{"entities":{"Q6689969":{"pageid":14408950,"ns":120,"title":"Item:Q6689969","lastrevid":54635963,"modified":"2026-01-29T18:50:18Z","type":"item","id":"Q6689969","labels":{"en":{"language":"en","value":"Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data"}},"descriptions":{"en":{"language":"en","value":"Dataset published at Zenodo repository."}},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"dae155fd0809a7906855cd4fa50dd7d71bed552b","datavalue":{"value":{"entity-type":"item","numeric-id":56885,"id":"Q56885"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6689969$85C4675C-EAEC-48B9-A232-B5387A05801C","rank":"normal"}],"P1459":[{"mainsnak":{"snaktype":"value","property":"P1459","hash":"6de088f3585a67f576b7a6994b3a4d5020bb6629","datavalue":{"value":"Background: The coronavirus disease 2019 (COVID-19) affects billions of lives around the world and has a significant impact on public healthcare. For quantitative assessment and disease monitoring medical imaging like computed tomography offers great potential as alternative to RT-PCR methods. For this reason, automated image segmentation is highly desired as clinical decision support. However, publicly available COVID-19 imaging data is limited which leads to overfitting of traditional approaches.  Methods: To address this problem, we propose an innovative automated segmentation pipeline for COVID-19 infected regions, which is able to handle small datasets by utilization as variant databases. Our method focuses on on-the-fly generation of unique and random image patches for training by performing several preprocessing methods and exploiting extensive data augmentation. For further reduction of the overfitting risk, we implemented a standard 3D U-Net architecture instead of new or computational complex neural network architectures.  Results: Through a k-fold cross-validation on 20 CT scans as training and validation of COVID-19, we were able to develop a highly accurate as well as robust segmentation model for lungs and COVID-19 infected regions without overfitting on limited data. We performed an in-detail analysis and discussion on the robustness of our pipeline through a sensitivity analysis based on the cross-validation and impact on model generalizability of applied preprocessing techniques. Our method achieved Dice similarity coefficients for COVID-19 infection between predicted and annotated segmentation from radiologists of 0.804 on validation and 0.661 on a separate testing set consisting of 100 patients.  Conclusions: We demonstrated that the proposed method outperforms related approaches, advances the state-of-the-art for COVID-19 segmentation and improves robust medical image analysis based on limited data.  The code and model are available under the following link: https://github.com/frankkramer-lab/covid19.MIScnn","type":"string"},"datatype":"string"},"type":"statement","id":"Q6689969$1F2F8D49-B6BF-4620-A9D5-CF8F4CAD6067","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"462f28db95341ffbe58cc070cbe484424975b487","datavalue":{"value":{"time":"+2021-05-30T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6689969$99DCAC6B-48AC-43D1-AAE3-4C99E80A38D7","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"392591ffebca30f8e79ea70fc5099ba5447c878d","datavalue":{"value":{"entity-type":"item","numeric-id":6689967,"id":"Q6689967"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6689969$7ED42066-59A0-421A-829D-BDC371B7BEE1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"106750c8032eed42fab10010a86bdc05d19b1143","datavalue":{"value":{"entity-type":"item","numeric-id":6689968,"id":"Q6689968"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6689969$752FC0BF-C160-4EF3-A433-BA350C4D8476","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"c09f820b378deb1b6ed6b13e86da367c7b4b2f86","datavalue":{"value":{"entity-type":"item","numeric-id":74395,"id":"Q74395"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6689969$2A3CE15F-A642-4D95-961E-68E34A1A8254","rank":"normal"}],"P227":[{"mainsnak":{"snaktype":"value","property":"P227","hash":"8d9588334ea9618d79e66d5dd3e6e4a24271c4bb","datavalue":{"value":"4875738","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6689969$99E75B3E-FD4F-4055-911B-C5442AB8CEF8","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"d83c14bbb5f7e699219c2066562a189ef49523f6","datavalue":{"value":"10.5281/zenodo.4875738","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6689969$6B2378F7-3938-4D63-93C7-A5E1D8B70D4E","rank":"normal"}],"P163":[{"mainsnak":{"snaktype":"value","property":"P163","hash":"45fcd4163b5f33e6e8c784f5522d7246c0a1a61e","datavalue":{"value":{"entity-type":"item","numeric-id":57056,"id":"Q57056"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6689969$41BAA902-24FE-4EA2-9EB3-4854FD03F50E","rank":"normal"}],"P1474":[{"mainsnak":{"snaktype":"value","property":"P1474","hash":"70b683199434dc151e5d10a144a9596cabbb8d8b","datavalue":{"value":"2.0","type":"string"},"datatype":"string"},"type":"statement","id":"Q6689969$52073E5B-2517-4B6F-B6A3-1C8AA6F6684B","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"d1e8073b72a070520efd3d14d4b3d2d3d03859e2","datavalue":{"value":{"entity-type":"item","numeric-id":5984635,"id":"Q5984635"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6689969$3BD92A54-8D8C-4F54-A711-745031ABFFD7","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Robust_Chest_CT_Image_Segmentation_of_COVID-19_Lung_Infection_based_on_limited_data"}}}}}