Panoramic dental film focus detection and segmentation method and device for deep learning

Abstract

The invention provides a panoramic dental film focus detection and segmentation method and device for deep learning. The method comprises the steps: obtaining panoramic dental film data, carrying outthe preprocessing of the panoramic dental film data, and obtaining to-be-detected segmentation data; multi-lesion detection positioning and contour segmentation are carried out on the to-be-detected segmentation data to obtain lesion detection results, and the lesion detection results comprise lesion classification, lesion position coordinates and lesion segmentation contours; performing tooth detection positioning on the to-be-detected segmentation data by using a tooth position classification detection model to obtain a tooth position detection result, the tooth position detection result comprising an FDI standard tooth position number corresponding to each tooth; matching the tooth position detection result with the focus detection result to obtain a tooth position number correspondingto each focus; smoothing the focus segmentation contour through a contour smoothing algorithm to obtain a processed contour; and visually outputting a panoramic dental film focus detection and segmentation result.

Description

Technical field [0001] The invention relates to the field of computer vision, in particular to a method and a device for detecting and segmenting lesions of panoramic dental films by deep learning. technical background [0002] Deep learning has been widely used in the field of computer vision, including target detection, instance segmentation, semantic segmentation, image classification and other subdivision fields. Panoramic dental film is the most important means of clinical dental examination and auxiliary diagnosis, and researchers at home and abroad have done a lot of related research combined with deep learning technology. [0003] The application scenarios of simple tooth detection, segmentation or single lesion detection are very limited, which makes it difficult to meet the clinical diagnosis requirements of panoramic dental films. However, most of the existing technologies focus on the detection of large lesions such as tooth segmentation or damaged teeth, and cannot b...

AI Technical Summary

Problems solved by technology

[0005] It can be seen that there is currently no research on automatic detection and segmentation algorithms for periodontal and dental multi-lesions. It is difficult to label multi-disease data, and the morphological differences of different lesions make detection and segmentation difficult. Building a set based on panorama The multi-lesion detection and segmentation system of dental films has high technical barriers and industry competitiveness

Images