COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans.

Autor: Suri JS; Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA.; Advanced Knowledge Engineering Centre, GBTI, Roseville, CA 95661, USA., Agarwal S; Advanced Knowledge Engineering Centre, GBTI, Roseville, CA 95661, USA.; Department of Computer Science Engineering, PSIT, Kanpur 209305, India., Chabert GL; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy., Carriero A; Department of Radiology, 'Maggiore della Carità' Hospital, University of Piemonte Orientale (UPO), Via Solaroli 17, 28100 Novara, Italy., Paschè A; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy., Danna PSC; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy., Saba L; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy., Mehmedović A; Department of Radiology, University Hospital for Infectious Diseases, 10000 Zagreb, Croatia., Faa G; Department of Pathology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy., Singh IM; Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA., Turk M; The Hanse-Wissenschaftskolleg Institute for Advanced Study, 27753 Delmenhorst, Germany., Chadha PS; Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA., Johri AM; Department of Medicine, Division of Cardiology, Queen's University, Kingston, ON K7L 3N6, Canada., Khanna NN; Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi 110076, India., Mavrogeni S; Cardiology Clinic, Onassis Cardiac Surgery Center, 17674 Athens, Greece., Laird JR; Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA 94574, USA., Pareek G; Minimally Invasive Urology Institute, Brown University, Providence, RI 02912, USA., Miner M; Men's Health Center, Miriam Hospital, Providence, RI 02912, USA., Sobel DW; Minimally Invasive Urology Institute, Brown University, Providence, RI 02912, USA., Balestrieri A; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy., Sfikakis PP; Rheumatology Unit, National Kapodistrian University of Athens, 17674 Athens, Greece., Tsoulfas G; Department of Surgery, Aristoteleion University of Thessaloniki, 54124 Thessaloniki, Greece., Protogerou AD; Cardiovascular Prevention and Research Unit, Department of Pathophysiology, National & Kapodistrian University of Athens, 15772 Athens, Greece., Misra DP; Department of Immunology, SGPIMS, Lucknow 226014, India., Agarwal V; Department of Immunology, SGPIMS, Lucknow 226014, India., Kitas GD; Academic Affairs, Dudley Group NHS Foundation Trust, Dudley DY1 2HQ, UK.; Arthritis Research UK Epidemiology Unit, Manchester University, Manchester M13 9PL, UK., Teji JS; Ann and Robert H. Lurie Children's Hospital of Chicago, Chicago, IL 60611, USA., Al-Maini M; Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON M5G 1N8, Canada., Dhanjil SK; AtheroPoint LLC., Roseville, CA 95661, USA., Nicolaides A; Vascular Screening and Diagnostic Centre, University of Nicosia Medical School, Engomi 2408, Cyprus., Sharma A; Division of Cardiovascular Medicine, University of Virginia, Charlottesville, VA 22902, USA., Rathore V; AtheroPoint LLC., Roseville, CA 95661, USA., Fatemi M; Department of Physiology & Biomedical Engineering, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA., Alizad A; Department of Radiology, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA., Krishnan PR; Neurology Department, Fortis Hospital, Bengaluru 560076, India., Nagy F; Internal Medicine Department, University of Szeged, 6725 Szeged, Hungary., Ruzsa Z; Invasive Cardiology Division, University of Szeged, 1122 Budapest, Hungary., Fouda MM; Department of ECE, Idaho State University, Pocatello, ID 83209, USA., Naidu S; Electrical Engineering Department, University of Minnesota, Duluth, MN 55812, USA., Viskovic K; Department of Radiology, University Hospital for Infectious Diseases, 10000 Zagreb, Croatia., Kalra MK; Department of Radiology, Massachusetts General Hospital, 55 Fruit Street, Boston, MA 02114, USA.
Jazyk: angličtina
Zdroj: Diagnostics (Basel, Switzerland) [Diagnostics (Basel)] 2022 Jun 16; Vol. 12 (6). Date of Electronic Publication: 2022 Jun 16.
DOI: 10.3390/diagnostics12061482
Abstrakt: Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.
Databáze: MEDLINE
Nepřihlášeným uživatelům se plný text nezobrazuje