Can convolutional neural networks identify external carotid artery calcifications?

John Nelson; Anusha Vaddi; Aditya Tadinada

doi:10.1016/j.oooo.2023.01.017

Can convolutional neural networks identify external carotid artery calcifications?

Oral Surg Oral Med Oral Pathol Oral Radiol. 2023 Apr 20:S2212-4403(23)00430-3. doi: 10.1016/j.oooo.2023.01.017. Online ahead of print.

Authors

John Nelson¹, Anusha Vaddi¹, Aditya Tadinada²

Affiliations

¹ Section of Oral and Maxillofacial Radiology, Division of Oral and Maxillofacial Diagnostic Sciences, UConn School of Dental Medicine, UConn Health, Farmington, CT, USA.
² Section of Oral and Maxillofacial Radiology, Division of Oral and Maxillofacial Diagnostic Sciences, UConn School of Dental Medicine, UConn Health, Farmington, CT, USA. Electronic address: Tadinada@uchc.edu.

PMID: 37633789
DOI: 10.1016/j.oooo.2023.01.017

Abstract

Objective: We developed and evaluated the accuracy and reliability of a convolutional neural network (CNN) in detecting external carotid artery calcifications (ECACs) in cone-beam computed tomography scans.

Study design: Using TensorFlow, we developed a program to identify calcification in 427 cone-beam computed tomography scans evaluated to determine the presence of ECACs. We compared the results to the findings of a human evaluator. Using an 80:20 training-to-validation ratio, we calculated the k-fold cross-validation accuracy of the initial dataset and extrapolated the F1 score and Matthews Correlation Coefficient.

Results: We calculated a k-fold cross-validation accuracy of 76%, with a recall and precision of 66% and 79%, respectively, and a combined F1 score of 0.72. We extrapolated a Matthews correlation coefficient of 0.53, showing a strong balance between confusion matrix categories.

Conclusion: Our CNN model can reliably identify ECACs in cone-beam computed tomography scans.