Published October 31, 2026 | Version v1

AI-Driven rTMS Target Localization and Brain Segmentation via Deep Learning

  • 1. Independent Researcher

Description

This repository presents a production-ready, deep learning-driven pipeline optimized for automatic brain segmentation and target coil localization in Repetitive Transcranial Magnetic Stimulation (rTMS) therapy. Leveraging a customized U-Net encoder-decoder topology with skip-connections, the architecture counters severe class spatial imbalances through a specialized Dice Loss optimization tracker. To optimize resource allocation and circumvent local storage constraints, the data engine utilizes an advanced IterableDataset cloud-streaming pipeline to dynamically fetch and process genuine 2D human brain MRI matrices directly from cloud repositories in real-time. Upon segmenting target anatomical boundaries, the system applies a multi-panel visualization interface and high-fidelity center-of-mass spatial extraction logic to map exact targeting coordinates (\(X\) and \(Y\)). The resulting diagnostics dashboard tracks model error optimization curves against true references, providing an end-to-end framework for precision neuroanatomical targeting.

Files

download (47).png

Files (1.7 MB)

Name Size
md5:3429f858130d7ef7058facd3c7ed61f1
105.5 kB Preview Download
md5:09e17633227fcf1c3e8af91b3c0e77f7
89.5 kB Preview Download
md5:744487995a7d3e9ced80c68c7c9252f9
71.7 kB Preview Download
md5:a9c01fd5cd74fcca5bf88ccbefb1cf70
118.0 kB Preview Download
md5:f914548ac53fd8f01599a1ca6e17347d
603.3 kB Preview Download
md5:8787f42ebb16d5356eb359cff0c9f1a5
729.9 kB Preview Download

Additional details

Software

Programming language
Python console , Python
Development Status
Active