1
|
Migliorelli G, Fiorentino MC, Di Cosmo M, Villani FP, Mancini A, Moccia S. On the use of contrastive learning for standard-plane classification in fetal ultrasound imaging. Comput Biol Med 2024; 174:108430. [PMID: 38613892 DOI: 10.1016/j.compbiomed.2024.108430] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 03/06/2024] [Accepted: 04/07/2024] [Indexed: 04/15/2024]
Abstract
BACKGROUND To investigate the effectiveness of contrastive learning, in particular SimClr, in reducing the need for large annotated ultrasound (US) image datasets for fetal standard plane identification. METHODS We explore SimClr advantage in the cases of both low and high inter-class variability, considering at the same time how classification performance varies according to different amounts of labels used. This evaluation is performed by exploiting contrastive learning through different training strategies. We apply both quantitative and qualitative analyses, using standard metrics (F1-score, sensitivity, and precision), Class Activation Mapping (CAM), and t-Distributed Stochastic Neighbor Embedding (t-SNE). RESULTS When dealing with high inter-class variability classification tasks, contrastive learning does not bring a significant advantage; whereas it results to be relevant for low inter-class variability classification, specifically when initialized with ImageNet weights. CONCLUSIONS Contrastive learning approaches are typically used when a large number of unlabeled data is available, which is not representative of US datasets. We proved that SimClr either as pre-training with backbone initialized via ImageNet weights or used in an end-to-end dual-task may impact positively the performance over standard transfer learning approaches, under a scenario in which the dataset is small and characterized by low inter-class variability.
Collapse
Affiliation(s)
| | | | - Mariachiara Di Cosmo
- Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy
| | | | - Adriano Mancini
- Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy
| | - Sara Moccia
- The BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna, Pisa, Italy
| |
Collapse
|
2
|
Peng J, Zeng J, Lai M, Huang R, Ni D, Li Z. One-Stop Automated Diagnostic System for Carpal Tunnel Syndrome in Ultrasound Images Using Deep Learning. ULTRASOUND IN MEDICINE & BIOLOGY 2024; 50:304-314. [PMID: 38044200 DOI: 10.1016/j.ultrasmedbio.2023.10.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 08/23/2023] [Accepted: 10/22/2023] [Indexed: 12/05/2023]
Abstract
OBJECTIVE Ultrasound (US) examination has unique advantages in diagnosing carpal tunnel syndrome (CTS), although identification of the median nerve (MN) and diagnosis of CTS depend heavily on the expertise of examiners. In the aim of alleviating this problem, we developed a one-stop automated CTS diagnosis system (OSA-CTSD) and evaluated its effectiveness as a computer-aided diagnostic tool. METHODS We combined real-time MN delineation, accurate biometric measurements and explainable CTS diagnosis into a unified framework, called OSA-CTSD. We then collected a total of 32,301 static images from US videos of 90 normal wrists and 40 CTS wrists for evaluation using a simplified scanning protocol. RESULTS The proposed model exhibited better segmentation and measurement performance than competing methods, with a Hausdorff distance (95th percentile) score of 7.21 px, average symmetric surface distance score of 2.64 px, Dice score of 85.78% and intersection over union score of 76.00%. In the reader study, it exhibited performance comparable to the average performance of experienced radiologists in classifying CTS and outperformed inexperienced radiologists in terms of classification metrics (e.g., accuracy score 3.59% higher and F1 score 5.85% higher). CONCLUSION Diagnostic performance of the OSA-CTSD was promising, with the advantages of real-time delineation, automation and clinical interpretability. The application of such a tool not only reduces reliance on the expertise of examiners but also can help to promote future standardization of the CTS diagnostic process, benefiting both patients and radiologists.
Collapse
Affiliation(s)
- Jiayu Peng
- Department of Ultrasound, Second People's Hospital of Shenzhen, First Affiliated Hospital of Shenzhen University, Shenzhen, China; Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China
| | - Jiajun Zeng
- Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China
| | - Manlin Lai
- Ultrasound Division, Department of Medical Imaging, University of Hong Kong-Shenzhen Hospital, Shenzhen, China
| | - Ruobing Huang
- Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China
| | - Dong Ni
- Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China
| | - Zhenzhou Li
- Department of Ultrasound, Second People's Hospital of Shenzhen, First Affiliated Hospital of Shenzhen University, Shenzhen, China; Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China.
| |
Collapse
|
3
|
Duan X, Yang L, Zhu W, Yuan H, Xu X, Wen H, Liu W, Chen M. Is the diagnostic model based on convolutional neural network superior to pediatric radiologists in the ultrasonic diagnosis of biliary atresia? Front Med (Lausanne) 2024; 10:1308338. [PMID: 38259860 PMCID: PMC10800889 DOI: 10.3389/fmed.2023.1308338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Accepted: 12/11/2023] [Indexed: 01/24/2024] Open
Abstract
Background Many screening and diagnostic methods are currently available for biliary atresia (BA), but the early and accurate diagnosis of BA remains a challenge with existing methods. This study aimed to use deep learning algorithms to intelligently analyze the ultrasound image data, build a BA ultrasound intelligent diagnostic model based on the convolutional neural network, and realize an intelligent diagnosis of BA. Methods A total of 4,887 gallbladder ultrasound images of infants with BA, non-BA hyperbilirubinemia, and healthy infants were collected. Two mask region convolutional neural network (Mask R-CNN) models based on different backbone feature extraction networks were constructed. The diagnostic performance between the two models was compared through good-quality images at the image level and the patient level. The diagnostic performance between the two models was compared through poor-quality images. The diagnostic performance of BA between the model and four pediatric radiologists was compared at the image level and the patient level. Results The classification performance of BA in model 2 was slightly higher than that in model 1 in the test set, both at the image level and at the patient level, with a significant difference of p = 0.0365 and p = 0.0459, respectively. The classification accuracy of model 2 was slightly higher than that of model 1 in poor-quality images (88.3% vs. 86.4%), and the difference was not statistically significant (p = 0.560). The diagnostic performance of model 2 was similar to that of the two radiology experts at the image level, and the differences were not statistically significant. The diagnostic performance of model 2 in the test set was higher than that of the two radiology experts at the patient level (all p < 0.05). Conclusion The performance of model 2 based on Mask R-CNN in the diagnosis of BA reached or even exceeded the level of pediatric radiology experts.
Collapse
Affiliation(s)
- Xingxing Duan
- Department of Ultrasound, Changsha Hospital for Maternal and Child Health Care, Changsha, China
| | - Liu Yang
- Department of Ultrasound, Hunan Children’s Hospital, Changsha, China
| | - Weihong Zhu
- Department of Ultrasound, Chenzhou Children’s Hospital, Chenzhou, China
| | - Hongxia Yuan
- Department of Ultrasound, Changsha Hospital for Maternal and Child Health Care, Changsha, China
| | - Xiangfen Xu
- Department of Ultrasound, Hunan Children’s Hospital, Changsha, China
| | - Huan Wen
- Department of Ultrasound, Hunan Children’s Hospital, Changsha, China
| | - Wengang Liu
- Department of Ultrasound, The Third Xiangya Hospital of Central South University, Changsha, China
| | - Meiyan Chen
- Department of Ultrasound, Chaling Hospital for Maternal and Child Health Care, Chaling, China
| |
Collapse
|
4
|
Ando S, Loh PY. Convolutional Neural Network Approaches in Median Nerve Morphological Assessment from Ultrasound Images. J Imaging 2024; 10:13. [PMID: 38248998 PMCID: PMC10817571 DOI: 10.3390/jimaging10010013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Revised: 12/27/2023] [Accepted: 12/29/2023] [Indexed: 01/23/2024] Open
Abstract
Ultrasound imaging has been used to investigate compression of the median nerve in carpal tunnel syndrome patients. Ultrasound imaging and the extraction of median nerve parameters from ultrasound images are crucial and are usually performed manually by experts. The manual annotation of ultrasound images relies on experience, and intra- and interrater reliability may vary among studies. In this study, two types of convolutional neural networks (CNNs), U-Net and SegNet, were used to extract the median nerve morphology. To the best of our knowledge, the application of these methods to ultrasound imaging of the median nerve has not yet been investigated. Spearman's correlation and Bland-Altman analyses were performed to investigate the correlation and agreement between manual annotation and CNN estimation, namely, the cross-sectional area, circumference, and diameter of the median nerve. The results showed that the intersection over union (IoU) of U-Net (0.717) was greater than that of SegNet (0.625). A few images in SegNet had an IoU below 0.6, decreasing the average IoU. In both models, the IoU decreased when the median nerve was elongated longitudinally with a blurred outline. The Bland-Altman analysis revealed that, in general, both the U-Net- and SegNet-estimated measurements showed 95% limits of agreement with manual annotation. These results show that these CNN models are promising tools for median nerve ultrasound imaging analysis.
Collapse
Affiliation(s)
- Shion Ando
- Department of Mechanical Engineering, Faculty of Engineering, Kyushu University, Fukuoka 819-0395, Japan;
| | - Ping Yeap Loh
- Department of Human Life Design and Science, Faculty of Design, Kyushu University, Fukuoka 819-0395, Japan
| |
Collapse
|
5
|
Gujarati KR, Bathala L, Venkatesh V, Mathew RS, Yalavarthy PK. Transformer-Based Automated Segmentation of the Median Nerve in Ultrasound Videos of Wrist-to-Elbow Region. IEEE TRANSACTIONS ON ULTRASONICS, FERROELECTRICS, AND FREQUENCY CONTROL 2024; 71:56-69. [PMID: 37930930 DOI: 10.1109/tuffc.2023.3330539] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/08/2023]
Abstract
Segmenting the median nerve is essential for identifying nerve entrapment syndromes, guiding surgical planning and interventions, and furthering understanding of nerve anatomy. This study aims to develop an automated tool that can assist clinicians in localizing and segmenting the median nerve from the wrist, mid-forearm, and elbow in ultrasound videos. This is the first fully automated single deep learning model for accurate segmentation of the median nerve from the wrist to the elbow in ultrasound videos, along with the computation of the cross-sectional area (CSA) of the nerve. The visual transformer architecture, which was originally proposed to detect and classify 41 classes in YouTube videos, was modified to predict the median nerve in every frame of ultrasound videos. This is achieved by modifying the bounding box sequence matching block of the visual transformer. The median nerve segmentation is a binary class prediction, and the entire bipartite matching sequence is eliminated, enabling a direct comparison of the prediction with expert annotation in a frame-by-frame fashion. Model training, validation, and testing were performed on a dataset comprising ultrasound videos collected from 100 subjects, which were partitioned into 80, ten, and ten subjects, respectively. The proposed model was compared with U-Net, U-Net++, Siam U-Net, Attention U-Net, LSTM U-Net, and Trans U-Net. The proposed transformer-based model effectively leveraged the temporal and spatial information present in ultrasound video frames and efficiently segmented the median nerve with an average dice similarity coefficient (DSC) of approximately 94% at the wrist and 84% in the entire forearm region.
Collapse
|
6
|
Yeh CL, Wu CH, Hsiao MY, Kuo PL. Real-Time Automated Segmentation of Median Nerve in Dynamic Ultrasonography Using Deep Learning. ULTRASOUND IN MEDICINE & BIOLOGY 2023; 49:1129-1136. [PMID: 36740461 DOI: 10.1016/j.ultrasmedbio.2022.12.014] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/09/2022] [Revised: 12/01/2022] [Accepted: 12/22/2022] [Indexed: 05/11/2023]
Abstract
OBJECTIVE The morphological dynamics of the median nerve across the level extracted from dynamic ultrasonography are valuable for the diagnosis and evaluation of carpal tunnel syndrome (CTS), but the data extraction requires tremendous labor to manually segment the nerve across the image sequence. Our aim was to provide visually real-time, automated median nerve segmentation and subsequent data extraction in dynamic ultrasonography. METHODS We proposed a deep-learning model modified from SOLOv2 and tailored for median nerve segmentation. Ensemble strategies combining several state-of-the-art models were also employed to examine whether the segmentation accuracy could be improved. Image data were acquired from nine normal participants and 59 patients with idiopathic CTS. DISCUSSION Our model outperformed several state-of-the-art models with respect to inference speed, whereas the segmentation accuracy was on a par with that achieved by these models. When evaluated on a single 1080Ti GPU card, our model achieved an intersection over union score of 0.855 and Dice coefficient of 0.922 at 28.9 frames/s. The ensemble models slightly improved segmentation accuracy. CONCLUSION Our model has great potential for use in the clinical setting, as the real-time, automated extraction of the morphological dynamics of the median nerve allows clinicians to diagnose and treat CTS as the images are acquired.
Collapse
Affiliation(s)
- Cheng-Liang Yeh
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan
| | - Chueh-Hung Wu
- Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei, Taiwan; College of Medicine, National Taiwan University, Taipei, Taiwan
| | - Ming-Yen Hsiao
- Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei, Taiwan; College of Medicine, National Taiwan University, Taipei, Taiwan
| | - Po-Ling Kuo
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan; College of Medicine, National Taiwan University, Taipei, Taiwan; Electrical Engineering Department, National Taiwan University, Taipei, Taiwan.
| |
Collapse
|