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

TL;DR

This paper presents a semi-supervised GAN-based method for segmenting early ischemic stroke regions in NCCT images, aiming to improve diagnosis accuracy with limited labeled data and support clinical decision-making.

Contribution

It introduces a novel semi-supervised GAN framework that effectively utilizes unlabeled scans for early stroke segmentation, reducing the need for extensive manual annotations.

Findings

Improved segmentation accuracy on AISD dataset

Reduced manual annotation requirements

Enhanced early stroke detection capabilities

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.