Automated Segmentation of MRI White Matter Hyperintensities in 8421 Patients with Acute Ischemic Stroke

Authors

Hosung Kim
Wi-Sun Ryu
Dawid Schellingerhout
Jonghyeok Park
Jinyong Chung
Sang-Wuk Jeong
Dong-Seok Gwak
Beom Joon Kim
Joon-Tae Kim
Keun-Sik Hong
Kyung Bok Lee
Tai Hwan Park
Jong-Moo Park
Kyusik Kang
Yong-Jin Cho
Byung-Chul Lee
Kyung-Ho Yu
Mi Sun Oh
Soo Joo Lee
Jae-Kwan Cha
Dae-Hyun Kim
Jun Lee
Man Seok Park
Hee-Joon Bae
Dong-Eog Kim

Language

English

Publication Date

12-9-2024

Journal

American Journal of Neuroradiology

DOI

10.3174/ajnr.A8418

PMID

39013565

PMCID

PMC11630893

PubMedCentral® Posted Date

12-1-2024

PubMedCentral® Full Text Version

Post-print

Abstract

Background and purpose: To date, only a few small studies have attempted deep learning-based automatic segmentation of white matter hyperintensity (WMH) lesions in patients with cerebral infarction; this issue is complicated because stroke-related lesions can obscure WMH borders. We developed and validated deep learning algorithms to segment WMH lesions accurately in patients with cerebral infarction using multisite data sets involving 8421 patients with acute ischemic stroke.

Materials and methods: We included 8421 patients with stroke from 9 centers in Korea. 2D UNet and squeeze-and-excitation (SE)-UNet models were trained using 2408 FLAIR MRIs from 3 hospitals and validated using 6013 FLAIR MRIs from 6 hospitals. WMH segmentation performance was assessed by calculating the Dice similarity coefficient (DSC), the correlation coefficient, and the concordance correlation coefficient compared with a human-segmented criterion standard. In addition, we obtained an uncertainty index that represents overall ambiguity in the voxel classification for WMH segmentation in each patient based on the Kullback-Leibler divergence.

Results: In the training data set, the mean age was 67.4 (SD, 13.0) years, and 60.4% were men. The mean (95% CI) DSCs for UNet in internal testing and external validation were, respectively, 0.659 (0.649-0.669) and 0.710 (0.707-0.714), which were slightly lower than the reliability between humans (DSC = 0.744; 95% CI, 0.738-0.751; P = .031). Compared with the UNet, the SE-UNet demonstrated better performance, achieving a mean DSC of 0.675 (95% CI, 0.666-0.685; P < .001) in the internal testing and 0.722 (95% CI, 0.719-0.726; P < .001) in the external validation; moreover, it achieved high DSC values (ranging from 0.672 to 0.744) across multiple validation data sets. We observed a significant correlation between WMH volumes that were segmented automatically and manually for the UNet (r = 0.917, P < .001), and it was even stronger for the SE-UNet (r = 0.933, P < .001). The SE-UNet also attained a high concordance correlation coefficient (ranging from 0.841 to 0.956) in the external test data sets. In addition, the uncertainty indices in most patients (86%) in the external data sets were < 0.35, with an average DSC of 0.744 in these patients.

Conclusions: We developed and validated deep learning algorithms to segment WMH in patients with acute cerebral infarction using the largest-ever MRI data sets. In addition, we showed that the uncertainty index can be used to identify cases in which automatic WMH segmentation is less accurate and requires human review.

Keywords

Humans, Male, Female, Ischemic Stroke, Aged, Magnetic Resonance Imaging, White Matter, Deep Learning, Middle Aged, Algorithms, Republic of Korea, Image Interpretation, Computer-Assisted, Reproducibility of Results

Published Open-Access

yes

Recommended Citation

Kim, Hosung; Ryu, Wi-Sun; Schellingerhout, Dawid; et al., "Automated Segmentation of MRI White Matter Hyperintensities in 8421 Patients with Acute Ischemic Stroke" (2024). Faculty, Staff and Student Publications. 6486.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/6486