{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T11:14:42Z","timestamp":1768821282189,"version":"3.49.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Tremendous efforts have been made to improve diagnosis and treatment of COVID-19, but knowledge on long-term complications is limited. In particular, a large portion of survivors has respiratory complications, but currently, experienced radiologists and state-of-the-art artificial intelligence systems are not able to detect many abnormalities from follow-up computerized tomography (CT) scans of COVID-19 survivors. Here we propose Deep-LungParenchyma-Enhancing (DLPE), a computer-aided detection (CAD) method for detecting and quantifying pulmonary parenchyma lesions on chest CT. Through proposing a number of deep-learning-based segmentation models and assembling them in an interpretable manner, DLPE removes irrelevant tissues from the perspective of pulmonary parenchyma, and calculates the scan-level optimal window, which considerably enhances parenchyma lesions relative to the lung window. Aided by DLPE, radiologists discovered novel and interpretable lesions from COVID-19 inpatients and survivors, which were previously invisible under the lung window. Based on DLPE, we removed the scan-level bias of CT scans, and then extracted precise radiomics from such novel lesions. We further demonstrated that these radiomics have strong predictive power for key COVID-19 clinical metrics on an inpatient cohort of 1,193 CT scans and for sequelae on a survivor cohort of 219 CT scans. Our work sheds light on the development of interpretable medical artificial intelligence and showcases how artificial intelligence can discover medical findings that are beyond sight.<\/jats:p>","DOI":"10.1038\/s42256-022-00483-7","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T16:03:19Z","timestamp":1653321799000},"page":"494-503","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["An interpretable deep learning workflow for discovering subvisual abnormalities in CT scans of COVID-19 inpatients and survivors"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0116-9361","authenticated-orcid":false,"given":"Longxi","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5091-3260","authenticated-orcid":false,"given":"Xianglin","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juexiao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuetan","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dexuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiannan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizhen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7381-2374","authenticated-orcid":false,"given":"Guohua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6277-7948","authenticated-orcid":false,"given":"Lawrence","family":"Carin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2795-9823","authenticated-orcid":false,"given":"Xigang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8456-9664","authenticated-orcid":false,"given":"Kaijiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5292-0333","authenticated-orcid":false,"given":"Zhaowen","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7108-3574","authenticated-orcid":false,"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,23]]},"reference":[{"key":"483_CR1","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/S0140-6736(20)32656-8","volume":"397","author":"C Huang","year":"2021","unstructured":"Huang, C. et al. 6-Month consequences of COVID-19 in patients discharged from hospital: a cohort study. Lancet 397, 220\u2013232 (2021).","journal-title":"Lancet"},{"key":"483_CR2","first-page":"299","volume":"1","author":"X Han","year":"2021","unstructured":"Han, X. et al. Six-month follow-up chest CT findings after severe COVID-19 pneumonia. Radiology 1, 299 (2021).","journal-title":"Radiology"},{"key":"483_CR3","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1016\/j.cell.2020.04.045","volume":"181","author":"K Zhang","year":"2020","unstructured":"Zhang, K. et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell 181, 1423\u20131433 (2020).","journal-title":"Cell"},{"key":"483_CR4","doi-asserted-by":"publisher","first-page":"6808","DOI":"10.1007\/s00330-020-07033-y","volume":"30","author":"M Francone","year":"2020","unstructured":"Francone, M. et al. Chest CT score in COVID-19 patients: correlation with disease severity and short-term prognosis. Eur. Radiol. 30, 6808\u20136817 (2020).","journal-title":"Eur. Radiol."},{"key":"483_CR5","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/s00415-020-10067-3","volume":"268","author":"X Chen","year":"2021","unstructured":"Chen, X. et al. A systematic review of neurological symptoms and complications of COVID-19. J. Neurol. 268, 392\u2013402 (2021).","journal-title":"J. Neurol."},{"key":"483_CR6","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1097\/RLI.0000000000000448","volume":"53","author":"M Mannil","year":"2018","unstructured":"Mannil, M. et al. Texture analysis and machine learning for detecting myocardial infarction in noncontrast low-dose computed tomography: unveiling the invisible. Invest. Radiol. 53, 338\u2013343 (2018).","journal-title":"Invest. Radiol."},{"key":"483_CR7","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1007\/s00330-018-5674-x","volume":"29","author":"P Savadjiev","year":"2019","unstructured":"Savadjiev, P. et al. Demystification of AI-driven medical image interpretation: past, present and future. Eur. Radiol. 29, 1616\u20131624 (2019).","journal-title":"Eur. Radiol."},{"key":"483_CR8","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-018-0061-6","volume":"2","author":"F Pesapane","year":"2018","unstructured":"Pesapane, F. et al. Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine. Eur. Radiol. Exp. 2, 35 (2018).","journal-title":"Eur. Radiol. Exp."},{"key":"483_CR9","doi-asserted-by":"publisher","first-page":"e486","DOI":"10.1016\/S2589-7500(20)30160-6","volume":"2","author":"O Oren","year":"2020","unstructured":"Oren, O. et al. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. Lancet Digital Health 2, e486\u2013e488 (2020).","journal-title":"Lancet Digital Health"},{"key":"483_CR10","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.1109\/TMI.2020.3001810","volume":"39","author":"L Zhou","year":"2020","unstructured":"Zhou, L. et al. A rapid, accurate and machine-agnostic segmentation and quantification method for CT-based COVID-19 diagnosis. IEEE Trans. Med. Imaging 39, 2638\u20132652 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"483_CR11","doi-asserted-by":"crossref","unstructured":"Zheng, H. et al. Alleviating class-wise gradient imbalance for pulmonary airway segmentation. IEEE Trans. Med. Imaging 40, 2452\u20132462 (2021).","DOI":"10.1109\/TMI.2021.3078828"},{"key":"483_CR12","doi-asserted-by":"crossref","unstructured":"Nam, J. G. et al. Automatic pulmonary vessel segmentation on noncontrast chest CT: deep learning algorithm developed using spatiotemporally matched virtual noncontrast images and low-keV contrast-enhanced vessel maps. Eur. Radiol. 31, 9012\u20139021 (2021).","DOI":"10.1007\/s00330-021-08036-z"},{"key":"483_CR13","doi-asserted-by":"publisher","DOI":"10.1186\/s12955-014-0124-1","volume":"12","author":"JJ Swigris","year":"2014","unstructured":"Swigris, J. J. et al. The psychometric properties of the St George\u2019s Respiratory Questionnaire (SGRQ) in patients with idiopathic pulmonary fibrosis: a literature review. Health Qual. Life Outcomes 12, 124 (2014).","journal-title":"Health Qual. Life Outcomes"},{"key":"483_CR14","doi-asserted-by":"crossref","unstructured":"Vasarmidi, E. et al. Pulmonary fibrosis in the aftermath of the COVID-19 era (review). Exp. Ther. Med. 20, 2557\u20132560 (2020).","DOI":"10.3892\/etm.2020.8980"},{"key":"483_CR15","doi-asserted-by":"publisher","first-page":"E72","DOI":"10.1016\/S1473-3099(20)30582-X","volume":"21","author":"F Grillo","year":"2021","unstructured":"Grillo, F. et al. Lung fibrosis: an undervalued finding in COVID-19 pathological series. Lancet Infect. Dis. 21, E72 (2021).","journal-title":"Lancet Infect. Dis."},{"key":"483_CR16","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/S2213-2600(20)30225-3","volume":"8","author":"M Peter","year":"2020","unstructured":"Peter, M. et al. Pulmonary fibrosis and COVID-19: the potential role for antifibrotic therapy. Lancet Resp. Med. 8, 807\u2013815 (2020).","journal-title":"Lancet Resp. Med."},{"key":"483_CR17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3109\/15412555.2011.630248","volume":"9","author":"T Ringbaek","year":"2012","unstructured":"Ringbaek, T. et al. A comparison of the assessment of quality of life with CAT, CCQ, and SGRQ in COPD patients participating in pulmonary rehabilitation. COPD 9, 12\u201315 (2012).","journal-title":"COPD"},{"key":"483_CR18","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1378\/chest.15-1752","volume":"149","author":"M Karloh","year":"2016","unstructured":"Karloh, M. et al. The COPD assessment test: what do we know so far?: A systematic review and meta-analysis about clinical outcomes prediction and classification of patients into GOLD stages. Chest 149, 413\u2013425 (2016).","journal-title":"Chest"},{"key":"483_CR19","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1183\/09031936.00196412","volume":"43","author":"EL Burnham","year":"2014","unstructured":"Burnham, E. L. et al. The fibroproliferative response in acute respiratory distress syndrome: mechanisms and clinical significance. Eur. Resp. J. 43, 276\u2013285 (2014).","journal-title":"Eur. Resp. J."},{"key":"483_CR20","first-page":"2526","volume":"307","author":"V Ranieri","year":"2012","unstructured":"Ranieri, V. M. Acute respiratory distress syndrome: the Berlin definition. JAMA 307, 2526\u20132533 (2012).","journal-title":"JAMA"},{"key":"483_CR21","doi-asserted-by":"crossref","unstructured":"Fu, L. et al. Influence factors of death risk among COVID-19 patients in Wuhan, China: a hospital-based case-cohort study. Preprint at https:\/\/www.medrxiv.org\/content\/10.1101\/2020.03.13.20035329v1 (2020)","DOI":"10.21203\/rs.3.rs-26775\/v1"},{"key":"483_CR22","doi-asserted-by":"crossref","unstructured":"Brown, S. M. et al. Non-linear imputation of PaO2\/FIO2 from SpO2\/FIO2 among mechanically ventilated patients in the intensive care unit: a prospective, observational study. Crit. Care Med. 45, 1317\u20131324 (2017).","DOI":"10.1097\/CCM.0000000000002514"},{"key":"483_CR23","doi-asserted-by":"crossref","unstructured":"Mathias, P. et al. One network to segment them all: a general, lightweight system for accurate 3D medical image segmentation. In Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2019 30\u201338 (Springer, 2019).","DOI":"10.1007\/978-3-030-32245-8_4"},{"key":"483_CR24","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1038\/35036627","volume":"407","author":"H Jeong","year":"2000","unstructured":"Jeong, H. et al. The large-scale organization of metabolic networks. Nature 407, 651\u2013654 (2000).","journal-title":"Nature"},{"key":"483_CR25","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In Proc. IEEE International Conference on Computer Vision (ICCV) 618\u2013626 (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"483_CR26","doi-asserted-by":"crossref","unstructured":"Vinogradova, K. et al. Towards interpretable semantic segmentation via gradient-weighted class activation mapping. Proceedings of the AAAI Conference on Artificial Intelligence 13943\u201313944 (AAAI 2020).","DOI":"10.1609\/aaai.v34i10.7244"},{"key":"483_CR27","doi-asserted-by":"publisher","first-page":"101619","DOI":"10.1016\/j.media.2019.101619","volume":"60","author":"K Wickstom","year":"2020","unstructured":"Wickstom, K. et al. Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps. Med. Image Anal. 60, 101619 (2020).","journal-title":"Med. Image Anal."},{"key":"483_CR28","doi-asserted-by":"publisher","unstructured":"Zhou, L. et al. 1.0 LongxiZhou\/DLPE-method: DeepLungParenchymaEnhancement (Zenodo, 2022); https:\/\/doi.org\/10.5281\/ZENODO.6387701","DOI":"10.5281\/ZENODO.6387701"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-022-00483-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-022-00483-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-022-00483-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T09:30:42Z","timestamp":1669368642000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-022-00483-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["483"],"URL":"https:\/\/doi.org\/10.1038\/s42256-022-00483-7","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,23]]},"assertion":[{"value":"19 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}