A construction method and application of a localization model of a lesion area in a chest image
A construction method and image technology, applied in the field of medical imaging, can solve problems such as difficulty in ensuring diagnostic efficiency and accuracy, and achieve the effects of improving diagnostic efficiency and accuracy, reducing diagnostic time, and improving efficiency and accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0046] Such as figure 1 As shown, the present application provides a method for constructing a localization model of a lesion area in a chest image, including:
[0047] S101. Acquire chest X-ray images of a specified number of chest disease patients; the chest X-ray images may use a large number of existing chest X-ray images of chest disease patients.
[0048] Then in steps S102-104, image preprocessing is performed on the X-ray image to obtain preprocessed image data.
[0049] S102, performing chest X-ray image segmentation, including: using the Unet network to train a chest segmentation model, and performing chest segmentation on all chest X-ray images to obtain segmented chest X-ray images. Specifically, it includes: B11. Preliminarily locate the chest area through connected domain analysis. B12. Delete the non-image area at the edge of the chest area. Such as figure 2 As shown, the picture on the right shows that the segmented chest radiograph (chest X-ray image) can...
Embodiment 2
[0071] The present application also provides a method for locating a lesion area in a chest image based on the above-mentioned locating model of a lesion area in a chest image, comprising the following steps:
[0072] A', input patient's chest X-ray image;
[0073] B', preprocessing the chest X-ray image to obtain preprocessed image data;
[0074] C'. Input the preprocessed image data into the trained localization model of the lesion area in the chest image to locate the lesion area in the chest image.
[0075] To sum up, the present application can quickly and accurately provide a location result of a lesion area in a chest image for the user's reference, so as to reduce the doctor's diagnosis time and improve the efficiency and accuracy of diagnosis.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


