公开(公告)号：US20240394890A1

公开(公告)日：2024-11-28

申请号：US18230228

申请日：2023-08-04

Applicant: University of Electronic Science and Technology of China

Inventor： Bing ZENG ,  Dingrui LIU ,  Haipeng LI ,  Yu ZENG ,  Xuanren HOU ,  Shikun ZHANG ,  Shuaicheng LIU ,  Nini RAO

IPC: G06T7/12 ,  G06T3/40 ,  G06T3/60 ,  G06T7/00 ,  G06T7/13 ,  G06V10/25 ,  G16H30/40

Abstract: An endoscopic image segmentation method based on a single image and a deep learning network achieves real-time and accurate segmentation for a single case, and provides support for making a treatment plan based on an endoscopic image in clinical medicine. The endoscopic image segmentation method first proposes a single image-based training set generation method to automatically generate a training set, and further proposes a lightweight deep learning network EUnet to perform feature fitting on the generated training set, to achieve endoscopic image segmentation and obtain a segmentation result of a lesion region. The endoscopic image segmentation method can significantly improve segmentation accuracy and has advantages of a small volume, high real-time performance, and easy operation. Especially in processing of endoscopic images of rare cases such as a gastric cancer and an esophageal cancer, the endoscopic image segmentation method has significant advantages in accuracy and speed, and has clinical application value.