Development of an Automated Deep Learning Diagnostic Platform for Medical Imaging

Motivation: Deep learning in medical imaging offers great potential, but accessibility for clinicians is challenging. Goal(s): To develop an automated, user-friendly platform for seamless image preprocessing, model selection, training, evaluation, and interpretation. Approach: Built in Python using MONAI, the platform includes features like image cropping, normalization, dataset splitting, and model selection (ResNet, DenseNet). Grad-CAM support enhances interpretability. The TCAI glioma dataset was used for testing. Results: The platform achieved high accuracy on the TCAI dataset and is easy to use, making it accessible to clinicians without extensive technical expertise. Impact: This platform enhances clinical accessibility to deep learning diagnostic tools, supporting high-precision diagnostics and interpretability through an intuitive interface, and reducing the technical barrier to AI in medical imaging.