To develop a deep convolutional neural network (DCNN) that can automatically detect laryngeal cancer (LCA) in laryngoscopic images. A DCNN-based diagnostic system was constructed and trained using 13,721 laryngoscopic images of LCA, precancerous laryngeal lesions (PRELCA), benign laryngeal tumors (BLT) and normal tissues (NORM) from 2 tertiary hospitals in China, including 2293 from 206 LCA subjects, 1807 from 203 PRELCA subjects, 6448 from 774 BLT subjects and 3191 from 633 NORM subjects. An independent test set of 1176 laryngoscopic images from other 3 tertiary hospitals in China, including 132 from 44 LCA subjects, 129 from 43 PRELCA subjects, 504 from 168 BLT subjects and 411 from 137 NORM subjects, was applied to the constructed DCNN to evaluate its performance against experienced endoscopists. The DCCN achieved a sensitivity of 0.731, a specificity of 0.922, an AUC of 0.922, and the overall accuracy of 0.867 for detecting LCA and PRELCA among all lesions and normal tissues. When compared to human experts in an independent test set, the DCCN' s performance on detection of LCA and PRELCA achieved a sensitivity of 0.720, a specificity of 0.948, an AUC of 0.953, and the overall accuracy of 0.897, which was comparable to that of an experienced human expert with 10-20 years of work experience. Moreover, the overall accuracy of DCNN for detection of LCA was 0.773, which was also comparable to that of an experienced human expert with 10-20 years of work experience and exceeded the experts with less than 10 years of work experience. The DCNN has high sensitivity and specificity for automated detection of LCA and PRELCA from BLT and NORM in laryngoscopic images. This novel and effective approach facilitates earlier diagnosis of early LCA, resulting in improved clinical outcomes and reducing the burden of endoscopists.

Cisplatin-induced ototoxicity is one of the major adverse effects in cisplatin chemotherapy, and hearing protective approaches are unavailable in clinical practice. Recent work unveiled a critical role of autophagy in cell survival in various types of hearing loss. Since the excessive activation of autophagy can contribute to apoptotic cell death, whether the activation of autophagy increases or decreases the rate of cell death in CDDP ototoxicity is still being debated. In this study, we showed that CDDP induced activation of autophagy in the auditory cell HEI-OC1 at the early stage. We then used rapamycin, an autophagy activator, to increase the autophagy activity, and found that the cell death significantly decreased after CDDP injury. In contrast, treatment with the autophagy inhibitor 3-methyladenine (3-MA) significantly increased cell death. In accordance with in vitro results, rapamycin alleviated CDDP-induced death of hair cells in zebrafish lateral line and cochlear hair cells in mice. Notably, we found that CDDP-induced increase of Sirtuin 1 (SIRT1) in the HEI-OC1 cells modulated the autophagy function. The specific SIRT1 activator SRT1720 could successfully protect against CDDP-induced cell loss in HEI-OC1 cells, zebrafish lateral line, and mice cochlea. These findings suggest that SIRT1 and autophagy activation can be suggested as potential therapeutic strategies for the treatment of CDDP-induced ototoxicity.

Cisplatin‐induced ototoxicity is one of the common side effects during its treatment and there are no effective measures to prevent it. Our study aimed to investigate the effect of ACSL4‐catalyzed lipid peroxidation on cisplatin‐induced hearing loss and its possible protective mechanisms. We used a variety of cisplatin ototoxicity models, including HEI‐OC1 cell line, cochlear explants, and ET4 GFP+ zebrafish. After measuring the experimental concentrations of cisplatin by CCK8 assay and immunofluorescence, respectively, we examined the levels of lipid peroxidation by MDA content, 4‐HNE content, and C11‐BODIPY (581/591) probe. Then, we used two ferroptosis inhibitors, FER‐1, and Vit‐E to protect hair cells. We found that cisplatin significantly increased the levels of lipid peroxidation and that this process can be resisted by the ferroptosis inhibitors. Afterwards, we performed metabolomic assays on the cisplatin‐treated hair cells. The metabolite levels were significantly altered in the experimental group compared to the control group, and the highest degree of change was observed in the glutathione metabolic pathway and the arachidonic acid metabolic pathway. Therefore, we screened the key enzymes on the arachidonic acid metabolic pathway in the hair cells after cisplatin treatment and found that ACSL4 had the greatest regulatory value. Further, we reduced the level of lipid peroxide in hair cells by specifically inhibiting the expression of ACSL4, which protected hair cells from cisplatin damage at source. In conclusion, the lipid peroxidation process regulated by ACSL4 may be an important factor contributing to the sensitivity of hair cells to cisplatin. Inhibition of ACSL4 expression may be an effective preventive measure against cisplatin ototoxicity.

Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results. This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. Data analysis included pre-processing of the WAI data, statistical analysis and classification model development, and key regions extraction from the 2D frequency-pressure WAI images. The experimental results show that ML tools appear to hold great potential for the automated diagnosis of middle ear diseases from WAI data. The identified key regions in the WAI provide guidance to practitioners to better understand and interpret WAI data and offer the prospect of quick and accurate diagnostic decisions.