Effectiveness of convolutional neural networks in the interpretation of pulmonary cytologic images in endobronchial ultrasound procedures

CHING-KAI LINChang, JerryJerryChangCHING-CHUN HUANGWen, Yueh-FengYueh-FengWenCHAO-CHI HOCheng, Yun-ChienYun-ChienCheng2021-11-172021-11-172021-11-012045-7634https://scholars.lib.ntu.edu.tw/handle/123456789/586922Rapid on-site cytologic evaluation (ROSE) helps to improve the diagnostic accuracy in endobronchial ultrasound (EBUS) procedures. However, cytologists are seldom available to perform ROSE in many institutions. Recent studies have investigated the application of deep learning in cytologic image analysis. As such, the present study analyzed lung cytologic images obtained by EBUS procedures, and employed deep-learning methods to distinguish between benign and malignant cells and to semantically segment malignant cells.enbenign and malignant classification; convolutional neural network; deep learning; endobronchial ultrasound; lung cytologic image; semantic segmentation[SDGs]SDG3Effectiveness of convolutional neural networks in the interpretation of pulmonary cytologic images in endobronchial ultrasound proceduresjournal article10.1002/cam4.4383347259532-s2.0-85118359164https://api.elsevier.com/content/abstract/scopus_id/85118359164