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.

Local drug delivery has become an effective method for disease therapy in fine organs including ears, eyes, and noses. However, the multiple anatomical and physiological barriers, unique clearance pathways, and sensitive perceptions characterizing these organs have led to suboptimal drug delivery efficiency. Here, we developed dexamethasone sodium phosphate-encapsulated gelatin methacryloyl (Dexsp@GelMA) microgel particles, with finely tunable size through well-designed microfluidics, as otic drug delivery vehicles for hearing loss therapy. The release kinetics, encapsulation efficiency, drug loading efficiency, and cytotoxicity of the GelMA microgels with different degrees of methacryloyl substitution were comprehensively studied to optimize the microgel formulation. Compared to bulk hydrogels, Dexsp@GelMA microgels of certain sizes hardly cause air-conducted hearing loss in vivo. Besides, strong adhesion of the microgels on the round window membrane was demonstrated. Moreover, the Dexsp@GelMA microgels, via intratympanic administration, could ameliorate acoustic noise-induced hearing loss and attenuate hair cell loss and synaptic ribbons damage more effectively than Dexsp alone. Our results strongly support the adhesive and intricate microfluidic-derived GelMA microgels as ideal intratympanic delivery vehicles for inner ear disease therapies, which provides new inspiration for microfluidics in drug delivery to the fine organs.

Herein, we purposed to explore whether hypoxia triggers proliferation of cholesteatoma keratinocytes via the PI3K-Akt signaling cascade. Cells were inoculated with different concentration of CoCl2. The proliferation and cellular HIF-1α, p-PDK1 and p-Akt expression levels of cholesteatoma keratinocytes were assessed in vitro. Hypoxia escalated cell proliferation via upregulating p-PDK1 and p-Akt expressions. Specific inhibitor of the PI3K-Akt signaling cascade, LY294002 markedly inhibited the expression of p-Akt and significantly reduces the hypoxia-induced proliferation of cholesteatoma keratinocytes. Our data provides research evidence confirming that hypoxia participates in the onset and progress of cholesteatoma.