Colonoscope pathological section screening and segmenting system based on sliding window

Abstract

The invention discloses a colonoscope pathological section screening and segmenting system based on a sliding window. The system comprises a computer, a screening and segmenting model is stored in a memory of the computer; when the system works, a pathological section picture with an original giant size is cut into small image blocks which can be input by a computer by using a sliding window; in order to better extract lesion features of an image, a feature extraction module based on massive natural image classification tasks is used as an image feature extractor, image resolution is recoveredlayer by layer based on a previous feature map and semantic information of a corresponding position, so that a more accurate lesion area segmentation result is obtained, and finally, the probabilityof illness of a patient is output according to the generated segmentation result. By means of the system, screening and diagnosis processes of pathologists can be effectively assisted, film reading pressure and time cost are greatly reduced, and the system has important significance in medical development of underdeveloped areas.

Description

technical field [0001] The invention belongs to the field of medical artificial intelligence, and in particular relates to a screening and segmentation system for colonoscope pathological slices based on a sliding window. Background technique [0002] Colorectal cancer is one of the most common cancers in my country. In 2014, the incidence and mortality of colorectal cancer in my country ranked among the top five among all cancers, and it is also the cancer with the fastest-rising incidence in recent years, with an average annual rate of 4%. -5% increase rate, according to this rate, it is expected that in a few years, colorectal cancer will become the number one cancer in our country. [0003] Screening for precancerous lesions and cancers can significantly reduce colorectal cancer incidence and mortality. Colonoscopy-based pathological images are the gold standard for diagnosis and screening of digestive system cancers. This procedure is performed by an expert pathologist...

AI Technical Summary

Problems solved by technology

However, due to the limitation of computing resources, the huge size of pathological slice images cannot be directly trained with the above-mentioned fully convolutional neural network, and because the pathological slices come from different regions and institutions, the production methods are very different, resulting in huge differences in the final imaging results. The fully convolutional neural network is limited by its simple feature extraction module, and its performance on the colonoscopy pathological slice segmentation task is unsatisfactory

Images