Leveraging Unlabeled Scans for NCCT Image Segmentation in Early Stroke Diagnosis: A Semi-Supervised GAN Approach

2025/11/24 by Thoma, Maria, Savelonas, Michalis A., Iakovidis, Dimitris K.
Computer Science · Medicine · Neuroscience · #Acute Ischemic Stroke Management #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis

paper · doi:10.48550/arxiv.2511.19576

openalex publication_date 2025/11/24 · openalex created_date 2025/11/28 · openalex updated_date 2026/07/28

Abstract

Ischemic stroke is a time-critical medical emergency where rapid diagnosis is essential for improving patient outcomes. Non-contrast computed tomography (NCCT) serves as the frontline imaging tool, yet it often fails to reveal the subtle ischemic changes present in the early, hyperacute phase. This limitation can delay crucial interventions. To address this diagnostic challenge, we introduce a semi-supervised segmentation method using generative adversarial networks (GANs) to accurately delineate early ischemic stroke regions. The proposed method employs an adversarial framework to effectively learn from a limited number of annotated NCCT scans, while simultaneously leveraging a larger pool of unlabeled scans. By employing Dice loss, cross-entropy loss, a feature matching loss and a self-training loss, the model learns to identify and delineate early infarcts, even when they are faint or their size is small. Experiments on the publicly available Acute Ischemic Stroke Dataset (AISD) demonstrate the potential of the proposed method to enhance diagnostic capabilities, reduce the burden of manual annotation, and support more efficient clinical decision-making in stroke care.

Citations

• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Gradient-based learning applied to document recognition

Related

• Clinically-Informed Preprocessing Improves Stroke Segmentation in Low-Resource Settings
• Ischemic Stroke Lesion Segmentation Using Adversarial Learning
• CT-To-MR Conditional Generative Adversarial Networks for Ischemic Stroke Lesion Segmentation
• Automated Segmentation of Ischemic Stroke Lesions in Non-Contrast Computed Tomography Images for Enhanced Treatment and Prognosis
• Adversarially Trained Convolutional Neural Networks for Semantic Segmentation of Ischaemic Stroke Lesion using Multisequence Magnetic Resonance Imaging