Brainiac improves brain lesion finding in varied mri scans with interactive help
BrainIAC: Interactive 3D Brain Lesion Segmentation across Heterogeneous MRI Modalities with Online Adaptation
Computer Vision and Pattern Recognition
Summary
Brain lesions are areas of damaged tissue in the brain that doctors need to find and study using MRI scans. BrainIAC is a new computer program designed to identify these lesions more accurately, even when the MRI images come from different machines or show different kinds of brain problems. It allows doctors to help guide the program by clicking or drawing boxes on the scans, improving the results while still working automatically if no help is given. The program also learns and adapts as it goes, making it better at handling new types of images and brain issues.
What this means in practice
- •For medical imaging teams: Use the tool to segment brain lesions in MRI scans with different imaging setups, improving diagnosis and treatment planning.
- •For medical device developers: Integrate the adaptive segmentation framework into MRI analysis software for better handling of new scanning protocols and brain pathologies.$Commercial implications: Enables enhanced brain lesion analysis features in commercial MRI software that adapt to diverse and evolving clinical data.
Authors
Wentian Xu, Anthony P Addison, Ziyun Liang, Harry Anthony, Guang Yang, Konstantinos Kamnitsas
Abstract
Brain lesion segmentation is a fundamental task in medical image analysis, playing a critical role in diagnosis, treatment planning, and longitudinal disease monitoring. Yet existing models still struggle to meet the demands of real clinical use, where deployments contain data distribution shifts, arising from differences in scanner hardware, imaging protocol (varying MRI modality sets), and new pathologies. We present BrainIAC (Brain lesion Interactive Adaptive Continuously learning segmentation), a unified framework that integrates (i) a multi-modal backbone network trained to segment multiple types of brain lesions and handle heterogeneous sets of modalities via zero-filling and random modality dropping; (ii) 3D interactive segmentation with bounding-box and click prompts that preserves fully automatic prediction when no prompt is given; and (iii) an online adaptation mechanism combining Mid-Interaction adaptation and Post-Interaction adaptation, supervised by the network's own predictions as pseudo labels and guided by an extra Click-Centered Gaussian loss. To our knowledge, this is one of the first 3D online adaptation methods for interactive segmentation, and the first to combine handling of heterogeneous modality sets with online adaptation. Experiments across seven brain MRI datasets demonstrate that the proposed components provide complementary and synergistic benefits. The method consistently outperforms existing approaches and generalizes well across heterogeneous imaging modalities, including those unseen during training, as well as previously unseen brain pathology types. The code and a 3D Slicer plug-in will be released at https://github.com/WenTXuL/BrainIAC upon publication.