Anatomy-Aware 3D GAN with Local Mask Refinement for Brain MRI Inpainting

Brain tumor MRI inpainting aims to synthesize plausible healthy-appearing tissue in regions removed from pathological scans. We present an anatomy-aware three-dimensional generative adversarial network for Task 4 of the BraTS 2026 challenge. The method combines mask-aware gated convolutions, mirrored contralateral context, attention-modulated skip fusion, boundary-aware refinement, and a local masked-region refiner, each adapted from established components in the image synthesis and inpainting literature. The model is trained with a two-stage objective that first emphasizes voxel-wise and structural reconstruction and then applies low-weight adversarial fine-tuning. On a deterministic local held-out split, the proposed method substantially improves over a simple 3D AutoEncoder baseline but does not surpass the challenge's Pix2Pix3D baseline. On the official BraTS 2026 Task 4 evaluation server, the submitted model obtained a mean SSIM of 0.658 and a mean PSNR of 14.81~dB over 219 evaluated cases, lower than the local held-out figures. We report these results transparently, analyze likely contributing factors, and identify the controlled ablations (removal of the mirrored-context channel and of the two-stage schedule) required to isolate the contribution of each architectural component.

Authors

Institutions

Publication Details

Journal
medRxiv
Published
2026-11-15
DOI
https://doi.org/10.64898/2026.11.12.26367904
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Anatomy-Aware 3D GAN with Local Mask Refinement for Brain MRI Inpainting

Hari Mohan Rai, Sayed Yasar Ahmad Mushtaq, Abdul Fatah Rahimi
medRxiv
Generative Adversarial Networks and Image Synthesis
preprint

Anatomy-Aware 3D GAN with Local Mask Refinement for Brain MRI Inpainting

Hari Mohan Rai, Sayed Yasar Ahmad Mushtaq, Abdul Fatah Rahimi
preprint en

Abstract

Brain tumor MRI inpainting aims to synthesize plausible healthy-appearing tissue in regions removed from pathological scans. We present an anatomy-aware three-dimensional generative adversarial network for Task 4 of the BraTS 2026 challenge. The method combines mask-aware gated convolutions, mirrored contralateral context, attention-modulated skip fusion, boundary-aware refinement, and a local masked-region refiner, each adapted from established components in the image synthesis and inpainting literature. The model is trained with a two-stage objective that first emphasizes voxel-wise and structural reconstruction and then applies low-weight adversarial fine-tuning. On a deterministic local held-out split, the proposed method substantially improves over a simple 3D AutoEncoder baseline but does not surpass the challenge's Pix2Pix3D baseline. On the official BraTS 2026 Task 4 evaluation server, the submitted model obtained a mean SSIM of 0.658 and a mean PSNR of 14.81~dB over 219 evaluated cases, lower than the local held-out figures. We report these results transparently, analyze likely contributing factors, and identify the controlled ablations (removal of the mirrored-context channel and of the two-stage schedule) required to isolate the contribution of each architectural component.

medRxiv
Nazarbayev University (KZ)
Generative Adversarial Networks and Image Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Anatomy-Aware 3D GAN with Local Mask Refinement for Brain MRI Inpainting — Hari Mohan Rai, Sayed Yasar Ahmad Mushtaq, et al. · medRxiv (2026) | TGRS Research Map | TGRS