Semantic-Aware Semi-Supervised Systematic Segmentation for Brain Magnetic Resonance Image
- 31 August 2026
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 37 (03)
Abstract
Accurate segmentation of brain MRI images is essential for early diagnosis and prevention of brain tumors and strokes. However, it is challenging due to data scarcity, domain shift, complexity, and blurred edges. Recent methods use mean-teacher model learning for the semantic details of an individual image based on the efficiency of teacher architecture. However, to enhance the segmentation in brain MRI, the paper introduces SemS4, a semi-supervised method on the basis of cross-image architecture. SemS4 uses a single architecture integrating an Edge Prototype Attention (EPA) and a foreground prototype attention (FPA). More specifically, EPA uses edge prototype integrated with adaptive edge container to improve the edge features for which global edge features are stored to produce edge prototype. Moreover, FPA stabilizes the segmentation by transferring complementary foreground information. Furthermore, the proposed method uses Pixel Affinity Loss (PAL) for missing contextual correlation during supervision to enhance segmentation performance on edges. The performance of the proposed approach in experimental results for two brain MRI benchmarks, LGG and BRISC, validates the superiority over existing methods under different partitioning settings.Keywords
Funding Information
- FVG region “Supporting the diagnosis of rare diseases through artificial intelligence” (2023-26)
- Project A with CUP (F53C22001770002)
- Project B with CUP (F53C22001780002)
This publication has 45 references indexed in Scilit:
- Multi-level feature fusion network for kidney disease detectionComputers in Biology and Medicine, 2025
- Self-Supervised Learning for Near-Wild Cognitive Workload EstimationJournal of Medical Systems, 2024
- ICDAR 2024 Competition on Few-Shot and Many-Shot Layout Segmentation of Ancient Manuscripts (SAM)2024
- Self-supervised learning for medical image analysis: a comprehensive reviewEvolving Systems, 2024
- AI‐Enhanced Detection of Clinically Relevant Structural and Functional Anomalies in MRI: Traversing the Landscape of Conventional to Explainable ApproachesJournal of Magnetic Resonance Imaging, 2024
- A domain knowledge powered hybrid regularization strategy for semi-supervised breast cancer diagnosisExpert Systems with Applications, 2023
- An efficient deep learning model to categorize brain tumor using reconstruction and fine-tuningExpert Systems with Applications, 2023
- Interpretable features fusion with precision MRI images deep hashing for brain tumor detectionComputer Methods and Programs in Biomedicine, 2023
- An intelligent driven deep residual learning framework for brain tumor classification using MRI imagesExpert Systems with Applications, 2022
- Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithmComputers in Biology and Medicine, 2019