Deep insights into gastrointestinal health: A comprehensive analysis of GastroVision dataset using convolutional neural networks and explainable AI
Muhammad Fahad, Noor E Mobeen, Ali Shariq Imran, Sher Muhammad Daudpota, Zenun Kastrati, Faouzi Alaya Cheikh, Mohib Ullah
Abstract
The gastrointestinal (GI) tract is critical in digestion and nutrient absorption, thus vital for human health. However, it is prone to diseases like cancer. Manual assessments introduce accuracy variations, consistency issues, and delays. Resources like the GastroVision dataset were introduced to advance AI in this field. Yet, it faces class imbalance issues, and baseline evaluation lacks novel methodologies, impacting accuracy. We propose a novel deep-learning model to enhance accuracy and robustness. Our approach involves averaging weights of multiple models fine-tuned with diverse hyper-parameters. In contrast to classical ensembles, our approach uses DenseNet-121 as a baseline and enables the averaging of numerous models without incurring extra inference or memory costs. Data augmentation techniques are incorporated to address class imbalance. We achieve promising results on standard performance metrics, substantially improving over baseline, notably 2.4% points in Macro Precision. Additionally, we integrate explainable AI (XAI) techniques to enhance reliability and interpretability, shedding light on the model’s decision-making processes. Our study contributes to robust methodologies for imbalanced datasets, promoting model transparency and trust in predictive outcomes for clinical decision support systems. • Proposed a novel approach that leverages Greedy Soup with DenseNet-121 for GI disease detection. • Performed SoTA experiments on the GastroVision dataset and with dataset categories. • Enhanced accuracy using GAN and data augmentation. • Incorporated XAI (SHAP and GradCAM) for the model interpretability.