Crowdsourcing pneumothorax annotations using machine learning annotations on the NIH chest X-ray dataset
- 43 Downloads
Pneumothorax is a potentially life-threatening condition that requires prompt recognition and often urgent intervention. In the ICU setting, large numbers of chest radiographs are performed and must be interpreted on a daily basis which may delay diagnosis of this entity. Development of artificial intelligence (AI) techniques to detect pneumothorax could help expedite detection as well as localize and potentially quantify pneumothorax. Open image analysis competitions are useful in advancing state-of-the art AI algorithms but generally require large expert annotated datasets. We have annotated and adjudicated a large dataset of chest radiographs to be made public with the goal of sparking innovation in this space. Because of the cumbersome and time-consuming nature of image labeling, we explored the value of using AI models to generate annotations for review. Utilization of this machine learning annotation (MLA) technique appeared to expedite our annotation process with relatively high sensitivity at the expense of specificity. Further research is required to confirm and better characterize the value of MLAs. Our adjudicated dataset is now available for public consumption in the form of a challenge.
KeywordsArtificial intelligence Machine learning annotations Public datasets Challenge Pneumothorax Chest radiograph
Anna Zawacki from the Society of Imaging Informatics in Medicine (SIIM) for administrative support during the STR review process.
Compliance with ethical standards
Conflict of Interest
The annotation platform used for this work was provided by MD.ai at no cost. Two authors (Anouk Stein, M.D. and George Shih, M.D., M.S.) serve as stakeholders and/or consultants for MD.ai.
- 3.Onuki T, Ueda S, Yamaoka M, Sekiya Y, Yamada H, Kawakami N, Araki Y, Wakai Y, Saito K, Inagaki M, Matsumiya N. Primary and secondary spontaneous pneumothorax: prevalence, clinical features, and in-hospital mortality. Can Respir J. 2017Google Scholar
- 5.Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L. ImageNet large scale visual recognition challenge. arXiv:1409.0575v3 [cs.CV] 30 Jan 2015.Google Scholar
- 6.Prevedello LM, Halabi SS, Shih G, Wu CC, Kohli MD, Chokshi FH, Erickson BJ, Kalpathy-Cramer J, Andriole KP, Flanders AE. Challenges related to artificial intelligence research in medical imaging and the importance of image analysis competitions. Radiology: Artificial Intelligence. 2019 Jan;1(1).Google Scholar
- 7.Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, Pan I, Pereira LA, Sousa RT, Abdala N, Kitamura FC, Thodberg HH, Chen L, Shih G, Andriole K, Kohli MD, Erickson BJ, Flanders AE: The RSNA pediatric bone age machine learning challenge. Radiology. 290(2):498–503, 2019CrossRefGoogle Scholar
- 8.Rajpurkar P, Irvin J, Bagul A, Ding D, Duan T, Mehta H, Yang B, Zhu K, Laird D, Ball RL, Langlotz C, Shpanskaya K, Lungren MP, Ng AY. MURA: a large dataset for abnormality detection in musculoskeletal radiographs. arXiv: 1712.06957v4 [physics.med-ph] 22 May 2018.Google Scholar
- 9.Shih G, Wu CC, Halabi SS, Kohli MD, Prevedello LM, Cook TS, Sharma A, Amorosa JK, Arteaga V, Galperin-Aizenberg M. Augmenting the National Institutes of Health chest radiograph dataset with expert annotations of possible pneumonia. Radiology: Artificial Intelligence. 2019 Jan;1(1).Google Scholar
- 10.SIIM-ACR Pneumothorax Segmentation Challenge. https://www.kaggle.com/c/siim-acr-pneumothorax-segmentation/overview
- 11.Wang X, Peng Y, Lu L. ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases arXiv:1705.02315v5 [cs.CV] Dec 2017.Google Scholar
- 12.Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. arXiv:1512.04150 [cs.CV] 14 Dec 2015.Google Scholar
- 13.Bach S, Rodriguez D, Liu Y, Luo C, Shao H, Xia C, Souvik S, Ratner A, Hancock B, Al Borzi H, Kuchkal R, Re C, Malkin R. Snorkel Drybell: a case study in deploying weak supervision at industrial scale. arXiv:1812.00417v1 [cs.LG] 2 Dec 2018.Google Scholar
- 14.Dunnmon J, Ratner A, Khandwala N, Saab K, Markert M, Sagreiya H, Goldman R, Lee-Messer C, Lungren M, Rubin D, Re C. Cross-modal data programming enables rapid medical machine learning. arXiv:1903.11101 [cs.LG] 26 Mar 2019.Google Scholar
- 15.Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv:1311.2524v5 [cs.CV] Oct 2014.Google Scholar
- 16.He K,Gkioxari G, Dollar P. Mask R-CNN arXiv:1703.06870v3 [cs.CV] Jan 2018.Google Scholar