Medical image learning with limited and noisy data : second international workshop, MILLanD 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, proceedings. MILLanD (Workshop) : (2nd : 2023 : Vancouver, B...最新文献

筛选

英文中文

Automatic Quantification of COVID-19 Pulmonary Edema by Self-supervised Contrastive Learning. 通过自监督对比学习自动量化 COVID-19 肺水肿

Medical image learning with limited and noisy data : second international workshop, MILLanD 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, proceedings. MILLanD (Workshop) : (2nd : 2023 : Vancouver, B... Pub Date : 2023-10-01 Epub Date: 2023-10-08 DOI: 10.1007/978-3-031-44917-8_12

Zhaohui Liang, Zhiyun Xue, Sivaramakrishnan Rajaraman, Yang Feng, Sameer Antani

{"title":"Automatic Quantification of COVID-19 Pulmonary Edema by Self-supervised Contrastive Learning.","authors":"Zhaohui Liang, Zhiyun Xue, Sivaramakrishnan Rajaraman, Yang Feng, Sameer Antani","doi":"10.1007/978-3-031-44917-8_12","DOIUrl":"10.1007/978-3-031-44917-8_12","url":null,"abstract":"We proposed a self-supervised machine learning method to automatically rate the severity of pulmonary edema in the frontal chest X-ray radiographs (CXR) which could be potentially related to COVID-19 viral pneumonia. For this we use the modified radiographic assessment of lung edema (mRALE) scoring system. The new model was first optimized with the simple Siamese network (SimSiam) architecture where a ResNet-50 pretrained by ImageNet database was used as the backbone. The encoder projected a 2048-dimension embedding as representation features to a downstream fully connected deep neural network for mRALE score prediction. A 5-fold cross-validation with 2,599 frontal CXRs was used to examine the new model's performance with comparison to a non-pretrained SimSiam encoder and a ResNet-50 trained from scratch. The mean absolute error (MAE) of the new model is 5.05 (95%CI 5.03-5.08), the mean squared error (MSE) is 66.67 (95%CI 66.29-67.06), and the Spearman's correlation coefficient (Spearman ρ) to the expert-annotated scores is 0.77 (95%CI 0.75-0.79). All the performance metrics of the new model are superior to the two comparators (P<0.01), and the scores of MSE and Spearman ρ of the two comparators have no statistical difference (P>0.05). The model also achieved a prediction probability concordance of 0.811 and a quadratic weighted kappa of 0.739 with the medical expert annotations in external validation. We conclude that the self-supervised contrastive learning method is an effective strategy for mRALE automated scoring. It provides a new approach to improve machine learning performance and minimize the expert knowledge involvement in quantitative medical image pattern learning.","PeriodicalId":517398,"journal":{"name":"Medical image learning with limited and noisy data : second international workshop, MILLanD 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, proceedings. MILLanD (Workshop) : (2nd : 2023 : Vancouver, B...","volume":"14307 ","pages":"128-137"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10896252/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139984982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images. 在不知道医学图像异常的情况下进行通用异常检测的可行性

Can Cui, Yaohong Wang, Shunxing Bao, Yucheng Tang, Ruining Deng, Lucas W Remedios, Zuhayr Asad, Joseph T Roland, Ken S Lau, Qi Liu, Lori A Coburn, Keith T Wilson, Bennett A Landman, Yuankai Huo

{"title":"Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images.","authors":"Can Cui, Yaohong Wang, Shunxing Bao, Yucheng Tang, Ruining Deng, Lucas W Remedios, Zuhayr Asad, Joseph T Roland, Ken S Lau, Qi Liu, Lori A Coburn, Keith T Wilson, Bennett A Landman, Yuankai Huo","doi":"10.1007/978-3-031-44917-8_8","DOIUrl":"10.1007/978-3-031-44917-8_8","url":null,"abstract":"Many anomaly detection approaches, especially deep learning methods, have been recently developed to identify abnormal image morphology by only employing normal images during training. Unfortunately, many prior anomaly detection methods were optimized for a specific \"known\" abnormality (e.g., brain tumor, bone fraction, cell types). Moreover, even though only the normal images were used in the training process, the abnormal images were often employed during the validation process (e.g., epoch selection, hyper-parameter tuning), which might leak the supposed \"unknown\" abnormality unintentionally. In this study, we investigated these two essential aspects regarding universal anomaly detection in medical images by (1) comparing various anomaly detection methods across four medical datasets, (2) investigating the inevitable but often neglected issues on how to unbiasedly select the optimal anomaly detection model during the validation phase using only normal images, and (3) proposing a simple decision-level ensemble method to leverage the advantage of different kinds of anomaly detection without knowing the abnormality. The results of our experiments indicate that none of the evaluated methods consistently achieved the best performance across all datasets. Our proposed method enhanced the robustness of performance in general (average AUC 0.956).","PeriodicalId":517398,"journal":{"name":"Medical image learning with limited and noisy data : second international workshop, MILLanD 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, proceedings. MILLanD (Workshop) : (2nd : 2023 : Vancouver, B...","volume":"14307 ","pages":"82-92"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10959499/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140208818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Dual-Branch Network with Mixed and Self-Supervision for Medical Image Segmentation: An Application to Segment Edematous Adipose Tissue. 混合自监督双分支网络在医学图像分割中的应用——水肿性脂肪组织分割。

Medical image learning with limited and noisy data : second international workshop, MILLanD 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, proceedings. MILLanD (Workshop) : (2nd : 2023 : Vancouver, B... Pub Date : 2023-01-01 Epub Date: 2023-10-08 DOI: 10.1007/978-3-031-44917-8_15

Jianfei Liu, Omid Shafaat, Ronald M Summers

{"title":"A Dual-Branch Network with Mixed and Self-Supervision for Medical Image Segmentation: An Application to Segment Edematous Adipose Tissue.","authors":"Jianfei Liu, Omid Shafaat, Ronald M Summers","doi":"10.1007/978-3-031-44917-8_15","DOIUrl":"10.1007/978-3-031-44917-8_15","url":null,"abstract":"In clinical applications, one often encounters reduced segmentation accuracy when processing out-of-distribution (OOD) patient data. Segmentation models could be leveraged by utilizing either transfer learning or semi-supervised learning on a limited number of strong labels from manual annotation. However, over-fitting could potentially arise due to the small data size. This work develops a dual-branch network to improve segmentation on OOD data by also applying a large number of weak labels from inaccurate results generated by existing segmentation models. The dual-branch network consists of a shared encoder and two decoders to process strong and weak labels, respectively. Mixed supervision from both labels not only transfers the guidance from the strong decoder to the weak one, but also stabilizes the strong decoder. Additionally, weak labels are iteratively replaced with the segmentation masks from the strong decoder by self-supervision. We illustrate the proposed method on the adipose tissue segmentation of 40 patients with edema. Image data from edematous patients are OOD for existing segmentation methods, which often induces under-segmentation. Overall, the dual-branch segmentation network yielded higher accuracy than two baseline methods; the intersection over union (IoU) improved from 60.1% to 71.2% (p < 0.05). These findings demonstrate the potential of the dual-branch segmentation network with mixed- and self-supervision to process the OOD data in clinical applications.","PeriodicalId":517398,"journal":{"name":"Medical image learning with limited and noisy data : second international workshop, MILLanD 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, proceedings. MILLanD (Workshop) : (2nd : 2023 : Vancouver, B...","volume":"14307 ","pages":"158-167"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12016013/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0