Lung focus detection device, detection equipment and readable storage medium

Abstract

The invention provides a lung focus detection device, detection equipment and a readable storage medium, applied to the technical field of image processing. An obtaining module is used for inputting alung image to be analyzed into the trained detection model, and obtaining an initial detection result including a target heat map corresponding to the lung image and the relationship between the position information of each voxel in the target heat map and the size feature. A position determination module is used for obtaining the central point position information of the lung focus from the target heat map according to the first voxel feature of each voxel in the target heat map. The first voxel feature comprises a first voxel value used for representing the probability that the voxel is thecentral point of the lung lesion. And a size determination module is used for obtaining the size characteristics of the focus according to the central point position information and the relationshipbetween the position information and the size characteristics. Therefore, the central point position information and the size characteristics of the focus can be automatically obtained from the lung image.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular, to a lung lesion detection device, detection equipment and a readable storage medium. Background technique [0002] Relevant studies have shown that the annual growth rate of lung medical images to be analyzed in China is 30%, while the annual growth rate of radiologists is only 4.1%, which is far lower than the growth rate of images. Understaffed radiologists lead to increased workload, and this overload leads to increased rates of misdiagnosis and missed diagnoses. The traditional way of reading films is: the doctor checks each film one by one, and determines the specific location of the lung lesion based on experience. For a medical image, doctors usually need more than 10 minutes to make a diagnosis, and need to watch it repeatedly for confirmation, which is time-consuming. At the same time, there are differences in the ability of doctors to read images. Do...

AI Technical Summary

Problems solved by technology

For a medical image, doctors usually need more than 10 minutes to make a diagnosis, and need to watch it repeatedly for confirmation, which is time-consuming

At the same time, there are differences in the ability of doctors to read images. Doctors rely on experience to find suspicious areas and observe them. Different doctors may give different diagnostic results.

The current method of manually reading images by doctors is time-consuming and labor-intensive, and there are deficiencies such as missed detection, wrong detection, instability, etc.

Images