Femoral region and key point detection method and system

Abstract

The embodiment of the invention discloses a femur area and key point detection method and system, and the method comprises the steps: carrying out the image data preprocessing of a dicom femur image, and obtaining a hip joint image; marking coordinate points and key point coordinates of the left and right areas of the femur in the hip joint image, and performing normalization processing to obtain a data set required by a yolk model; setting parameters before training of the yolk model, so that the key point coordinates are loaded while the loading area detects the position; establishing a loss function of region detection and key point detection, and minimizing the loss function through a gradient descent method to obtain an improved yolo model; inputting the preprocessed image into the improved yolo model, and restoring the normalized coordinates to the position of the original image; and according to the area coordinates and the key point coordinates, drawing the restored coordinates in the original image to obtain left and right femur areas and key points. Besides predicting left and right femur areas, key points in the femur areas can be predicted, and a convenient and accurate automatic method is provided for calculating femur key indexes.

Description

technical field [0001] The embodiments of the present application relate to the field of artificial intelligence medical technology, and in particular to a detection method and system for a femoral region and key points. Background technique [0002] Hip replacement has become one of the most common surgeries at home and abroad. With the aggravation of the population aging problem, the number of operations will increase. During the operation, doctors need to accurately identify each tissue structure in order to match a suitable prosthesis. Once there is a subjective judgment error, the result of the operation will be seriously affected. Therefore, it is very important to find a method to safely and accurately identify and locate each important key point. [0003] For the delineation of the femoral area and the location marking of important structures, the doctor needs to manually outline the key points of the important structures before the operation to assist in judging ...

AI Technical Summary

Problems solved by technology

Currently, there are no tools and solutions for automatically outlining areas and marking key points

Images