Rapid Polyp Classification in Colonoscopy Using Textural and Convolutional Features

Chung Ming Lo, Yu Hsuan Yeh, Jui Hsiang Tang, Chun Chao Chang, Hsing Jung Yeh

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


Colorectal cancer is the leading cause of cancer-associated morbidity and mortality worldwide. One of the causes of developing colorectal cancer is untreated colon adenomatous polyps. Clinically, polyps are detected in colonoscopy and the malignancies are determined according to the biopsy. To provide a quick and objective assessment to gastroenterologists, this study proposed a quantitative polyp classification via various image features in colonoscopy. The collected image database was composed of 1991 images including 1053 hyperplastic polyps and 938 adenomatous polyps and adenocarcinomas. From each image, textural features were extracted and combined in machine learning classifiers and machine-generated features were automatically selected in deep convolutional neural networks (DCNN). The DCNNs included AlexNet, Inception-V3, ResNet-101, and DenseNet-201. AlexNet trained from scratch achieved the best performance of 96.4% accuracy which is better than transfer learning and textural features. Using the prediction models, the malignancy level of polyps can be evaluated during a colonoscopy to provide a rapid treatment plan.

Original languageEnglish
Article number1494
JournalHealthcare (Switzerland)
Issue number8
Publication statusPublished - Aug 2022


  • colon polyp
  • colorectal cancer
  • convolutional neural network
  • image features

ASJC Scopus subject areas

  • Leadership and Management
  • Health Policy
  • Health Informatics
  • Health Information Management


Dive into the research topics of 'Rapid Polyp Classification in Colonoscopy Using Textural and Convolutional Features'. Together they form a unique fingerprint.

Cite this