A deep learning algorithm to identify carotid plaques and assess their stability Provisionally Accepted

Lan He¹ Zekun Yang² Yudong Wang² Weidao Chen² Yitong Wang³ Wei Yuan⁴ Xu Li⁵ Ying Zhang^3* Yong-Ming He^5* E Shen^6*

• ¹Shanghai Eighth People Hospital, China
• ²Advanced Institute, Infervision, China
• ³Affiliated Xinhua Hospital of Dalian University, China
• ⁴Other, China
• ⁵The First Affiliated Hospital of Soochow University, China
• ⁶Shanghai Chest Hospital, Shanghai Jiao Tong University, China

Background: Carotid plaques are major risk factors for stroke. Carotid ultrasound can help to assess the risk and incidence rate of stroke，the diagnostic results inevitably involve the subjectivity of the diagnostician. Thus, we attempted to develop an automated algorithm to identify the presence and stability of carotid plaques using deep learning. Methods: 3860 ultrasound images from 1339 participants at the Shanghai Eighth People's Hospital were divided into a 4:1 ratio for training and internal testing. The external test included 1564 ultrasound images from 674 participants at Xinhua Hospital affiliated with Dalian University. Deep learning algorithms, based on the fusion of a bilinear convolutional neural network with a residual neural network (BCNN-Resnet), were used for modeling to detect carotid plaques and assess plaque stability. We chose AUC as the main evaluation index, along with accuracy, sensitivity, and specificity as auxiliary evaluation indices. Results: Modeling for detecting carotid plaques involved training and internal testing on 1291 ultrasound images, with 617 images showing plaques and 674 without plaques. The external test comprised 470 ultrasound images, including 321 images with plaques and 149 without.Modeling for assessing plaque stability involved training and internal testing on 764 ultrasound images, consistingof 494 images with unstable plaques and 270 with stable plaques. The external test was composed of 279 ultrasound images, including 197 images with unstable plaques and 82 with stable plaques. Identifying the presence of carotid plaques, our model achieved an AUC of 0.989 (95% CI: 0.840, 0.998) with a sensitivity of 93.2% and a specificity of 99.21% on the internal test. On the external test, the AUC was 0.951 (95% CI: 0.962, 0.939) with a sensitivity of 95.3% and a specificity of 82.24%. Identifying the stability of carotid plaques, our model achieved an AUC of 0.896 (95% CI: 0.865, 0.922) on the internal test with a sensitivity of 81.63% and a specificity of 87.27%. On the external test, the AUC was 0.854 (95% CI: 0.889, 0.830) with a sensitivity of 68.52% and a specificity of 89.49%.Deep learning using BCNN-Resnet algorithms based on routine ultrasound images could be useful for detecting carotid plaques and assessing plaque instability.