mammary gland MRI lesion area detection method based on multi-dimensional information fusion

Abstract

The invention discloses a mammary gland MRI lesion area detection method based on multi-dimensional information fusion, and the method comprises the steps: carrying out the feature learning of a preset image through employing a convolutional neural network, and enabling the convolutional neural network to learn the difference between a lesion area and a normal tissue in the preset image; Acquiringa mammary gland MRI image to be detected, wherein the mammary gland MRI image comprises a same-period continuous tomography image and a same-fault different-period image; According to the trained convolutional neural network, lesion area selection is carried out on the continuous tomography images of the same period, and more than one candidate window is obtained; Encoding the images of differentperiods of the same fault by adopting a recurrent neural network to obtain relevant information between the signal intensity and the lesion type of the images of different periods of the same fault;And mapping more than one candidate window into the related information, and classifying through a preset classifier to obtain a final lesion area detection result. According to the technical scheme provided by the invention, the lesion area in the mammary gland can be more accurately detected.

Description

technical field [0001] The invention relates to the technical field of magnetic resonance imaging, in particular to a method for detecting breast MRI lesion regions based on multi-dimensional information fusion. Background technique [0002] Magnetic resonance imaging (Magnetic Resonance Imaging, MRI) technology is a technology that uses the nuclear magnetic resonance phenomenon of hydrogen protons for imaging. With the continuous maturity of magnetic resonance imaging technology in recent years, its importance in the diagnosis of breast diseases is increasing. Breast magnetic resonance technology is more sensitive to the further judgment of the nature of breast lesions. It can not only make further judgments on the benign and malignant lesions, but also help doctors identify whether there are multiple lesions. In particular, breast magnetic resonance technology can make a more accurate judgment on the benign and malignant lesions according to the change of the signal inten...

AI Technical Summary

Problems solved by technology

However, the image features of some diseased areas in the breast have a high degree of similarity with normal tissues (for example, blood vessel sections) in a single image, and it is difficult to effectively distinguish them using the above-mentioned prior art

Moreover, when the existing saliency detection extracts the candidate window, the feature expression of the lesion area is not comprehensive, which may easily cause the target detection recall rate of the lesion area to be low.

The above problems all lead to inaccurate detection results of lesion areas in breast magnetic resonance images

Images