Poster Presentation Asia Pacific Stroke Conference 2024

Segmentation of haemorrhagic transformation after acute ischemic stroke using adaptive thresholding: Comparable performance to a state-of-the-art method (#444)

Jiacheng Sun 1 2 , Freda Werdiger 3 4 , Christopher Blair 1 2 5 , Chushuang Chen 1 2 , Qing Yang 6 , Andrew Bivard 3 4 , Longting Lin 1 2 , Mark Parsons 1 2 5
  1. South Western Sydney Clinical School, University of New South Wales, Sydney, New South Wales, Australia
  2. Sydney Brain Centre , The Ingham Institute for Applied Medical Research, Liverpool, New South Wales, Australia
  3. Melbourne Brain Centre , Royal Melbourne Hospital, Melbourne, Victoria, Australia
  4. Department of Medicine, University of Melbourne, Melbourne, Victoria, Australia
  5. Department of Neurology and Neurophysiology, Liverpool Hospital, Sydney, New South Wales, Australia
  6. Apollo Medical Imaging Technology Pty Ltd, Melbourne, Victoria, Australia

Background: For patients with acute ischemic stroke, haemorrhagic transformation (HT) is a feared complication following reperfusion therapies. Automatic segmentation of haemorrhage provides an objective assessment of outcome and improves audit quality. This study aims to automatically segment haemorrhagic regions on follow-up non-contrast head CT (NCCT) for stroke patients treated with endovascular thrombectomy (EVT).

Methods:  We propose a semi-automated approach with adaptive thresholding methods, eliminating the requirement for large training data and reducing computational burden. We compare the proposed method with a state-of-the-art segmentation model SAMIHS to evaluate the effectiveness using Dice Similarity Coefficient (DSC).

Results: A total of 51 patients from 10 stroke centres were included, with 28 Type 2 haemorrhagic infarction (HI2) cases and 23 parenchymal hematoma (PH) cases. Our method achieved DSC scores of 0.66 ± 0.17, 0.73 ± 0.14, and 0.61 ± 0.18 for total, PH, and HI2 cases respectively, which is comparable to SAMIHS (DSC scores of 0.66 ± 0.02, 0.69 ± 0.03 and 0.64 ± 0.07 for total, PH, and HI2 cases respectively). In addition, the algorithm demonstrated excellent processing time, with an average of 2.7 seconds for each patient case.

Conclusions: To our knowledge, this is the first study to perform automated segmentation of post-treatment haemorrhage for acute stroke patients and evaluate the performance based on the radiological severity of HT. Our approach offers a balance between accuracy and practicality, presenting a promising tool for aiding prognosis prediction in stroke patients with HT after EVT, without the computational overhead of novel methods.