COMPUTED TOMOGRAPHY IMAGE SEGMENTATION FOR ISCHEMIC STROKE LESION DELINEATION: A COMPREHENSIVE BIBLIOMETRIC ANALYSIS AND ADVANCED METHODOLOGICAL REVIEW

Ischemic stroke remains a leading cause of global morbidity and mortality, necessitating rapid and accurate diagnosis for effective treatment. Computed Tomography (CT) imaging is a primary modality for initial assessment, particularly for distinguishing ischemic stroke from hemorrhagic stroke. Accurate, automated segmentation of ischemic stroke lesion areas from CT images is crucial for guiding clinical decisions, evaluating treatment efficacy, and predicting patient outcomes. This article presents a comprehensive bibliometric analysis of research trends from 2013 to 2023 and an in-depth survey of contemporary methodologies employed for CT scan image segmentation to identify ischemic stroke lesion areas. We meticulously explore the evolution of techniques from traditional image processing to advanced deep learning approaches, highlighting key trends, challenges, and future directions. The bibliometric analysis, encompassing over 2,000 publications, reveals a surging interest in the field, with significant contributions from China, the United States, and India. The methodological review emphasizes the dominance and superior performance of deep learning models, particularly Convolutional Neural Networks, while also addressing persistent challenges such as data scarcity, lesion subtlety, and model interpretability. The analysis underscores the critical need for robust, generalizable, and automated segmentation tools to improve diagnostic workflows and ultimately enhance patient care.