Automatic etiological classification of stroke thrombus digital photographs using a deep learning model

Abstract

Background: Etiological classification of ischemic stroke is fundamental for secondary prevention, but frequently results in undetermined cause. We aimed to develop a Deep Learning (DL)-based model for automatic etiological classification of ischemic stroke using digital images of thrombi retrieved by mechanical thrombectomy.

Methods: Patients with large vessel occlusion stroke subjected to mechanical thrombectomy between April 2016 and January 2023 at La Fe University and Polytechnic Hospital in Valencia were included. Thrombus digital images were obtained and clinical characteristics, including TOAST etiological classification as reference standard, were retrieved. Statistical analysis was performed to compare clinical characteristics between atherothrombotic and cardioembolic strokes. A DL method was designed based on two deep neural networks for: (1) image segmentation and (2) image classification including clinical characteristics. The metrics used were DICE coefficient for the segmentation network, and accuracy, precision, sensitivity, specificity and area under the curve (AUC) for the predictions of the classification network.

Results: A total of 166 patients (mean age 69 [SD, 13], 67 female) were included. TOAST classification was: 31 atherothrombotic, 87 cardioembolic, and 48 cryptogenic. The segmentation network achieved an average DICE coefficient of 0.96 [SD, 0.13]. The optimal fused imaging and clinical classification network had a 0.968 accuracy [95% CI, 0.935-0.994], and AUC of 0.947 [95% CI, 0.870-1]. Cryptogenic thrombi were classified as cardioembolic (96%) or atherothrombotic (4%).

Conclusion: Two convolutional neural networks perform the automatic segmentation of thrombus images and, combined with selected clinical characteristics, their accurate and precise classification into atherothrombotic or cardioembolic etiology in patients with acute ischemic stroke.

Keywords: artificial intelligence; classification; deep learning; etiology; ischemic stroke; segmentation.

Figure 1

Representative images of retrieved thrombi. Images of a cardioembolic thrombus (A) and an atherothrombotic thrombus (B) as captured by the camera, and their corresponding manual segmentations, the thrombus masks (C,D).

Figure 2

Segmentation neural network. Architecture of the U-NET neural network used for thrombus image segmentation.

Figure 3

Classification neural network. Architecture of the LeNet neural network used for the etiological classification of thrombus images concatenated with patient’s demographic and clinical characteristics.

Figure 4

Study flowchart. LVO, large vessel occlusion; MT, mechanical thrombectomy; TOAST, Trial of Org 10,172 in Acute Stroke Treatment.

Figure 5

DL-model classification of cryptogenic thrombi into cardioembolic or atherothrombotic. The votes of the 5-fold model for each clot are shown. Red arrows indicate 5 cases clinically confirmed as cardioembolic stroke by further diagnostic workup.