Orientation-Aware Unsupervised Domain Adaptation for Brain Tumor Classification Across Multi-Modal MRI

TL;DR

This paper presents an orientation-aware unsupervised domain adaptation framework for brain tumor classification across multi-modal MRI, improving model generalization amidst limited annotations and domain shifts.

Contribution

It introduces a novel orientation-aware architecture with multi-modal transfer and pseudo-label guided adaptation for improved brain tumor classification.

Findings

Enhanced target-domain accuracy over prior methods

Orientation-specific learning improves classification

Multi-modal knowledge transfer benefits domain adaptation

Abstract

The clinical integration of deep learning models for brain tumor diagnosis in neuro-oncology is severely constrained by limited expert-annotated MRI data and substantial inter-institutional domain shift arising from variations in scanners, imaging protocols, and contrast settings. These challenges significantly impair model generalization in real-world settings. To address this, we propose a novel orientation-aware unsupervised domain-adaptive framework for automated brain tumor classification using mixed 2D MRI slices. Initially, a CNN with large receptive field first categorizes input slices into axial, sagittal, and coronal views. For each orientation, a CNN architecture with ResNet50 backbone augmented with four fully connected layers is trained to extract discriminative features for tumor classification. To mitigate annotation scarcity and domain discrepancies, we introduce a slice-wise unsupervised domain adaptation strategy that transfers knowledge from the multi-modal such as T1, T2, and FLAIR source domain to the post-contrast T1 target domain. Feature-level alignment is enforced using maximum mean discrepancy loss, complemented by pseudo-label guided adaptation to preserve class discriminability. Extensive experiments demonstrate improved target-domain performance over prior approaches, highlighting the benefits of orientation-specific learning, multi-modal knowledge transfer, pseudo-label-guided adaptation, and unsupervised domain adaptation.