Deep learning-based lung sound analysis for intelligent stethoscope

Auscultation is crucial for the diagnosis of respiratory system diseases.However,traditional stethoscopes have inherent limitations,such as inter-listener variability and subjectivity,and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine.The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education.On this basis,machine learning,particularly deep learning,enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes.This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence(AI)in this field.We focus on each component of deep learning-based lung sound analysis systems,including the task categories,public datasets,denoising methods,and,most importantly,existing deep learning methods,i.e.,the state-of-the-art approaches to convert lung sounds into two-dimensional(2D)spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds.Additionally,this review highlights current challenges in this field,including the variety of devices,noise sensitivity,and poor interpretability of deep models.To address the poor reproducibility and variety of deep learning in this field,this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension:https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis.

Facial reanimation with interposition nerve graft or masseter nerve transfer:a comparative retrospective study

Both interposition nerve grafts and masseter nerve transfers have been successfully used for facial reanimation after irreversible injuries to the cranial portion of the facial nerve.However,no comparative study of these two procedures has yet been reported.In this two-site,twoarm,retrospective case review study,32 patients were included.Of these,17 patients(eight men and nine women,mean age 42.1 years)underwent interposition nerve graft after tumor extirpation or trauma between 2003 and 2006 in the Ear Institute,School of Medicine,Shanghai Jiao Tong University,China,and 15 patients(six men and nine women,mean age 40.6 years)underwent masseter-to-facial nerve transfer after tumor extirpation or trauma between November 2010 and February 2016 in Shanghai Ninth People's Hospital,China.More patients achieved House-Brackmann III recovery after masseter nerve repair than interposition nerve graft repair(15/15 vs.12/17).The mean oral commissure excursion ratio was also higher in patients who underwent masseter nerve transfer than in patients subjected to an interposition nerve graft.These findings suggest that masseter nerve transfer results in strong oral commissure excursion,avoiding obvious synkinesis,while an interposition nerve graft provides better resting symmetry.This study was approved by the Institutional Ethics Committee,Shanghai Ninth People's Hospital,China(approval No.SH9 H-2019-T332-1)on December 12,2019.