CN-121074014-B - Tumor cell auxiliary positioning system and method based on composite image

CN121074014BCN 121074014 BCN121074014 BCN 121074014BCN-121074014-B

Abstract

The invention provides a tumor cell auxiliary positioning system and method based on a composite image, which relate to the technical field of medical images and comprise a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for synchronously acquiring radio frequency echo signals, ultrasonic images and computed tomography data of target biological tissues to generate an original fusion data set; the device comprises a feature processing module, an identification imaging module and a synchronous ultrasonic image processing module, wherein the feature processing module is used for carrying out space registration and feature extraction on an original fusion data set to obtain a multi-dimensional feature set, and the identification imaging module is used for extracting a multi-frequency-band radio-frequency echo signal intensity level value of a target area based on the multi-dimensional feature set, generating a tissue radio-frequency characteristic map through logarithmic compression, and carrying out pixel level fusion with the synchronous ultrasonic image to generate a composite image. According to the invention, through multi-mode data fusion and accurate calibration, the three-dimensional coordinates of the tumor boundary are determined by combining anatomical structure constraint, so that the tumor cell positioning accuracy is improved.

Inventors

YUN YU
TAO TAO
WU ZHE
Samir Miloha
Eusep.Modafali

Assignees

西安曼塔信息技术有限公司

Dates

Publication Date: 20260508
Application Date: 20251013

Claims (8)

1. Tumor cell auxiliary positioning system based on composite image, characterized by comprising: the data acquisition module is used for synchronously acquiring radio frequency echo signals, ultrasonic images and computed tomography data of the target biological tissue to generate an original fusion data set; the feature processing module is used for carrying out space registration and feature extraction on the original fusion data set so as to obtain a multi-dimensional feature set; The identification imaging module is used for extracting the intensity level value of the multi-band radio-frequency echo signal of the target area based on the multi-dimensional feature set, generating a tissue radio-frequency characteristic diagram through logarithmic compression, and carrying out pixel level fusion with the synchronous ultrasonic image to generate a composite image; The positioning analysis module is used for carrying out subcellular distribution analysis on the composite image so as to obtain a nuclear positioning positive cell coordinate set; the method comprises the steps of calculating intensity correlation of a nuclear marker signal and a target protein marker signal in a composite image pixel by pixel to obtain a three-dimensional data set representing the co-localization degree of each three-dimensional space position point, identifying all three-dimensional space areas with values larger than a judgment threshold value in the three-dimensional data set as candidate nuclear localization positive cell areas by setting the judgment threshold value based on the three-dimensional data set representing the co-localization degree, dividing the mutually communicated space areas into independent single candidate cell three-dimensional structures according to the candidate nuclear localization positive cell areas by applying three-dimensional space connectivity analysis, obtaining centroid coordinates of cells in the three-dimensional space by calculating geometric centers based on the independent single candidate cell three-dimensional structures, and integrating the centroid coordinates of all independent candidate cells in the three-dimensional space to obtain a nuclear localization positive cell coordinate set; The positioning calibration module is used for selecting a group of preset biomarkers from the nuclear positioning positive cell coordinate set, constructing a space topological relation, quantifying the micro-environment heterogeneity of the space topological relation, and generating positioning calibration parameters based on the regional heterogeneity distribution characteristics; the method comprises the steps of generating a three-dimensional coordinate set of a target biomarker cell subset by screening cell coordinates with preset biomarker marks based on a nuclear positioning positive cell coordinate set, constructing a three-dimensional space adjacent network with cell coordinates as nodes and a space adjacent relation as sides by calculating three-dimensional Euclidean distances among coordinate points and applying an adjacent distance threshold value to judge connectivity according to the three-dimensional coordinate set of the target biomarker cell subset, generating a comprehensive heterogeneity quantification data set by calculating a local cell density gradient value set, a node clustering coefficient value set and a network global space entropy value of all nodes in the network based on the three-dimensional space adjacent network, extracting a heterogeneity spatial distribution feature description in a metabolic target area by mapping to a three-dimensional space grid of the metabolic target area and analyzing numerical distribution in a grid unit according to the comprehensive heterogeneity quantification data set, deriving a boundary correction vector parameter set by establishing a space mapping relation between features and an original boundary of the metabolic target area based on the heterogeneity spatial distribution feature description, and generating positioning calibration parameters; And the positioning output module is used for cooperatively determining the three-dimensional coordinates of the tumor boundary through spatial gradient change analysis and the radio frequency signal characteristic attenuation association rule based on the positioning calibration parameters so as to obtain a tumor cell positioning result.
2. The composite image-based tumor cell assisted localization system of claim 1, wherein spatially registering and feature extracting the original fused dataset to obtain a multi-dimensional feature set comprises: Based on the original fusion data set, rigid transformation and affine transformation are sequentially carried out on the radio-frequency echo signals, the ultrasonic images and the computed tomography data to realize spatial precise alignment, and a fusion data set after spatial registration is generated; Extracting texture features and computed tomography density distribution features of the ultrasonic images from the fused data set subjected to spatial registration, and calculating frequency domain energy features of radio frequency echo signals through fast Fourier transformation; And integrating the ultrasonic image texture features, the computed tomography density distribution features and the frequency domain energy features to obtain a multi-dimensional feature set.
3. The tumor cell assisted localization system based on composite image of claim 2, wherein extracting the multi-band rf echo signal intensity level values of the target region based on the multi-dimensional feature set, generating the tissue rf characteristic map via logarithmic compression, and performing pixel level fusion with the synchronous ultrasound image, generating the composite image comprises: Extracting and separating radio frequency echo signal intensity level values of a plurality of frequency bands corresponding to a target area from a multi-dimensional feature set; carrying out dynamic range logarithmic compression processing on the intensity level value of the multi-band radio frequency echo signal of the target area to generate a radio frequency signal intensity distribution matrix representing the intensity distribution of the radio frequency signal of the target area; mapping the radio frequency signal intensity distribution matrix to a two-dimensional plane corresponding to the space position of the ultrasonic image to generate a tissue radio frequency characteristic map reflecting the tissue radio frequency characteristic of the target area; and combining the tissue radio frequency characteristic map with the ultrasonic images of the corresponding target areas acquired synchronously according to a preset rule to realize superposition and fusion of pixel levels and generate a composite image.
4. The tumor cell auxiliary positioning system based on composite image according to claim 3, wherein determining tumor boundary three-dimensional coordinates by spatial gradient change analysis and radio frequency signal characteristic attenuation association rule in cooperation based on positioning calibration parameters to obtain tumor cell positioning results comprises: Based on the positioning calibration parameters and the lesion classification result, generating calibrated candidate boundary initial spatial position data by superposing the spatial mapping information of the positioning calibration parameters on a three-dimensional spatial coordinate frame of the original fusion data set; Simultaneously calculating image space gradient strength values of the regions nearby the same position in the ultrasonic image component data, and carrying out matching verification based on a preset space collaborative association rule to generate a candidate boundary space position data set; based on the candidate boundary space position data set, adjusting the space continuity of boundary points by applying a dynamic programming algorithm to generate a boundary point set conforming to the constraint of the anatomical structure; And extracting three-dimensional space coordinate information based on the boundary point set conforming to the anatomical structure constraint to obtain a tumor boundary three-dimensional coordinate point set as a tumor cell positioning result.
5. The composite image-based tumor cell assisted localization system of claim 4, wherein generating a set of boundary points that meet anatomical constraints by adjusting spatial continuity of the boundary points by applying a dynamic programming algorithm based on the candidate boundary spatial location dataset comprises: the tumor boundary three-dimensional coordinate set is used as a candidate boundary space position data set and is input into a frame based on a dynamic planning algorithm; Generating a path evaluation rule for measuring the smoothness of a connecting path between any two candidate boundary points according to the target organ anatomical structure constraint aiming at the candidate boundary space position data set; Based on a path evaluation rule, calculating by a dynamic programming algorithm, and searching a final boundary point space connection sequence of global smoothness in a candidate boundary space position data set; based on the boundary point space connection sequence, a final tumor boundary point set conforming to the anatomical structure smoothness constraint is generated.
6. A method for assisting in locating tumor cells based on a composite image, the method implementing the system of any one of claims 1 to 5, comprising: step 1, synchronously acquiring radio frequency echo signals, ultrasonic images and computed tomography data of a target biological tissue to generate an original fusion data set; Step 2, carrying out space registration and feature extraction on the original fusion data set to obtain a multi-dimensional feature set; Step 3, extracting the intensity level value of the multi-band radio frequency echo signal of the target area based on the multi-dimensional feature set, generating a tissue radio frequency characteristic diagram through logarithmic compression, and carrying out pixel level fusion with the synchronous ultrasonic image to generate a composite image; step 4, performing subcellular distribution analysis on the composite image to obtain a nuclear localization positive cell coordinate set; step 5, selecting a group of preset biomarkers from the nuclear localization positive cell coordinate set, constructing a space topological relation, quantifying micro-environment heterogeneity of the space topological relation, and generating a localization calibration parameter based on regional heterogeneity distribution characteristics; and 6, determining the three-dimensional coordinates of the tumor boundary in a cooperative manner through spatial gradient change analysis and a radio frequency signal characteristic attenuation association rule based on the positioning calibration parameters so as to obtain a tumor cell positioning result.
7. A computing device, comprising: One or more processors; Storage means for storing one or more programs that when executed by the one or more processors cause the one or more processors to implement the system of any of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the system according to any of claims 1 to 5.

Description

Tumor cell auxiliary positioning system and method based on composite image Technical Field The invention relates to the technical field of medical images, in particular to a tumor cell auxiliary positioning system and method based on a composite image. Background In early screening of breast cancer, the conventional technology for positioning tumor cells has some limitations, and the suitability of imaging definition and tissue depth is insufficient, for example, when the breast cancer is screened by using an ultrasonic technology alone, the morphology and boundary of a breast tumor with a shallow position can be clearly displayed, but when the tumor is positioned in a deep layer of the breast (such as near the chest wall), the tumor can be attenuated to a certain extent when passing through thicker breast tissue or chest wall muscle, so that the condition of blurred tumor images and unclear edges can be caused, and the difficulty of accurately positioning the size and infiltration range of the tumor is increased. In addition, the multi-dimensional information fusion capability is weak, for example, when breast cancer tumor positioning is carried out by singly relying on Magnetic Resonance Imaging (MRI), the anatomical structure details of breast soft tissues can be better presented, but the method is not direct in the aspect of reflecting functional information such as blood flow perfusion of tumors. When encountering early tumors with atypical blood supply characteristics, it may be difficult to accurately distinguish the boundaries of the tumor from surrounding benign hyperplastic tissue by means of anatomical images alone, thereby affecting the accuracy of localization. Disclosure of Invention The invention aims to solve the technical problem of providing a tumor cell auxiliary positioning system and a tumor cell auxiliary positioning method based on a composite image, which can accurately fuse multi-source image information and improve the accuracy and efficiency of tumor cell positioning. In order to solve the technical problems, the technical scheme of the invention is as follows: in a first aspect, a tumor cell assisted localization system based on a composite image, comprising: the data acquisition module is used for synchronously acquiring radio frequency echo signals, ultrasonic images and computed tomography data of the target biological tissue to generate an original fusion data set; the feature processing module is used for carrying out space registration and feature extraction on the original fusion data set so as to obtain a multi-dimensional feature set; The identification imaging module is used for extracting the intensity level value of the multi-band radio-frequency echo signal of the target area based on the multi-dimensional feature set, generating a tissue radio-frequency characteristic diagram through logarithmic compression, and carrying out pixel level fusion with the synchronous ultrasonic image to generate a composite image; the positioning analysis module is used for carrying out subcellular distribution analysis on the composite image so as to obtain a nuclear positioning positive cell coordinate set; The positioning calibration module is used for selecting a group of preset biomarkers from the nuclear positioning positive cell coordinate set, constructing a space topological relation, quantifying the micro-environment heterogeneity of the space topological relation, and generating positioning calibration parameters based on the regional heterogeneity distribution characteristics; And the positioning output module is used for cooperatively determining the three-dimensional coordinates of the tumor boundary through spatial gradient change analysis and the radio frequency signal characteristic attenuation association rule based on the positioning calibration parameters so as to obtain a tumor cell positioning result. Further, performing spatial registration and feature extraction on the original fusion data set to obtain a multi-dimensional feature set, including: Based on the original fusion data set, rigid transformation and affine transformation are sequentially carried out on the radio-frequency echo signals, the ultrasonic images and the computed tomography data to realize spatial precise alignment, and a fusion data set after spatial registration is generated; Extracting texture features and computed tomography density distribution features of the ultrasonic images from the fused data set subjected to spatial registration, and calculating frequency domain energy features of radio frequency echo signals through fast Fourier transformation; And integrating the ultrasonic image texture features, the computed tomography density distribution features and the frequency domain energy features to obtain a multi-dimensional feature set. Further, based on extracting the multi-band radio frequency echo signal intensity level value of the target area based on the multi-dimensional fea