Underwater Image Enhancement Based on Multi-scale Adversarial Network

In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.

YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

Advancements in Remote Sensing Image Dehazing: Introducing URA-Net with Multi-Scale Dense Feature Fusion Clusters and Gated Jump Connection

The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various domains.Dehazing methodologies have emerged as pivotal components of image preprocessing,fostering an improvement in the quality of remote sensing imagery.This enhancement renders remote sensing data more indispensable,thereby enhancing the accuracy of target iden-tification.Conventional defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed images.In response to this challenge,a novel UNet Residual Attention Network(URA-Net)is proposed.This paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump connections.The essence of our methodology lies in local feature fusion within dense residual clusters,enabling the extraction of pertinent features from both preceding and current local data,depending on contextual demands.The intelligently orchestrated gated structures facilitate the propagation of these features to the decoder,resulting in superior outcomes in haze removal.Empirical validation through a plethora of experiments substantiates the efficacy of URA-Net,demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image defogging.On the RICE-1 dataset,URA-Net achieves a Peak Signal-to-Noise Ratio(PSNR)of 29.07 dB,surpassing the Dark Channel Prior(DCP)by 11.17 dB,the All-in-One Network for Dehazing(AOD)by 7.82 dB,the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing(OTM-AAL)by 5.37 dB,the Unsupervised Single Image Dehazing(USID)by 8.0 dB,and the Superpixel-based Remote Sensing Image Dehazing(SRD)by 8.5 dB.Particularly noteworthy,on the SateHaze1k dataset,URA-Net attains preeminence in overall performance,yielding defogged images characterized by consistent visual quality.This underscores the contribution of the research to the advancement of remote sensing technology,providing a robust and efficient solution for alleviating the adverse effects of haze on image quality.

Multi-scale cross-domain alignment for person image generation

Person image generation aims to generate images that maintain the original human appearance in different target poses.Recent works have revealed that the critical element in achieving this task is the alignment of appearance domain and pose domain.Previous alignment methods,such as appearance flow warping,correspondence learning and cross attention,often encounter challenges when it comes to producing fine texture details.These approaches suffer from limitations in accurately estimating appearance flows due to the lack of global receptive field.Alternatively,they can only perform cross-domain alignment on high-level feature maps with small spatial dimensions since the computational complexity increases quadratically with larger feature sizes.In this article,the significance of multi-scale alignment,in both low-level and high-level domains,for ensuring reliable cross-domain alignment of appearance and pose is demonstrated.To this end,a novel and effective method,named Multi-scale Crossdomain Alignment(MCA)is proposed.Firstly,MCA adopts global context aggregation transformer to model multi-scale interaction between pose and appearance inputs,which employs pair-wise window-based cross attention.Furthermore,leveraging the integrated global source information for each target position,MCA applies flexible flow prediction head and point correlation to effectively conduct warping and fusing for final transformed person image generation.Our proposed MCA achieves superior performance on two popular datasets than other methods,which verifies the effectiveness of our approach.

Few-shot image recognition based on multi-scale features prototypical network

In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.

Research on Multi-Scale Feature Fusion Network Algorithm Based on Brain Tumor Medical Image Classification

Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.

A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

Enhancing the Quality of Low-Light Printed Circuit Board Images through Hue, Saturation, and Value Channel Processing and Improved Multi-Scale Retinex

To address the issue of deteriorated PCB image quality in the quality inspection process due to insufficient or uneven lighting, we proposed an image enhancement fusion algorithm based on different color spaces. Firstly, an improved MSRCR method was employed for brightness enhancement of the original image. Next, the color space of the original image was transformed from RGB to HSV, followed by processing the S-channel image using bilateral filtering and contrast stretching algorithms. The V-channel image was subjected to brightness enhancement using adaptive Gamma and CLAHE algorithms. Subsequently, the processed image was transformed back to the RGB color space from HSV. Finally, the images processed by the two algorithms were fused to create a new RGB image, and color restoration was performed on the fused image. Comparative experiments with other methods indicated that the contrast of the image was optimized, texture features were more abundantly preserved, brightness levels were significantly improved, and color distortion was prevented effectively, thus enhancing the quality of low-lit PCB images.

A semi-analytical model for coupled flow in stress-sensitive multi-scale shale reservoirs with fractal characteristics

A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes due to stress sensitivity, which plays a crucial role in controlling pressure propagation and oil flow. This paper proposes a multi-scale coupled flow mathematical model of matrix nanopores, induced fractures, and hydraulic fractures. In this model, the micro-scale effects of shale oil flow in fractal nanopores, fractal induced fracture network, and stress sensitivity of multi-scale media are considered. We solved the model iteratively using Pedrosa transform, semi-analytic Segmented Bessel function, Laplace transform. The results of this model exhibit good agreement with the numerical solution and field production data, confirming the high accuracy of the model. As well, the influence of stress sensitivity on permeability, pressure and production is analyzed. It is shown that the permeability and production decrease significantly when induced fractures are weakly supported. Closed induced fractures can inhibit interporosity flow in the stimulated reservoir volume (SRV). It has been shown in sensitivity analysis that hydraulic fractures are beneficial to early production, and induced fractures in SRV are beneficial to middle production. The model can characterize multi-scale flow characteristics of shale oil, providing theoretical guidance for rapid productivity evaluation.

Microwave-induced thermoacoustic elastic imaging:A simulation study

Microwave-induced thermoacoustic imaging(MTI)has the advantages of high resolution,high contrast,non-ionization,and non-invasive.Recently,MTI was used in the¯eld of breast cancer screening.In this paper,based on the¯nite element method(FEM)and COMSOL Multiphysics software,a three-dimensional breast cancer model suitable for exploring the MTI process is proposed to investigate the in°uence of Young's modulus(YM)of breast cancer tissue on MTI.It is found that the process of electromagnetic heating and initial pressure generation of the entire breast tissue is earlier in time than the thermal expansion process.Besides,compared with normal breast tissue,tumor tissue has a greater temperature rise,displacement,and pressure rise.In particular,YM of the tumor is related to the speed of thermal expansion.In particular,the larger the YM of the tumor is,the higher the heating and contraction frequency is,and the greater the maximum pressure is.Di®erent Young's moduli correspond to di®erent thermoacoustic signal spectra.In MTI,this study can be used to judge di®erent degrees of breast cancer based on elastic imaging.In addition,this study is helpful in exploring the possibility of microwave-induced thermoacoustic elastic imaging(MTAE).

Multi-scale physics-informed neural networks for solving high Reynolds number boundary layer flows based on matched asymptotic expansions

Multi-scale system remains a classical scientific problem in fluid dynamics,biology,etc.In the present study,a scheme of multi-scale Physics-informed neural networks is proposed to solve the boundary layer flow at high Reynolds numbers without any data.The flow is divided into several regions with different scales based on Prandtl's boundary theory.Different regions are solved with governing equations in different scales.The method of matched asymptotic expansions is used to make the flow field continuously.A flow on a semi infinite flat plate at a high Reynolds number is considered a multi-scale problem because the boundary layer scale is much smaller than the outer flow scale.The results are compared with the reference numerical solutions,which show that the msPINNs can solve the multi-scale problem of the boundary layer in high Reynolds number flows.This scheme can be developed for more multi-scale problems in the future.

Data-driven polarimetric imaging: a review

This study reviews the recent advances in data-driven polarimetric imaging technologies based on a wide range of practical applications.The widespread international research and activity in polarimetric imaging techniques demonstrate their broad applications and interest.Polarization information is increasingly incorporated into convolutional neural networks(CNN)as a supplemental feature of objects to improve performance in computer vision task applications.Polarimetric imaging and deep learning can extract abundant information to address various challenges.Therefore,this article briefly reviews recent developments in data-driven polarimetric imaging,including polarimetric descattering,3D imaging,reflection removal,target detection,and biomedical imaging.Furthermore,we synthetically analyze the input,datasets,and loss functions and list the existing datasets and loss functions with an evaluation of their advantages and disadvantages.We also highlight the significance of data-driven polarimetric imaging in future research and development.

Preoperative prediction of perineural invasion of rectal cancer based on a magnetic resonance imaging radiomics model:A dual-center study

BACKGROUND Perineural invasion(PNI)has been used as an important pathological indicator and independent prognostic factor for patients with rectal cancer(RC).Preoperative prediction of PNI status is helpful for individualized treatment of RC.Recently,several radiomics studies have been used to predict the PNI status in RC,demonstrating a good predictive effect,but the results lacked generalizability.The preoperative prediction of PNI status is still challenging and needs further study.AIM To establish and validate an optimal radiomics model for predicting PNI status preoperatively in RC patients.METHODS This retrospective study enrolled 244 postoperative patients with pathologically confirmed RC from two independent centers.The patients underwent preoperative high-resolution magnetic resonance imaging(MRI)between May 2019 and August 2022.Quantitative radiomics features were extracted and selected from oblique axial T2-weighted imaging(T2WI)and contrast-enhanced T1WI(T1CE)sequences.The radiomics signatures were constructed using logistic regression analysis and the predictive potential of various sequences was compared(T2WI,T1CE and T2WI+T1CE fusion sequences).A clinical-radiomics(CR)model was established by combining the radiomics features and clinical risk factors.The internal and external validation groups were used to validate the proposed models.The area under the receiver operating characteristic curve(AUC),DeLong test,net reclassification improvement(NRI),integrated discrimination improvement(IDI),calibration curve,and decision curve analysis(DCA)were used to evaluate the model performance.RESULTS Among the radiomics models,the T2WI+T1CE fusion sequences model showed the best predictive performance,in the training and internal validation groups,the AUCs of the fusion sequence model were 0.839[95%confidence interval(CI):0.757-0.921]and 0.787(95%CI:0.650-0.923),which were higher than those of the T2WI and T1CE sequence models.The CR model constructed by combining clinical risk factors had the best predictive performance.In the training and internal and external validation groups,the AUCs of the CR model were 0.889(95%CI:0.824-0.954),0.889(95%CI:0.803-0.976)and 0.894(95%CI:0.814-0.974).Delong test,NRI,and IDI showed that the CR model had significant differences from other models(P<0.05).Calibration curves demonstrated good agreement,and DCA revealed significant benefits of the CR model.CONCLUSION The CR model based on preoperative MRI radiomics features and clinical risk factors can preoperatively predict the PNI status of RC noninvasively,which facilitates individualized treatment of RC patients.

Two-photon live imaging of direct glia-to-neuron conversion in the mouse cortex

Over the past decade,a growing number of studies have reported transcription factor-based in situ reprogramming that can directly conve rt endogenous glial cells into functional neurons as an alternative approach for n euro regeneration in the adult mammalian central ne rvous system.Howeve r,many questions remain regarding how a terminally differentiated glial cell can transform into a delicate neuron that forms part of the intricate brain circuitry.In addition,concerns have recently been raised around the absence of astrocyte-to-neuron conversion in astrocytic lineage-tra cing mice.In this study,we employed repetitive two-photon imaging to continuously capture the in situ astrocyte-to-neuron conversion process following ecto pic expression of the neural transcription factor NeuroD1 in both prolife rating reactive astrocytes and lineage-tra ced astrocytes in the mouse cortex.Time-lapse imaging over several wee ks revealed the ste p-by-step transition from a typical astrocyte with numero us short,tapered branches to a typical neuro n with a few long neurites and dynamic growth cones that actively explored the local environment.In addition,these lineage-converting cells were able to migrate ra dially or to ngentially to relocate to suitable positions.Furthermore,two-photon Ca2+imaging and patch-clamp recordings confirmed that the newly generated neuro ns exhibited synchronous calcium signals,repetitive action potentials,and spontaneous synaptic responses,suggesting that they had made functional synaptic connections within local neural circuits.In conclusion,we directly visualized the step-by-step lineage conversion process from astrocytes to functional neurons in vivo and unambiguously demonstrated that adult mammalian brains are highly plastic with respect to their potential for neuro regeneration and neural circuit reconstruction.

Laser spectroscopy imaging technique coupled withnanomaterials for cancer diagnosis: A review

Laser spectroscopic imaging techniques have received tremendous attention in the-eld of cancer diagnosis due to their high sensitivity,high temporal resolution,and short acquisition time.However,the limited tissue penetration of the laser is still a challenge for the in vivo diagnosis of deep-seated lesions.Nanomaterials have been universally integrated with spectroscopic imaging techniques for deeper cancer diagnosis in vivo.The components,morphology,and sizes of nanomaterials are delicately designed,which could realize cancer diagnosis in vivo or in situ.Considering the enhanced signal emitting from the nanomaterials,we emphasized their combination with spectroscopic imaging techniques for cancer diagnosis,like the surface-enhanced Raman scattering(SERS),photoacoustic,fluorescence,and laser-induced breakdown spectroscopy(LIBS).Applications ofthe above spectroscopic techniques offer new prospectsfor cancer diagnosis.

NIR-II fluorescence imaging in liver tumor surgery: A narrative review

In liver tumor surgery,the recognition of tumor margin and radical resection of microcancer focis have always been the crucial points to reduce postoperative recurrence of tumor.However,naked-eye inspection and palpation have limited effectiveness in identifying tumor boundaries,and traditional imaging techniques cannot consistently locate tumors in real time.As an intraoperative real-time navigation imaging method,NIRfluorescence imaging has been extensively studied for its simplicity,reliable safety,and superior sensitivity,and is expected to improve the accuracy of liver tumor surgery.In recent years,the research focus of NIRfluorescence has gradually shifted from the-rst near-infrared window(NIR-I,700–900 nm)to the second near-infrared window(NIR-II,1000–1700 nm).Fluorescence imaging in NIR-II reduces the scattering effect of deep tissue,providing a preferable detection depth and spatial resolution while signi-cantly eliminating liver autofluorescence background to clarify tumor margin.Developingfluorophores combined with tumor antibodies will further improve the precision offluorescence-guided surgical navigation.With the development of a bunch offluorophores with phototherapy ability,NIR-II can integrate tumor detection and treatment to explore a new therapeutic strategy for liver cancer.Here,we review the recent progress of NIR-IIfluorescence technology in liver tumor surgery and discuss its challenges and potential development direction.

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

Magnetic resonance imaging of extraocular rectus muscles abnormalities in acute acquired concomitant esotropia

AIM:To investigate the difference of medial rectus(MR)and lateral rectus(LR)between acute acquired concomitant esotropia(AACE)and the healthy controls(HCs)detected by magnetic resonance imaging(MRI).METHODS:A case-control study.Eighteen subjects with AACE and eighteen HCs were enrolled.MRI scanning data were conducted in target-controlled central gaze with a 3-Tesla magnetic resonance scanner.Extraocular muscles(EOMs)were scanned in contiguous image planes 2-mm thick spanning the EOM origins to the globe equator.To form posterior partial volumes(PPVs),the LR and MR cross-sections in the image planes 8,10,12,and 14 mm posterior to the globe were summed and multiplied by the 2-mm slice thickness.The data were classified according to the right eye,left eye,dominant eye,and non-dominant eye,and the differences in mean cross-sectional area,maximum cross-sectional area,and PPVs of the MR and LR muscle in the AACE group and HCs group were compared under the above classifications respectively.RESULTS:There were no significant differences between the two groups of demographic characteristics.The mean cross-sectional area of the LR muscle was significantly greater in the AACE group than that in the HCs group in the non-dominant eyes(P=0.028).The maximum cross-sectional area of the LR muscle both in the dominant and non-dominant eye of the AACE group was significantly greater than the HCs group(P=0.009,P=0.016).For the dominant eye,the PPVs of the LR muscle were significantly greater in the AACE than that in the HCs group(P=0.013),but not in the MR muscle(P=0.698).CONCLUSION:The size and volume of muscles dominant eyes of AACE subjects change significantly to overcome binocular diplopia.The LR muscle become larger to compensate for the enhanced convergence in the AACE.

Potential applications of 7 Tesla magnetic resonance imaging in paediatric neuroimaging:Feasibility and challenges

The integration of 7 Tesla magnetic resonance imaging(7 T MRI)in adult patients has marked a revolutionary stride in radiology.In this article we explore the feasibility of 7 T MRI in paediatric practice,emphasizing its feasibility,applications,challenges,and safety considerations.The heightened resolution and tissue contrast of 7 T MRI offer unprecedented diagnostic accuracy,particularly in neuroimaging.Applications range from neuro-oncology to neonatal brain imaging,showcasing its efficacy in detecting subtle structural abnormalities and providing enhanced insights into neurological conditions.Despite the promise,challenges such as high cost,discomfort,and safety concerns necessitate careful consideration.Research suggests that,with precautions,7 T MRI is feasible in paediatrics,yet ongoing studies and safety assessments are imperative.

Staging liver fibrosis with various diffusion-weighted magnetic resonance imaging models

BACKGROUND Diffusion-weighted imaging(DWI)has been developed to stage liver fibrosis.However,its diagnostic performance is inconsistent among studies.Therefore,it is worth studying the diagnostic value of various diffusion models for liver fibrosis in one cohort.AIM To evaluate the clinical potential of six diffusion-weighted models in liver fibrosis staging and compare their diagnostic performances.METHODS This prospective study enrolled 59 patients suspected of liver disease and scheduled for liver biopsy and 17 healthy participants.All participants underwent multi-b value DWI.The main DWI-derived parameters included Mono-apparent diffusion coefficient(ADC)from mono-exponential DWI,intravoxel incoherent motion model-derived true diffusion coefficient(IVIM-D),diffusion kurtosis imaging-derived apparent diffusivity(DKI-MD),stretched exponential model-derived distributed diffusion coefficient(SEM-DDC),fractional order calculus(FROC)model-derived diffusion coefficient(FROC-D)and FROC model-derived microstructural quantity(FROC-μ),and continuous-time random-walk(CTRW)model-derived anomalous diffusion coefficient(CTRW-D)and CTRW model-derived temporal diffusion heterogeneity index(CTRW-α).The correlations between DWI-derived parameters and fibrosis stages and the parameters’diagnostic efficacy in detecting significant fibrosis(SF)were assessed and compared.RESULTS CTRW-D(r=-0.356),CTRW-α(r=-0.297),DKI-MD(r=-0.297),FROC-D(r=-0.350),FROC-μ(r=-0.321),IVIM-D(r=-0.251),Mono-ADC(r=-0.362),and SEM-DDC(r=-0.263)were significantly correlated with fibrosis stages.The areas under the ROC curves(AUCs)of the combined index of the six models for distinguishing SF(0.697-0.747)were higher than each of the parameters alone(0.524-0.719).The DWI models’ability to detect SF was similar.The combined index of CTRW model parameters had the highest AUC(0.747).CONCLUSION The DWI models were similarly valuable in distinguishing SF in patients with liver disease.The combined index of CTRW parameters had the highest AUC.