A dual-branch hybrid network with bilateral-difference awareness for collateral scoring on CT angiography of acute ischemic stroke patients.

Journal: Physics in medicine and biology
PMID:

Abstract

Acute ischemic stroke (AIS) patients with good collaterals tend to have better outcomes after endovascular therapy. Existing collateral scoring methods rely mainly on vessel segmentation and convolutional neural networks (CNNs), often ignoring bilateral brain differences. This study aims to develop an automated collateral scoring model incorporating bilateral-difference awareness to improve prediction accuracy.In this paper, we propose a new dual-branch hybrid network to achieve vessel-segmentation-free collateral scoring on the CT Angiography (CTA) of 255 AIS patients. Specifically, we first adopt a data preprocessing method based on maximum intensity projection. To capture the differences between the left and right sides of the brain, we propose a novel bilateral-difference awareness module (BDAM). Then we design a hybrid network that consists of a multi-scale module, a CNN branch, a transformer branch and a feature interaction enhancement module in each stage. In addition, to learn more effective features, we propose a novel local enhancement module and a novel global enhancement module (GEM) to strengthen the local features captured by the CNN branch and the global features of the transformer branch, respectively.Experiments on a private clinical dataset with CTA images of 255 AIS patients show that our proposed method achieves an accuracy of 85.49% and an intraclass correlation coefficient of 0.9284 for 3-point collateral scoring, outperforming 13 state-of-the-art methods. Besides, for the binary classification tasks (good vs. non-good collateral scoring, poor vs. non-poor collateral scoring), our proposed method also achieves the best accuracies (89.02% and 92.94%).In this paper, we propose a novel dual-branch hybrid network that incorporates distinct local and GEMs, along with a BDAM, to achieve collateral scoring without the need for vessel segmentation. Our experimental evaluation shows that our model achieves state-of-the-art performance, providing valuable support for improving the efficiency of stroke treatment.

Authors

  • Hulin Kuang
    From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.).
  • Bin Hu
    Department of Thoracic Surgery Beijing Chao-Yang Hospital Affiliated Capital Medical University Beijing China.
  • Wenfang Wan
    Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, People's Republic of China.
  • Shulin Liu
    College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an 710054, China.
  • Shuai Yang
    School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei, Anhui, China.
  • Weihua Liao
    Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, China.
  • Li Yuan
    Research Institute of Natural Gas Technology, Petro China Southwest Oil and Gas Field Company, Chengdu, 610213, China.
  • Guanghua Luo
    The First Affiliated Hospital, Department of Radiology, Hengyang Medical School, University of South China, Hengyang, Hunan 421001, China (J.D., B.L., G.L., H.Z.).
  • Wu Qiu
    From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.).