A Novel Approach to Breast Tumor Detection: Enhanced Speckle Reduction and Hybrid Classification in Ultrasound Imaging

Breast cancer detection heavily relies on medical imaging, particularly ultrasound, for early diagnosis and effectivetreatment. This research addresses the challenges associated with computer-aided diagnosis (CAD) of breastcancer fromultrasound images. The primary challenge is accurately distinguishing between malignant and benigntumors, complicated by factors such as speckle noise, variable image quality, and the need for precise segmentationand classification. The main objective of the research paper is to develop an advanced methodology for breastultrasound image classification, focusing on speckle noise reduction, precise segmentation, feature extraction, andmachine learning-based classification. A unique approach is introduced that combines Enhanced Speckle ReducedAnisotropic Diffusion (SRAD) filters for speckle noise reduction, U-NET-based segmentation, Genetic Algorithm(GA)-based feature selection, and Random Forest and Bagging Tree classifiers, resulting in a novel and efficientmodel. To test and validate the hybrid model, rigorous experimentations were performed and results state thatthe proposed hybrid model achieved accuracy rate of 99.9%, outperforming other existing techniques, and alsosignificantly reducing computational time. This enhanced accuracy, along with improved sensitivity and specificity,makes the proposed hybrid model a valuable addition to CAD systems in breast cancer diagnosis, ultimatelyenhancing diagnostic accuracy in clinical applications.

Automatic Fetal Segmentation Designed on Computer-Aided Detection with Ultrasound Images

In the present research,we describe a computer-aided detection(CAD)method aimed at automatic fetal head circumference(HC)measurement in 2D ultrasonography pictures during all trimesters of pregnancy.The HC might be utilized toward determining gestational age and tracking fetal development.This automated approach is particularly valuable in low-resource settings where access to trained sonographers is limited.The CAD system is divided into two steps:to begin,Haar-like characteristics were extracted from ultrasound pictures in order to train a classifier using random forests to find the fetal skull.We identified the HC using dynamic programming,an elliptical fit,and a Hough transform.The computer-aided detection(CAD)program was well-trained on 999 pictures(HC18 challenge data source),and then verified on 335 photos from all trimesters in an independent test set.A skilled sonographer and an expert in medicine personally marked the test set.We used the crown-rump length(CRL)measurement to calculate the reference gestational age(GA).In the first,second,and third trimesters,the median difference between the standard GA and the GA calculated by the skilled sonographer stayed at 0.7±2.7,0.0±4.5,and 2.0±12.0 days,respectively.The regular duration variance between the baseline GA and the health investigator’s GA remained 1.5±3.0,1.9±5.0,and 4.0±14 a couple of days.The mean variance between the standard GA and the CAD system’s GA remained between 0.5 and 5.0,with an additional variation of 2.9 to 12.5 days.The outcomes reveal that the computer-aided detection(CAD)program outperforms an expert sonographer.When paired with the classifications reported in the literature,the provided system achieves results that are comparable or even better.We have assessed and scheduled this computerized approach for HC evaluation,which includes information from all trimesters of gestation.

A Modified CycleGAN for Multi-Organ Ultrasound Image Enhancement via Unpaired Pre-Training

Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.

Data augmentation of ultrasound imaging for non-invasive white blood cell in vitro peritoneal dialysis

The limited amount of data in the healthcare domain and the necessity of training samples for increased performance of deep learning models is a recurrent challenge,especially in medical imaging.Newborn Solutions aims to enhance its non-invasive white blood cell counting device,Neosonics,by creating synthetic in vitro ultrasound images to facilitate a more efficient image generation process.This study addresses the data scarcity issue by designing and evaluating a continuous scalar conditional Generative Adversarial Network(GAN)to augment in vitro peritoneal dialysis ultrasound images,increasing both the volume and variability of training samples.The developed GAN architecture incorporates novel design features:varying kernel sizes in the generator’s transposed convolutional layers and a latent intermediate space,projecting noise and condition values for enhanced image resolution and specificity.The experimental results show that the GAN successfully generated diverse images of high visual quality,closely resembling real ultrasound samples.While visual results were promising,the use of GAN-based data augmentation did not consistently improve the performance of an image regressor in distinguishing features specific to varied white blood cell concentrations.Ultimately,while this continuous scalar conditional GAN model made strides in generating realistic images,further work is needed to achieve consistent gains in regression tasks,aiming for robust model generalization.

The Application Value of Ultrasound Imaging in the Differential Diagnosis of Benign and Malignant Breast Nodules of BI-RADS 3 and Above

Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast nodules of BI-RADS 3 or above were selected as the research subjects.After pathological diagnosis,24 cases were malignant breast nodules of BI-RADS 3 or above,while 139 cases were benign breast nodules of BI-RADS 3 or above.The diagnosis rate of malignant and benign breast nodules of BI-RADS 3 or above,including 95%CI,was observed and analyzed.Results:The malignant and benign detection rates of conventional ultrasound were 88.63%and 75.00%,respectively,and the malignant and benign detection rates of ultrasound imaging were 93.18%and 87.50%,respectively,with 95%CIs greater than 0.7.Conclusion:Ultrasound imaging can help improve the diagnostic accuracy of benign and malignant breast nodules of BI-RADS 3 and above and reduce the misdiagnosis rate.

Using shapes correlation for active contour segmentation of uterine fibroid ultrasound images in computer-aided therapy

Segmenting the lesion regions from the ultrasound （US） images is an important step in the intra-operative planning of some computer-aided therapies. High-Intensity Focused Ultrasound （HIFU）, as a popular computer-aided therapy, has been widely used in the treatment of uterine fibroids. However, such segmentation in HIFU remains challenge for two reasons： （1） the blurry or missing boundaries of lesion regions in the HIFU images and （2） the deformation of uterine fibroids caused by the patient＇s breathing or an external force during the US imaging process, which can lead to complex shapes of lesion regions. These factors have prevented classical active contour-based segmentation methods from yielding desired results for uterine fibroids in US images. In this paper, a novel active contour-based segmentation method is proposed, which utilizes the correlation information of target shapes among a sequence of images as prior knowledge to aid the existing active contour method. This prior knowledge can be interpreted as a unsupervised clustering of shapes prior modeling. Meanwhile, it is also proved that the shapes correlation has the low-rank property in a linear space, and the theory of matrix recovery is used as an effective tool to impose the proposed prior on an existing active contour model. Finally, an accurate method is developed to solve the proposed model by using the Augmented Lagrange Multiplier （ALM）. Experimental results from both synthetic and clinical uterine fibroids US image sequences demonstrate that the proposed method can consistently improve the performance of active contour models and increase the robustness against missing or misleading boundaries, and can greatly improve the efficiency of HIFU therapy.

Ultrasound Imaging of Pipeline Crack Based on Composite Transducer Array

Cracks, especially small cracks are di cult to be detected in oil and gas transportation pipelines buried underground or covered with layers of material by using the traditional ultrasonic inspection techniques. Therefore, a new com?posite ultrasonic transducer array with three acoustic beam incidence modes is developed. The space model of the array is also established to obtain the defect reflection point location. And the crack ultrasound image is thus formed through a series of small cubical elements expanded around the point locations by using the projection of binariza?tion values extracted from the received ultrasonic echo signals. Laboratory experiments are performed on a pipeline sample with di erent types of cracks to verify the e ectiveness and performance of the proposed technique. From the image, the presence of small cracks can be clearly observed, in addition to the sizes and orientations of the cracks. The proposed technique can not only inspect common flaws, but also detect cracks with various orientations, which is helpful for defect evaluation in pipeline testing.

Preprocedure ultrasound imaging combined with palpation technique in epidural labor analgesia

BACKGROUND For parturients with paroxysmal uterine contraction pain,rapid analgesia is needed.We used preprocedure ultrasound imaging combined with the palpation technique in epidural analgesia for labor,and evaluated the usefulness of this technique in epidural labor analgesia.AIM To evaluate the usefulness of preprocedure ultrasound imaging in epidural analgesia for labor.METHODS In this prospective randomized observational study,72 parturients were assigned to two groups(combined or palpation group).The target interspace of all parturients was first identified by the palpation technique.Then in the combined group,preprocedure ultrasound imaging was used before epidural puncture.In the palpation group,only the traditional anatomical landmarks technique(palpation technique)was performed.The primary outcome was total duration of the epidural procedure(for the ultrasound group,the duration of the preprocedure ultrasound imaging was included).The secondary outcomes were the number of skin punctures,the success rate at first needle pass,the number of needle passes,the depth from the skin to epidural space,and the complications of the procedure.RESULTS Total duration of the epidural procedure was similar between the two groups(406.5±92.15 s in the combined group and 380.03±128.2 s in the palpation group;P=0.318).A significant improvement was demonstrated for epidural puncture and catheterization in the combined group.The number of needle passes was 1.14 in the combined group and 1.72 in the palpation group(P=0.001).The number of skin puncture sites was 1.20 in the combined group and 1.25 in the palpation group(P=0.398).The success rate at first needle pass was 88.89%in the combined group and 66.67%in the palpation group(P=0.045).CONCLUSION This study demonstrated that the total duration of epidural procedures with preprocedure ultrasound imaging combined with the palpation technique was not longer than the traditional anatomical landmarks technique,which were performed by six experienced anesthesiologists in parturients with normal weights undergoing labor analgesia.

Contrast enhancement of medical ultrasound imaging with reversal phase-inversion pulse technology

A new ultrasound contrast imaging technique was proposed for eliminating the harmonic components from the emission signal transmitted by the broadband ultrasonic system.Reversal phase-inversion pulse was used for the first time to separate the contrast harmonics from the harmonics in the emission signal to improve the detection of contrast micro-bubbles.Based on the nonlinear acoustic theory of finite-amplitude effects and the associated distortion of the propagating wave,the Bessel-Fubini series model was applied to describe the nonlinear propagation effects of the reversal phase-inversion pulse,and the Church's equation for zero-thickness encapsulation model was used to produce the scattering-pulse of the bubble.For harmonic imaging,the experiment was performed using a 64-element linear array,which was simulated by Field II.The results show that the harmonic components from the emission signal can be completely cancelled,and the harmonics generated by the nonlinear propagation of the wave through the tissue,can be reduced by 15-30 dB.Compared with the short pulse,the reversal phase-inversion pulse can improve the contrast and definition of the harmonic image significantly.

Ultrasound imaging of chitosan nerve conduits that bridge sciatic nerve defects in rats

The repair of peripheral nerve injuries with autologous nerve remains the gold standard （Wang et al., 2005; Yao et al., 2010; Deal et al., 2012; Kriebel et al., 2014; Liu et al., 2014; Tamaki et al., 2014; Yu et al., 2014; Zhu and Lou, 2014）. With advances in tissue engineering and biomaterials, tissue-engineered nerve conduits with various biomaterials and structures, such as collagen and chitosan nerve conduits, have already been used in the clinic as alternatives to autologous nerve in the repair of peripheral nerve injury （Wang et al., 2012; Svizenska et al., 2013; Eppenberger et al., 2014; Gu et al., 2014; Koudehi et al., 2014; MoyaDiaz et al., 2014; Novajra et al., 2014; Okamoto et al., 2014; Shea et al., 2014; Singh et al., 2014; Tamaki et al., 2014; Yu et al., 2014）. Therefore, new simple and effective methods

3D Elastic Registration of Ultrasound Images Based on Skeleton Feature

In order to eliminate displacement and elastic deformation between images of adjacent frames in course of 3D ultrasonic image reconstruction, elastic registration based on skeleton feature was adopt in this paper. A new automatically skeleton tracking extract algorithm is presented, which can extract connected skeleton to express figure feature. Feature points of connected skeleton are extracted automatically by accounting topical curvature extreme points several times. Initial registration is processed according to barycenter of skeleton. Whereafter, elastic registration based on radial basis function are processed according to feature points of skeleton. Result of example demonstrate that according to traditional rigid registration, elastic registration based on skeleton feature retain natural difference in shape for organr s different part, and eliminate slight elastic deformation between frames caused by image obtained process simultaneously. This algorithm has a high practical value for image registration in course of 3D ultrasound image reconstruction.

The Diagnosis of Diffuse Goitre by Ultrasound Imaging in Children

In order to find an easy and accurate procedure for diagnosis of diffuse goitre in children, we examined 50 patients with diffuse goitre using fine needle aspiration biopsy cytology, thyroid antibody detection, thyroid hormone analysis and ultrasound imaging. In the meantime, 109 healthy children (control) were examined by ultrasound imaging. The results showed that thyroid imaging in health children was a smooth echo pattern with stronger homogenous echogram than surrounding muscle tissues. The patients with diffuse goitre showed an normally enlarged thyroid volume. In 22 (84. 6 %) of 26 children With chronic lymphocytic thyroiditis, a varied patch hypoechogenicity was found, of whom 18 (81. 8 % ) had positive results of antibody testing. On the contrary, echo-pattern was normal in 17 (70. 8 %) of 24 patients with diffuse thyroid proliferation and only the remainder (7/24, 29. 1% ) had abnormal echo-pattern as well as elevated auto-antibody titers, of whom 2 were confirmed as chronic lymphocytic thyroiditis by a repeat fine needle aspiration biopsy 1 year later. By using combined ultrasound imaging and antibody determination, 92 % of the cases with chronic lymphocytic thyroiditis could be diagnosed. Our study suggests that ultrasonic imaging is an easy, non-invasive, reproducible and effective procedure in the differen,tial diagnosis of chronic lymphocytic thyroiditis in children.

Estimation of muscle pennation angle in ultrasound images using the beamlet transform

Ultrasound imaging has been widely used to investigate the architecture properties of skeletal muscle, including the measurement of the pennation angle. In this study, we propose a beamlet-based algorithm to detect the straight line- shaped patterns of aponeurosis, fascicle or bone, and then to quantify the pennation angle ix1 ultrasound images. The results demonstrate that the proposed algorithm can well detect the pennatoin angles in thirty ultrasound images with the correlation coefficient of 0.945, the standard root mean square error of 0.682°, and the relative root mean square error of 3.498%. The results suggest that this beamlet-based algorithm provides an alternative approach for the orientation estimation in muscu- loskeletal ultrasound images.

A diffusion method based on polar coordinate for ultrasound images denoising

The paper presents a novel anisotropic diffusion approach to the problem of ultrasound images denoising based on the polar-coordinate representation.Local gradients based on the polar coordinate are introduced and they are more suitable for ultrasound images than horizontal gradients and vertical gradients commonly used in anisotropic diffusion methods.Moreover,an adaptive adjustment scheme for the threshold parameter in conduction functions is presented according to the incident angle of the ultrasonic beam with respect to the organ surface.Furthermore,based on the structure matrix,an edge-adaptive diffusion model is introduced,which can selectively preserve the edge from the blurring or smooth noise.Experimental results of real ultrasound images show the validity of the presented approach,which takes the physical imaging mechanism of ultrasonic devices into account.

A Transfer Learning Approach Based on Ultrasound Images for Liver Cancer Detection

The convolutional neural network(CNN)is one of the main algorithms that is applied to deep transfer learning for classifying two essential types of liver lesions;Hemangioma and hepatocellular carcinoma(HCC).Ultrasound images,which are commonly available and have low cost and low risk compared to computerized tomography(CT)scan images,will be used as input for the model.A total of 350 ultrasound images belonging to 59 patients are used.The number of images with HCC is 202 and 148,respectively.These images were collected from ultrasound cases.info(28 Hemangiomas patients and 11 HCC patients),the department of radiology,the University of Washington(7 HCC patients),the Atlas of ultrasound Germany(3 HCC patients),and Radiopedia and others(10 HCC patients).The ultrasound images are divided into 225,52,and 73 for training,validation,and testing.A data augmentation technique is used to enhance the validation performance.We proposed an approach based on ensembles of the best-selected deep transfer models from the on-the-shelf models:VGG16,VGG19,DenseNet,Inception,InceptionResNet,ResNet,and EfficientNet.After tuning both the feature extraction and the classification layers,the best models are selected.Validation accuracy is used for model tuning and selection.The accuracy,sensitivity,specificity and AUROC are used to evaluate the performance.The experiments are concluded in five stages.The first stage aims to evaluate the base model performance by training the on-the-shelf models.The best accu-racy obtained in the first stage is 83.5%.In the second stage,we augmented the data and retrained the on-the-shelf models with the augmented data.The best accuracy we obtained in the second stage was 86.3%.In the third stage,we tuned the feature extraction layers of the on-the-shelf models.The best accuracy obtained in the third stage is 89%.In the fourth stage,we fine-tuned the classification layer and obtained an accuracy of 93%as the best accuracy.In the fifth stage,we applied the ensemble approach using the best three-performing models and obtained an accuracy,specificity,sensitivity,and AUROC of 94%,93.7%,95.1%,and 0.944,respectively.

Optically-excited simultaneous photoacoustic and ultrasound imaging based on aflexible gold-PDMS film

We constructed a flexible gold-polydimethylsiloxane(gold-PDMS)nanocomposites film with controllable thickness and light transmittance,to realize optically-excited simultaneous photo-acoustic(PA)and ultrasound(US)imaging under a single laser pulse irradiation.Benefiting from the excellent thermoelastic properties,the gold-PDMS film absorbs part of the incident laser energy and produces a high-intensity US,which is used to realize US imaging.Meanwhile,the partly transmitted light is used to excite samples for PA imaging.By controlling the thickness of the gold-PDMS,we can control the center frequency in the US imaging.We experimentally analyzed the frequency of the produced US signal by the gold-PDMSfilm and compared it with the finite element analysis(FEA)method,where the experiments agree with the FEA results.This method is demonstrated by the experiments on phantoms and a mouse model.Our work provides a cost-effective methodology for simultaneous PA and US imaging.

A Flexible and High Speed Digital Scan Converter for High Frequency Ultrasound Imaging

This paper presents a flexible and high speed digital scan converter (DSC) with the ability to handle high frequency ultrasound imaging in real-time. The characteristics in imaging system such as focus length of transducer, the swing radius and sampling length etc. could be changed easily in compliance with the researcher's application based on this flexible digital scan converter. Linear interpolation is employed to achieve the coordinate transformations algorithm. Custom-built software is programmed to preliminarily handle the algorithm according to different ultrasound imaging applications. High performance FPGA will implement high speed interpolation calculation based on the preliminary data which are stored in the DDR2 SDRAM from the software. 64 bit 66 MHz PCI is employed to accomplish high speed data transmission. Experiment has shown that more than 500 frame rate could be achieved based on this high speed digital scan converter. The designed flexible and high speed digital scan converter could be used in current FPGA based high frequency ultrasound imaging system.

Design and Experiments of Ultrasound Image-Guided Multi-DOF Robot System for Brachytherapy

To implant radioactive seeds through a needle precisely and safely, a novel multi-DOF surgical robotic system is presented in this paper for percutaneous prostate intervention through the patient’s perineum under real-time ultrasound image guidance. The proposed robot, which is designed with 9-DOF, consists of a 3-DOF automatic location platform for position adjustment, 2-DOF for automatic ultrasonic probe adjustment mounted with electromagnetic trackers, and 4-DOF for manually adjusting the guided template. Meanwhile, a new registration method based on the quaternion algorithm and least square method is developed, and the needle insertion is performed under the real-time guidance of a navigation system. Furthermore, the robot system has undergone some preliminary experiments with a laser tracker to evaluate the repeatability and accuracy of the robot system. The location error of the puncture needle tip can be controlled under 0.7 mm in air for the whole robotic system. The acquired results endorse the precision of the robot system for prostate seed implantation brachytherapy. © 2017, Tianjin University and Springer-Verlag GmbH Germany.

Adaptive diagonal loaded minimum variance beamforming applied to medical ultrasound imaging

In order to enhance the robustness and contrast in the minimum variance(MV) beamformer, adaptive diagonal loading method was proposed. The conventional diagonal loading technique has already been used in the MV beamformer, but has the drawback that its level is specified by predefined parameter and without consideration of input-data. To alleviate this problem, the level of diagonal loading was computed appropriately and automatically from the given data by shrinkage method in the proposed adaptive diagonal loaded beamformer. The performance of the proposed beamformer was tested on the simulated point target and cyst phantom was obtained using Field II. In the point target simulation, it is shown that the proposed method has higher lateral resolution than the conventional delay-and-sum beamformer and could be more robust in estimating the amplitude peak than the MV beamformer when acoustic velocity error exists. In the cyst phantom simulation, the proposed beamformer has shown that it achieves an improvement in contrast ratio and without distorting the edges of cyst.

Medical ultrasound image segmentation using genetic active contour

Image segmentation is one of the earliest and most important stages of image processing and plays an important role in both qualitative and quantitative analysis of medical ultrasound images but ultrasound images have low level of contrast and are corrupted with strong speckle noise. Due to these effects, segmentation of ultrasound images is very challenging and traditional image segmentation methods may not be leads to satisfactory results. The active contour method has been one of the widely used techniques for image segmentation;however, due to low quality of ultrasound images, it has encountered difficulties. In this paper, we presented a segmental method combined genetic algorithm and active contour with an energy minimization procedure based on genetic algorithms. This method have been proposed to overcome some limits of classical active contours, as con-tour initialization and local minima (speckle noise), and have been successfully applied on medical ultrasound images. Experimental result on medical ultrasound image show that our presented method only can correctly segment the circular tissue’s on ultra-sound images.