{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:54:32Z","timestamp":1763643272569,"version":"3.41.0"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Manage. Inf. Syst."],"published-print":{"date-parts":[[2021,12,31]]},"abstract":"<jats:p>Analysis of chest CT scans can be used in detecting parts of lungs that are affected by infectious diseases such as COVID-19. Determining the volume of lungs affected by lesions is essential for formulating treatment recommendations and prioritizing patients by severity of the disease. In this article we adopted an approach based on using an ensemble of deep convolutional neural networks for segmentation of slices of lung CT scans. Using our models, we are able to segment the lesions, evaluate patients\u2019 dynamics, estimate relative volume of lungs affected by lesions, and evaluate the lung damage stage. Our models were trained on data from different medical centers. We compared predictions of our models with those of six experienced radiologists, and our segmentation model outperformed most of them. On the task of classification of disease severity, our model outperformed all the radiologists.<\/jats:p>","DOI":"10.1145\/3467471","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T19:02:52Z","timestamp":1631127772000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["CoRSAI: A System for Robust Interpretation of CT Scans of COVID-19 Patients Using Deep Learning"],"prefix":"10.1145","volume":"12","author":[{"given":"Manvel","family":"Avetisian","sequence":"first","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Ilya","family":"Burenko","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Konstantin","family":"Egorov","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Vladimir","family":"Kokh","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Aleksandr","family":"Nesterov","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Aleksandr","family":"Nikolaev","sequence":"additional","affiliation":[{"name":"Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies, Russia"}]},{"given":"Alexander","family":"Ponomarchuk","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Elena","family":"Sokolova","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]},{"given":"Alex","family":"Tuzhilin","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory and New York University, New York, USA"}]},{"given":"Dmitry","family":"Umerenkov","sequence":"additional","affiliation":[{"name":"Sberbank AI Laboratory, Moscow, Russia"}]}],"member":"320","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020200642"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535865"},{"key":"e_1_2_1_3_1","volume-title":"Armato et\u00a0al","author":"Samuel","year":"2015","unstructured":"Samuel G. Armato et\u00a0al . 2015 . The Cancer Imaging Archive . http:\/\/doi.org\/10.7937\/K9\/TCIA.2015.LO9QL9SX 10.7937\/K9 Samuel G. Armato et\u00a0al. 2015. The Cancer Imaging Archive. http:\/\/doi.org\/10.7937\/K9\/TCIA.2015.LO9QL9SX"},{"key":"e_1_2_1_4_1","volume-title":"Katsamenis Iason, Doulamis Anastasios, and Doulamis Nikolaos.","author":"Athanasios Voulodimos","year":"2020","unstructured":"Voulodimos Athanasios , Protopapadakis Eftychios Katsamenis , Katsamenis Iason, Doulamis Anastasios, and Doulamis Nikolaos. 2020 . Deep learning models for COVID-19 infected area segmentation in CT images. medRxiv (2020). https:\/\/www.medrxiv.org\/content\/early\/2020\/05\/19\/2020.05.08.20094664. Voulodimos Athanasios, Protopapadakis Eftychios Katsamenis, Katsamenis Iason, Doulamis Anastasios, and Doulamis Nikolaos. 2020. Deep learning models for COVID-19 infected area segmentation in CT images. medRxiv (2020). https:\/\/www.medrxiv.org\/content\/early\/2020\/05\/19\/2020.05.08.20094664."},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Manvel Avetisian Vladimir Kohn Alexander Tuzhilin and Dmitry Umerenkov. 2019. Radiologist-level stroke classification on non-contrast CT scans with deep U-Net. In Medical Image Computing and Computer Assisted Intervention.  Manvel Avetisian Vladimir Kohn Alexander Tuzhilin and Dmitry Umerenkov. 2019. Radiologist-level stroke classification on non-contrast CT scans with deep U-Net. In Medical Image Computing and Computer Assisted Intervention.","DOI":"10.1007\/978-3-030-32248-9_91"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020201237"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.11.001"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.36416\/1806-3756\/e20200121"},{"key":"e_1_2_1_9_1","unstructured":"Xiaocong Chen Lina Yao Tao Zhou Jinming Dong and Yu Zhang. 2020. Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images. arxiv:2006.13276https:\/\/arxiv.org\/abs\/2006.13276.  Xiaocong Chen Lina Yao Tao Zhou Jinming Dong and Yu Zhang. 2020. Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images. arxiv:2006.13276https:\/\/arxiv.org\/abs\/2006.13276."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295200"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020200230"},{"key":"e_1_2_1_12_1","volume-title":"Alberto Traverso, and Bram van Ginneken.","author":"Jacobs Colin","year":"2016","unstructured":"Colin Jacobs , Arnaud Arindra Adiyoso Setio , Alberto Traverso, and Bram van Ginneken. 2016 . LUNA16 Dataset . https:\/\/luna16.grand-challenge.org\/Home\/. Colin Jacobs, Arnaud Arindra Adiyoso Setio, Alberto Traverso, and Bram van Ginneken. 2016. LUNA16 Dataset. https:\/\/luna16.grand-challenge.org\/Home\/."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/648054.743935"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2996645"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020200432"},{"volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916)","author":"He K.","key":"e_1_2_1_16_1","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun . 2016. Deep residual learning for image recognition . In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916) . 770\u2013778. K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916). 770\u2013778."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibmed.2021.100027"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30183-5"},{"key":"e_1_2_1_19_1","unstructured":"H. B. Jenssen. 2020. Covid-19 ct segmentation dataset. http:\/\/medicalsegmentation.com\/covid19\/.  H. B. Jenssen. 2020. Covid-19 ct segmentation dataset. http:\/\/medicalsegmentation.com\/covid19\/."},{"key":"e_1_2_1_20_1","first-page":"2015","article-title":"Computer-aided classification of lung nodules on computed tomography images via deep learning technique","volume":"8","author":"Hua Kai-Lung","year":"2015","unstructured":"Kai-Lung Hua , Che-Hao Hsu , Shintami Chusnul Hidayati , Wen-Huang Cheng , and Yu-Jen Chen . 2015 . Computer-aided classification of lung nodules on computed tomography images via deep learning technique . OncoTargets and Therapy 8 (2015), 2015 \u2013 2022 . Kai-Lung Hua, Che-Hao Hsu, Shintami Chusnul Hidayati, Wen-Huang Cheng, and Yu-Jen Chen. 2015. Computer-aided classification of lung nodules on computed tomography images via deep learning technique. OncoTargets and Therapy 8 (2015), 2015\u20132022.","journal-title":"OncoTargets and Therapy"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1097\/RTI.0000000000000387"},{"volume-title":"H-DenseUNet: Hybrid densely connected unet for liver and tumor segmentation from CT volumes","author":"\u00a0al Xiaomeng Li","key":"e_1_2_1_23_1","unstructured":"Xiaomeng Li et \u00a0al . [n.d.]. H-DenseUNet: Hybrid densely connected unet for liver and tumor segmentation from CT volumes . IEEE Transactions on Medical Imaging 37, 12 ([n.\u00a0d.]), 2663\u20132674. Xiaomeng Li et\u00a0al. [n.d.]. H-DenseUNet: Hybrid densely connected unet for liver and tumor segmentation from CT volumes. IEEE Transactions on Medical Imaging 37, 12 ([n.\u00a0d.]), 2663\u20132674."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.20.22954"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"volume-title":"2016 4th International Conference on 3D Vision (3DV\u201916)","author":"Milletari F.","key":"e_1_2_1_27_1","unstructured":"F. Milletari , N. Navab , and S. Ahmadi . 2016. V-Net: Fully convolutional neural networks for volumetric medical image segmentation . In 2016 4th International Conference on 3D Vision (3DV\u201916) . 565\u2013571. F. Milletari, N. Navab, and S. Ahmadi. 2016. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 4th International Conference on 3D Vision (3DV\u201916). 565\u2013571."},{"key":"e_1_2_1_28_1","volume-title":"MosMedData: Chest CT Scans with COVID-19 related findings. medRxiv","author":"\u00a0al Sergey Morozov","year":"2020","unstructured":"Sergey Morozov et \u00a0al . 2020. MosMedData: Chest CT Scans with COVID-19 related findings. medRxiv ( 2020 ). https:\/\/mosmed.ai\/datasets\/covid19\/_1110. Sergey Morozov et\u00a0al. 2020. MosMedData: Chest CT Scans with COVID-19 related findings. medRxiv (2020). https:\/\/mosmed.ai\/datasets\/covid19\/_1110."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2995508"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.03.026"},{"key":"e_1_2_1_31_1","unstructured":"Yu Qiu Yun Liu and Jing Xu. 2020. MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation. https:\/\/arxiv.org\/abs\/2004.09750.  Yu Qiu Yun Liu and Jing Xu. 2020. MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation. https:\/\/arxiv.org\/abs\/2004.09750."},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Sivaramakrishnan Rajaraman et\u00a0al. 2020. Iteratively pruned deep learning ensembles for COVID-19 detection in chest X-rays. (2020).  Sivaramakrishnan Rajaraman et\u00a0al. 2020. Iteratively pruned deep learning ensembles for COVID-19 detection in chest X-rays. (2020).","DOI":"10.1109\/ACCESS.2020.3003810"},{"key":"e_1_2_1_33_1","unstructured":"Pranav Rajpurkar et\u00a0al. 2017. CheXNet: Radiologist-Level Pneumonia Detection on Xhest X-rays with Deep Learning. https:\/\/arxiv.org\/abs\/1711.05225.  Pranav Rajpurkar et\u00a0al. 2017. CheXNet: Radiologist-Level Pneumonia Detection on Xhest X-rays with Deep Learning. https:\/\/arxiv.org\/abs\/1711.05225."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00307-0"},{"volume-title":"Medical Image Computing and Computer-Assisted Intervention (MICCAI\u201915)(LNCS","author":"Ronneberger Olaf","key":"e_1_2_1_35_1","unstructured":"Olaf Ronneberger , Philipp Fischer , and Thomas Brox . 2015. U-Net: Convolutional networks for biomedical image segmentation . In Medical Image Computing and Computer-Assisted Intervention (MICCAI\u201915)(LNCS , Vol. 9351). Springer, 234\u2013 241 . Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI\u201915)(LNCS, Vol. 9351). Springer, 234\u2013241."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.01.104"},{"key":"e_1_2_1_37_1","volume-title":"Le","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V . Le . 2019 . EfficientNet: Rethinking model scaling for convolutional neural networks. CoRR abs\/1905.11946 (2019). arxiv:1905.11946http:\/\/arxiv.org\/abs\/1905.11946. Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. CoRR abs\/1905.11946 (2019). arxiv:1905.11946http:\/\/arxiv.org\/abs\/1905.11946."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3147146"},{"key":"e_1_2_1_39_1","volume-title":"A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT","author":"\u00a0al Xinggang Wang","year":"2020","unstructured":"Xinggang Wang et \u00a0al . 2020. A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT . IEEE Transactions on Medical Imaging 8 ( 2020 ). https:\/\/doi.org\/10.1109\/TMI.2020.2995965 10.1109\/TMI.2020.2995965 Xinggang Wang et\u00a0al. 2020. A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT. IEEE Transactions on Medical Imaging 8 (2020). https:\/\/doi.org\/10.1109\/TMI.2020.2995965"},{"key":"e_1_2_1_40_1","first-page":"4","article-title":"Deep neural networks improve radiologists\u2019 performance in breast cancer screening","volume":"39","author":"\u00a0al Nan Wu","year":"2020","unstructured":"Nan Wu et \u00a0al . 2020 . Deep neural networks improve radiologists\u2019 performance in breast cancer screening . IEEE Transactions on Medical Imaging 39 , 4 (Apr. 2020), 1184\u20131194. Nan Wu et\u00a0al. 2020. Deep neural networks improve radiologists\u2019 performance in breast cancer screening. IEEE Transactions on Medical Imaging 39, 4 (Apr. 2020), 1184\u20131194.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_2_1_41_1","volume-title":"JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation. arxiv:2004.07054https:\/\/arxiv.org\/abs\/2004.07054.","author":"Wu Yu-Huan","year":"2020","unstructured":"Yu-Huan Wu , Shang-Hua Gao , Jie Mei , Jun Xu , Deng-Ping Fan , Rong-Guo Zhang , and Ming-Ming Cheng . 2020 . JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation. arxiv:2004.07054https:\/\/arxiv.org\/abs\/2004.07054. Yu-Huan Wu, Shang-Hua Gao, Jie Mei, Jun Xu, Deng-Ping Fan, Rong-Guo Zhang, and Ming-Ming Cheng. 2020. JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation. arxiv:2004.07054https:\/\/arxiv.org\/abs\/2004.07054."},{"key":"e_1_2_1_42_1","unstructured":"Pavel Yakubovskiy. 2020. Segmentation Models Pytorch. https:\/\/github.com\/qubvel\/segmentation_models.pytorch.  Pavel Yakubovskiy. 2020. Segmentation Models Pytorch. https:\/\/github.com\/qubvel\/segmentation_models.pytorch."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.04.045"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.20.22975"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106885"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00190-X"}],"container-title":["ACM Transactions on Management Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3467471","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3467471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:25:07Z","timestamp":1750195507000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3467471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,8]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12,31]]}},"alternative-id":["10.1145\/3467471"],"URL":"https:\/\/doi.org\/10.1145\/3467471","relation":{},"ISSN":["2158-656X","2158-6578"],"issn-type":[{"type":"print","value":"2158-656X"},{"type":"electronic","value":"2158-6578"}],"subject":[],"published":{"date-parts":[[2021,9,8]]},"assertion":[{"value":"2020-09-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}