Abstract
A state-of-the-art brain-MRI reporter can be fluent yet diagnostically mute, e.g. calling most meningiomas and metastases “glioma”. We present NeuroFusion, which surfaces the buried diagnostic signal in frozen segmentation features via discriminative field-classifier heads conditioning a draft-then-review decoder, restoring diagnostic recall and winning 8 of 9 prose-content comparisons at 5-6x lower latency.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MLCN_2026_052.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=QWhFC11zjc
BibTex
@InProceedings{HasKha_The_MICCAISAT2026,
author = { Hassan, Khawaja Murad ul AND Adil, Ruqiyya AND Qayyum, Adil AND Hassan, Rida AND Khan, Asad Mansoor AND Akram, Muhammad Usman AND Ebrahimi, Mehran},
title = { { The Diagnosis a Reporter Leaves Unspoken: Surfacing Frozen Tumor Features for Brain-Tumor MRI Reporting } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17255},
month = {pending},
page = {pending}
}