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

Abstract

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.

Brain Tumor Characterization Using Radiogenomics in Artificial Intelligence Framework

“…The concept of pruning AI is motivated by the amount of storage needed during the training process of the AI models [ 149 ]. In contrast, the concept of explainable AI is inspired by the process of knowing how the AI black box performs [ 150 , 151 ]. The origination of evidence for scientific validation is also nowadays coined under the umbrella of explainable AI because XAI is used for satisfying the evidence for scientific validation [ 15 , 123 , 128 , 152 , 153 , 154 ].…”

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

“…The hUNet for the vascular paradigm uses SegNet-UNet+, which is the combination of SegNet and UNet+ (Figure 17 (bottom)) [53,141], and VGG-UNet [178] and ResNet-UNet [179]. The same input images were given to SegNet and UNet+ separately and the outputs were obtained.…”

A Survey on AI Techniques for Thoracic Diseases Diagnosis Using Medical Images

“…For each class, we discuss the research that classifies these diseases whether the classification is binary or multiple, the type of image for each disease, the type of AI model that is used to detect this disease, the dataset used, and the performance of each model. Lung diseases include pneumonia [ 139 ], COVID-19 [ 137 , 161 , 162 , 163 , 164 , 165 ], edema [ 166 ], lesion [ 135 ], asbestosis signs [ 167 ], consolidation [ 168 ], atelectasis [ 169 ], COPD [ 170 ], pleural thickening [ 171 ], fibrosis [ 172 ], asthma [ 173 ], lung metastasis [ 98 ], pneumothorax [ 174 ], emphysema [ 175 ], tuberculosis (TB) [ 176 ], and infiltration [ 177 ]. Heart diseases include cardiomegaly [ 128 ] and heart insufficiency disease [ 178 ].…”