Radiomic V-Net Deep Learning Architecture for Breast Cancer Prediction Deployed on Medical Consumer Electronics

Abstract

This paper introduces a radiomic-integrated 2D V-Net architecture designed for deployment on medical consumer electronics (MCE) platforms. The system targets real-time detection of architectural distortion in mammograms, a critical indicator for early breast cancer screening. Unlike conventional clinical models, our approach is optimized for consumer-grade edge devices, including Jetson Nano, Raspberry Pi 4, and Snapdragon 865, enabling diagnostic capability in home, rural, and mobile health settings. To achieve this, we employ lightweight design strategies such as top-hat morphological preprocessing, radiomic feature integration, and skip-connected V-Net layers. Deployment efficiency is further enhanced with INT8 quantization, pruning, and operator fusion, reducing model size and latency while preserving accuracy. Experimental evaluation on the CBIS-DDSM and PINUM datasets demonstrates robust performance, with accuracies of 0.98 and 0.97 and specificities of 0.97 and 0.87, respectively. A dedicated visualization interface for smartphones and tablets provides interactive feedback and encrypted report sharing, bridging patients and healthcare providers. By combining radiomic insights, edge AI deployment, and consumer-grade accessibility, this work contributes a scalable, privacy-aware solution for smart healthcare ecosystems and next-generation MCE.

Ähnliche Arbeiten