{"ID":2880811,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.14151","arxiv_id":"2508.14151","title":"A Systematic Study of Deep Learning Models and xAI Methods for Region-of-Interest Detection in MRI Scans","abstract":"Magnetic Resonance Imaging (MRI) is an essential diagnostic tool for assessing knee injuries. However, manual interpretation of MRI slices remains time-consuming and prone to inter-observer variability. This study presents a systematic evaluation of various deep learning architectures combined with explainable AI (xAI) techniques for automated region of interest (ROI) detection in knee MRI scans. We investigate both supervised and self-supervised approaches, including ResNet50, InceptionV3, Vision Transformers (ViT), and multiple U-Net variants augmented with multi-layer perceptron (MLP) classifiers. To enhance interpretability and clinical relevance, we integrate xAI methods such as Grad-CAM and Saliency Maps. Model performance is assessed using AUC for classification and PSNR/SSIM for reconstruction quality, along with qualitative ROI visualizations. Our results demonstrate that ResNet50 consistently excels in classification and ROI identification, outperforming transformer-based models under the constraints of the MRNet dataset. While hybrid U-Net + MLP approaches show potential for leveraging spatial features in reconstruction and interpretability, their classification performance remains lower. Grad-CAM consistently provided the most clinically meaningful explanations across architectures. Overall, CNN-based transfer learning emerges as the most effective approach for this dataset, while future work with larger-scale pretraining may better unlock the potential of transformer models.","short_abstract":"Magnetic Resonance Imaging (MRI) is an essential diagnostic tool for assessing knee injuries. However, manual interpretation of MRI slices remains time-consuming and prone to inter-observer variability. This study presents a systematic evaluation of various deep learning architectures combined with explainable AI (xAI)...","url_abs":"https://arxiv.org/abs/2508.14151","url_pdf":"https://arxiv.org/pdf/2508.14151v2","authors":"[\"Justin Yiu\",\"Kushank Arora\",\"Daniel Steinberg\",\"Rohit Ghiya\"]","published":"2025-08-19T17:42:45Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Vision Transformer\",\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}