No abstract

Early detection and appropriate medical treatment are of great use for ear disease. However, a new diagnostic strategy is necessary for the absence of experts and relatively low diagnostic accuracy, in which deep learning plays an important role. This paper puts forward a mechanic learning model which uses abundant otoscope image data gained in clinical cases to achieve an automatic diagnosis of ear diseases in real time. A total of 20,542 endoscopic images were employed to train nine common deep convolution neural networks. According to the characteristics of the eardrum and external auditory canal, eight kinds of ear diseases were classified, involving the majority of ear diseases, such as normal, Cholestestoma of the middle ear, Chronic suppurative otitis media, External auditory cana bleeding, Impacted cerumen, Otomycosis external, Secretory otitis media, Tympanic membrane calcification. After we evaluate these optimization schemes, two best performance models are selected to combine the ensemble classifiers with real-time automatic classification. Based on accuracy and training time, we choose a transferring learning model based on DensNet-BC169 and DensNet-BC1615, getting a result that each model has obvious improvement by using these two ensemble classifiers, and has an average accuracy of 95.59%. Considering the dependence of classifier performance on data size in transfer learning, we evaluate the high accuracy of the current model that can be attributed to large databases. Current studies are unparalleled regarding disease diversity and diagnostic precision. The real-time classifier trains the data under different acquisition conditions, which is suitable for real cases. According to this study, in the clinical case, the deep learning model is of great use in the early detection and remedy of ear diseases.

Accumulating evidence has suggested that extracellular vesicles (EVs) play a crucial role in lung cancer treatment. Thus, we aimed to investigate the modulatory role of bone marrow mesenchymal stem cell (BMSC)‐EV‐derived let‐7i and their molecular mechanism in lung cancer progression. Microarray‐based analysis was applied to predict lung cancer‐related miRNAs and their downstream genes. RT‐qPCR and Western blot analyses were conducted to determine Let‐7i, lysine demethylase 3A (KDM3A), doublecortin‐like kinase 1 (DCLK1) and FXYD domain‐containing ion transport regulator 3 (FXYD3) expressions, after which dual‐luciferase reporter gene assay and ChIP assay were used to identify the relationship among them. After loss‐ and gain‐of‐function assays, the effects of let‐7i, KDM3A, DCLK1 and FXYD3 on the biological characteristics of lung cancer cells were assessed. Finally, tumour growth in nude mice was assessed by xenograft tumours in nude mice. Bioinformatics analysis screened out the let‐7i and its downstream gene, that is KDM3A. The findings showed the presence of a high expression of KDM3A and DCLK1 and reduced expression of let‐7i and FXYD3 in lung cancer. KDM3A elevated DCLK1 by removing the methylation of H3K9me2. Moreover, DCLK1 suppressed the FXYD3 expression. BMSC‐EV‐derived let‐7i resulted in the down‐regulation of KDM3A expression and reversed its promoting role in lung cancer development. Consistently, in vivo experiments in nude mice also confirmed that tumour growth was suppressed by the BMSC‐EV‐derived let‐7i. In conclusion, our findings demonstrated that the BMSC‐EV‐derived let‐7i possesses an inhibitory role in lung cancer progression through the KDM3A/DCLK1/FXYD3 axis, suggesting a new molecular target for lung cancer treatment.

No abstract