Objectives: The purpose of this study was to develop a deep-learning framework for the diagnosis of chronic otitis media (COM) based on temporal bone computed tomography (CT) scans. Design: A total of 562 COM patients with 672 temporal bone CT scans of both ears were included. The final dataset consisted of 1147 ears, and each of them was assigned with a ground truth label from one of the 3 conditions: normal, chronic suppurative otitis media, and cholesteatoma. A random selection of 85% dataset (n = 975) was used for training and validation. The framework contained two deep-learning networks with distinct functions: a region proposal network for extracting regions of interest from 2-dimensional CT slices; and a classification network for diagnosis of COM based on the extracted regions. The performance of this framework was evaluated on the remaining 15% dataset (n = 172) and compared with that of 6 clinical experts who read the same CT images only. The panel included 2 otologists, 3 otolaryngologists, and 1 radiologist. Results: The area under the receiver operating characteristic curve of the artificial intelligence model in classifying COM versus normal was 0.92, with sensitivity (83.3%) and specificity (91.4%) exceeding the averages of clinical experts (81.1% and 88.8%, respectively). In a 3-class classification task, this network had higher overall accuracy (76.7% versus 73.8%), higher recall rates in identifying chronic suppurative otitis media (75% versus 70%) and cholesteatoma (76% versus 53%) cases, and superior consistency in duplicated cases (100% versus 81%) compared with clinical experts. Conclusions: This article presented a deep-learning framework that automatically extracted the region of interest from two-dimensional temporal bone CT slices and made diagnosis of COM. The performance of this model was comparable and, in some cases, superior to that of clinical experts. These results implied a promising prospect for clinical application of artificial intelligence in the diagnosis of COM based on CT images.

No abstract

Objective: Chronic suppurative otitis media (CSOM) is mostly caused by bacterial infection of the middle ear and antibiotics are generally used empirically, which may lead to the emergence of resistant bacterial strains. The objective of the study is to assess the bacteriological profile of and evaluate the antibiotic susceptibility of strains isolated in a tertiary care hospital in Shanghai, China. Methods: This study included 289 individuals with clinical diagnosis of CSOM. Middle ear purulent discharge was obtained with sterile swabs and cultured for bacterial pathogens. The susceptibility of the isolated microorganisms to antibiotics was assessed by a microdilution method. Results: Bacterial pathogens were found in 223 (77.2%) of the 289 cases. A total of 236 strains were isolated. Staphylococcus aureus was the commonest bacteria (44.9%) followed by Pseudomonas aeruginosa (16.9%) and coagulase-negative Staphylococcus (8.5%). There were 18.9% methicillin-resistant S aureus (MRSA) among the obtained S aureus organisms. Multidrug-resistant P aeruginosa was found in 4 patients, making up 10% of all detected P aeruginosa. Staphylococcus aureus showed highest susceptibility to vancomycin (100%), then gentamicin (98.1%) and rifampicin (97.2%) and was most resistant to penicillin (61.3%) and erythromycin (50%). All isolated P aeruginosa showed susceptibility to piperacillin, piperacillin/tazobactam, and meropenem. High degree of resistance in P aeruginosa was observed toward levofloxacin (42.5%), ciprofloxacin (40%), and ceftriaxone (30%). Conclusion: The high prevalence of MRSA and fluoroquinolone-resistant P aeruginosa indicated cephalosporins and fluoroquinolone as primary empirical antibiotic drugs in CSOM to be cautiously used. In order to reduce the incidence of resistant strains and promote effective usage of antibiotics, all aural discharges should be cultured to determine antibacterial susceptibility patterns before treatment.

No abstract