Pre- and Post-Treatment Glioma Segmentation with the Medical Imaging Segmentation Toolkit

2025-07-25

AI Summary

Medical image segmentation lacks standardized, customizable post-processing tools, hindering fair method comparison and result reproducibility. To address this, we propose a modular, configurable post-processing pipeline built upon the MIST framework. It enables flexible, class-specific, multi-stage morphological operations—including small-object removal, largest connected component extraction, hole filling, and morphological closing—fully customizable per task and anatomy. Evaluated under the BraTS 2025 challenge protocol on multimodal glioma imaging, our approach significantly improves segmentation accuracy and robustness: Dice scores increase while Hausdorff distance decreases, enhancing both clinical applicability and research reproducibility. The pipeline is open-source, extensible, and establishes a standardized, domain-adapted post-processing paradigm for medical image segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Medical image segmentation continues to advance rapidly, yet rigorous comparison between methods remains challenging due to a lack of standardized and customizable tooling. In this work, we present the current state of the Medical Imaging Segmentation Toolkit (MIST), with a particular focus on its flexible and modular postprocessing framework designed for the BraTS 2025 pre- and post-treatment glioma segmentation challenge. Since its debut in the 2024 BraTS adult glioma post-treatment segmentation challenge, MIST's postprocessing module has been significantly extended to support a wide range of transforms, including removal or replacement of small objects, extraction of the largest connected components, and morphological operations such as hole filling and closing. These transforms can be composed into user-defined strategies, enabling fine-grained control over the final segmentation output. We evaluate three such strategies - ranging from simple small-object removal to more complex, class-specific pipelines - and rank their performance using the BraTS ranking protocol. Our results highlight how MIST facilitates rapid experimentation and targeted refinement, ultimately producing high-quality segmentations for the BraTS 2025 challenge. MIST remains open source and extensible, supporting reproducible and scalable research in medical image segmentation.

Problem

• Standardized tooling for glioma segmentation comparison
• Flexible postprocessing for BraTS 2025 challenge
• Enhancing segmentation quality with modular transforms

Innovation

• Modular postprocessing framework for glioma segmentation
• Supports diverse transforms like object removal and morphological operations
• Enables user-defined strategies for fine-grained segmentation control