Automated polyp segmentation for colonoscopy images: A method based on convolutional neural networks and ensemble learning.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: To automatically and efficiently segment the lesion area of the colonoscopy polyp image, a polyp segmentation method has been presented.

Authors

  • Xudong Guo
    School of Medical Instruments and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
  • Na Zhang
    Department of Nutrition and Food Hygiene, School of Public Health, Peking University, Beijing, China.
  • Jiefang Guo
    Department of Gastroenterology, Changhai Hospital, Shanghai, 200433, China.
  • Huihe Zhang
    School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China.
  • Youguo Hao
    Department of Rehabilitation, Shanghai Putuo People's Hospital, Shanghai, 200060, China.
  • Jingqing Hang
    Department of Rehabilitation, Shanghai Putuo People's Hospital, Shanghai, 200060, China.