Brain glioma molecular marker nondestructive prediction method and prediction system based on radiomics

Abstract

The invention belongs to the technical field of computer-aided diagnosis, and specifically relates to a brain glioma molecular marker nondestructive prediction method and a prediction system based on radiomics. The method comprises the following steps: adopting a three-dimensional magnetic resonance image automatic segmentation method based on a convolution neural network; registering a tumor obtained from segmentation to a standard brain atlas, and acquiring 116 position features of tumor distribution; getting 21 gray features, 15 shape features and 39 texture features through calculation; carrying out three-dimensional wavelet decomposition on the gray features and the texture features to get 480 wavelet features of eight sub-bands; acquiring 671 high-throughput features from the three-dimensional T2-Flair magnetic resonance image of each case; using a feature screening strategy combining p-value screening and a genetic algorithm to get 110 features highly associated with IDH1; and using a support vector machine and an AdaBoost classifier to get a classification of which the IDH1 prediction accuracy is 80%. As a novel method of radiomics, the method provides a nondestructive prediction scheme of important molecular markers for clinical diagnosis of gliomas.

Description

technical field

[0001] The invention belongs to the technical field of computer-aided diagnosis, in particular to a radiomics-based nondestructive prediction method and a prediction system for molecular markers of brain glioma. Background technique

[0002] Glioma is the most common brain malignancy, and about 30% of them are low-grade gliomas (LGG, WHO grades I and II). Although low-grade gliomas have a relatively good prognosis, almost all low-grade gliomas will develop into high-grade gliomas with high mortality. Compared with glioblastoma (GBM, WHO grade IV), research on gene expression analysis and understanding of LGG is relatively lacking.

[0003] IDH1 (isocitrate dehydrogenase 1) has significant diagnostic, prognostic, and predictive values, and is the most important molecular marker in glioma [1]. Most lower-grade gliomas (WHO grades II and III) and secondary GBMs have IDH1 mutations, while IDH1 mutations are rarely observed in primary GBMs; IDH1 is independent o...

Examples

Embodiment Construction

[0060] The following are the specific implementation steps of the entire algorithm:

[0061] 1. Firstly, perform operations such as brain removal and grayscale normalization on the original image, manually label 30 cases of 240 pieces of unbiased images as the training set of CNN, and divide the image into 32*32 small blocks and send them to the network for training .

[0062] 2. Use figure 2 The CNN shown segments the image, and subsequently adjusts the segmentation result with a CRF energy random field.

[0063] 3. Map the segmented tumors to the standard brain atlas MN152 with SPM12, superimpose 76 cases of IDH1 mutation and 34 cases of IDH1 wild-type tumors on the standard brain atlas, divide the superposition results into AAL116 partitions, and count the two Distribution of tumoroids on 116 partitions as 116 location features.

[0064] 4. A total of 555 grayscale, shape, texture, and wavelet features shown in Table 1 were extracted, plus 116 positional features, and a...

technical field

[0001] The invention belongs to the technical field of computer-aided diagnosis, in particular to a radiomics-based nondestructive prediction method and a prediction system for molecular markers of brain glioma. Background technique

[0002] Glioma is the most common brain malignancy, and about 30% of them are low-grade gliomas (LGG, WHO grades I and II). Although low-grade gliomas have a relatively good prognosis, almost all low-grade gliomas will develop into high-grade gliomas with high mortality. Compared with glioblastoma (GBM, WHO grade IV), research on gene expression analysis and understanding of LGG is relatively lacking.

[0003] IDH1 (isocitrate dehydrogenase 1) has significant diagnostic, prognostic, and predictive values, and is the most important molecular marker in glioma [1]. Most lower-grade gliomas (WHO grades II and III) and secondary GBMs have IDH1 mutations, while IDH1 mutations are rarely observed in primary GBMs; IDH1 is independent o...

Examples

Embodiment Construction

[0060] The following are the specific implementation steps of the entire algorithm:

[0061] 1. Firstly, perform operations such as brain removal and grayscale normalization on the original image, manually label 30 cases of 240 pieces of unbiased images as the training set of CNN, and divide the image into 32*32 small blocks and send them to the network for training .

[0062] 2. Use figure 2 The CNN shown segments the image, and subsequently adjusts the segmentation result with a CRF energy random field.

[0063] 3. Map the segmented tumors to the standard brain atlas MN152 with SPM12, superimpose 76 cases of IDH1 mutation and 34 cases of IDH1 wild-type tumors on the standard brain atlas, divide the superposition results into AAL116 partitions, and count the two Distribution of tumoroids on 116 partitions as 116 location features.

[0064] 4. A total of 555 grayscale, shape, texture, and wavelet features shown in Table 1 were extracted, plus 116 positional features, and a...

Images