Structure-aware deep learning for chronic middle ear disease

• Published in: Expert systems with applications Vol. 194; p. 116519
• Main Authors: Wang, Zheng, Song, Jian, Su, Ri, Hou, Muzhou, Qi, Min, Zhang, Jianglin, Wu, Xuewen
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.05.2022; Elsevier BV
• Subjects: Chronic Suppurative Otitis Media (CSOM); Computed tomography; Computed Tomography (CT); Convolutional Neural Networks (CNNs); Datasets; Deep learning; Diagnosis; Image classification; Machine learning; Medical imaging; Middle ear; Middle Ear (ME); Otology; Rural areas; Sorting algorithms; CT; CSOM; Computed Tomography (CT); Convolutional Neural Networks (CNNs); ROC; Middle Ear (ME); Chronic Suppurative Otitis Media (CSOM); MEC; CNNs; AUC
• ISSN: 0957-4174; 1873-6793; 1873-6793
• DOI: 10.1016/j.eswa.2022.116519

•A automatic diagnosis schema for middle ear diseases.•A criterion for choosing 5 CT feature maps to represent the middle ear.•Based on the "one vote veto", our study is biased towards the purpose.•Data augmentation based on the similarity of the left and right middle ears.•The proposed approach achieves the state-of-the-art results. The main purpose of this paper was to develop a deep-learning method for the diagnosis of different chronic middle ear diseases, including middle ear cholesteatoma and chronic suppurative otitis media, based on computed tomography (CT) images of the middle ear. The origin of the dataset was the CT scans of 499 patients, which included both ears and selected by specialized otologists. The final dataset was constructed from 973 ears, which labeled by a professional otolaryngologist and classified into 3 conditions: MEC, CSOM and normal. The diagnostic framework, called the “Middle Ear Structure Identification Classifier”(MESIC), was consisted of two deep-learning networks with dissimilar functions: a “region of interest” area search network for extracting the special image of the middle ear structure and a classification network for finishing the diagnosis. The area under the curve (AUC), which means receiver operating characteristic curve (ROC), reflects the robustness of the algorithm by comparing its sorting effectiveness. According to simulation experiments, we chose Visual Geometry Group 16 (VGG-16) as the model’s backbone. In our framework, the ROI search part exhibited an AUC of 0.99 on the right and 0.98 on the left. The classification part exhibited an average AUC of 0.96 for both sides based on VGG-16. The average precision (90.1%), recall (85.4%) and F1-score (87.2%) show the effectiveness of framework. This paper presents a deep-learning framework to automatically diagnose cholesteatoma and CSOM. The results show that MESIC can effectively and quickly classify these two common diseases through CT images, which can ameliorate the pressure of professional doctors and the practical problems of the lack of professional doctors in rural areas.