Deep learning detection system for nuclear division images in gastrointestinal stromal tumors at mobile terminal

Abstract

The invention discloses a deep learning detection system for nuclear division images in gastrointestinal stromal tumor at a mobile terminal. The method of the deep learning detection system comprisesthe following steps: preprocessing all acquired hematoxylin-eosin staining pathological images; establishing a deep learning segmentation model; inputting all the preprocessed pathological images intothe deep learning segmentation model, and training the deep learning segmentation model; acquiring a hematoxylin-eosin staining pathological image of a testee, and preprocessing the hematoxylin-eosinstaining pathological image; inputting the preprocessed hematoxylin-eosin staining pathological image of the testee into the trained deep learning segmentation model, and carrying out segmentation processing to obtain a segmentation result; and extracting and counting the nuclear division image contour in the segmentation result. The system can be installed on a server computer, the number of nuclear division images in the hematoxylin-eosin staining images is detected by analyzing the input hematoxylin-eosin staining images, and accurate intermediate data is provided for doctors to diagnose the gastrointestinal stromal tumor risk degree.

Description

technical field [0001] The invention relates to a method for detecting mitotic figures in gastrointestinal stromal tumors. In particular, it relates to a deep learning detection system for mitosis in gastrointestinal stromal tumors for mobile terminals. Background technique [0002] Gastrointestinal stromal tumor is a type of tumor originating from the mesenchymal tissue of the gastrointestinal tract, which accounts for the majority of gastrointestinal mesenchymal tumors and is the most common abdominal soft tissue malignant tumor. Gastrointestinal stromal tumors are most commonly found in the stomach (50%-60%), followed by the small intestine (30%-35%), colon and rectum (5%), esophagus (<1%), and a small part outside the digestive tract ( Mesentery, omentum, and retroperitoneum; <5%). The mean age at diagnosis was 63 years, with no gender difference. Gastrointestinal stromal tumors are mainly composed of spindle cells and epithelioid cells, and a few pleomorphic tu...

AI Technical Summary

Problems solved by technology

However, due to the characteristics of single category and extremely unbalanced foreground-background of pathological pictures, a new detection method based on deep learning is needed.

Images