biostudies-literatureUnknown5(3)Hong Y<h4>Background</h4>Heterogeneity is a critical characteristic of severe coronavirus disease 2019 (COVID-19) pneumonia. Integrating chest computed tomography (CT) imaging and plasma proteomics holds the potential to elucidate Image-Expression Axes (IEAs) that can effectively address this disease heterogeneity.<h4>Methods</h4>A cohort of subjects diagnosed with severe COVID-19 pneumonia at 12 participating hospitals between December 2022 and March 2023 was prospectively screened for eligibility. Context-aware self-supervised representation learning (CSRL) was employed to extract intricate features from CT images. Quantification of plasma proteins was achieved using the Olink® inflammation panel. A deep learning model was meticulously trained, with CSRL features serving as input and the proteJournal of intensive medicine252-261https://www.ebi.ac.uk/biostudies/studies/S-EPMC12417366biostudies-literatureDeep learning integration of chest computed tomography and plasma proteomics to identify novel aspects of severe COVID-19 pneumonia.PMC12417366Zhang GFang HLin RFang JGong RHuang JZhang JZhong CLiu NYu JZhao ZCheng YYu HLiu YZhan YXZheng YHZheng CWu RChen XFan BYu YSun KZheng YYang JXu PChen JNi HChen LYe BYuan LZheng SChen CZhou XQian XHuang ZHYe LHong YPan XMZhang ZChinese Multi-omics Advances In Sepsis (CMAISE) ConsortiumHan CfalseDeep learning integration of chest computed tomography and plasma proteomics to identify novel aspects of severe COVID-19 pneumonia.<h4>Background</h4>Heterogeneity is a critical characteristic of severe coronavirus disease 2019 (COVID-19) pneumonia. Integrating chest computed tomography (CT) imaging and plasma proteomics holds the potential to elucidate Image-Expression Axes (IEAs) that can effectively address this disease heterogeneity.<h4>Methods</h4>A cohort of subjects diagnosed with severe COVID-19 pneumonia at 12 participating hospitals between December 2022 and March 2023 was prospectively screened for eligibility. Context-aware self-supervised representation learning (CSRL) was employed to extract intricate features from CT images. Quantification of plasma proteins was achieved using the Olink® inflammation panel. A deep learning model was meticulously trained, with CSRL features serving as input and the prote2025-01-01T00:00:00Z2025 Jul2026-06-02T17:46:09.226Z2026-05-27T03:07:49.179ZS-EPMC124173664093374310.1016/j.jointm.2024.11.001