Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Brain Tumor Segmentation (BraTS) challenges have significantly advanced research in brain tumor segmentation and related medical imaging tasks. This paper provides a comprehensive review of the BraTS datasets from 2012 to 2024, examining their evolution, challenges, and contributions to MRI-based brain tumor segmentation. Over the years, the datasets have grown in size, complexity, and scope, incorporating refined pre-processing and annotation protocols. By synthesizing insights from over a decade of BraTS challenges, this review elucidates the progression of dataset curation, highlights the impact on state-of-the-art segmentation approaches, and identifies persisting limitations and future directions. Crucially, it provides researchers, clinicians, and industry stakeholders with a single, in-depth resource on the evolution and practical utility of BraTS datasets-demonstrating year-by-year improvements in the field and discussing their potential for enabling robust, clinically relevant segmentation methods that can further advance precision medicine. Additionally, an overview of the upcoming BraTS 2025 Challenge-currently in planning-is presented, highlighting its expanded focus across further clinical needs.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11945730 | PMC |
| http://dx.doi.org/10.3390/s25061838 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Diffusion Model with Relation-Aware Attention and Edge-Aware Constraint for Multi-Modal Brain Tumor Segmentation.
IEEE J Biomed Health Inform
September 2025
Multi-modal brain tumors segmentation is a critical step for diagnosing and monitoring brain-related disease. Many studies have developed models for this task, but two challenges remain, i.e.
View Article and Find Full Text PDFMedical SAM-Clip Grafting for brain tumor segmentation.
Comput Biol Med
August 2025
The First People Hospital of Foshan, Foshan City CN, China. Electronic address:
Brain Tumor Segmentation (BTS) is crucial for accurate diagnosis and treatment planning, but existing CNN and Transformer-based methods often struggle with feature fusion and limited training data. While recent large-scale vision models like Segment Anything Model (SAM) and CLIP offer potential, SAM is trained on natural images, lacking medical domain knowledge, and its decoder struggles with accurate tumor segmentation. To address these challenges, we propose the Medical SAM-Clip Grafting Network (MSCG), which introduces a novel SC-grafting module.
View Article and Find Full Text PDFEnhanced glioma semantic segmentation using U-net and pre-trained backbone U-net architectures.
Sci Rep
August 2025
Medical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
Gliomas are known to have different sub-regions within the tumor, including the edema, necrotic, and active tumor regions. Segmenting of these regions is very important for glioma treatment decisions and management. This paper aims to demonstrate the application of U-Net and pre-trained U-Net backbone networks in glioma semantic segmentation, utilizing different magnetic resonance imaging (MRI) image weights.
View Article and Find Full Text PDFFederated modality-specific encoders and partially personalized fusion decoder for multimodal brain tumor segmentation.
Med Image Anal
December 2025
National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, 361005, Fujian, China; Department of Computer Science at School of Informatics, Xiamen University, Xiamen, 361005, Fujian, China. Electronic address:
Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, some FL participants may possess only a subset of the complete imaging modalities, posing intermodal heterogeneity as a challenge to effectively training a global model on all participants' data. Meanwhile, each participant expects a personalized model tailored to its local data characteristics in FL.
View Article and Find Full Text PDFA Web-Deployed, Explainable AI System for Comprehensive Brain Tumor Diagnosis.
Neurol Int
August 2025
Department of Mechanical Engineering, Aydin Adnan Menderes University (ADU), Aytepe, 09010 Aydin, Turkey.
Background/objectives: Accurate diagnosis of brain tumors is one of the most important challenges in neuro-oncology since tumor classification and volumetric segmentation inform treatment planning. Two-dimensional classification and three-dimensional segmentation deep learning models can augment radiological workflows, particularly if paired with explainable AI techniques to improve model interpretability. The objective of this research was to develop a web-based brain tumor segmentation and classification diagnosis platform.
View Article and Find Full Text PDF