Literature DB >> 33354790

Toward data-efficient learning: A benchmark for COVID-19 CT lung and infection segmentation.

Jun Ma1, Yixin Wang2, Xingle An3, Cheng Ge4, Ziqi Yu5, Jianan Chen6, Qiongjie Zhu7, Guoqiang Dong7, Jian He7, Zhiqiang He8, Tianjia Cao3, Yuntao Zhu9, Ziwei Nie9, Xiaoping Yang9.   

Abstract

PURPOSE: Accurate segmentation of lung and infection in COVID-19 computed tomography (CT) scans plays an important role in the quantitative management of patients. Most of the existing studies are based on large and private annotated datasets that are impractical to obtain from a single institution, especially when radiologists are busy fighting the coronavirus disease. Furthermore, it is hard to compare current COVID-19 CT segmentation methods as they are developed on different datasets, trained in different settings, and evaluated with different metrics.
METHODS: To promote the development of data-efficient deep learning methods, in this paper, we built three benchmarks for lung and infection segmentation based on 70 annotated COVID-19 cases, which contain current active research areas, for example, few-shot learning, domain generalization, and knowledge transfer. For a fair comparison among different segmentation methods, we also provide standard training, validation and testing splits, evaluation metrics and, the corresponding code.
RESULTS: Based on the state-of-the-art network, we provide more than 40 pretrained baseline models, which not only serve as out-of-the-box segmentation tools but also save computational time for researchers who are interested in COVID-19 lung and infection segmentation. We achieve average dice similarity coefficient (DSC) scores of 97.3%, 97.7%, and 67.3% and average normalized surface dice (NSD) scores of 90.6%, 91.4%, and 70.0% for left lung, right lung, and infection, respectively.
CONCLUSIONS: To the best of our knowledge, this work presents the first data-efficient learning benchmark for medical image segmentation, and the largest number of pretrained models up to now. All these resources are publicly available, and our work lays the foundation for promoting the development of deep learning methods for efficient COVID-19 CT segmentation with limited data.
© 2020 American Association of Physicists in Medicine.

Entities:  

Keywords:  COVID-19 CT; domain generalization; few-shot learning; knowledge transfer; lung and infection segmentation

Year:  2020        PMID: 33354790     DOI: 10.1002/mp.14676

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  31 in total

1.  Self-Ensembling Co-Training Framework for Semi-Supervised COVID-19 CT Segmentation.

Authors:  Caizi Li; Li Dong; Qi Dou; Fan Lin; Kebao Zhang; Zuxin Feng; Weixin Si; Xuesong Deng; Zhe Deng; Pheng-Ann Heng
Journal:  IEEE J Biomed Health Inform       Date:  2021-11-05       Impact factor: 5.772

2.  Multi-task semantic segmentation of CT images for COVID-19 infections using DeepLabV3+ based on dilated residual network.

Authors:  Hasan Polat
Journal:  Phys Eng Sci Med       Date:  2022-03-14

3.  Exploiting Shared Knowledge From Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation.

Authors:  Yichi Zhang; Qingcheng Liao; Lin Yuan; He Zhu; Jiezhen Xing; Jicong Zhang
Journal:  IEEE J Biomed Health Inform       Date:  2021-11-05       Impact factor: 5.772

4.  A systematic review on AI/ML approaches against COVID-19 outbreak.

Authors:  Onur Dogan; Sanju Tiwari; M A Jabbar; Shankru Guggari
Journal:  Complex Intell Systems       Date:  2021-07-05

5.  MRI-based radiomics signature for identification of invisible basal cisterns changes in tuberculous meningitis: a preliminary multicenter study.

Authors:  Qiong Ma; Yinqiao Yi; Tiejun Liu; Xinnian Wen; Fei Shan; Feng Feng; Qinqin Yan; Jie Shen; Guang Yang; Yuxin Shi
Journal:  Eur Radiol       Date:  2022-06-24       Impact factor: 7.034

6.  xViTCOS: Explainable Vision Transformer Based COVID-19 Screening Using Radiography.

Authors:  Arnab Kumar Mondal; Arnab Bhattacharjee; Parag Singla; A P Prathosh
Journal:  IEEE J Transl Eng Health Med       Date:  2021-12-08       Impact factor: 3.316

7.  Joint Learning of 3D Lesion Segmentation and Classification for Explainable COVID-19 Diagnosis.

Authors:  Xiaofei Wang; Lai Jiang; Liu Li; Mai Xu; Xin Deng; Lisong Dai; Xiangyang Xu; Tianyi Li; Yichen Guo; Zulin Wang; Pier Luigi Dragotti
Journal:  IEEE Trans Med Imaging       Date:  2021-08-31       Impact factor: 11.037

8.  Quantitative Assessment of Chest CT Patterns in COVID-19 and Bacterial Pneumonia Patients: a Deep Learning Perspective.

Authors:  Myeongkyun Kang; Kyung Soo Hong; Philip Chikontwe; Miguel Luna; Jong Geol Jang; Jongsoo Park; Kyeong Cheol Shin; Sang Hyun Park; June Hong Ahn
Journal:  J Korean Med Sci       Date:  2021-02-01       Impact factor: 2.153

9.  Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study.

Authors:  Qi Dou; Tiffany Y So; Meirui Jiang; Quande Liu; Varut Vardhanabhuti; Georgios Kaissis; Zeju Li; Weixin Si; Heather H C Lee; Kevin Yu; Zuxin Feng; Li Dong; Egon Burian; Friederike Jungmann; Rickmer Braren; Marcus Makowski; Bernhard Kainz; Daniel Rueckert; Ben Glocker; Simon C H Yu; Pheng Ann Heng
Journal:  NPJ Digit Med       Date:  2021-03-29

10.  A deep learning semantic segmentation architecture for COVID-19 lesions discovery in limited chest CT datasets.

Authors:  Nour Eldeen M Khalifa; Gunasekaran Manogaran; Mohamed Hamed N Taha; Mohamed Loey
Journal:  Expert Syst       Date:  2021-05-31       Impact factor: 2.812

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.