Method for generating marker detection model and marker detection method

Abstract

The invention provides a mark point detection model generation method and a mark point detection method. The generating method comprises the following steps of: constructing a three-dimensional modelcontaining pre-marked marker points; Acquiring a plurality of two-dimensional images of different angles of view of the three-dimensional model, and converting the three-dimensional position data of the landmark points into two-dimensional position data; Using the depth learning method, the two-dimensional images of each view and the two-dimensional position data of the landmark points being usedas input to train the neural network models respectively. Obtaining a second response map with markers, modifying the first response map to obtain a modified first response map, inputting position data of markers on the modified first response map as a mapping layer, and obtaining predicted three-dimensional position data of markers through mapping relationship; According to the original three-dimensional position data and the predicted three-dimensional position data, the loss value is calculated, and the response loss value satisfies the preset conditions to obtain the training completed landmark detection model. The method provided by the invention has the advantages of good performance.

Description

【Technical field】 [0001] The invention relates to the technical field of medical image processing, in particular to a marker point detection model generation method and a marker point detection method. 【Background technique】 [0002] In the fields of clinical medical operation application, biological science research and morphological recognition, the accurate detection of landmarks plays an important role; at the same time, landmarks are also the basis of other research fields, such as registration and segmentation. Deep learning provides an effective tool for feature learning. In recent years, deep learning models and feature representations for 3D shapes have achieved great results. [0003] In related technologies, deep learning is used to process three-dimensional data, which is mainly divided into two types. The first type is the detection of landmarks based on 3D volume data. The volume data is composed of slices of CT (Computed Tomography, computerized tomography)...

AI Technical Summary

Problems solved by technology

The detection method proposed by Haggai et al.: firstly model based on volume data, then mark the built 3D model, and then convert the 3D data into 2D data for training, there will be discontinuous problems in some areas during the conversion process

The first type of method directly learns the original volume data, which saves the modeling part and simplifies data processing. However, in the training phase, due to the large amount of calculation of the volume data, the computational complexity is a big problem.

During the operation of the second type of method, the processing of each data is very time-consuming, and in order to deal with the discontinuity of the model during the conversion process, the converted two-dimensional data will be larger than the original data, and the training time naturally increased

Images