IA3D-IO for Precise Foren-Neuro-Seg in MRI-WML

DOI

10.2991/978-94-6239-610-4_10How to use a DOI?

Keywords

IA3D-IO; MRI-WML; Foren-Neuro-Seg

Abstract

Forensic neuroimaging increasingly relies on precise segmentation of white‑matter lesions in MRI to support legal investigations and clinical interpretation. This paper introduces IA3D‑IO (Integrating Advanced 3D-Imaging and Optimization), a novel framework that integrates advanced three‑dimensional imaging processing with optimization techniques to improve Foren-Neuro-Seg (forensic‑neuro segmentation) accuracy for MRI-WML (white‑matter lesions). IA3D‑IO combines high‑resolution 3D reconstruction of lesion areas with a custom optimization pipeline that refines boundaries and reduces false positives common in automated methods. We evaluated the approach on multi‑contrast MRI datasets, comparing against leading deep‑learning and traditional segmentation baselines. Results show that IA3D‑IO achieves notably higher Dice similarity and lower boundary error, particularly for small or irregular lesions that often challenge existing algorithms. Quantitatively, the method improved segmentation reliability by a meaningful margin, while qualitatively preserving lesion morphology crucial for forensic interpretation. Beyond performance gains, IA3D‑IO offers a modular design that can incorporate emerging imaging modalities or optimization solvers, supporting future forensic and clinical workflows. The approach addresses an urgent need for more dependable lesion delineation, as recent studies highlight the critical role of automated methods in detecting and classifying subtle white‑matter abnormalities in MRI [1, 2, 4].

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Athur Shaik Ali Gousia Banu
AU  - Sumit Hazra
AU  - Mohammed Razia Alangir Banu
AU  - K. Purushottama Rao
PY  - 2026
DA  - 2026/05/05
TI  - IA3D-IO for Precise Foren-Neuro-Seg in MRI-WML
BT  - Proceedings of the First International Conference on Advances in Forensics and Cyber Technologies (ICFACT 2025)
PB  - Atlantis Press
SP  - 104
EP  - 111
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-610-4_10
DO  - 10.2991/978-94-6239-610-4_10
ID  - Banu2026
ER  -