Abdomen multi-organ nuclear magnetic resonance image segmentation method and system based on FCN and medium

Abstract

The invention discloses an abdominal multi-organ nuclear magnetic resonance image segmentation method and system based on FCN, and a medium. The abdominal multi-organ nuclear magnetic resonance imagesegmentation method comprises the following implementation steps: acquiring an input image and carrying out data preprocessing and image normalization operation; inputting the normalized abdominal multi-organ nuclear magnetic resonance image into a trained high-resolution full convolutional neural network model to obtain a final prediction image, wherein the high-resolution full convolutional neural network model is pre-trained to establish a mapping relationship between the normalized abdominal multi-organ nuclear magnetic resonance image and the corresponding final prediction image; and activating the final prediction graph by using an activation function to obtain a prediction score graph, and taking a category with the highest prediction score at each pixel position as a prediction label category of the pixel position to obtain a final segmentation prediction graph. According to the abdominal multi-organ nuclear magnetic resonance image segmentation method, automatic segmentation of the abdominal multi-organ nuclear magnetic resonance image can be realized, for example, the abdominal multi-organ MR image is segmented according to five different region types of an organ-free region, a liver region, a right kidney region, a left kidney region and a spleen region.

Description

technical field [0001] The invention relates to the fields of digital medical image processing and analysis and computer-aided diagnosis, and in particular to an FCN-based method, system and medium for segmenting abdominal multi-organ nuclear magnetic resonance images. Background technique [0002] Understanding the prerequisites for complex medical procedures plays an important role in the success of the surgery. To enrich the level of understanding, physicians use advanced tools such as 3D visualization and printing, which are required to extract objects of interest from DICOM images. Accurate segmentation of multiple abdominal organs (i.e., liver, kidney, and spleen) is critical for several clinical procedures, including but not limited to liver pre-evaluation for living donor-based transplantation or detailed analysis of multiple abdominal Prior to arterial surgery, in order to properly position the vessels of the graft and access them. This prompts the ongoing researc...

AI Technical Summary

Problems solved by technology

[0006] The U-Net network structure uses the skip connection method to directly fuse the low-level feature map with the high-level feature map after upsampling (deconvolution), lacking the transformation of low-level features, and the serial network structure of encoding and decoding first. Feature fusion between feature maps of different resolutions

Images