cs.CVNov 10, 2026

MicroBT: Centroid-Guided Synergistic Learning for Multi-Modal Micro Brain Tumor Segmentation and Counting

Authors: Zhenye Lou, Qing Xu, Stefanie Thust, Dorothee P. Auer, Zhen Chen, Wenting Duan

Organizations: School of Engineering and Physical Science, University of Lincoln, Lincoln, UK · School of Computer Science, University of Nottingham, Nottingham, UK · Queen’s Medical Centre, University of Nottingham, Nottingham, UK · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR

Abstract

Multi-modal brain tumor segmentation is essential for clinical diagnosis, radiotherapy planning, and longitudinal monitoring. While recent studies have achieved remarkable overall segmentation performance, they rely on overlap-based objectives that inherently favor large regions, causing sub-3 mm micro-lesions to be systematically suppressed during training. Moreover, existing pixel-level segmentation frameworks lack explicit instance-level modeling, leading to unreliable lesion counting that directly impacts clinical staging and therapeutic decisions. To address these challenges, we propose MicroBT, a unified multi-modal framework for micro brain tumor segmentation and counting. Our core insight is that a fundamental geometric property is inherently scale-invariant: regardless of size, each lesion possesses a well-defined centroid. Leveraging this, we first devise a centroid-anchored synergistic paradigm that utilizes predicted centroids as shared anchors to simultaneously condition dense segmentation and instance-level localization. To counteract the tumor size imbalance, we further devise a Volume-Calibrated Loss (VC-Loss) that adaptively amplifies the gradient contribution of micro-lesions, alongside a Size-Aware Curriculum Optimization (SACO) that stabilizes multi-task training by establishing global representations before progressively unlocking fine-grained localization. Extensive experiments demonstrate that MicroBT outperforms state-of-the-art methods, particularly on metastases, where micro-lesion (≤3\leq 3 mm) localization precision improves by approximately 7% and counting estimation errors decrease by approximately 26%. The code is available at https://github.com/leonlou921/MicroBT.

Figures & tables

Explore similar work

CardsList
  1. Missing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation

    Oct 8, 2026Sol Lee, Hyunji Kim, Sungrae Hong +2Probability CalibrationBrain Tumor Segmentation

  2. Progressive multi-scale tumor-state memory for incomplete multimodal brain tumor segmentation

    Oct 19, 2026Milad Rostamian, Mohammadreza Mohammadi, Mohsen SoryaniMissing-Modality Medical Image SegmentationMedical Image Segmentation

  3. FSS-UBrain: Multi-region Few-Shot Brain Tumor MRI Segmentation

    Sep 26, 2026Truong Viet Vu, Nguyen Phuc Nguyen, Dang Thi Thu Hang +4Medical Image SegmentationFew-Shot Medical Image Segmentation