Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database

한글 요약

임상 현장에서 수집한 대규모 귀내시경 영상 데이터베이스를 이용해 귀 질환을 자동으로 진단하는 딥러닝 모델을 개발한 연구입니다. 만 장이 넘는 귀내시경 영상으로 아홉 가지 공개 CNN 구조를 학습시켜 고막과 외이도 소견을 정상, 상고실 함몰, 고막 천공, 외이도염, 종양 등 대부분의 귀 질환을 포괄하는 여섯 범주로 분류하도록 했습니다. 여러 최적화 방식을 비교한 뒤 성능이 가장 좋은 Inception-V3와 ResNet101 기반 전이학습 모델 두 개를 앙상블로 결합했으며, 이 앙상블 분류기는 개별 모델보다 유의하게 향상되어 교차검증에서 약 94%의 정확도를 보였습니다. 이는 평균적인 이비인후과 전문의와 대등하거나 그 이상의 수준으로, 질환 다양성과 진단 정확도 양면에서 전례 없는 결과입니다. 다양한 촬영 조건의 영상으로 학습해 실제 진료 환경에 적합하며, 전문의가 부족한 상황에서 귀 질환의 조기 발견과 치료에 딥러닝이 기여할 수 있음을 보여준 연구입니다.

BACKGROUND: Ear and mastoid disease can easily be treated by early detection and appropriate medical care. However, short of specialists and relatively low diagnostic accuracy calls for a new way of diagnostic strategy, in which deep learning may play a significant role. The current study presents a machine learning model to automatically diagnose ear disease using a large database of otoendoscopic images acquired in the clinical environment.

METHODS: Total 10,544 otoendoscopic images were used to train nine public convolution-based deep neural networks to classify eardrum and external auditory canal features into six categories of ear diseases, covering most ear diseases (Normal, Attic retraction, Tympanic perforation, Otitis externa±myringitis, Tumor). After evaluating several optimization schemes, two best-performing models were selected to compose an ensemble classifier, by combining classification scores of each classifier.

FINDINGS: According to accuracy and training time, transfer learning models based on Inception-V3 and ResNet101 were chosen and the ensemble classifier using the two models yielded a significant improvement over each model, the accuracy of which is in average 93·67% for the 5-folds cross-validation. Considering substantial data-size dependency of classifier performance in the transfer learning, evaluated in this study, the high accuracy in the current model is attributable to the large database.

INTERPRETATION: The current study is unprecedented in terms of both disease diversity and diagnostic accuracy, which is compatible or even better than an average otolaryngologist. The classifier was trained with data in a various acquisition condition, which is suitable for the practical environment. This study shows the usefulness of utilizing a deep learning model in the early detection and treatment of ear disease in the clinical situation. FUND: This research was supported by Brain Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT(NRF-2017M3C7A1049051).