Ultrasound Imaging In Diagnosis Research Articles

Pictorial review of hepatic echinococcosis: Ultrasound imaging and differential diagnosis.

Echinococcosis is a zoonotic disease caused by parasites belonging to the genus Echinococcus that primarily affect the liver. The western plateau and pastoral areas of China are high-risk regions for hepatic cystic echinococcosis and hepatic alveolar echinococcosis (HAE). The high late mortality rate associated with HAE underscores the critical need for early diagnosis to improve cure rates and mitigate the disease burden in endemic areas. Currently, the World Health Organization recommends ultrasonography as the preferred initial screening method for hepatic echinococcosis. However, distinguishing between specific types of lesions, such as those of hepatic cystic echinococcosis and HAE, and other focal liver lesions is challenging. To address this issue, contrast-enhanced ultrasound is recommended as a tool to differentiate solid and cysto-solid hepatic echinococcosis from other focal liver lesions, significantly enhancing diagnostic accuracy. In this comprehensive review, we discuss the progression of hepatic echinococcosis and detail the imaging features of various types of echinococcosis using conventional, contrast-enhanced, and intraoperative ultrasound techniques. Our objective is to provide robust imaging evidence and guidance for early diagnosis, clinical decision making, and postoperative follow-up in regions with high disease prevalence.

YOLO-based thyroid ultrasound for assisted diagnosis

Abstract Real-time intelligent diagnosis of thyroid ultrasound images using deep learning techniques can mitigate the impact of human subjective factors on diagnostic outcomes. Three thousand and fifty-five thyroid ultrasound images were acquired from 205 selected patients aged 10 to 77 years who underwent ultrasound examinations between 2019 and 2023. Each image contained at least one area of thyroid nodules, totaling 3, 088 nodules, including 1, 752 benign and 1, 336 malignant nodules. YOLOV8 is the baseline model for developing an end-to-end architecture for thyroid nodule detection. This architecture automatically identifies nodule lesions in ultrasound images, classifies them as benign or malignant, and enables real-time detection in video frames. The experimental results on 611 clinical thyroid ultrasound images demonstrate that our method can accurately diagnose benign and malignant nodal lesions in thyroid ultrasound with 88.1% and 84.6% accuracy, respectively. The mean average accuracy is as high as 91.1%, indicating a 5.1% improvement compared to the baseline model.

Image quality improvement in single plane-wave imaging using deep learning

In ultrasound image diagnosis, single plane-wave imaging (SPWI), which can acquire ultrasound images at more than 1000 fps, has been used to observe detailed tissue and evaluate blood flow. SPWI achieves high temporal resolution by sacrificing the spatial resolution and contrast of ultrasound images. To improve spatial resolution and contrast in SPWI, coherent plane-wave compounding (CPWC) is used to obtain high-quality ultrasound images, i.e., compound images, by coherent addition of radio frequency (RF) signals acquired by transmitting plane waves in different directions. Although CPWC produces high-quality ultrasound images, their temporal resolution is lower than that of SPWI. To address this problem, some methods have been proposed to reconstruct a ultrasound image comparable to a compound image from RF signals obtained by transmitting a small number of plane waves in different directions. These methods do not fully consider the properties of RF signals, resulting in lower image quality compared to a compound image. In this paper, we propose methods to reconstruct high-quality ultrasound images in SPWI by considering the characteristics of RF signal of a single plane wave to obtain ultrasound images with image quality comparable to CPWC. The proposed methods employ encoder–decoder models of 1D U-Net, 2D U-Net, and their combination to generate the high-quality ultrasound images by minimizing the loss that considers the point spread effect of plane waves and frequency spectrum of RF signals in training. We also create a public large-scale SPWI/CPWC dataset for developing and evaluating deep-learning methods. Through a set of experiments using the public dataset and our dataset, we demonstrate that the proposed methods can reconstruct higher-quality ultrasound images from RF signals in SPWI than conventional method.

Ultrasound Imaging in Diagnosis and Management of Lower Limb Injuries: A Comprehensive Review.

Medical imaging tests are widely used to diagnose a broad spectrum of lower-limb injuries. Among these modalities, ultrasound (US) imaging has gained significant traction as a valuable diagnostic instrument for assessing conditions primarily affecting muscles, tendons, ligaments, and other soft tissues. However, there are important dilemmas related to the indications and possibilities of US in lower-limb injuries. Conflicting findings and approaches raise questions regarding the validity, accuracy, and usefulness of the US in that area. This narrative review attempts to summarize the current state of knowledge regarding US imaging of lower-limb injuries. The study provides a detailed discussion of the existing literature and contemporary insights on the diagnosis of lower-limb injuries using US examination, and draws attention to the role of the US in interventional procedures and monitoring of the healing process. The characteristics of normal muscles, tendons, and ligaments in US imaging are presented, along with the most commonly documented conditions affecting these tissues. Furthermore, the benefits and justifications for employing US in interventional procedures are discussed, ranging from platelet-rich plasma injections to physiotherapeutic treatments like percutaneous electrolysis. The study was further augmented with US pictures depicting various lower-limb injuries, mainly affecting young athletes. This article aims to review the role of US imaging in the diagnosis and management of common lower-limb injuries.

Deep Learning With Ultrasound Images Enhance the Diagnosis of Nonalcoholic Fatty Liver

ObjectiveThis research aimed to improve diagnosis of non-alcoholic fatty liver disease (NAFLD) by deep learning with ultrasound Images and reduce the impact of the professional competence and personal bias of the diagnostician. MethodThree convolutional neural network models were used to classify and identify the ultrasound images to obtain the best network. Then, the features in the ultrasound images were extracted and a new convolutional neural network was created based on the best network. Finally, the accuracy of several networks was compared and the best network was evaluated using AUC. ResultsModels of VGG16, ResNet50, and Inception-v3 were individually applied to classify and identify 710 ultrasound images containing NAFLD, demonstrating accuracies of 66.2%, 58.5%, and 59.2%, respectively. To further improve the classification accuracy, two features are presented: the ultrasound echo attenuation coefficient (θ), derived from fitting brightness values within sliding region of interest (ROIs), and the ratio of Doppler effect (ROD), identified through analyzing spots exhibiting the Doppler effect. Then, a multi-input deep learning network framework based on the VGG16 model is established, where the VGG16 model processes ultrasound image, while the fully connected layers handle θ and ROD. Ultimately, these components are combined to jointly generate predictions, demonstrating robust diagnostic capabilities for moderate to severe fatty liver (AUC = 0.95). Moreover, the average accuracy is increased from 64.8% to 77.5%, attributed to the introduction of two advanced features with domain knowledge. ConclusionThis research holds significant potential in aiding doctors for more precise and efficient diagnosis of ultrasound images related to NAFLD.

Influence of Image Factors on the Performance of Ophthalmic Ultrasound Deep Learning Model

ObjectiveThis study aims to evaluate the impact of image factors on the performance of deep learning models used for ophthalmic ultrasound image diagnosis. MethodsA total of 3,373 ophthalmic ultrasound images are used to deeply evaluate the influence of image factors on the performance of deep learning classification models. Inceptionv3, Xception, and the fusion model Inceptionv3-Xception are used to explore how brightness, contrast, gain, noise, size, format, pseudo-color seven image-related factors affect the classification performance of the model. ResultsInceptionv3-Xception has advantages in the recognition accuracy of various image factors. When the image brightness changes, the model's performance shows a downward trend (0.5 vs. 1 vs. 1.8, ACC 95.73 vs. 97.06 vs. 93.54, P < 0.05). When the image contrast changes, the model's performance is comparable (0.5 vs. 1 vs. 1.2, ACC 96.23 vs. 96.95 vs. 97.45, P > 0.05). When the image gain drops to 50 dB, the model's accuracy decreases significantly (50 dB vs. 105 dB, ACC 96.49 vs. 97.57, P < 0.05). When Gaussian noise is added to the image, the model's performance gradually decreases (0.02 vs. 0, ACC 89.48vs97.06, P < 0.05). When the image size drops to 25% of the original image, the model's performance decreases significantly (25% vs. 100%, ACC 93.18 vs. 97.06, P < 0.01). When the image format changes, the model's recognition accuracy is similar (JPG vs. BMP vs. PNG, ACC 96.98 vs. 97.06 vs. 97.06, P > 0.05). The accuracy of the model in recognizing pseudo-color images decreases significantly compared to grayscale images (grayscale vs. pseudo-color, ACC 35.96 vs. 97.06). ConclusionThese results indicate that image quality greatly influences the model training process, and acquiring high-quality images is an important prerequisite for high recognition performance of the model. This study offers valuable insights for the improvement of other robust deep learning models for ophthalmic ultrasound image recognition.

Fully automated diagnosis of thyroid nodule ultrasound using brain-inspired inference

The interpretability of artificial intelligence (AI) based medical diagnostic systems is crucial to make the diagnosis adequately convincible. Deep learning has been extensively investigated and utilized in the area of medical assistance diagnosis in recent decades due to its outstanding performance and objective prediction. However, a huge semantic chasm dividing clinicians and unexplainable deep models emerges. Here we design a brain-inspired inference framework from medical images to explainable features, then to the final diagnostic conclusions. The fast thinking module is responsible for recognizing medical features in ultrasound (US) images, and the slow-thinking module builds a model for inferring from medical features to diagnostic results by constructing a knowledge graph of medical features with tensor decomposition. The whole model infers through intuition and thinking like a human being, and gives the recognized medical image features while inferring the diagnosis, which greatly improves the interpretability of the model. We conducted studies on thyroid cancer diagnoses using US images. The American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) characteristics are employed as medical features describing thyroid nodules. Our brain-inspired medical inference framework outperforms commonly used deep learning algorithms, with an AUC score of 0.963 (95% confidential interval (CI)=0.923–1.000) for thyroid US image diagnosis. Results indicate that our framework improves diagnostic objectivity and interpretability while providing performance that is better than deep models. Our proposed brain-inspired medical inference framework could improve the efficiency of diagnosis and our technique is performant, objective and interpretable.

Application of an artificial intelligence-based system in the diagnosis of breast ultrasound images obtained using a smartphone

BackgroundBreast ultrasound (US) is useful for dense breasts, and the introduction of artificial intelligence (AI)-assisted diagnoses of breast US images should be considered. However, the implementation of AI-based technologies in clinical practice is problematic because of the costs of introducing such approaches to hospital information systems (HISs) and the security risk of connecting HIS to the Internet to access AI services. To solve these problems, we developed a system that applies AI to the analysis of breast US images captured using a smartphone.MethodsTraining data were prepared using 115 images of benign lesions and 201 images of malignant lesions acquired at the Division of Breast Surgery, Gifu University Hospital. YOLOv3 (object detection models) was used to detect lesions on US images. A graphical user interface (GUI) was developed to predict an AI server. A smartphone application was also developed for capturing US images displayed on the HIS monitor with its camera and displaying the prediction results received from the AI server. The sensitivity and specificity of the prediction performed on the AI server and via the smartphone were calculated using 60 images spared from the training.ResultsThe established AI showed 100% sensitivity and 75% specificity for malignant lesions and took 0.2 s per prediction with the AI sever. Prediction using a smartphone required 2 s per prediction and showed 100% sensitivity and 97.5% specificity for malignant lesions.ConclusionsGood-quality predictions were obtained using the AI server. Moreover, the quality of the prediction via the smartphone was slightly better than that on the AI server, which can be safely and inexpensively introduced into HISs.

Review on ultrasonographic diagnosis of thyroid diseases based on deep learning

In recent years, the incidence of thyroid diseases has increased significantly and ultrasound examination is the first choice for the diagnosis of thyroid diseases. At the same time, the level of medical image analysis based on deep learning has been rapidly improved. Ultrasonic image analysis has made a series of milestone breakthroughs, and deep learning algorithms have shown strong performance in the field of medical image segmentation and classification. This article first elaborates on the application of deep learning algorithms in thyroid ultrasound image segmentation, feature extraction, and classification differentiation. Secondly, it summarizes the algorithms for deep learning processing multimodal ultrasound images. Finally, it points out the problems in thyroid ultrasound image diagnosis at the current stage and looks forward to future development directions. This study can promote the application of deep learning in clinical ultrasound image diagnosis of thyroid, and provide reference for doctors to diagnose thyroid disease.

Rapid Segmentation and Diagnosis of Breast Tumor Ultrasound Images at the Sonographer Level Using Deep Learning.

Breast cancer is one of the most common malignant tumors in women. A noninvasive ultrasound examination can identify mammary-gland-related diseases and is well tolerated by dense breast, making it a preferred method for breast cancer screening and of significant clinical value. However, the diagnosis of breast nodules or masses via ultrasound is performed by a doctor in real time, which is time-consuming and subjective. Junior doctors are prone to missed diagnoses, especially in remote areas or grass-roots hospitals, due to limited medical resources and other factors, which bring great risks to a patient's health. Therefore, there is an urgent need to develop fast and accurate ultrasound image analysis algorithms to assist diagnoses. We propose a breast ultrasound image-based assisted-diagnosis method based on convolutional neural networks, which can effectively improve the diagnostic speed and the early screening rate of breast cancer. Our method consists of two stages: tumor recognition and tumor classification. (1) Attention-based semantic segmentation is used to identify the location and size of the tumor; (2) the identified nodules are cropped to construct a training dataset. Then, a convolutional neural network for the diagnosis of benign and malignant breast nodules is trained on this dataset. We collected 2057 images from 1131 patients as the training and validation dataset, and 100 images of the patients with accurate pathological criteria were used as the test dataset. The experimental results based on this dataset show that the MIoU of tumor location recognition is 0.89 and the average accuracy of benign and malignant diagnoses is 97%. The diagnosis performance of the developed diagnostic system is basically consistent with that of senior doctors and is superior to that of junior doctors. In addition, we can provide the doctor with a preliminary diagnosis so that it can be diagnosed quickly. Our proposed method can effectively improve diagnostic speed and the early screening rate of breast cancer. The system provides a valuable aid for the ultrasonic diagnosis of breast cancer.

EP06.10: Diagnosis of normal or abnormal fetal brain ultrasound images in the first trimester based on AI

EP06.10: Diagnosis of normal or abnormal fetal brain ultrasound images in the first trimester based on AI

CAS: Breast cancer diagnosis framework based on lesion region recognition in ultrasound images

Automated diagnosis of complex breast ultrasound images using deep learning has important clinical implications. In this study, we propose a novel breast cancer diagnosis framework, the CAS framework, based on lesion region to effectively recognize benign and malignant tumors. Firstly, train the segmentation network CRA-ENet on a public dataset with masks and save the trained weights. Then, the weights are used to segment clinical data without masks to obtain masks. Next, cover the masks on the corresponding original images to obtain ultrasound images that only include the lesion region. Finally, the SA-Net is employed to recognize benign and malignant tumors in images. Both the CRA-ENet and SA-Net are novel models explicitly designed for this study. The CRA-ENet is a network derived from ENet through pruning, convolutional replacement, and the incorporation of a hybrid attention mechanism, which can accurately segment breast tumor boundaries, allowing precise localization of lesion regions. The SA-Net is an innovative multi-branch parallel lightweight network that can enable effective artifact suppression and extraction of lesion-relevant features, significantly improving classification accuracy. In experimental, to validate the performance and efficiency of the proposed framework on clinical data provided by Yunnan Cancer Hospital based on the public dataset BUSI. Compared with simple classification utilizing only the classification network, the proposed approach improved accuracy, precision, and F1 score by 4.01%, 3.98%, and 4.00%, respectively, demonstrating the advantages of the framework.

Breast ultrasound image classification and physiological assessment based on GoogLeNet

BackgroundMedical ultrasound image classification based on convolutional neural network is the mainstream breast cancer classification model, but its limited perceptual ability limits its ability to obtain global information. MethodologyA total of 880 breast ultrasound images were collected from 700 patients including 103 normal images, 467 malignant tumor images and 210 benign tumor images. In this paper, the diagnosis of breast ultrasound images was realized by constructing the CNN model of GoogLeNet. Firstly, the breast images were preprocessed based on the TV model. After that, the CNN model was trained and a more accurate model with a wider range of application was obtained based on improved Inception. Then we extract image features of different sizes; Then, feature classification was completed in different model classifiers to realize benign and malignant detection of breast cancer. Meanwhile, comparative analysis was performed to verify the excellence of the GoogLeNet model. ResultsThe training time for classification was effectively reduced, and the classification accuracy rate was improved, reaching 96.37% combined with transformer learning. The loss value is down to 0.3492. Then, the classification accuracy of different structural models is discussed in the two models. The results show that GoogLeNet has great advantages in the detection of breast cancer ultrasound images. The influence of migration on experimental results is further discussed. Finally, combined with transfer learning, the three models were tested separately. The results show that transfer learning can improve system performance. ConclusionBased on the TV model and the GoogLeNet model, this paper designs a method of breast cancer detection and classification based on the combination of TV and GoogLeNet model and transfer learning. Experiments show that this method can repair part of the texture damaged by markers in ultrasonic images, effectively extract the features of thyroid nodule, and accurately judge whether the breast is diseased, which greatly improves the diagnostic efficiency of doctors.

A tunable sub-wavelength acoustic imaging planar metalens

Acoustic metamaterials can be used to fabricate metalenses that can achieve sub-wavelength imaging resolution, but the reported devices are often passive and cannot adapt to changes in working frequency. To this end, we propose a dynamic tunable acoustic imaging planar metalens by introducing a telescopic tube between two sets of perforated Fabry–Pérot resonant metamaterial lenses to adjust the combined length of the imaging hole. Since the working frequency of the Fabry–Pérot resonant structure is directly related to the thickness of the metalens, continuous adjustment of the working frequency can be achieved by continuously changing the length of the imaging hole. This Fabry–Pérot resonant perforated structure belongs to an acoustic metamaterial unit, which can be resonantly coupled with evanescent waves to enhance the evanescent waves carrying detailed information of objects, thereby realizing high-resolution imaging. Relying on the resonance tunneling effect of the imaging hole, high acoustic transmittance can be obtained at the working frequency, ensuring excellent imaging quality. Through numerical calculation and experimental measurement results, the imaging performance and tunability of the tunable sub-wavelength acoustic imaging metalens are demonstrated. The proposed tunable acoustic planar metalens overcomes the shortcomings of the fixed working frequency of passive metalenses and has potential applications in the fields of ultrasound imaging and medical diagnosis.

Contrast-enhanced ultrasound combined targeted microbubbles for diagnosis of highly aggressive papillary thyroid carcinoma.

Accurate diagnosis of highly aggressive papillary thyroid cancer (PTC) may greatly help avoid overdiagnosis and overtreatment of PTC. However, there is still a lack of a convenient and accurate method. Targeted microbubbles, an emerging ultrasound contrast agent, have the potential to accurately diagnose highly aggressive PTC. To design and prepare a targeted microbubble for specific contrast-enhanced ultrasound (CEUS) imaging of highly invasive PTC. Using β-galactoside-binding protein galectin-3 (Gal-3) overexpressed on the surface of highly invasive PTC cells as a target, C12 polypeptide (ANTPCGPYTHDCPVKR) with high affinity and specificity for Gal-3 was coupled to the surface of lipid microbubbles to prepare targeted microbubbles (Gal-3-C12@lipo MBs). The targeted microbubbles were prepared by thin-film hydration method and mechanical shaking method. The morphology, diameter, concentration and stability of microbubbles were investigated by fluorescence microscopy and an AccuSizer. The biosafety of microbubbles was studied using BCPAP cells through CCK8 assay. Confocal laser scanning microscope and flow cytometry were applied to research the cellular uptake of microbubbles to investigate the targeting ability to highly aggressive PTC. Finally, the specific contrast-enhanced ultrasound imaging of microbubbles in highly invasive PTC was validated on the mice bearing subcutaneous BCPAP tumor model via a clinically ultrasound imaging system. Gal-3-C12@lipo MBs were successfully prepared which showed a well-defined spherical morphology with an average diameter of 1.598 ± 0.848 μm. Gal-3-C12@lipo MBs showed good stability without rupture within 4 hours after preparation. At the cellular level, Gal-3-C12@lipo MBs exhibited favorable biosafety and superior targeting ability to BCPAP cells, with 2.8-fold higher cellular uptake than non-targeted lipid microbubbles (Lipo MBs). At the animal level, Gal-3-C12@lipo MBs significantly improved the quality of contrast-enhanced ultrasound imaging in highly invasive PTC, with an echo intensity of tumor significantly higher than that of Lipo MBs. We designed and fabricated a novel targeted microbubble for the specific ultrasound imaging diagnosis of highly aggressive PTC. The targeted microbubbles have good stability, superior biosafety and high targeting specificity, which can significantly improve the tumor signal-to-noise ratio of highly invasive PTC, and have the potential to facilitate and accurately diagnose highly invasive PTC.

Automatic detection and diagnosis of thyroid ultrasound images based on attention mechanism

Incidents of thyroid cancer have dramatically increased in recent years; however, early ultrasound diagnosis can reduce morbidity and mortality. The work in clinical situations relies heavily on the subjective experience of the sonographer. Numerous computer-aided diagnostic techniques exist, but most consider how good the results are, ignoring the pre-image collecting and its usefulness in post-clinical practise. To address these issues, this study proposes a computer-aided diagnosis method based on an attentional mechanism. Due to its lightweight properties, the model can rapidly identify nodules and distinguish between benign and malignant ones without using much hardware. The model uses a bounding box to locate the thyroid nodule and determines whether it is benign or cancerous, and outputs the diagnostic result of the thyroid nodule ultrasound images. The latest attention mechanisms are used to get better results at a fraction of the cost. Additionally, ultrasound images with different features of benign and malignant thyroid nodules were collected following the Thyroid Imaging Reporting and Data System standards. The experimental results showed that the approach identifies and classifies thyroid nodules rapidly and effectively; the mAP value of the results reached 0.89, and the mAP value of malignant nodules reached 0.94, with detection rate of single image reached 7 ms. Young physicians and small hospitals with limited resources can benefit from using this method to assist with thyroid ultrasound examination diagnosis.

Combined CNN and Pixel Feature Image for Fatty Liver Ultrasound Image Classification.

Recent revolutionary results of deep learning indicate the advent of reliable classifiers to perform difficult tasks in medical diagnosis. Fatty liver is a common liver disease, and it is also one of the major challenges people face in disease prevention. It will cause many complications, which need to be found and treated in time. In the field of automatic diagnosis of fatty liver ultrasound images, there are problems of less data amount, and the pathological images of different severity are similar. Therefore, this paper proposes a classification method through combining convolutional neural network with the differential image patches based on pixel-level features for fatty liver ultrasonic images. It can automatically diagnose the ultrasonic images of normal liver, low-grade fatty liver, moderate grade fatty liver, and severe fatty liver. The proposed method not only solves the problem of less data amount but also improves the accuracy of classification. Compared with other deep learning methods and traditional methods, the experimental results show that our method has better accuracy than other classification methods.

Ultrasound image intelligent diagnosis in community-acquired pneumonia of children using convolutional neural network-based transfer learning.

Studies show that lung ultrasound (LUS) can accurately diagnose community-acquired pneumonia (CAP) and keep children away from radiation, however, it takes a long time and requires experienced doctors. Therefore, a robust, automatic and computer-based diagnosis of LUS is essential. To construct and analyze convolutional neural networks (CNNs) based on transfer learning (TL) to explore the feasibility of ultrasound image diagnosis and grading in CAP of children. 89 children expected to receive a diagnosis of CAP were prospectively enrolled. Clinical data were collected, a LUS images database was established comprising 916 LUS images, and the diagnostic values of LUS in CAP were analyzed. We employed pre-trained models (AlexNet, VGG 16, VGG 19, Inception v3, ResNet 18, ResNet 50, DenseNet 121 and DenseNet 201) to perform CAP diagnosis and grading on the LUS database and evaluated the performance of each model. Among the 89 children, 24 were in the non-CAP group, and 65 were finally diagnosed with CAP, including 44 in the mild group and 21 in the severe group. LUS was highly consistent with clinical diagnosis, CXR and chest CT (kappa values = 0.943, 0.837, 0.835). Experimental results revealed that, after k-fold cross-validation, Inception v3 obtained the best diagnosis accuracy, PPV, sensitivity and AUC of 0.87 ± 0.02, 0.90 ± 0.03, 0.92 ± 0.04 and 0.82 ± 0.04, respectively, for our dataset out of all pre-trained models. As a result, best accuracy, PPV and specificity of 0.75 ± 0.03, 0.89 ± 0.05 and 0.80 ± 0.10 were achieved for severity classification in Inception v3. LUS is a reliable method for diagnosing CAP in children. Experiments showed that, after transfer learning, the CNN models successfully diagnosed and classified LUS of CAP in children; of these, the Inception v3 achieves the best performance and may serve as a tool for the further research and development of AI automatic diagnosis LUS system in clinical applications. www.chictr.org.cn ChiCTR2200057328.

An enhanced multiscale generation and depth-perceptual loss-based super-resolution network for prostate ultrasound images

Computer-aided diagnosis of prostate ultrasound images is gradually being combined with deep learning to help detect and treat diseases. However, ultrasound images of the prostate have problems such as low resolution and unbalanced categories. In addition, the current image classification algorithms have difficulty with classification network performance due to insufficient data volume. To solve these problems, inspired by CycleGAN, we propose an enhanced multiscale generation and depth-perceptual loss-based super-resolution (SR) network for prostate ultrasound images (EGDL-CycleGAN). We study and improve the generative network and perceptual loss of CycleGAN. In this work we achieve multiscale feature extraction through an improved generator, and utilize full-scale skip connections between encoder and decoder to capture fine-grained details and coarse-grained semantics at full scale. This effectively improves the performance of the generative network and makes the reconstruction effect better. We also use the residual structure for deep extraction of features to obtain perceptual loss, and add this to the network loss function for training the model. This enables the model to learn the global and local differences between the real and generated images. This approach pays more attention to the edge information and spatial information of the image, and provides relevant spatial information feedback to the generator to improve the generator’s ability to perceive consistent super-resolution. The method can enhance the prostate ultrasound image dataset and provide rich images for the next step in intelligence-assisted classification and diagnosis of prostate cancer ultrasound images. The evaluation of peak signal-to-noise ratio/structural similarity and visual effects against the benchmark of our datasets illustrates that our proposed approach is effective and superior to the bicubic classic image SR reconstruction algorithm, the SRGAN perception-driven method and the CycleGAN method applied to ultrasound images. In addition, the method of using the original dataset combined with the SR reconstruction image dataset can effectively improve the accuracy of the classification network in intelligence-assisted classification diagnosis of prostate cancer ultrasound images. In EfficientNetV2 the accuracy is improved from 0.843 to 0.867 and in Swin Transformer the accuracy is improved from 0.893 to 0.917.

Self-supervised multi-modal fusion network for multi-modal thyroid ultrasound image diagnosis

Ultrasound is a typical non-invasive diagnostic method often used to detect thyroid cancer lesions. However, due to the limitations of the information provided by ultrasound images, shear wave elastography (SWE) and color doppler ultrasound (CDUS) are also used clinically to assist in diagnosis, which makes the diagnosis time-consuming, labor-intensive, and highly subjective process. Therefore, automatic diagnosis of benign and malignant thyroid nodules is beneficial for the clinical diagnosis of the thyroid. To this end, based on three modalities of gray-scale ultrasound images(US), SWE, and CDUS, we propose a deep learning-based multi-modal feature fusion network for the automatic diagnosis of thyroid disease based on the ultrasound images. First, three ResNet18s initialized by self-supervised learning are used as branches to extract the image information of each modality, respectively. Then, a multi-modal multi-head attention branch is used to remove the common information of three modalities, and the knowledge of each modal is combined for thyroid diagnosis. At the same time, to better integrate the features between modalities, a multi-modal feature guidance module is also proposed to guide the feature extraction of each branch and reduce the difference between each-modal feature. We verify the multi-modal thyroid ultrasound image diagnosis method on the self-collected dataset, and the results prove that this method could provide fast and accurate assistance for sonographers in diagnosing thyroid nodules.