Artificial intelligence for assessing the severity of microtia via deep convolutional neural networks

Abstract

BackgroundMicrotia is a congenital abnormality varying from slightly structural abnormalities to the complete absence of the external ear. However, there is no gold standard for assessing the severity of microtia.ObjectivesThe purpose of this study was to develop and test models of artificial intelligence to assess the severity of microtia using clinical photographs.MethodsA total of 800 ear images were included, and randomly divided into training, validation, and test set. Nine convolutional neural networks (CNNs) were trained for classifying the severity of microtia. The evaluation metrics, including accuracy, precision, recall, F1 score, receiver operating characteristic curve, and area under the curve (AUC) values, were used to evaluate the performance of the models.ResultsEight CNNs were tested with accuracy greater than 0.8. Among them, Alexnet and Mobilenet achieved the highest accuracy of 0.9. Except for Mnasnet, all CNNs achieved high AUC values higher than 0.9 for each grade of microtia. In most CNNs, the grade I microtia had the lowest AUC values and the normal ear had the highest AUC values.ConclusionCNN can classify the severity of microtia with high accuracy. Artificial intelligence is expected to provide an objective, automated assessment of the severity of microtia.

Current Status of Auricular Reconstruction Strategy Development

“…The application of AI is expected to provide objective, automated assessments of microtia severity. Avila et al 108 utilized AI virtual assistants accessible through telephone, simulating human conversation and answering common preoperative questions with a 98.5% accuracy rate. Patients expressed satisfaction with the use of AI virtual assistants for addressing common presurgical inquiries.…”

“…In the field of plastic surgery, AI is primarily used for preoperative diagnosis assistance, surgical planning, and postoperative outcome prediction 107 . Wang et al 108 collected 800 ear images and randomly divided them into training, validation, and test sets. Nine convolutional neural networks were trained to classify the severity of microtia, with 8 of them achieving accuracies above 0.8.…”