Automated Segmentation of Ischemic Stroke Lesions in Non-Contrast Computed Tomography Images for Enhanced Treatment and Prognosis

TL;DR

This paper presents an automated nnU-Net based method for segmenting ischemic stroke lesions in NCCT images, aiming to improve early diagnosis and treatment outcomes in stroke care.

Contribution

It introduces a novel application of nnU-Net for ischemic stroke lesion segmentation in NCCTs, achieving promising accuracy scores.

Findings

Dice score of 0.596 on initial dataset

Improved Dice score of 0.752 after outlier adjustment

Enhanced lesion delineation can aid clinical decision-making

Abstract

Stroke is the second leading cause of death worldwide, and is increasingly prevalent in low- and middle-income countries (LMICs). Timely interventions can significantly influence stroke survivability and the quality of life after treatment. However, the standard and most widely available imaging method for confirming strokes and their sub-types, the NCCT, is more challenging and time-consuming to employ in cases of ischemic stroke. For this reason, we developed an automated method for ischemic stroke lesion segmentation in NCCTs using the nnU-Net frame work, aimed at enhancing early treatment and improving the prognosis of ischemic stroke patients. We achieved Dice scores of 0.596 and Intersection over Union (IoU) scores of 0.501 on the sampled dataset. After adjusting for outliers, these scores improved to 0.752 for the Dice score and 0.643 for the IoU. Proper delineation of the region of infarction can help clinicians better assess the potential impact of the infarction, and guide treatment procedures.