COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans
Author
Suri JSAgarwal S
Chabert GL
Carriero A
Pasch� A
Danna PSC
Saba L
Mehmedovi? A
Faa G
Singh IM
Turk M
Chadha PS
Johri AM
Khanna NN
Mavrogeni S
Laird JR
Pareek G
Miner M
Sobel DW
Balestrieri A
Sfikakis PP
Tsoulfas G
Protogerou AD
Misra DP
Agarwal V
Kitas GD
Teji JS
Al-Maini M
Dhanjil SK
Nicolaides A
Sharma A
Rathore V
Fatemi M
Alizad A
Krishnan PR
Nagy F
Ruzsa Z
Fouda MM
Naidu S
Viskovic K
Kalra MK.
Publication date
2022-06-24Subject
Respiratory medicine
Metadata
Show full item recordAbstract
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.Citation
Diagnostics (Basel). 2022 Jun 16;12(6):1482. doi: 10.3390/diagnostics12061482.Type
ArticlePMID
35741292Journal
DiagnosticsPublisher
MDPIae974a485f413a2113503eed53cd6c53
10.3390/diagnostics12061482