Ultrasonic endoscope, artificial intelligence auxiliary identification method and system, terminal and medium

Abstract

The invention belongs to the technical field of medical artificial intelligence, and discloses an ultrasonic endoscope, an artificial intelligence auxiliary identification method and system, a terminal and a medium, and the method comprises the steps: obtaining the image data of an ultrasonic endoscope video or a static image in an ultrasonic endoscope monitor in real time through an image collection module, and intercepting an image frame; segmenting and extracting the tumor part image based on the acquired image by adopting artificial image segmentation or utilizing a deep learning segmentation model through an image segmentation module; unifying the sizes of the segmented images through an image conversion module, and carrying out normalization processing to obtain a modularized picture, namely a standardized lesion part image; dividing the modular picture into an interstitial tumor image or a smooth myoma image by using a deep learning classification model through an image classification module; and outputting an image classification result through an output module. According to the method provided by the invention, the image identification accuracy can be effectively improved, and misdiagnosis is reduced.

Description

technical field [0001] The invention belongs to the technical field of medical artificial intelligence, and in particular relates to an ultrasonic endoscope, an artificial intelligence-assisted identification method, a system, a terminal, and a medium, and in particular to an artificial intelligence-assisted identification method for stromal tumors and leiomyomas under an ultrasonic endoscope . Background technique [0002] At present, endoscopic ultrasonography can clearly display the layers of the gastrointestinal tract wall and the origin of submucosal lesions. It is currently the most accurate imaging technique for diagnosing gastrointestinal submucosal tumors and is widely used in gastrointestinal submucosal lesions. Cancer screening and diagnosis. [0003] Stromal tumors and leiomyomas are the most common tumors in the submucosal tumors of the gastrointestinal tract. Stromal tumors are malignant or potentially malignant tumors that require close follow-up and surgica...

AI Technical Summary

Problems solved by technology

[0006] (1) Existing imaging detection or identification methods cannot accurately identify images of stromal tumors and leiomyomas, resulting in a high rate of misdiagnosis

[0007] (2) Human tissue biopsy under endoscopy is difficult to operate, especially for small lesions (diameter < 20mm), the qualified rate of specimens is low, resulting in low diagnostic rate and unclear diagnostic conclusion; at the same time, biopsy is an invasive examination, Risk of bleeding, gastrointestinal perforation

[0008] (3) At present, there is no artificial intelligence diagnosis application for endoscopic ultrasonography, especially for the identification of stromal tumors

Images