Deep Learning based Collateral Scoring on Multi-Phase CTA in patients with acute ischemic stroke in MCA region

Hao Liu; Jianhai Zhang; Shengcai Chen; Aravind Ganesh; Yang Xu; Bo Hu; Bijoy K Menon; Wu Qiu

doi:10.3174/ajnr.A8911

Deep Learning based Collateral Scoring on Multi-Phase CTA in patients with acute ischemic stroke in MCA region

AJNR Am J Neuroradiol. 2025 Jul 7:ajnr.A8911. doi: 10.3174/ajnr.A8911. Online ahead of print.

Authors

Hao Liu¹, Jianhai Zhang², Shengcai Chen³, Aravind Ganesh², Yang Xu^{1

4}, Bo Hu³, Bijoy K Menon², Wu Qiu^{1

5}

Affiliations

¹ College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China.
² Department of Clinical Neuroscience, University of Calgary, Canada.
³ Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
⁴ China Hubei Medical Devices Quality Supervision and Test Institute, Wuhan, China.
⁵ Advanced Biomedical Imaging Facility, Wuhan, China.

PMID: 40623825
DOI: 10.3174/ajnr.A8911

Abstract

Background and purpose: Collateral circulation is a critical determinant of clinical outcomes in acute ischemic stroke (AIS) patients and plays a key role in patient selection for endovascular therapy. This study aimed to develop an automated method for assessing and quantifying collateral circulation on multi-phase CT angiography, aiming to reduce observer variability and improve diagnostic efficiency.

Materials and methods: This retrospective study included mCTA images from 420 AIS patients within 14 hours of stroke symptom onset. A deep learning-based classification method with a tailored preprocessing module was developed to assess collateral circulation status. Manual evaluations using the simplified Menon method served as the ground truth. Model performance was assessed through five-fold cross-validation using metrics including accuracy, F1 score, precision, sensitivity, specificity, and the area under the receiver operating characteristic curve.

Results: The median age of the 420 patients was 73 years (IQR: 64-80 years; 222 men), and the median time from symptom onset to mCTA acquisition was 123 minutes (IQR: 79-245.5 minutes). The proposed framework achieved an accuracy of 87.6% for three-class collateral scores (good, intermediate, poor), with F1 score (85.7%), precision (83.8%), sensitivity (89.3%), specificity (92.9%), AUC (93.7%), ICC (0.832), and Kappa (0.781). For two-class collateral scores, we obtained 94.0% accuracy for good vs. non-good scores (F1 score(94.4%), precision (95.9%), sensitivity (93.0%), specificity (94.1%), AUC (97.1%),ICC(0.882),kappa(0.881)) and 97.1% for poor vs. non-poor scores (F1 score (98.5%), precision (98.0%), sensitivity (99.0%), specificity (84.8%), AUC (95.6%), ICC(0.740), kappa(0.738)). Additional analyses demonstrated that multi-phase CTA showed improved performance over single or two-phase CTA in collateral assessment.

Conclusions: The proposed deep learning framework demonstrated high accuracy and consistency with radiologist-assigned scores for evaluating collateral circulation on multi-phase CTA in AIS patients. This method may offer a useful tool to aid clinical decision-making, reducing variability and improving diagnostic workflow.

Abbreviations: AIS = Acute Ischemic Stroke; mCTA = multi-phase Computed Tomography Angiography; DL = deep learning; AUC = area under the receiver operating characteristic curve; IQR = interquartile range; ROC = receiver operating characteristic.