CN114792569A - Method for predicting tumor treatment prognosis by establishing inflammatory cell infiltration model based on imagemics - Google Patents
Method for predicting tumor treatment prognosis by establishing inflammatory cell infiltration model based on imagemics Download PDFInfo
- Publication number
- CN114792569A CN114792569A CN202210051363.2A CN202210051363A CN114792569A CN 114792569 A CN114792569 A CN 114792569A CN 202210051363 A CN202210051363 A CN 202210051363A CN 114792569 A CN114792569 A CN 114792569A
- Authority
- CN
- China
- Prior art keywords
- model
- cell infiltration
- data
- inflammatory cell
- establishing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000008595 infiltration Effects 0.000 title claims abstract description 53
- 238000001764 infiltration Methods 0.000 title claims abstract description 53
- 206010028980 Neoplasm Diseases 0.000 title claims abstract description 42
- 210000004969 inflammatory cell Anatomy 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004393 prognosis Methods 0.000 title claims abstract description 17
- 238000003384 imaging method Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 210000002865 immune cell Anatomy 0.000 claims description 10
- 108091028043 Nucleic acid sequence Proteins 0.000 claims description 9
- 150000007523 nucleic acids Chemical group 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000003559 RNA-seq method Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000001574 biopsy Methods 0.000 claims description 6
- 210000004027 cell Anatomy 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 108090000623 proteins and genes Proteins 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000002560 therapeutic procedure Methods 0.000 claims 3
- 239000011159 matrix material Substances 0.000 description 12
- 238000012360 testing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000002512 chemotherapy Methods 0.000 description 2
- 230000036039 immunity Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000005311 nuclear magnetism Effects 0.000 description 2
- 238000001959 radiotherapy Methods 0.000 description 2
- 206010027476 Metastases Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000035269 cancer or benign tumor Diseases 0.000 description 1
- 230000004663 cell proliferation Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009169 immunotherapy Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000009401 metastasis Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
- 231100000588 tumorigenic Toxicity 0.000 description 1
- 230000000381 tumorigenic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/30—Detection of binding sites or motifs
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Biology (AREA)
- Biotechnology (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioethics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of tumor treatment, in particular to a method for predicting tumor treatment prognosis by establishing an inflammatory cell infiltration model based on imaging omics.
Description
Technical Field
The invention relates to the technical field of tumor treatment, in particular to a method for predicting tumor treatment prognosis by establishing an inflammatory cell infiltration model based on imaging omics.
Background
Tumor refers to a new organism formed by local tissue cell proliferation under the action of various tumorigenic factors, because the new organism mostly presents space-occupying blocky protrusions, which is also called neoplasm.
The research shows that the infiltration condition of inflammatory cells in the tumor has great correlation with the prognosis of tumor radiotherapy and chemotherapy. Laboratory examination of tumor tissue by biopsy is currently the only standard for obtaining inflammatory cell infiltration in tumors. However, this method has the following problems:
(1) invasive, increasing the risk of metastasis: the biopsy process has trauma, which easily causes the tumor to be transferred along the cavity.
(2) The time is as follows: the specimen needs to be processed before detection, so at least one week is required to obtain a result.
(3) Non-repeatability: patients are not advised to take multiple biopsy tests due to the multiple risks.
In summary, the development of a method for predicting prognosis of tumor treatment by establishing an inflammatory cell infiltration model based on imaging omics is still a key problem to be solved urgently in the technical field of tumor treatment.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method for establishing an inflammatory cell infiltration model based on imaging omics to predict the prognosis of tumor treatment, the immune infiltration ratio is obtained through patient genome data, then the immune infiltration ratio is subjected to imaging omics analysis or neural network learning with corresponding imaging data (CT or nuclear magnetism), the output result is a corresponding immune infiltration result, an immune cell infiltration model is established, and finally the model is used for predicting the image of a new patient to obtain the infiltration condition of the new patient.
In order to realize the purpose of the invention, the invention provides the following technical scheme:
a method for establishing an inflammatory cell infiltration model to predict tumor treatment prognosis based on imaging omics comprises the following steps:
(1) obtaining a gene detection sequence through patient tumor biopsy, performing data analysis on the nucleic acid sequence RNA-seq by using an analysis algorithm to obtain various inflammatory cell infiltration ratios, and using the obtained immune cell infiltration data as the output of the subsequent model training;
(2) acquiring image data of a patient with the nucleic acid sequence RNA-seq data acquired in the step (1) near the corresponding time, processing the image data to be used as input end data of model training, importing the acquired image data into a plan design system or an image processing system, manually delineating a tumor region on the system, and processing the delineated tumor range;
(3) acquiring image characteristics of an annular region of interest (ROI);
(4) performing feature screening on the feature value obtained in the step (3) on python by using variance inspection and inhaul cable regression, establishing a lasso regression model, a polynomial regression model and principal component analysis with a corresponding immune cell infiltration result, and performing K-fold cross inspection screening on the lasso regression model and the polynomial regression model for optimal selection;
(5) predicting the immune infiltration condition of another group of patients by using the screened model, comparing the immune infiltration condition with an immune infiltration result obtained by an experimental laboratory, and performing model verification;
(6) and adjusting sample data in the model to optimize the model, and verifying the model.
The invention is further configured to: in the step (1), the analysis algorithm is a TIMER algorithm, the TIMER algorithm obtains different inflammatory cell infiltration percentages through a nucleic acid sequence RNA-sque, and one of the cell percentages is screened as an output result of the training of the imaging omics model.
The invention is further configured to: in the step (2), the image data is either CT data or MRI data.
The invention is further configured to: in the step (2), the method for processing the delineated tumor range comprises the following steps: and simultaneously expanding the distance of 3mm inwards and outwards to form an annular region of interest (ROI), setting the internal density of the annular region of interest (ROI) to be 1 and the external density to be 0 by using 3D-slicer or Python programming software, and obtaining a mask which is used as an image range for acquiring the image omics information subsequently.
The invention is further configured to: in the step (3), the image features include histogram features and texture features.
The invention is further configured to: in step (6), the sample data includes the number of CT data or nuclear magnetic images, the number of target delineations, the accuracy of the target, and regularization parameters, iteration times, and threshold size in the model.
The invention is further configured to: in step (6), the verification of the model is to guide a new batch of patients, and the prediction result determines the final model condition through the condition of the receiver operating characteristic curve ROC.
Advantageous effects
Compared with the known public technology, the technical scheme provided by the invention has the following beneficial effects:
the invention obtains the immune infiltration ratio through genome data of a patient, then performs image omics analysis or neural network learning with corresponding imaging data (CT or nuclear magnetism), outputs the result as a corresponding immune infiltration result, establishes an immune cell infiltration model, and finally predicts the image of a new patient by using the model to obtain the infiltration condition of the new patient.
Drawings
FIG. 1 is a flow chart of the present invention for obtaining the infiltration ratio of immune cells using an algorithm;
FIG. 2 is a diagram of the ratio of different cells in a tumor according to the present invention;
FIG. 3 is a Timer analysis results heatmap in accordance with the present invention;
FIG. 4 is an exemplary illustration of target treatment in accordance with the present invention;
FIG. 5 is an exemplary graph of the ROC curve of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to achieve the effects of the present invention, the present invention will be further described with reference to the following examples.
Example (b):
referring to fig. 1-5, a method for predicting prognosis of tumor treatment by establishing an inflammatory cell infiltration model based on imaging omics comprises the following steps:
(1) obtaining a gene detection sequence through patient tumor biopsy, performing data analysis on the nucleic acid sequence RNA-seq by using an analysis algorithm to obtain various inflammatory cell infiltration ratios, and using the obtained immune cell infiltration data as the output of the subsequent model training.
Further, the analysis algorithm is a TIMER algorithm, the TIMER algorithm obtains different inflammatory cell infiltration percentages through the nucleic acid sequence RNA-sque, and one of the cell percentages is screened to serve as an output result of the image omics model training.
In the step, the current assessment algorithm about immune infiltration comprises TIMER, CIBERS ORT, qualTIseq, xCell, MCP-counter and the like, and many of the algorithms need to be implemented by downloading codes by themselves, but the TIMER algorithm has a webpage version, and the analysis process is relatively simple, so the invention adopts the TIMER algorithm. The basic process for obtaining the infiltration ratio of immune cells is shown in FIG. 1 below.
In addition, it should be noted that the TIMER database in the TIMER algorithm may perform three-aspect analysis: (a) correlation analysis of immunity; (b) expansion of tumor genes (similar to GEPIA analysis); (c) and uploading own data to evaluate the immunity condition. The operation method is simple: the ratio of various cells can be automatically analyzed by uploading the RNA-seq data to a Timer database in an Excel format, and the result can be displayed in the form of a data table and a heat map or manually stored locally, as shown in FIG. 2 and FIG. 3.
(2) Acquiring image data of a patient with the nucleic acid sequence RNA-seq data acquired in the step (1) near the corresponding time, processing the image data to be used as input end data of model training, importing the acquired image data into a plan design system or an image processing system, manually delineating a tumor region on the system, and processing the delineated tumor range.
Further, the image data is either CT data or MRI data.
Further, the method for processing the delineated tumor range comprises the following steps: and simultaneously, inwards and outwards expanding for 3mm to form an annular region of interest (ROI), setting the internal density of the annular ROI to be 1 and the external density to be 0 by using 3D-slicer or Python programming software, and obtaining a mask which is used as an image range for subsequently obtaining the image omics information.
In this step, since the site of inflammatory cell infiltration is often located in the peritumoral region, it is necessary to further treat the delineated tumor area. The processing result is shown in fig. 4.
(3) And acquiring image characteristics of the annular region of interest ROI.
Further, the image features include histogram features and texture features.
In this step, the histogram feature and texture feature are extracted by setting the gray scale Width (Bin Width) to 10 and the sampling size to 1 × 1 mm.
Wherein, it needs to be explained that:
1) histogram feature
The simplest statistical descriptors are based on a global gray histogram, including the gray mean, maximum, minimum, variance, and percentile. These features are referred to as First Order features (First Order) because they are based on single pixel or single pixel analysis. More complex features include skewness and kurtosis, which describe the shape of the data intensity distribution: skewness reflects the asymmetry of the data distribution curve to the left (negative bias, below the mean) or right (positive bias, above the mean); and the kurtosis reflects the tailing of the data distribution relative to the gaussian distribution due to outliers.
2) Texture features
Absolute Gradient (Absolute Gradient): reflecting the degree or abruptness of the gray scale intensity fluctuations in the image. For 2 neighboring pixels or voxels, the gradient is highest if one is black and the other is white, and the gradient at the location is zero if both pixels are black (or both are white). Whether the gray scale changes from black to white (positive gradient) or white to black (negative gradient) is independent of the gradient size. Similar to the histogram features, the gradient features include gradient mean, variance, skewness, and kurtosis.
Gray level co-occurrence matrix (GLCM): a Gray Level Co-occurance Matrix (GLCM for short) is a second order Gray histogram that captures the spatial relationship of pairs of pixels or voxels with predefined Gray intensities in different directions (13 directions for horizontal, vertical or diagonal or 3D analysis of 2D analysis) and predefined distances between pixels or voxels. GLCM features include: entropy, which is a measure of gray level non-uniformity or randomness; angular second moment (also called homogeneity or energy), reflecting the homogeneity or order of the grey levels; contrast, which emphasizes pixels or voxel pairs (gray level differences between pixels or voxels).
Gray level run matrix (GLRLM): a Gray Level Run-Length Matrix (GLRLM for short) provides information about the spatial distribution of consecutive pixels having the same Gray Level in one or more directions, 2-or 3-dimensions. The GLRLM feature includes a score that evaluates the percentage of pixels or voxels within the ROI that are part of the run, thus reflecting the granularity; long-term emphasis and short-term emphasis (inverse) moments, weighted against the number of long-term and short-term runs, respectively; non-uniformity of gray levels and runlengths.
Grayscale size area matrix (GLSZM): the Gray Level Size Zone Matrix (GLSZM for short) is based on a similar principle as GLRLM, but here the counting of the number of groups of interconnected neighboring pixels or voxels (so-called zones) with the same Gray Level forms the basis of the Matrix. A more uniform texture will result in a wider and flatter matrix. The GLSZM is not calculated for different directions but may be calculated for different pixel or voxel distances defining a neighborhood. The GLSZM features can be computed in 2-dimension (8 neighboring pixels) or 3-dimension (26 neighboring voxels).
Neighborhood grayscale difference matrix (NGTDM): a Neighborhood Gray Tone Difference Matrix (NGTDM) quantifies the sum of differences between the Gray level of a pixel or voxel and the average Gray level of its neighbors within a predefined distance. The main characteristics include the roughness, busyness and complexity of NGTDM. The roughness reflects the gray level difference between the central pixel or voxel and its neighborhood, thereby capturing the spatial rate of gray level intensity change; that is, an ROI consisting of a larger region with a relatively uniform gray level (i.e., a lower rate of spatial intensity change) will have a higher roughness value. On the other hand, busy reflects fast gray scale changes (i.e., high spatial frequency of intensity changes) between the central pixel or voxel and its neighboring pixels.
Grayscale dependent matrix (GLDM): the Gray Level Dependency Matrix (GLDM) is also based on the Gray Level relationship between the central pixel or voxel and its neighborhood. If the correlation criterion is met in terms of a defined range of gray level differences, neighboring pixels or voxels within a predetermined distance are considered to be connected to the central pixel or voxel. The ROI is then analyzed for the presence of a central pixel or voxel whose intensity depends on the neighboring pixels or voxels of i and j. Also, similar to GLRLM, characteristics of GLDM include large-dependency emphasis and small-dependency emphasis reflecting heterogeneity and homogeneity, and gray-level heterogeneity and dependency uniformity reflecting gray-level similarity and gray-level dependency in the entire ROI.
(4) And (4) performing feature screening on the feature value obtained in the step (3) on python by using variance detection and inhaul cable regression, establishing a lasso regression model, a polynomial regression model and principal component analysis with the corresponding immune cell infiltration result, and performing K-fold cross detection screening on the lasso regression model and the polynomial regression model to obtain the optimal screening.
In this step, the specific method of K-fold verification is as follows: the data set D is randomly divided into K packets (here, K is assumed to be 6), one packet is taken as a test set test each time, and the rest K-1 packets are taken as a training set train for training, at the moment, the training set train is changed from D to K by D, finally, the average value of the classification rates obtained by K times is calculated and taken as the real classification rate of the model or the hypothesis function, the occurrence of over-learning and under-learning states is effectively avoided, and the finally obtained result is comparatively convincing.
(5) And (4) predicting the immune infiltration condition of another group of patients by using the screened model, comparing the immune infiltration condition with the immune infiltration result obtained in the laboratory, and verifying the model.
In this step, the selected model refers to the model selected in step (4) by K-fold cross-testing.
(6) And adjusting sample data in the model to optimize the model, and verifying the model.
Further, the sample data includes the number of CT data or nuclear magnetic images, the number of target delineations, the accuracy of the target, and regularization parameters, iteration times, and threshold size in the model.
Further, the verification of the model means that a new batch of patients are introduced, and the final model condition is determined according to the condition of the receiver operation characteristic curve ROC according to the prediction result.
In this step, the ROC curve obtained by the model test is shown in fig. 5, which is a comprehensive index reflecting continuous variables of sensitivity and specificity, and is a curve drawn by different results obtained by using different judgment standards under a specific stimulation condition, and after the model meets requirements, the model can be used for predicting the infiltration condition of inflammatory cells in a tumor, and a corresponding relation is established between the infiltration result of the inflammatory cells and the effects of radiotherapy, chemotherapy and immunotherapy.
The invention has the advantages of no wound (only CT or nuclear magnetic image of a patient needs to be obtained), high speed (the time for predicting a group of patients after the model is built is at most several minutes), repeatability (image data scanned in different periods can be predicted at any time by the model), and the like, and can provide a new means for judging the prognosis condition of tumor treatment.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not cause the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for predicting tumor treatment prognosis by establishing an inflammatory cell infiltration model based on imaging omics is characterized by comprising the following steps:
(1) obtaining a gene detection sequence through tumor biopsy of a patient, performing data analysis on a nucleic acid sequence RNA-seq by using an analysis algorithm to obtain various inflammatory cell infiltration ratios, and using the obtained immune cell infiltration data as the output of subsequent model training;
(2) acquiring image data of a patient with the nucleic acid sequence RNA-seq data acquired in the step (1) near the corresponding time, processing the image data to be used as input end data of model training, importing the acquired image data into a plan design system or an image processing system, manually delineating a tumor region on the system, and processing the delineated tumor range;
(3) acquiring image characteristics of an annular region of interest (ROI);
(4) performing feature screening on the feature value obtained in the step (3) on python by using variance detection and inhaul cable regression, establishing a lasso regression model, a polynomial regression model and principal component analysis with a corresponding immune cell infiltration result, and performing K-fold cross detection screening on the lasso regression model and the polynomial regression model to obtain the optimal features;
(5) predicting the immune infiltration condition of another group of patients by using the screened model, comparing the immune infiltration condition with an immune infiltration result obtained in a laboratory, and verifying the model;
(6) and adjusting sample data in the model to optimize the model, and verifying the model.
2. The method for establishing an inflammatory cell infiltration model to predict tumor treatment prognosis based on imaging omics as claimed in claim 1, wherein in step (1), the analysis algorithm is a TIMER algorithm, the TIMER algorithm obtains different inflammatory cell infiltration percentages through a nucleic acid sequence RNA-sque, and one of the cell percentages is screened as an output result of the imaging omics model training.
3. The method for establishing an inflammatory cell infiltration model for predicting tumor treatment prognosis based on imagemics as claimed in claim 1, wherein in step (2), the image data is any one of CT data or MRI data.
4. The method for establishing an inflammatory cell infiltration model to predict prognosis of tumor therapy based on imaging omics as claimed in claim 1, wherein in step (2), the method for processing the delineated tumor range comprises: and simultaneously, inwards and outwards expanding for 3mm to form an annular region of interest (ROI), setting the internal density of the annular ROI to be 1 and the external density to be 0 by using 3D-slicer or Python programming software, and obtaining a mask which is used as an image range for subsequently obtaining the image omics information.
5. The method for predicting prognosis of tumor therapy based on imaging omics based on the model of inflammatory cell infiltration as claimed in claim 1, wherein in step (3), the image features comprise histogram features and texture features.
6. The method for establishing an inflammatory cell infiltration model based on imagery omics to predict tumor therapy prognosis as claimed in claim 1, wherein, in step (6), the sample data comprises CT data or the number of magnetic resonance images, the number of delineations in the target area, the accuracy of the target area, and the regularization parameters, the number of iterations, and the size of the threshold in the model.
7. The method for establishing an inflammatory cell infiltration model for predicting tumor treatment prognosis based on imagemics as claimed in claim 1, wherein in step (6), the model verification means introducing a new batch of patients, and the prediction result determines the final model condition by the condition of receiver operating characteristic curve ROC.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210051363.2A CN114792569A (en) | 2022-01-17 | 2022-01-17 | Method for predicting tumor treatment prognosis by establishing inflammatory cell infiltration model based on imagemics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210051363.2A CN114792569A (en) | 2022-01-17 | 2022-01-17 | Method for predicting tumor treatment prognosis by establishing inflammatory cell infiltration model based on imagemics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114792569A true CN114792569A (en) | 2022-07-26 |
Family
ID=82459160
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210051363.2A Pending CN114792569A (en) | 2022-01-17 | 2022-01-17 | Method for predicting tumor treatment prognosis by establishing inflammatory cell infiltration model based on imagemics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114792569A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115440386A (en) * | 2022-09-30 | 2022-12-06 | 中国医学科学院北京协和医院 | Prediction of immunotherapy effect of advanced cancer patients based on weighted multi-lesion imagemics features |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110197236A (en) * | 2018-10-17 | 2019-09-03 | 中山大学附属第三医院 | A kind of prediction and verification method based on image group to glucocorticoid curative effect |
CN111094977A (en) * | 2017-07-13 | 2020-05-01 | 古斯塔夫·鲁西研究所 | Imaging tools based on imaging omics to monitor tumor lymphocyte infiltration and prognosis in anti-PD-1/PD-L1 treated tumor patients |
CN111462116A (en) * | 2020-05-13 | 2020-07-28 | 吉林大学第一医院 | Multimodal parameter model optimization fusion method based on imagery omics characteristics |
CN112951426A (en) * | 2021-03-15 | 2021-06-11 | 山东大学齐鲁医院 | Construction method and evaluation system of pancreatic ductal adenoma inflammatory infiltration degree judgment model |
CN112951406A (en) * | 2021-01-27 | 2021-06-11 | 安徽理工大学 | Lung cancer prognosis auxiliary evaluation method and system based on CT (computed tomography) image omics |
CN113140258A (en) * | 2021-04-28 | 2021-07-20 | 上海海事大学 | Method for screening potential prognosis biomarkers of lung adenocarcinoma based on tumor infiltrating immune cells |
CN113208640A (en) * | 2021-04-26 | 2021-08-06 | 复旦大学附属肿瘤医院 | Method for predicting axillary lymph node metastasis based on PET (positron emission tomography) imaging omics special for mammary gland |
-
2022
- 2022-01-17 CN CN202210051363.2A patent/CN114792569A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111094977A (en) * | 2017-07-13 | 2020-05-01 | 古斯塔夫·鲁西研究所 | Imaging tools based on imaging omics to monitor tumor lymphocyte infiltration and prognosis in anti-PD-1/PD-L1 treated tumor patients |
CN110197236A (en) * | 2018-10-17 | 2019-09-03 | 中山大学附属第三医院 | A kind of prediction and verification method based on image group to glucocorticoid curative effect |
CN111462116A (en) * | 2020-05-13 | 2020-07-28 | 吉林大学第一医院 | Multimodal parameter model optimization fusion method based on imagery omics characteristics |
CN112951406A (en) * | 2021-01-27 | 2021-06-11 | 安徽理工大学 | Lung cancer prognosis auxiliary evaluation method and system based on CT (computed tomography) image omics |
CN112951426A (en) * | 2021-03-15 | 2021-06-11 | 山东大学齐鲁医院 | Construction method and evaluation system of pancreatic ductal adenoma inflammatory infiltration degree judgment model |
CN113208640A (en) * | 2021-04-26 | 2021-08-06 | 复旦大学附属肿瘤医院 | Method for predicting axillary lymph node metastasis based on PET (positron emission tomography) imaging omics special for mammary gland |
CN113140258A (en) * | 2021-04-28 | 2021-07-20 | 上海海事大学 | Method for screening potential prognosis biomarkers of lung adenocarcinoma based on tumor infiltrating immune cells |
Non-Patent Citations (3)
Title |
---|
余彩裙;裴晶晶;: "基于CIBERSORT预测乳腺癌浸润性免疫细胞比例及亚型预后分析", 云南民族大学学报(自然科学版), no. 01 * |
段亚阳;周坤鹏;边杰;李思瑶;: "基于非增强MRI的影像组学术前预测肝细胞癌微血管浸润的研究", 磁共振成像, no. 03 * |
蒋怀礼;沈纳;周雷;黄新生;: "Toll样受体-5在喉鳞状细胞癌中的表达及作用", 中国眼耳鼻喉科杂志, no. 03 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115440386A (en) * | 2022-09-30 | 2022-12-06 | 中国医学科学院北京协和医院 | Prediction of immunotherapy effect of advanced cancer patients based on weighted multi-lesion imagemics features |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111488921B (en) | Intelligent analysis system and method for panoramic digital pathological image | |
CN112116605A (en) | Pancreas CT image segmentation method based on integrated depth convolution neural network | |
CN105809175B (en) | Cerebral edema segmentation method and system based on support vector machine algorithm | |
CN110866893A (en) | Pathological image-based TMB classification method and system and TMB analysis device | |
Tomakova et al. | Automatic fluorography segmentation method based on histogram of brightness submission in sliding window | |
CN109903282B (en) | Cell counting method, system, device and storage medium | |
CN110516759B (en) | Soft tissue sarcoma transfer risk prediction system based on machine learning | |
Xu et al. | Using transfer learning on whole slide images to predict tumor mutational burden in bladder cancer patients | |
CN114463609B (en) | Method and device for determining fluorescent mixed points in cell microscopic image | |
CN116137036B (en) | Gene detection data intelligent processing system based on machine learning | |
Wu et al. | Ultrasound image segmentation method for thyroid nodules using ASPP fusion features | |
Babu et al. | Colon cancer prediction using 2DR e CA segmentation and hybrid features on histopathology images | |
CN114792569A (en) | Method for predicting tumor treatment prognosis by establishing inflammatory cell infiltration model based on imagemics | |
CN112651507A (en) | Method for constructing microvascular invasion prediction model of hepatocellular carcinoma and probability prediction method | |
Kumarganesh et al. | An efficient approach for brain image (tissue) compression based on the position of the brain tumor | |
Ghahramani et al. | Brain tumour detection in magnetic resonance imaging using Levenberg–Marquardt backpropagation neural network | |
WO2022165433A1 (en) | Systems and methods for classifying biomedical image data using a graph neural network | |
CN116912240A (en) | Mutation TP53 immunology detection method based on semi-supervised learning | |
Chauhan et al. | Exploring genetic-histologic relationships in breast cancer | |
CN116229176A (en) | Medical image classification method and device combining image histology characteristics and clinical characteristics | |
RU2656761C1 (en) | Method and system of segmentation of lung foci images | |
US20210338194A1 (en) | Analysis method for breast image and electronic apparatus using the same | |
CN115064270A (en) | Liver cancer recurrence prediction method based on image omics image characteristics | |
CN114842960A (en) | Method for evaluating disease progression and prognosis of new coronary patient based on CT (computed tomography) image and clinical data | |
CN113069137A (en) | Esophagus tumor segmentation method based on DDAUnet |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |