Choi, B. Y. | bioRxiv Science

bioRxiv2020

Mutations in TMEM43 cause autosomal dominant auditory neuropathy spectrum disorder via interaction with Connexin-mediated passive conductance channels

Genes that are primarily expressed in cochlear glia-like supporting cells (GLSs) have never been clearly associated with progressive deafness. Herein, we present a novel deafness locus mapped to chromosome 3p25.1 and a new auditory neuropathy spectrum disorder (ANSD) gene TMEM43 mainly expressed in GLSs. We identify p.R372X of TMEM43 by linkage analysis and exome sequencing in two large Asian families. The knock-in (KI) mouse with p.R372X mutation recapitulates a progressive hearing loss with histological abnormalities exclusively in GLSs. Mechanistically, TMEM43 interacts with Cx26 and Cx30 gap junction channels, disrupting the passive conductance current in GLSs in a dominant-negative fashion when the p.R372X mutation is introduced. Based on the mechanistic insights, cochlear implant was performed on two patients and speech discrimination was successfully restored. Our study highlights a pathological role of cochlear GLSs by identifying a novel deafness gene and its causal relationship with ANSD.

genetics↗

bioRxiv2019

The semantic segmentation approach for normal and pathologic tympanic membrane using deep learning

ObjectivesThe purpose of this study was to create a deep learning model for the detection and segmentation of major structures of the tympanic membrane.\n\nMethodsTotal 920 tympanic endoscopic images had been stored were obtained, retrospectively. We constructed a detection and segmentation model using Mask R-CNN with ResNet-50 backbone targeting three clinically meaningful structures: (1) tympanic membrane (TM); (2) malleus with side of tympanic membrane; and (3) suspected perforation area. The images were randomly divided into three sets - taining set, validation set, and test set - at a ratio of 0.6:0.2:0.2, resulting in 548, 187, and 185 images, respectively. After assignment, 548 tympanic membrane images were augmented 50 times each, reaching 27,400 images.\n\nResultsAt the most optimized point of the model, it achieved a mean average precision of 92.9% on test set. When an intersection over Union (IoU) score of greater than 0.5 was used as the reference point, the tympanic membrane was 100% detectable, the accuracy of side of the tympanic membrane based on the malleus segmentation was 88.6% and detection accuracy of suspicious perforation was 91.4%.\n\nConclusionsAnatomical segmentation may allow the inclusion of an explanation provided by deep learning as part of the results. This method is applicable not only to tympanic endoscope, but also to sinus endoscope, laryngoscope, and stroboscope. Finally, it will be the starting point for the development of automated medical records descriptor of endoscope images.

bioinformatics↗