{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:58:15Z","timestamp":1787878695095,"version":"build-2784847793"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T00:00:00Z","timestamp":1647216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["U24CA215109"],"award-info":[{"award-number":["U24CA215109"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006034","name":"University of Southern California","doi-asserted-by":"publisher","award":["Zumberge Research and Innovation Fund"],"award-info":[{"award-number":["Zumberge Research and Innovation Fund"]}],"id":[{"id":"10.13039\/100006034","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Ground-glass opacity (GGO)\u2014a hazy, gray appearing density on computed tomography (CT) of lungs\u2014is one of the hallmark features of SARS-CoV-2 in COVID-19 patients. This AI-driven study is focused on segmentation, morphology, and distribution patterns of GGOs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>We use an AI-driven unsupervised machine learning approach called PointNet++ to detect and quantify GGOs in CT scans of COVID-19 patients and to assess the severity of the disease. We have conducted our study on the \u201cMosMedData\u201d, which contains CT lung scans of 1110 patients with or without COVID-19 infections. We quantify the morphologies of GGOs using Minkowski tensors and compute the abnormality score of individual regions of segmented lung and GGOs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>PointNet++ detects GGOs with the highest evaluation accuracy (98%), average class accuracy (95%), and intersection over union (92%) using only a fraction of 3D data. On average, the shapes of GGOs in the COVID-19 datasets deviate from sphericity by 15% and anisotropies in GGOs are dominated by dipole and hexapole components. These anisotropies may help to quantitatively delineate GGOs of COVID-19 from other lung diseases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The PointNet++ and the Minkowski tensor based morphological approach together with abnormality analysis will provide radiologists and clinicians with a valuable set of tools when interpreting CT lung scans of COVID-19 patients. Implementation would be particularly useful in countries severely devastated by COVID-19 such as India, where the number of cases has outstripped available resources creating delays or even breakdowns in patient care. This AI-driven approach synthesizes both the unique GGO distribution pattern and severity of the disease to allow for more efficient diagnosis, triaging and conservation of limited resources.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0263916","type":"journal-article","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T13:44:04Z","timestamp":1647265444000},"page":"e0263916","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["AI-driven quantification of ground glass opacities in lungs of COVID-19 patients using 3D computed tomography imaging"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6470-3544","authenticated-orcid":true,"given":"Monjoy","family":"Saha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sagar B.","family":"Amin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T. K. Satish","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajiv K.","family":"Kalia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,3,14]]},"reference":[{"key":"pone.0263916.ref001","doi-asserted-by":"crossref","first-page":"108427","DOI":"10.1016\/j.clim.2020.108427","article-title":"COVID-19 pathophysiology: A review","volume":"215","author":"K Yuki","year":"2020","journal-title":"Clinical immunology"},{"issue":"5","key":"pone.0263916.ref002","article-title":"Anosmia and ageusia as the only indicators of coronavirus disease 2019 (COVID-19)","volume":"12","author":"Q Zhang","year":"2020","journal-title":"Cureus"},{"issue":"6","key":"pone.0263916.ref003","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1017\/S000711452000330X","article-title":"Nutritional status of micronutrients as a possible and modifiable risk factor for COVID-19: a UK perspective","volume":"125","author":"DP Richardson","year":"2021","journal-title":"British journal of nutrition"},{"issue":"4","key":"pone.0263916.ref004","doi-asserted-by":"crossref","first-page":"505","DOI":"10.3348\/kjr.2020.0146","article-title":"False-negative results of real-time reverse-transcriptase polymerase chain reaction for severe acute respiratory syndrome coronavirus 2: role of deep-learning-based CT diagnosis and insights from two cases","volume":"21","author":"D Li","year":"2020","journal-title":"Korean journal of radiology"},{"issue":"1","key":"pone.0263916.ref005","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1148\/radiol.2020201365","article-title":"The role of chest imaging in patient management during the COVID-19 pandemic: a multinational consensus statement from the Fleischner Society","volume":"296","author":"GD Rubin","year":"2020","journal-title":"Radiology"},{"issue":"3","key":"pone.0263916.ref006","doi-asserted-by":"crossref","first-page":"E289","DOI":"10.1148\/radiol.2020202504","article-title":"Review of the chest CT differential diagnosis of ground-glass opacities in the COVID era","volume":"297","author":"M Parekh","year":"2020","journal-title":"Radiology"},{"key":"pone.0263916.ref007","doi-asserted-by":"crossref","first-page":"6129","DOI":"10.1007\/s00330-020-06975-7","article-title":"CT in coronavirus disease 2019 (COVID-19): a systematic review of chest CT findings in 4410 adult patients","volume":"30","author":"V Ojha","year":"2020","journal-title":"European radiology"},{"key":"pone.0263916.ref008","doi-asserted-by":"crossref","first-page":"101792","DOI":"10.1016\/j.artmed.2020.101792","article-title":"An effective approach for CT lung segmentation using mask region-based convolutional neural networks","volume":"103","author":"Q Hu","year":"2020","journal-title":"Artificial intelligence in medicine"},{"key":"pone.0263916.ref009","doi-asserted-by":"crossref","first-page":"101817","DOI":"10.1016\/j.compmedimag.2020.101817","article-title":"LGAN: Lung segmentation in CT scans using generative adversarial network","volume":"87","author":"J Tan","year":"2021","journal-title":"Computerized Medical Imaging and Graphics"},{"key":"pone.0263916.ref010","doi-asserted-by":"crossref","first-page":"105864","DOI":"10.1016\/j.cmpb.2020.105864","article-title":"Pathological lung segmentation in chest CT images based on improved random walker","volume":"200","author":"C Chen","year":"2021","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"1","key":"pone.0263916.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-80936-4","article-title":"CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network","volume":"11","author":"SE Gerard","year":"2021","journal-title":"Scientific reports"},{"issue":"8","key":"pone.0263916.ref012","doi-asserted-by":"crossref","first-page":"2626","DOI":"10.1109\/TMI.2020.2996645","article-title":"Inf-net: Automatic covid-19 lung infection segmentation from ct images","volume":"39","author":"DP Fan","year":"2020","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0263916.ref013","doi-asserted-by":"crossref","first-page":"614440","DOI":"10.1117\/12.653053","volume-title":"Medical Imaging 2006: Image Processing","author":"Y Yoo","year":"2006"},{"key":"pone.0263916.ref014","doi-asserted-by":"crossref","unstructured":"Zhou J, Chang S, Metaxas DN, Zhao B, Ginsberg MS, Schwartz LH. An automatic method for ground glass opacity nodule detection and segmentation from CT studies. In 2006 International Conference of the IEEE Engineering in Medicine and Biology Society 2006 Sep (pp. 3062\u20133065). IEEE.","DOI":"10.1109\/IEMBS.2006.260285"},{"issue":"2","key":"pone.0263916.ref015","doi-asserted-by":"crossref","first-page":"295","DOI":"10.2214\/AJR.12.9640","article-title":"Computer-aided segmentation and volumetry of artificial ground-glass nodules at chest CT","volume":"201","author":"ET Scholten","year":"2013","journal-title":"American Journal of Roentgenology"},{"key":"pone.0263916.ref016","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1007\/s13312-020-1816-8","article-title":"Radiographic and clinical features of children with coronavirus disease (COVID-19) pneumonia","volume":"57","author":"B Li","year":"2020","journal-title":"Indian pediatrics"},{"key":"pone.0263916.ref017","doi-asserted-by":"crossref","first-page":"185786","DOI":"10.1109\/ACCESS.2020.3027738","article-title":"MSD-Net: Multi-scale discriminative network for COVID-19 lung infection segmentation on CT","volume":"8","author":"B Zheng","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0263916.ref018","doi-asserted-by":"crossref","first-page":"114848","DOI":"10.1016\/j.eswa.2021.114848","article-title":"Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images","volume":"176","author":"Q Jin","year":"2021","journal-title":"Expert Systems with Applications"},{"issue":"18","key":"pone.0263916.ref019","doi-asserted-by":"crossref","first-page":"6448","DOI":"10.3390\/app10186448","article-title":"Neural network based country wise risk prediction of COVID-19","volume":"10","author":"R Pal","year":"2020","journal-title":"Applied Sciences"},{"issue":"1","key":"pone.0263916.ref020","first-page":"1","article-title":"Machine learning based early warning system enables accurate mortality risk prediction for COVID-19","volume":"11","author":"Y Gao","year":"2020","journal-title":"Nature communications"},{"key":"pone.0263916.ref021","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.isprsjprs.2020.05.008","article-title":"GRNet: Geometric relation network for 3D object detection from point clouds","volume":"165","author":"Y Li","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0263916.ref022","first-page":"490","article-title":"Covid-CT-dataset: a CT scan dataset about covid-19","author":"J Zhao","year":"2020","journal-title":"arXiv preprint arXiv:2003.13865"},{"key":"pone.0263916.ref023","article-title":"Sample-efficient deep learning for COVID-19 diagnosis based on CT scans","author":"X He","year":"2020","journal-title":"medrxiv"},{"key":"pone.0263916.ref024","article-title":"COVID-CT-dataset: a CT scan dataset about COVID-19","author":"X Yang","year":"2020","journal-title":"arXiv preprint arXiv:2003.13865"},{"key":"pone.0263916.ref025","doi-asserted-by":"crossref","unstructured":"Rusu RB, Cousins S. 3d is here: Point cloud library (pcl). In2011 IEEE international conference on robotics and automation 2011 May 9 (pp. 1\u20134). IEEE.","DOI":"10.1109\/ICRA.2011.5980567"},{"issue":"2","key":"pone.0263916.ref026","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/S0890-6955(01)00120-1","article-title":"A new segmentation method for point cloud data","volume":"42","author":"H Woo","year":"2002","journal-title":"International Journal of Machine Tools and Manufacture"},{"key":"pone.0263916.ref027","doi-asserted-by":"crossref","unstructured":"Unal O, Van Gool L, Dai D. Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection. InProceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 2021 (pp. 2950\u20132959).","DOI":"10.1109\/WACV48630.2021.00299"},{"key":"pone.0263916.ref028","unstructured":"Qi CR, Su H, Mo K, Guibas LJ. Pointnet: Deep learning on point sets for 3d classification and segmentation. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 652\u2013660)."},{"key":"pone.0263916.ref029","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"CR Qi","year":"2017","journal-title":"arXiv preprint arXiv:1706.02413"},{"key":"pone.0263916.ref030","doi-asserted-by":"crossref","first-page":"105798","DOI":"10.1016\/j.cmpb.2020.105798","article-title":"A novel segmentation method for cervical vertebrae based on PointNet++ and converge segmentation","volume":"200","author":"L Zhang","year":"2021","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"1","key":"pone.0263916.ref031","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-18297-9","article-title":"Developing a COVID-19 mortality risk prediction model when individual-level data are not available","volume":"11","author":"N Barda","year":"2020","journal-title":"Nature communications"},{"issue":"13","key":"pone.0263916.ref032","doi-asserted-by":"crossref","first-page":"E2970","DOI":"10.1073\/pnas.1717139115","article-title":"Predicting cancer outcomes from histology and genomics using convolutional networks","volume":"115","author":"P Mobadersany","year":"2018","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"408","key":"pone.0263916.ref033","doi-asserted-by":"crossref","first-page":"1074","DOI":"10.1080\/01621459.1989.10478874","article-title":"The robust inference for the Cox proportional hazards model","volume":"84","author":"DY Lin","year":"1989","journal-title":"Journal of the American statistical Association"},{"key":"pone.0263916.ref034","unstructured":"\u201cMinkowski functionals: Robust and versatile shape descriptors,\u201d https:\/\/morphometry.org\/morphometer\/index.html?mode=EXPERT?type=IM?anaparam=other?anatype=grayscale, accessed: 2021-03-31."},{"issue":"22\u201323","key":"pone.0263916.ref035","doi-asserted-by":"crossref","first-page":"2535","DOI":"10.1002\/adma.201100562","article-title":"Minkowski tensor shape analysis of cellular, granular and porous structures","volume":"23","author":"GE Schr\u00f6der-Turk","year":"2011","journal-title":"Advanced Materials"},{"key":"pone.0263916.ref036","doi-asserted-by":"crossref","unstructured":"El-Baz A, Nitzken M, Khalifa F, Elnakib A, Gimel\u2019farb G, Falk R, et al. 3D shape analysis for early diagnosis of malignant lung nodules. InBiennial International Conference on Information Processing in Medical Imaging 2011 Jul 3 (pp. 772\u2013783). Springer, Berlin, Heidelberg.","DOI":"10.1007\/978-3-642-22092-0_63"},{"key":"pone.0263916.ref037","volume-title":"Cardiopulmonary imaging","author":"EA Kazerooni","year":"2004"},{"issue":"1","key":"pone.0263916.ref038","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1097\/RCT.0b013e31815e6291","article-title":"Detection of nodules showing ground-glass opacity in the lungs at low-dose multidetector computed tomography: phantom and clinical study","volume":"33","author":"Y Funama","year":"2009","journal-title":"Journal of computer assisted tomography"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0263916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T13:44:47Z","timestamp":1647265487000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0263916"}},"subtitle":[],"editor":[{"given":"Francesco","family":"Bianconi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,3,14]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,3,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0263916","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.07.06.21260109","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,14]]}}}