Multicentric thrombus segmentation using an attention-based recurrent network with gradual modality dropout
This work addresses a critical problem in medical imaging for ischemic stroke diagnosis and treatment, with potential transfer to other small-lesion tasks, though it appears incremental as it builds on existing attention-based and recurrent network methods.
The paper tackled the challenge of detecting and delineating small, low-contrast thrombi in 3D brain scans across multi-center data with domain shifts and missing modalities, achieving detection rates of >90% with a Dice score of 0.65 in monocentric settings and around 80% with a Dice score of 0.35 in multi-center settings with missing modalities.
Detecting and delineating tiny targets in 3D brain scans is a central yet under-addressed challenge in medical imaging.In ischemic stroke, for instance, the culprit thrombus is small, low-contrast, and variably expressed across modalities(e.g., susceptibility-weighted T2 blooming, diffusion restriction on DWI/ADC), while real-world multi-center dataintroduce domain shifts, anisotropy, and frequent missing sequences. We introduce a methodology that couples an attention-based recurrent segmentation network (UpAttLLSTM), a training schedule that progressively increases the difficulty of hetero-modal learning, with gradual modality dropout, UpAttLLSTM aggregates context across slices via recurrent units (2.5D) and uses attention gates to fuse complementary cues across available sequences, making it robust to anisotropy and class imbalance. Gradual modality dropout systematically simulates site heterogeneity,noise, and missing modalities during training, acting as both augmentation and regularization to improve multi-center generalization. On a monocentric cohort, our approach detects thrombi in >90% of cases with a Dice score of 0.65. In a multi-center setting with missing modalities, it achieves-80% detection with a Dice score around 0.35. Beyond stroke, the proposed methodology directly transfers to other small-lesion tasks in 3D medical imaging where targets are scarce, subtle, and modality-dependent