{"ID":5935792,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03203","arxiv_id":"2607.03203","title":"Mutually Exclusive Multiclass Lesion Segmentation in Neuroimaging: Binary-Guided Weak Supervision with Inter-Class Orthogonality","abstract":"Weakly supervised segmentation of co-occurring neuroimaging lesion subclasses remains challenging due to overlapping activations, noisy pseudo-labels, and the absence of explicit inter-class exclusivity constraints. We propose BiMEx-MS (Binary-guided Mutually Exclusive Multiclass Segmentation), a framework that decomposes multiclass segmentation into whole-lesion localization and exclusive class assignment: a binary localization module provides a class-frequency-agnostic structural prior confining multiclass predictions within the detected lesion domain, while a multi-exit classification architecture with supervised contrastive pretraining produces multi-scale class-discriminative activation maps aggregated via a class-specific attention network. Inter-class exclusivity is enforced through a tri-partite loss comprising per-class separation, inter-class orthogonality, and binary-multiclass spatial consensus, followed by hierarchical morphological pseudo-label refinement. Evaluated across brain tumor MRI (BraTS 2020, BraTS 2023 SSA) and intracranial hemorrhage CT (RSNA-ICH to BHSD) against sixteen weakly supervised baselines, BiMEx-MS achieves Edema HD95 of 29.56 mm (the only method below 40 mm) and subdural hemorrhage Dice of 0.704, with gains consistently largest on boundary metrics and rare subtypes. Cross-dataset generalization, backbone ablations across six architectures, and uncertainty quantification confirm that structural guidance rather than model capacity drives performance. Code: https://github.com/ashutoshkr45/BiMEx-MS-Neuro.","short_abstract":"Weakly supervised segmentation of co-occurring neuroimaging lesion subclasses remains challenging due to overlapping activations, noisy pseudo-labels, and the absence of explicit inter-class exclusivity constraints. We propose BiMEx-MS (Binary-guided Mutually Exclusive Multiclass Segmentation), a framework that decompo...","url_abs":"https://arxiv.org/abs/2607.03203","url_pdf":"https://arxiv.org/pdf/2607.03203v1","authors":"[\"Ashutosh Kumar\",\"Vivek Dhamale\",\"Vaanathi Sundaresan\"]","published":"2026-07-03T11:16:01Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613933,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T01:22:02.77346169Z","DeletedAt":null,"paper_id":5935792,"paper_url":"https://arxiv.org/abs/2607.03203","paper_title":"Mutually Exclusive Multiclass Lesion Segmentation in Neuroimaging: Binary-Guided Weak Supervision with Inter-Class Orthogonality","repo_url":"https://github.com/ashutoshkr45/BiMEx-MS-Neuro","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}