Classification of Pancreatic Cystic Lesions Using ResNet Deep Learning Network in Confocal Laser Endomicroscopy Videos

Clara Lavita Angelina, Chien Ming Pan, Tsung Chun Lee, Ming Lun Han, Pradermchai Kongkam, Hsiu Po Wang, Chuan Yu Chang, Hsuan Ting Chang

研究成果: 雜誌貢獻Conference article同行評審

1 引文 斯高帕斯(Scopus)

摘要

Accurate classification of pancreatic cystic lesions is crucial to differentiate mucinous lesions of malignant potential. We utilized the ResNet-50 and ResNet-101 network to develop a model for classification of the pancreatic cystic lesions. A total of 50 videos, 13,425 images, from five types of pancreatic cystic lesions and utilize the image rotation and contrast reversal scheme for the training. We adopt a contrast limited adaptive histogram equalization method onto the test video. Our method can automatically classify the feature type and record the prediction results frame by frame. The method has been evaluated on 18 test videos and achieves an accuracy 94% overall.
原文英語
頁(從 - 到)357-363
頁數7
期刊Procedia Computer Science
234
DOIs
出版狀態已發佈 - 2024
事件7th Information Systems International Conference, ISICO 2023 - Washington, 美國
持續時間: 7月 26 20237月 28 2023

ASJC Scopus subject areas

  • 一般電腦科學

指紋

深入研究「Classification of Pancreatic Cystic Lesions Using ResNet Deep Learning Network in Confocal Laser Endomicroscopy Videos」主題。共同形成了獨特的指紋。

引用此