Deep learning for predicting COVID-19 malignant progression.

Journal: Medical image analysis
Published Date: May 12, 2021

Abstract

As COVID-19 is highly infectious, many patients can simultaneously flood into hospitals for diagnosis and treatment, which has greatly challenged public medical systems. Treatment priority is often determined by the symptom severity based on first assessment. However, clinical observation suggests that some patients with mild symptoms may quickly deteriorate. Hence, it is crucial to identify patient early deterioration to optimize treatment strategy. To this end, we develop an early-warning system with deep learning techniques to predict COVID-19 malignant progression. Our method leverages CT scans and the clinical data of outpatients and achieves an AUC of 0.920 in the single-center study. We also propose a domain adaptation approach to improve the generalization of our model and achieve an average AUC of 0.874 in the multicenter study. Moreover, our model automatically identifies crucial indicators that contribute to the malignant progression, including Troponin, Brain natriuretic peptide, White cell count, Aspartate aminotransferase, Creatinine, and Hypersensitive C-reactive protein.

Authors

  • Cong Fang
    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Song Bai
    Department of Engineering Science, University of Oxford, Parks Road, Oxford OX1 3PJ, United Kingdom.
  • Qianlan Chen
    School of Economics and Management, Guangxi Normal University, Guilin, China.
  • Yu Zhou
    Department of Biospectroscopy, Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V., Dortmund, Germany.
  • Liming Xia
    From the Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T., E.H.M.P., D.P.S., A.d.R., H.J.L., R.J.v.d.G.); Department of Electrical Engineering, Fudan University, Shanghai, China (W.Y., Y.W.); Multidisciplinary Cardiovascular Research Centre & Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, England (P.G., S.P.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); and Departments of Cardiology (M.S.) and Radiology (J.T.), Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Lixin Qin
    From the Department of Radiology, Wuhan Huangpi People's Hospital, Wuhan, China (L.L., Z.X., X.F., S.Z., Juan Xia); Jianghan University Affiliated Huangpi People's Hospital, Wuhan, China (L.L.); Department of Radiology, Wuhan Pulmonary Hospital, Wuhan, China (L.Q.); Keya Medical Technology Co, Ltd, Shenzhen, China (Y.Y., X.W., B.K., J.B., Y.L., Z.F., Q.S., K.C.); Department of Radiology, Liaocheng People's Hospital, Liaocheng, China (D.L.); Department of CT, The Third Medical Center of Chinese PLA General Hospital, Beijing, China (G.W.); and Department of Radiology, Shenzhen Second People's Hospital/the First Affiliated Hospital of Shenzhen University Health Science Center, Shenzhen, China 518035 (Q.X., Jun Xia).
  • Shi Gong
    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Xudong Xie
    School of Automation, Huazhong University of Science and Technology, Wuhan 430074, China; Department of Automation, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Chunhua Zhou
    Departement of Medical Oncology, Lung Cancer and Gastrointestinal Unit, Hunan Cancer Hospital/Affiliated Cancer Hospital of Xiangya School of Medicine, Changsha 410013, China.
  • Dandan Tu
    From the School of Electronic Information and Communications, Huazhong University of Science and Technology, South 1st Building, Luoyu Road 1037, Wuhan 430074, China (J.Y., C.H., Y.X.); Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (M.X., O.A., J.L., T.J., X. Long); Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China (M.X., O.A., J.L., T.J., X. Long); Department of Radiology, Xin Cai People's Hospital, Xin Cai, China (Changde Li); and Huawei Technologies, Shenzhen, China (D.T., X. Liu, C.Z., Cixing Li).
  • Changzheng Zhang
    From the School of Electronic Information and Communications, Huazhong University of Science and Technology, South 1st Building, Luoyu Road 1037, Wuhan 430074, China (J.Y., C.H., Y.X.); Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (M.X., O.A., J.L., T.J., X. Long); Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China (M.X., O.A., J.L., T.J., X. Long); Department of Radiology, Xin Cai People's Hospital, Xin Cai, China (Changde Li); and Huawei Technologies, Shenzhen, China (D.T., X. Liu, C.Z., Cixing Li).
  • Xiaowu Liu
    From the School of Electronic Information and Communications, Huazhong University of Science and Technology, South 1st Building, Luoyu Road 1037, Wuhan 430074, China (J.Y., C.H., Y.X.); Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (M.X., O.A., J.L., T.J., X. Long); Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China (M.X., O.A., J.L., T.J., X. Long); Department of Radiology, Xin Cai People's Hospital, Xin Cai, China (Changde Li); and Huawei Technologies, Shenzhen, China (D.T., X. Liu, C.Z., Cixing Li).
  • Weiwei Chen
    Department of Developmental and Behavioral Pediatrics, Shanghai Children's Medical Center affiliated to Shanghai Jiaotong University School of Medicine, Ministry of Education-Shanghai Key Laboratory of Children's Environmental Health, Shanghai, China.
  • Xiang Bai
  • Philip H S Torr
    Department of Engineering Science, University of Oxford, Parks Road, Oxford OX1 3PJ, United Kingdom.

Keywords

External Resources

Popular Topics
Recent Journals