.The method converts the low-resolution color image from RGB to YCbCr.The L2/3 sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image.Then the color channel-constraint method is adopted to remove artifacts of the reconstructed highresolution image.The method not only ensures the reconstruction quality of the color image details,but also improves the removal ability of color artifacts.The experimental results on natural images validate that our method has improved both subjective and objective evaluation.展开更多
Although there has been a great breakthrough in the accuracy and speed of super-resolution(SR)reconstruction of a single image by using a convolutional neural network,an important problem remains unresolved:how to res...Although there has been a great breakthrough in the accuracy and speed of super-resolution(SR)reconstruction of a single image by using a convolutional neural network,an important problem remains unresolved:how to restore finer texture details during image super-resolution reconstruction?This paper proposes an Enhanced Laplacian Pyramid Generative Adversarial Network(ELSRGAN),based on the Laplacian pyramid to capture the high-frequency details of the image.By combining Laplacian pyramids and generative adversarial networks,progressive reconstruction of super-resolution images can be made,making model applications more flexible.In order to solve the problem of gradient disappearance,we introduce the Residual-in-Residual Dense Block(RRDB)as the basic network unit.Network capacity benefits more from dense connections,is able to capture more visual features with better reconstruction effects,and removes BN layers to increase calculation speed and reduce calculation complexity.In addition,a loss of content driven by perceived similarity is used instead of content loss driven by spatial similarity,thereby enhancing the visual effect of the super-resolution image,making it more consistent with human visual perception.Extensive qualitative and quantitative evaluation of the baseline datasets shows that the proposed algorithm has higher mean-sort-score(MSS)than any state-of-the-art method and has better visual perception.展开更多
Sparse representation has attracted extensive attention and performed well on image super-resolution(SR) in the last decade. However, many current image SR methods face the contradiction of detail recovery and artif...Sparse representation has attracted extensive attention and performed well on image super-resolution(SR) in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning(MRDL) model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method(APPM). The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.展开更多
基金Guangdong Science and Technology Program under Grant No.202206010052Foshan Province R&D Key Project under Grant No.2020001006827Guangdong Academy of Sciences Integrated Industry Technology Innovation Center Action Special Project under Grant No.2022GDASZH-2022010108.
文摘The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)research.However,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction performance.These methods commonly use standard convolutions,which increase the convolutional operation cost of the model.In this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this problem.Specifically,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image reconstruction.Additionally,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature representations.Inspired by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an image.MFFB can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature information.As the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.
基金supported by Beijing Municipal Science and Technology Project(No.Z221100007122003).
文摘Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.
文摘Digital in-line holographic microscopy(DIHM)is a widely used interference technique for real-time reconstruction of living cells’morphological information with large space-bandwidth product and compact setup.However,the need for a larger pixel size of detector to improve imaging photosensitivity,field-of-view,and signal-to-noise ratio often leads to the loss of sub-pixel information and limited pixel resolution.Additionally,the twin-image appearing in the reconstruction severely degrades the quality of the reconstructed image.The deep learning(DL)approach has emerged as a powerful tool for phase retrieval in DIHM,effectively addressing these challenges.However,most DL-based strategies are datadriven or end-to-end net approaches,suffering from excessive data dependency and limited generalization ability.Herein,a novel multi-prior physics-enhanced neural network with pixel super-resolution(MPPN-PSR)for phase retrieval of DIHM is proposed.It encapsulates the physical model prior,sparsity prior and deep image prior in an untrained deep neural network.The effectiveness and feasibility of MPPN-PSR are demonstrated by comparing it with other traditional and learning-based phase retrieval methods.With the capabilities of pixel super-resolution,twin-image elimination and high-throughput jointly from a single-shot intensity measurement,the proposed DIHM approach is expected to be widely adopted in biomedical workflow and industrial measurement.
基金This work was supported by Science and Technology Cooperation Special Project of Shijiazhuang(SJZZXA23005).
文摘In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural cavities.However,in clinical operating environments,endoscopic images often suffer from challenges such as low texture,uneven illumination,and non-rigid structures,which affect feature observation and extraction.This can severely impact surgical navigation or clinical diagnosis due to missing feature points in endoscopic images,leading to treatment and postoperative recovery issues for patients.To address these challenges,this paper introduces,for the first time,a Cross-Channel Multi-Modal Adaptive Spatial Feature Fusion(ASFF)module based on the lightweight architecture of EfficientViT.Additionally,a novel lightweight feature extraction and matching network based on attention mechanism is proposed.This network dynamically adjusts attention weights for cross-modal information from grayscale images and optical flow images through a dual-branch Siamese network.It extracts static and dynamic information features ranging from low-level to high-level,and from local to global,ensuring robust feature extraction across different widths,noise levels,and blur scenarios.Global and local matching are performed through a multi-level cascaded attention mechanism,with cross-channel attention introduced to simultaneously extract low-level and high-level features.Extensive ablation experiments and comparative studies are conducted on the HyperKvasir,EAD,M2caiSeg,CVC-ClinicDB,and UCL synthetic datasets.Experimental results demonstrate that the proposed network improves upon the baseline EfficientViT-B3 model by 75.4%in accuracy(Acc),while also enhancing runtime performance and storage efficiency.When compared with the complex DenseDescriptor feature extraction network,the difference in Acc is less than 7.22%,and IoU calculation results on specific datasets outperform complex dense models.Furthermore,this method increases the F1 score by 33.2%and accelerates runtime by 70.2%.It is noteworthy that the speed of CMMCAN surpasses that of comparative lightweight models,with feature extraction and matching performance comparable to existing complex models but with faster speed and higher cost-effectiveness.
文摘Objective:To explore the implementation of gastrointestinal endoscopy technology and endoscopic narrow-band imaging(NBI)in the early screening of gastric cancer and to observe and study their application effects.Methods:During the period from March 2023 to August 2023,312 patients who received gastroscopy in the Kunming Guandu District People’s Hospital were selected,and they underwent both conventional gastroscopy and endoscopic NBI,with clinicopathological tissue biopsy serving as the gold standard.The application value for early screening of gastric cancer was observed and analyzed.Results:The scoring data showed that the clarity of gastric mucosal glandular tube structure,microvascular structure clarity,and lesion contour scoring data of conventional gastroscopy were lower than those of the NBI technology(P<0.05).The screening rate of pathological biopsy in 312 patients was 18.59%(58 cases).Conventional gastroscopy showed a screening rate of 11.53%(36 cases),while NBI technology examined a screening rate of 17.63%(55 cases),and the two-by-two comparison of the screening rate data of the three groups was not statistically significant(P>0.05).The sensitivity,specificity,accuracy,positive predictive value,and negative predictive value of conventional gastroscopy appeared to be lower than those of NBI technology(P<0.05).Conclusion:In the early screening of gastric cancer,endoscopic NBI technology can be applied to patients.Compared with conventional gastroscopy,it provides a clearer visualization of the structure of the gastric mucosal glandular structure and microvascular structure,with a certain screening rate.Additionally,its sensitivity,specificity,accuracy,positive predictive value,and negative predictive value are higher,demonstrating outstanding effectiveness.
基金supported in part by the National Natural Science Foundation of China(62276192)。
文摘Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.
基金supported by Balochistan University of Engineering and Technology,Khuzdar,Balochistan,Pakistan.
文摘Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the rapid progress in convolutional neural networks(CNNs)has achieved superior performance in the area of medical image super-resolution.However,the traditional CNN approaches use interpolation techniques as a preprocessing stage to enlarge low-resolution magnetic resonance(MR)images,adding extra noise in the models and more memory consumption.Furthermore,conventional deep CNN approaches used layers in series-wise connection to create the deeper mode,because this later end layer cannot receive complete information and work as a dead layer.In this paper,we propose Inception-ResNet-based Network for MRI Image Super-Resolution known as IRMRIS.In our proposed approach,a bicubic interpolation is replaced with a deconvolution layer to learn the upsampling filters.Furthermore,a residual skip connection with the Inception block is used to reconstruct a high-resolution output image from a low-quality input image.Quantitative and qualitative evaluations of the proposed method are supported through extensive experiments in reconstructing sharper and clean texture details as compared to the state-of-the-art methods.
基金supported by the National Natural Science Foundation under Grants No.62271127,No.61872405,and No.81171411Natural Science Foundation of Sichuan Province,China under Grant No.23NSFSC0627Medico-Engineering Cooperation Funds from University of Electronic Science and Technology of China and West China Hospital of Sichuan University under Grants No.ZYGX2022YGRH011 and No.HXDZ22005.
文摘Automatic segmentation of early esophagus cancer(EEC)in gastrointestinal endoscopy(GIE)images is a critical and challenging task in clinical settings,which relies primarily on labor-intensive and time-consuming routines.EEC has often been diagnosed at the late stage since early signs of cancer are not obvious,resulting in low survival rates.This work proposes a deep learning approach based on the U-Net++method to segment EEC in GIE images.A total of 2690 GIE images collected from 617 patients at the Digestive Endoscopy Center,West China Hospital of Sichuan University,China,have been utilized.The experimental result shows that our proposed method achieved promising results.Furthermore,the comparison has been made between the proposed and other U-Net-related methods using the same dataset.The mean and standard deviation(SD)of the dice similarity coefficient(DSC),intersection over union(IoU),precision(Pre),and recall(Rec)achieved by the proposed framework were DSC(%)=94.62±0.02,IoU(%)=90.99±0.04,Pre(%)=94.61±0.04,and Rec(%)=95.00±0.02,respectively,outperforming the others.The proposed method has the potential to be applied in EEC automatic diagnoses.
文摘BACKGROUND It has been confirmed that three-dimensional(3D)imaging allows easier identification of bile duct anatomy and intraoperative guidance of endoscopic retrograde cholangiopancreatography(ERCP),which reduces the radiation dose and procedure time with improved safety.However,current 3D biliary imaging does not have good real-time fusion with intraoperative imaging,a process meant to overcome the influence of intraoperative respiratory motion and guide navigation.The present study explored the feasibility of real-time continuous image-guided ERCP.AIM To explore the feasibility of real-time continuous image-guided ERCP.METHODS We selected 23D-printed abdominal biliary tract models with different structures to simulate different patients.The ERCP environment was simulated for the biliary phantom experiment to create a navigation system,which was further tested in patients.In addition,based on the estimation of the patient’s respiratory motion,preoperative 3D biliary imaging from computed tomography of 18 patients with cholelithiasis was registered and fused in real-time with 2D fluoroscopic sequence generated by the C-arm unit during ERCP.RESULTS Continuous image-guided ERCP was applied in the biliary phantom with a registration error of 0.46 mm±0.13 mm and a tracking error of 0.64 mm±0.24mm.After estimating the respiratory motion,3D/2D registration accurately transformed preoperative 3D biliary images to each image in the X-ray image sequence in real-time in 18 patients,with an average fusion rate of 88%.CONCLUSION Continuous image-guided ERCP may be an effective approach to assist the operator and reduce the use of X-ray and contrast agents.
基金Subjects funded by the National Natural Science Foundation of China(Nos.62275216 and 61775181)the Natural Science Basic Research Programme of Shaanxi Province-Major Basic Research Special Project(Nos.S2018-ZC-TD-0061 and TZ0393)the Special Project for the Development of National Key Scientific Instruments and Equipment No.(51927804).
文摘Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural network based on a generative adversarial network(GAN).The generator employs a U-Net-based network,which integrates Dense Net for the downsampling component.The proposed method has excellent properties,for example,the network model is trained with several different datasets of biological structures;the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging;and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets.In addition,experimental results showed that the method improved the resolution of caveolin-coated pits(CCPs)structures from 264 nm to 138 nm,a 1.91-fold increase,and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.
基金the National Natural Science Foundation of China(62273359)the General Project of Hunan Natural Science Foundation of China(2022JJ30748)the National Major Scientific Research Equipment of China(61927803)。
文摘Blast furnace(BF)burden surface contains the most abundant,intuitive and credible smelting information and acquiring high-definition and high-brightness optical images of which is essential to realize precise material charging control,optimize gas flow distribution and improve ironmaking efficiency.It has been challengeable to obtain high-quality optical burden surface images under high-temperature,high-dust,and extremelydim(less than 0.001 Lux)environment.Based on a novel endoscopic sensing detection idea,a reverse telephoto structure starlight imaging system with large field of view and large aperture is designed.Combined with a water-air dual cooling intelligent self-maintenance protection device and the imaging system,a starlight high-temperature industrial endoscope is developed to obtain clear optical burden surface images stably under the harsh environment.Based on an endoscope imaging area model,a material flow trajectory model and a gas-dust coupling distribution model,an optimal installation position and posture configuration method for the endoscope is proposed,which maximizes the effective imaging area and ensures large-area,safe and stable imaging of the device in a confined space.Industrial experiments and applications indicate that the proposed method obtains clear and reliable large-area optical burden surface images and reveals new BF conditions,providing key data support for green iron smelting.
文摘This editorial elaborates on the current and future applications of linear endoscopic ultrasound(EUS),a substantial diagnostic and therapeutic modality for various anatomical regions.The scope of endosonographic assessment is broad and,among other factors,allows for the evaluation of the mediastinal anatomy and related pathologies,such as mediastinal lymphadenopathy and the staging of central malignant lung lesions.Moreover,EUS assessment has proven more accurate in detecting small lesions missed by standard imaging examinations,such as computed tomography or magnetic resonance imaging.We focus on its current uses in the mediastinum,including lung and esophageal cancer staging,as well as evaluating mediastinal lymphadenopathy and submucosal lesions.The editorial also explores future perspectives of EUS in mediastinal examination,including ultrasound-guided therapies,artificial intelligence integration,advancements in mediastinal modalities,and improved diagnostic approaches for various mediastinal lesions.
文摘BACKGROUND Conventional magnifying endoscopy with narrow-band imaging(NBI)observation of the gastric body mucosa shows dominant patterns in relation to the regular arrangement of collecting venules,subepithelial capillary network,and gastric pits.AIM To evaluate the effectiveness of a new one-dual(near)focus,NBI mode in the assessment of the microscopic features of gastric body mucosa compared to conventional magnification.METHODS During 2021 and 2022,68 patients underwent proximal gastrointestinal endoscopy using magnification endoscopic modalities subsequently applying acetic acid(AA).The GIF-190HQ series NBI system with dual focus capability was used for the investigation of gastric mucosa.At the time of the endoscopy,the gastric body mucosa of all enrolled patients was photographed using the white light endoscopy(WLE),near focus(NF),NF-NBI,AA-NF,and AA-NF-NBI modes.RESULTS The WLE,NF and NF-NBI endoscopic modes for all patients(204 images)were classified in the same order into three groups.Two images from each patient for the AA-NF and AA-NF-NBI endoscopic modes were classified in the same order.According to all three observers who completed the work independently,NF magnification was significantly superior to WLE(P<0.01),and the NF-NBI mode was significantly superior to NF magnification(P<0.01).After applying AA,the three observers confirmed that AA-NF-NBI was significantly superior to AA-NF(P<0.01).Interobserver kappa values for WLE were 0.609,0.704,and 0.598,respectively and were 0.600,0.721,and 0.637,respectively,for NF magnification.For the NF-NBI mode,the values were 0.378,0.471,and 0.553,respectively.For AA-NF,they were 0.453,0.603,and 0.480,respectively,and for AA-NF-NBI,they were 0.643,0.506,and 0.354,respectively.CONCLUSION When investigating gastric mucosa in microscopic detail,NF-NBI was the most powerful endoscopic mode for assessing regular arrangement of collecting venules,subepithelial capillary network,and gastric pits among the five endoscopic modalities investigated in this study.AA-NF-NBI was the most powerful endoscopic mode for analyzing crypt opening and intervening part.
基金Supported by The National Natural Science Foundation of China,No.30801362 and 81001074
文摘AIM:To develop a fuzzy classification method to score the texture features of pancreatic cancer in endoscopic ultrasonography(EUS)images and evaluate its utility in making prognosis judgments for patients with unresectable pancreatic cancer treated by EUS-guided interstitial brachytherapy.METHODS:EUS images from our retrospective database were analyzed.The regions of interest were drawn,and texture features were extracted,selected,and scored with a fuzzy classification method using a C++program.Then,patients with unresectable pancreatic cancer were enrolled to receive EUS-guided iodine 125 radioactive seed implantation.Their fuzzy classification scores,tumor volumes,and carbohydrate antigen 199(CA199)levels before and after the brachytherapy were recorded.The association between the changes in these parameters and overall survival was analyzed statistically.RESULTS:EUS images of 153 patients with pancreatic cancer and 63 non-cancer patients were analyzed.A total of 25 consecutive patients were enrolled,and they tolerated the brachytherapy well without any complications.There was a correlation between the change in the fuzzy classification score and overall survival(Spearman test,r=0.616,P=0.001),whereas no correlation was found to be significant between the change in tumor volume(P=0.663),CA199 level(P=0.659),and overall survival.There were 15 patients with a decrease in their fuzzy classification score after brachytherapy,whereas the fuzzy classification score increased in another 10 patients.There was a significant difference in overall survival between the two groups(67 d vs 151 d,P=0.001),but not in the change of tumor volume and CA199 level.CONCLUSION:Using the fuzzy classification method to analyze EUS images of pancreatic cancer is feasible,and the method can be used to make prognosis judgments for patients with unresectable pancreatic cancer treated by interstitial brachytherapy.
文摘AIM: To compare the diagnostic yield of heterotopic gastric mucosa (HGM) in the cervical esophagus with conventional imaging (CI) and narrow-band imaging (NBI).
基金Project(2008041001) supported by the Academician Foundation of China Project(N0601-041) supported by the General Armament Department Science Foundation of China
文摘A super-resolution reconstruction approach of (SVD) technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function (PSF) matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar (SAR) images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio (SNR). Five versions of SVD algorithms, namely 1 ) using all singular values, 2) using the top 80% singular values, 3) using the top 50% singular values, 4) using the top 20% singular values and 5) using singular values s such that S2≥/max(s2)/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/(rinSNR)1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.
基金The authors are highly thankful to the Development Research Center of Guangxi Relatively Sparse-populated Minorities(ID:GXRKJSZ201901)to the Natural Science Foundation of Guangxi Province(No.2018GXNSFAA281164)This research was financially supported by the project of outstanding thousand young teachers’training in higher education institutions of Guangxi,Guangxi Colleges and Universities Key Laboratory Breeding Base of System Control and Information Processing.
文摘Single image super resolution(SISR)is an important research content in the field of computer vision and image processing.With the rapid development of deep neural networks,different image super-resolution models have emerged.Compared to some traditional SISR methods,deep learning-based methods can complete the super-resolution tasks through a single image.In addition,compared with the SISR methods using traditional convolutional neural networks,SISR based on generative adversarial networks(GAN)has achieved the most advanced visual performance.In this review,we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics.Then,we review the improved network structures and loss functions of GAN-based perceptual SISR.Subsequently,the advantages and disadvantages of different networks are analyzed by multiple comparative experiments.Finally,we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.
基金supported by the National Natural Science Foundation of China(61761028)。
文摘Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images.This paper presents a color super-resolution reconstruction method combining the L2/3 sparse regularization model with color channel constraints.The method converts the low-resolution color image from RGB to YCbCr.The L2/3 sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image.Then the color channel-constraint method is adopted to remove artifacts of the reconstructed highresolution image.The method not only ensures the reconstruction quality of the color image details,but also improves the removal ability of color artifacts.The experimental results on natural images validate that our method has improved both subjective and objective evaluation.
基金This work was supported in part by the National Science Foundation of China under Grant 61572526.
文摘Although there has been a great breakthrough in the accuracy and speed of super-resolution(SR)reconstruction of a single image by using a convolutional neural network,an important problem remains unresolved:how to restore finer texture details during image super-resolution reconstruction?This paper proposes an Enhanced Laplacian Pyramid Generative Adversarial Network(ELSRGAN),based on the Laplacian pyramid to capture the high-frequency details of the image.By combining Laplacian pyramids and generative adversarial networks,progressive reconstruction of super-resolution images can be made,making model applications more flexible.In order to solve the problem of gradient disappearance,we introduce the Residual-in-Residual Dense Block(RRDB)as the basic network unit.Network capacity benefits more from dense connections,is able to capture more visual features with better reconstruction effects,and removes BN layers to increase calculation speed and reduce calculation complexity.In addition,a loss of content driven by perceived similarity is used instead of content loss driven by spatial similarity,thereby enhancing the visual effect of the super-resolution image,making it more consistent with human visual perception.Extensive qualitative and quantitative evaluation of the baseline datasets shows that the proposed algorithm has higher mean-sort-score(MSS)than any state-of-the-art method and has better visual perception.
文摘Sparse representation has attracted extensive attention and performed well on image super-resolution(SR) in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning(MRDL) model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method(APPM). The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.