Identifying Ear Abnormality from 2D Photographs Using Convolutional Neural Networks

Abstract

Quantifying ear deformity using linear measurements and mathematical modeling is difficult due to the ear’s complex shape. Machine learning techniques, such as convolutional neural networks (CNNs), are well-suited for this role. CNNs are deep learning methods capable of finding complex patterns from medical images, automatically building solution models capable of machine diagnosis. In this study, we applied CNN to automatically identify ear deformity from 2D photographs. Institutional review board (IRB) approval was obtained for this retrospective study to train and test the CNNs. Photographs of patients with and without ear deformity were obtained as standard of care in our photography studio. Profile photographs were obtained for one or both ears. A total of 671 profile pictures were used in this study including: 457 photographs of patients with ear deformity and 214 photographs of patients with normal ears. Photographs were cropped to the ear boundary and randomly divided into training (60%), validation (20%), and testing (20%) datasets. We modified the softmax classifier in the last layer in GoogLeNet, a deep CNN, to generate an ear deformity detection model in Matlab. All images were deemed of high quality and usable for training and testing. It took about 2 hours to train the system and the training accuracy reached almost 100%. The test accuracy was about 94.1%. We demonstrate that deep learning has a great potential in identifying ear deformity. These machine learning techniques hold the promise in being used in the future to evaluate treatment outcomes.

Deep learning based prediction of extraction difficulty for mandibular third molars

“…Deep learning has been widely used in various fields. Among the many deep learning models, CNNs are the most efficient 6 . CNNs have shown excellent results in the analysis of radiographic images when compared to the results by medical experts.…”

“…CNNs have shown excellent results in the analysis of radiographic images when compared to the results by medical experts. Previous studies have shown that deep learning can be used to recognize anatomical structures, find anomalies, measure the distance, and classify structures in medical images 1,[3][4][5][6][7][8][9][10][11][12][13][14][15] . However, in most studies, object detection was conducted manually, and tasks were limited to performing simple measurements, comparisons, or classifications.…”

“…In recent years, CNNs have been extensively used in many fields. In the healthcare industry, numerous studies have reported that a CNN can be used to analyze and diagnose medical images [1][2][3][4][5][6][7] . CNNs have also been used to better interpret the complexities of medical imaging by revealing patterns in large numbers of data and acquiring essential information to gain more knowledge 2 .…”

Assessing outcomes of ear molding therapy by health care providers and convolutional neural network

“…Recently, nonsurgical techniques have been used to correct ear deformity, such as splinting and ear molding 3 . These techniques are noninvasive, painless, and avoid morbidities that can be associated with traditional otoplasty 4 , 5 . The range of deformities that are treatable with neonatal molding is distinct from those congenital deformities that result from hypoplasia of skin or cartilage, which generally require surgical correction 6 , 7 .…”

“…CNN is a deep learning method that has had great success in medical image analysis to classify and analyze diseases and is a promising solution to assess ear deformity and treatment outcomes 5 . In addition, its application has been successful in ear recognition 10 – 12 and has shown to be superior to traditional computer vision systems that uses feature extraction algorithm such as principal component analysis, speeded up robust features 11 , or even handcrafted features 13 .…”