CN116721761A - Radiotherapy data processing method, system, equipment and medium - Google Patents
Radiotherapy data processing method, system, equipment and medium Download PDFInfo
- Publication number
- CN116721761A CN116721761A CN202310738298.5A CN202310738298A CN116721761A CN 116721761 A CN116721761 A CN 116721761A CN 202310738298 A CN202310738298 A CN 202310738298A CN 116721761 A CN116721761 A CN 116721761A
- Authority
- CN
- China
- Prior art keywords
- data
- radiotherapy
- training
- data set
- tumor
- 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
- 238000001959 radiotherapy Methods 0.000 title claims abstract description 374
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 89
- 230000000694 effects Effects 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 41
- 230000008816 organ damage Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 110
- 206010028980 Neoplasm Diseases 0.000 claims description 82
- 238000011282 treatment Methods 0.000 claims description 40
- 238000011156 evaluation Methods 0.000 claims description 29
- 239000012472 biological sample Substances 0.000 claims description 28
- 238000005516 engineering process Methods 0.000 claims description 26
- 210000001165 lymph node Anatomy 0.000 claims description 22
- 210000000056 organ Anatomy 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 18
- 201000010099 disease Diseases 0.000 claims description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 11
- 210000004369 blood Anatomy 0.000 claims description 10
- 239000008280 blood Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 102100032752 C-reactive protein Human genes 0.000 claims description 8
- 230000007969 cellular immunity Effects 0.000 claims description 8
- 210000004556 brain Anatomy 0.000 claims description 6
- 230000000391 smoking effect Effects 0.000 claims description 6
- 208000019155 Radiation injury Diseases 0.000 claims description 5
- 230000007059 acute toxicity Effects 0.000 claims description 5
- 231100000403 acute toxicity Toxicity 0.000 claims description 5
- 230000003920 cognitive function Effects 0.000 claims description 5
- 230000007774 longterm Effects 0.000 claims description 5
- 108010074051 C-Reactive Protein Proteins 0.000 claims description 4
- 239000005556 hormone Substances 0.000 claims description 4
- 229940088597 hormone Drugs 0.000 claims description 4
- 230000007170 pathology Effects 0.000 claims description 4
- 238000000547 structure data Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 230000006378 damage Effects 0.000 description 33
- 210000000920 organ at risk Anatomy 0.000 description 20
- 208000014829 head and neck neoplasm Diseases 0.000 description 18
- 238000012795 verification Methods 0.000 description 16
- 238000002595 magnetic resonance imaging Methods 0.000 description 12
- 208000027418 Wounds and injury Diseases 0.000 description 11
- 208000014674 injury Diseases 0.000 description 11
- 238000002597 diffusion-weighted imaging Methods 0.000 description 10
- 210000005259 peripheral blood Anatomy 0.000 description 10
- 239000011886 peripheral blood Substances 0.000 description 10
- 239000000090 biomarker Substances 0.000 description 9
- 238000002591 computed tomography Methods 0.000 description 7
- 238000005065 mining Methods 0.000 description 7
- 210000001519 tissue Anatomy 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000013136 deep learning model Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 239000000523 sample Substances 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 5
- 210000002966 serum Anatomy 0.000 description 5
- 239000000243 solution Substances 0.000 description 5
- 102000018997 Growth Hormone Human genes 0.000 description 4
- 108010051696 Growth Hormone Proteins 0.000 description 4
- AUYYCJSJGJYCDS-LBPRGKRZSA-N Thyrolar Chemical class IC1=CC(C[C@H](N)C(O)=O)=CC(I)=C1OC1=CC=C(O)C(I)=C1 AUYYCJSJGJYCDS-LBPRGKRZSA-N 0.000 description 4
- 238000009792 diffusion process Methods 0.000 description 4
- 239000000122 growth hormone Substances 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 230000005855 radiation Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 229940036555 thyroid hormone Drugs 0.000 description 4
- 239000005495 thyroid hormone Substances 0.000 description 4
- 239000001993 wax Substances 0.000 description 4
- 210000001744 T-lymphocyte Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002503 metabolic effect Effects 0.000 description 3
- 230000001575 pathological effect Effects 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 238000004393 prognosis Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000004083 survival effect Effects 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000002872 contrast media Substances 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000004980 dosimetry Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000002599 functional magnetic resonance imaging Methods 0.000 description 2
- 210000004907 gland Anatomy 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000002721 intensity-modulated radiation therapy Methods 0.000 description 2
- 230000004089 microcirculation Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000011269 treatment regimen Methods 0.000 description 2
- 208000019743 Cranial nerve injury Diseases 0.000 description 1
- 206010016654 Fibrosis Diseases 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 206010028851 Necrosis Diseases 0.000 description 1
- CTQNGGLPUBDAKN-UHFFFAOYSA-N O-Xylene Chemical compound CC1=CC=CC=C1C CTQNGGLPUBDAKN-UHFFFAOYSA-N 0.000 description 1
- 206010031264 Osteonecrosis Diseases 0.000 description 1
- 108091008605 VEGF receptors Proteins 0.000 description 1
- 102100033177 Vascular endothelial growth factor receptor 2 Human genes 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000002671 adjuvant Substances 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000008081 blood perfusion Effects 0.000 description 1
- 210000003461 brachial plexus Anatomy 0.000 description 1
- 210000000133 brain stem Anatomy 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 238000009104 chemotherapy regimen Methods 0.000 description 1
- 210000003477 cochlea Anatomy 0.000 description 1
- 238000013170 computed tomography imaging Methods 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000012153 distilled water Substances 0.000 description 1
- 206010013781 dry mouth Diseases 0.000 description 1
- 230000002124 endocrine Effects 0.000 description 1
- 102000052116 epidermal growth factor receptor activity proteins Human genes 0.000 description 1
- 108700015053 epidermal growth factor receptor activity proteins Proteins 0.000 description 1
- 210000003238 esophagus Anatomy 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000004761 fibrosis Effects 0.000 description 1
- 238000000684 flow cytometry Methods 0.000 description 1
- 230000009760 functional impairment Effects 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 208000016354 hearing loss disease Diseases 0.000 description 1
- 230000000887 hydrating effect Effects 0.000 description 1
- 238000013115 immunohistochemical detection Methods 0.000 description 1
- 230000002055 immunohistochemical effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000001990 intravenous administration Methods 0.000 description 1
- NTHXOOBQLCIOLC-UHFFFAOYSA-N iohexol Chemical group OCC(O)CN(C(=O)C)C1=C(I)C(C(=O)NCC(O)CO)=C(I)C(C(=O)NCC(O)CO)=C1I NTHXOOBQLCIOLC-UHFFFAOYSA-N 0.000 description 1
- 229960001025 iohexol Drugs 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 210000004698 lymphocyte Anatomy 0.000 description 1
- 125000001288 lysyl group Chemical group 0.000 description 1
- 210000004373 mandible Anatomy 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 239000002207 metabolite Substances 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- YOHYSYJDKVYCJI-UHFFFAOYSA-N n-[3-[[6-[3-(trifluoromethyl)anilino]pyrimidin-4-yl]amino]phenyl]cyclopropanecarboxamide Chemical compound FC(F)(F)C1=CC=CC(NC=2N=CN=C(NC=3C=C(NC(=O)C4CC4)C=CC=3)C=2)=C1 YOHYSYJDKVYCJI-UHFFFAOYSA-N 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 210000000440 neutrophil Anatomy 0.000 description 1
- 238000001208 nuclear magnetic resonance pulse sequence Methods 0.000 description 1
- 210000001328 optic nerve Anatomy 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 238000002638 palliative care Methods 0.000 description 1
- 239000012188 paraffin wax Substances 0.000 description 1
- 210000003681 parotid gland Anatomy 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 230000001817 pituitary effect Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 210000000278 spinal cord Anatomy 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 210000001913 submandibular gland Anatomy 0.000 description 1
- 210000003478 temporal lobe Anatomy 0.000 description 1
- 210000001738 temporomandibular joint Anatomy 0.000 description 1
- 210000001685 thyroid gland Anatomy 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 230000008791 toxic response Effects 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 210000003437 trachea Anatomy 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 239000008096 xylene Substances 0.000 description 1
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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4046—Scaling the whole image or part thereof using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4053—Super resolution, i.e. output image resolution higher than sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
- G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
-
- 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
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application discloses a method, a system, equipment and a medium for processing radiotherapy data, relates to the technical field of intelligent information prediction, and aims to solve the technical problem that the prior art cannot effectively process the radiotherapy data so as to predict the curative effect of radiotherapy. The radiotherapy data processing method comprises the following steps: acquiring a characteristic data set of a target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set; after the feature data set is normalized, inputting the feature data set into a radiotherapy data processing model to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a radiotherapy data processing method, a radiotherapy data processing system, radiotherapy data processing equipment and a radiotherapy data processing medium.
Background
Radiotherapy is one of tumor treatment means, the most common method for evaluating the curative effect of head and neck tumor radiotherapy is RECIST standard at present, but after clinical solid tumor radiotherapy, the radiotherapy is usually expressed as reduction of internal microcirculation blood flow perfusion, and then the tumor size is changed, and the RECIST standard can only evaluate the curative effect from the tumor size. And at present, multi-mode imaging, clinical indexes, biological samples and other data sets based on multi-dimensionality, multi-node and multi-time point are lacking at home and abroad so as to carry out multi-mode intelligent evaluation schemes for early prediction of treatment efficacy and damage to organs caused by radiotherapy. Therefore, the prior art lacks an effective treatment method for radiotherapy data, so that effective prediction of early-stage sensitive radiotherapy curative effects and side effects cannot be performed.
Disclosure of Invention
The application mainly aims to provide a radiotherapy data processing method, a radiotherapy data processing system, radiotherapy data processing equipment and a radiotherapy data processing medium, and aims to solve the technical problem that the radiotherapy data cannot be effectively processed in the prior art so as to predict the curative effect of radiotherapy.
In order to solve the above technical problems, the embodiments of the present application provide: a method for processing radiotherapy data, comprising the steps of:
acquiring a characteristic data set of a target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set;
after the feature data set is subjected to normalization processing, inputting the feature data set into a radiotherapy data processing model to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results;
the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
As some optional embodiments of the application, the full cycle of radiotherapy includes before the beginning of radiotherapy, after the 5 th radiotherapy, after the 15 th radiotherapy, after the full-course radiotherapy, 3 months after the full-course radiotherapy and 6 months after the full-course radiotherapy.
As some optional embodiments of the present application, the dynamically acquired characteristic data during the whole period of radiotherapy of the training subject includes:
in the whole period of radiotherapy of a training object, biological samples of the training object are collected and detected to obtain basic data and biological characteristic data of the training object;
in the whole period of radiotherapy of a training object, image scanning is carried out on the training object so as to obtain dynamic image data of the target part and normal parts around the target part; based on the dynamic image data, multi-mode image histology feature data are obtained.
As some optional embodiments of the present application, the image scanning of the training object during the whole period of the radiotherapy of the training object to obtain dynamic image data of the target portion and the normal portion around the target portion includes:
in the whole period of radiotherapy of a training object, image scanning is carried out on each part of the training object so as to obtain dynamic image data of a target part and normal parts around the target part;
And integrating the dynamic image data of the target part and the normal part around the target part based on a super resolution technology and a super-cross-level filling technology to obtain effective dynamic image data.
As some optional embodiments of the present application, the base data includes: basic information data and tumor-related data of a training object; wherein the basic information data includes: age data, gender data, body mass index data, concomitant disease data, smoking history data, ECOG scoring data, PG-SGA scoring data, and NRS2002 scoring data; the tumor-related data includes: training tumor-related data of the subject; the tumor-related data includes primary tumor site data, invasive sub-anatomical structure data, pathology type data, TNM stage (UICC 8) th ) Data and primary tumor volume data.
As some optional embodiments of the present application, the biometric data comprises: EBV titer data, blood routine data, biochemical index data, cellular immunity data, C-reactive protein data, and hormone data of the training subjects;
the dynamic image data includes: training image data of a tumor area of a subject and image data of a normal organ;
The multi-modal image histology feature data comprises: volume data of tumor and positive lymph nodes, magnetic resonance data of tumor and positive lymph nodes, and SUV values of tumor and positive lymph nodes of the subject were trained.
As some optional embodiments of the present application, the radiotherapy data processing result includes: a near-term efficacy prediction result and a far-term efficacy prediction result; wherein the recent efficacy prediction result includes: objective remission rate prediction results and disease control rate prediction results; the long-term efficacy prediction results comprise a progression-free lifetime prediction result, a remission duration prediction result and a total lifetime prediction result;
the organ damage prediction result includes: EORTC (electronic monitoring system) scale-head and neck special scale information, acute toxicity grading standard-CTCAE v5.0 information, RTOG late radiation injury grading standard information, pain VRS scale information, brain cognitive function MMSE scale information and hearing-vision scale information of a target object.
In order to solve the technical problems, the embodiment of the application further provides: a radiotherapy data processing apparatus, comprising:
the information acquisition module is used for acquiring a characteristic data set of the target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set;
The prediction module is used for inputting the feature data set into a radiotherapy data processing model after normalization processing so as to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results; the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
In order to solve the technical problems, the embodiment of the application further provides: an electronic device comprising a memory in which a computer program is stored and a processor executing the computer program for implementing a radiotherapy data processing method as described above.
In order to solve the technical problems, the embodiment of the application further provides: a computer readable storage medium having stored thereon a computer program, the computer program being executable by a processor to implement a radiotherapy data processing method as described above.
Based on the technical problems, the radiotherapy data processing method provided by the embodiment of the application comprises the following steps: acquiring a characteristic data set of a target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set; after the feature data set is subjected to normalization processing, inputting the feature data set into a radiotherapy data processing model to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results; the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data. Compared with the prior art, the method is used as a novel noninvasive and multidimensional intelligent head and neck tumor radiotherapy data processing method, and the radiotherapy curative effect is predicted based on the processed data so as to reduce the occurrence of radiotherapy side effects as much as possible.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a radiotherapy data processing method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a radiotherapy data processing apparatus according to an embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In recent years, the incidence rate of head and neck tumors in China is in an increasing trend year by year. Radiotherapy is one of main treatment means of head and neck tumor, can increase local control rate of tumor, evaluate treatment effect in time during treatment period, adjust treatment scheme, and is helpful for prolonging life of target object.
Radiotherapy is an adjuvant or local palliative treatment, and its efficacy is difficult to evaluate accurately and objectively. The most commonly used method for evaluating the curative effect of head and neck tumor radiotherapy is RECIST standard, but after clinical solid tumor radiotherapy, the method is usually characterized by reduced internal microcirculation blood perfusion, and then the tumor size is changed, and the RECIST standard can only evaluate the curative effect from the tumor size. In addition, at present, multi-mode intelligent evaluation schemes for early prediction of treatment efficacy and damage to organs caused by radiotherapy based on multi-mode imaging, clinical indexes, biological samples and other data sets of multiple dimensions, multiple nodes and multiple time points are lacking at home and abroad. Therefore, a novel, noninvasive and multidimensional intelligent head and neck tumor radiotherapy data processing method is needed, and the radiotherapy curative effect is predicted based on the processed data, so that the occurrence of radiotherapy side effects is reduced as much as possible.
With the wide application of Intensity Modulated Radiation Therapy (IMRT) and the improvement of radiotherapy and chemotherapy strategies, the survival prognosis of head and neck tumor groups is obviously improved, but the toxic and side effects related to treatment are still not neglected. Due to the anatomical nature of the head and neck tumor, the surrounding normal organs will inevitably receive a partial dose of radiotherapy, resulting in associated functional impairment. Post-injury such as dry mouth, hearing impairment, brain necrosis, cranial nerve injury, osteonecrosis, soft tissue fibrosis, endocrine changes caused by radiotherapy can seriously affect the quality of life of a target object. Thus, a balance between disease control and toxic response is critical for optimal treatment of head and neck tumors.
Based on the technical problems, the embodiment of the application provides a radiotherapy data processing method, which comprises the following steps: acquiring a characteristic data set of a target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set; after the feature data set is subjected to normalization processing, inputting the feature data set into a radiotherapy data processing model to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results; the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
Compared with the prior art, the method is used as a novel noninvasive and multidimensional intelligent head and neck tumor radiotherapy data processing method, and the radiotherapy curative effect is predicted based on the processed data so as to reduce the occurrence of radiotherapy side effects as much as possible; the prediction result is obtained through data processing and based on the data after the data processing, so that the early-stage sensitive radiotherapy curative effect can be predicted, and the organ damage degree can be estimated.
Specifically, the method according to the embodiment of the application gradually highlights advantages in diagnosis, treatment effect prediction and prognosis of head and neck tumors with complex anatomy and function by using a digital image processing technology, an artificial intelligence technology, a computer-aided diagnosis technology and a multi-modal image (CT technology, MRI technology, functional MRI technology and PET-CT technology). Among them, CT and MRI images can be used for prediction of efficacy and toxicity, and Diffusion Weighted Imaging (DWI) and Apparent Diffusion Coefficient (ADC) in functional MRI are closely related to radiotherapy sensitivity and prognosis. Wherein, image histology can catch crowd heterogeneity and internal changes of tumor and normal organ, and has great potential in evaluating tumor and normal organ function, and is possible to become a novel noninvasive marker.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware running environment according to an embodiment of the present application.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and an electronic program may be included in the memory 1005 as one type of storage medium.
In the electronic device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present application may be provided in the electronic device, where the electronic device invokes a radiotherapy data processing apparatus stored in the memory 1005 through the processor 1001, and executes a radiotherapy data processing method provided by the embodiment of the present application.
Referring to fig. 2, an embodiment of the present application provides a radiotherapy data processing method, including:
step S10, acquiring a characteristic data set of a target object; the characteristic data set comprises a basic data set, a first biological characteristic data set and a multi-mode image group science characteristic data set. The target object refers to a patient who needs to predict the curative effect of radiotherapy.
In practical applications, the basic data includes: basic information data and tumor-related data of the target object; wherein the basic information data includes: age data, sex Data, body mass index data, concomitant disease data, smoking history data, ECOG scoring data, PG-SGA scoring data, and NRS2002 scoring data; the tumor-related data includes: tumor-related data of the target subject; the tumor-related data includes primary tumor site data, invasive sub-anatomical structure data, pathology type data, TNM stage (UICC 8) th ) Data and primary tumor volume data.
In practical applications, the biometric data includes: EBV titer data, blood routine data, biochemical index data, cellular immunity data, C-reactive protein data, and hormone data for the target subject.
The biological characteristic data is based on the biological sample of the target object dynamically acquired in the radiotherapy period and the biological characteristic data obtained by extracting from the biological sample. The dynamic collection of the biological sample of the target object means: dynamically collecting a tumor fresh tissue sample or wax block as a biological sample in a radiotherapy period; or collecting serum samples of the target object before the beginning of the radiotherapy, after the 5 th radiotherapy, after the 15 th radiotherapy, after the whole-course radiotherapy, 3 months after the whole-course radiotherapy and 6 months after the whole-course radiotherapy. Wherein, the biological characteristic data extracted from the biological sample means: dynamically measuring the peripheral blood biomarker before the beginning of the radiotherapy, after the 5 th radiotherapy, after the 15 th radiotherapy, after the whole-course radiotherapy, 3 months after the whole-course radiotherapy and 6 months after the whole-course radiotherapy; among other peripheral blood biomarkers include, but are not limited to, EBV titer, blood convention, biochemistry, cellular immunity, CRP, growth hormone, thyroid hormone.
In practical application, the dynamic image data includes: image data of a tumor region of a target object and image data of a normal organ. Wherein, the dynamic image data refers to: CT, MRI and DWI scanning is carried out on a target object before the beginning of the radiotherapy, after the 5 th radiotherapy, after the 15 th radiotherapy, after the whole-course radiotherapy, 3 months after the whole-course radiotherapy and 6 months after the whole-course radiotherapy, and PET-CT scanning is carried out on the target object before the beginning of the radiotherapy and at the end of the whole-course radiotherapy, so that image data of tumors and normal organs are acquired.
In practical application, the multi-mode image histology feature data includes: volume data of tumor and positive lymph node, magnetic resonance data of tumor and positive lymph node, and SUV value of tumor and positive lymph node of the target object. The multi-mode image histology feature data is obtained based on dynamic image data extraction, and specifically refers to: tumor and positive lymph node volumes were determined before the start of radiotherapy, after the end of radiotherapy 5 th, after the end of radiotherapy 15 th, after the end of radiotherapy full, 3 months after the end of radiotherapy full and 6 months after the end of radiotherapy full, and the ADC values and SUV values of tumor and positive lymph nodes were measured.
In practical application, when the multi-mode image histology feature data is extracted and obtained based on the dynamic image data, the method specifically comprises the following steps: the method comprises the steps of carrying out position registration on dynamic image data of a target object in a radiotherapy period and a radiotherapy target area sketch, and then carrying out global standardization processing and spatial resolution unification processing to obtain a digital image; denoising and statistical equalization processing are carried out on the digital image, a region of interest (ROI) is segmented again, the structure of dynamic image data is constructed, and a multi-mode image histology characteristic dataset of dynamic image data in the whole period of radiotherapy is constructed by adopting a gray level co-occurrence matrix technology; and sequencing the importance degree of each histology feature in the multi-mode image histology feature data set to finish the mining and extraction of the multi-mode image histology features.
The global normalization process and the spatial resolution unification process refer to a process of converting data into a data with a mean value of 0 and a standard deviation of 1 for distribution. The denoising and statistical equalization processing means that the gray level histogram of the original image is changed from a gray level interval in a comparison set to be distributed in a wider gray level range, the image is subjected to nonlinear stretching, and the pixel values of the image are redistributed so that the number of pixels in a certain range is approximately the same. The region of interest refers to the bilateral parotid gland and the bilateral mandibular gland as the region of interest. The repartitioning refers to remapping to 0-255 according to a gray level histogram curve; voxels within the non-ROI region are set to a value of null (NaN). The gray level co-occurrence matrix technology is to combine different sequences of images differently and build a model by using a support vector machine (Support Vector Machines, SVM) classifier. For the combination of two or three sequences, the support vector machine model with key characteristics is trained based on a training group respectively, and then an ROC curve is drawn in a verification group to evaluate the model.
The method includes the steps that importance degrees of various group features in a multi-mode image group feature data set are ordered, namely, preprocessed data are used for calculating gray level co-occurrence matrixes in four directions for the ROI area of each layer of image, and then contrast, correlation, entropy, smoothness and second moment in the 4 directions of the gray level co-occurrence matrixes are calculated; the sum of the above-mentioned characteristic values of the 4 directions is regarded as the characteristic value of the image of this layer; the sum of the eigenvalues of all layers with delineated data is used as the tested output characteristic.
Step S20, after normalization processing is carried out on the characteristic data set, inputting the characteristic data set into a radiotherapy data processing model so as to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results; the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
In practical application, the full period of radiotherapy comprises before the beginning of radiotherapy, the end of radiotherapy for the 5 th time, the end of radiotherapy for the 15 th time, the end of radiotherapy for the whole course, 3 months after the end of radiotherapy for the whole course and 6 months after the end of radiotherapy for the whole course.
In practical application, the dynamically acquired characteristic data in the whole period of radiotherapy of the training object comprises:
in the whole period of radiotherapy of a training object, biological samples of the training object are collected and detected to obtain basic data and biological characteristic data of the training object;
in the whole period of radiotherapy of a training object, image scanning is carried out on the training object so as to obtain dynamic image data of the target part and normal parts around the target part; based on the dynamic image data, multi-mode image histology feature data are obtained.
In practical application, the image scanning is performed on the training object during the whole period of the radiotherapy of the training object to obtain dynamic image data of the target portion and the normal portion around the target portion, including:
in the whole period of radiotherapy of a training object, image scanning is carried out on each part of the training object so as to obtain dynamic image data of a target part and normal parts around the target part;
And integrating the dynamic image data of the target part and the normal part around the target part based on a super resolution technology and a super-cross-level filling technology to obtain effective dynamic image data.
In practical applications, the basic data includes: basic information data and tumor-related data of a training object; wherein the basic information data includes: age data, gender data, body mass index data, concomitant disease data, smoking history data, ECOG scoring data, PG-SGA scoring data, and NRS2002 scoring data; the tumor-related data includes: training tumor-related data of the subject; the tumor-related data includes primary tumor site data, invasive sub-anatomical structure data, pathology type data, TNM stage (UICC 8) th ) Data and primary tumor volume data.
In practical applications, the biometric data includes: EBV titer data, blood routine data, biochemical index data, cellular immunity data, C-reactive protein data, and hormone data for the training subjects.
The biological characteristic data is based on the biological sample of the training object which is dynamically acquired in the radiotherapy period and the biological characteristic data obtained by extracting from the biological sample. The dynamic collection of biological samples of training subjects refers to: dynamically collecting a tumor fresh tissue sample or wax block as a biological sample in a radiotherapy period; or collecting serum samples of the training subjects before the beginning of the radiotherapy, after the 5 th radiotherapy, after the 15 th radiotherapy, after the whole-course radiotherapy, 3 months after the whole-course radiotherapy and 6 months after the whole-course radiotherapy. Wherein, the biological characteristic data extracted from the biological sample means: dynamically measuring the peripheral blood biomarker before the beginning of the radiotherapy, after the 5 th radiotherapy, after the 15 th radiotherapy, after the whole-course radiotherapy, 3 months after the whole-course radiotherapy and 6 months after the whole-course radiotherapy; among other peripheral blood biomarkers include, but are not limited to, EBV titer, blood convention, biochemistry, cellular immunity, CRP, growth hormone, thyroid hormone.
In practical application, the dynamic image data includes: training image data of a tumor region of a subject and image data of a normal organ. Wherein, the dynamic image data refers to: CT, MRI and DWI scanning is carried out on a training object before the beginning of radiotherapy, the end of radiotherapy for the 5 th time, the end of radiotherapy for the 15 th time, the end of radiotherapy for the whole course, 3 months after the end of radiotherapy for the whole course and 6 months after the end of radiotherapy for the whole course, and PET-CT scanning is carried out on the training object before the beginning of radiotherapy and at the end of radiotherapy for the whole course, so that image data of tumors and normal organs are acquired.
In practical application, the multi-mode image histology feature data includes: volume data of tumor and positive lymph nodes, magnetic resonance data of tumor and positive lymph nodes, and SUV values of tumor and positive lymph nodes of the subject were trained. The multi-mode image histology feature data is obtained based on dynamic image data extraction, and specifically refers to: tumor and positive lymph node volumes were determined before the start of radiotherapy, after the end of radiotherapy 5 th, after the end of radiotherapy 15 th, after the end of radiotherapy full, 3 months after the end of radiotherapy full and 6 months after the end of radiotherapy full, and the ADC values and SUV values of tumor and positive lymph nodes were measured.
In practical application, when the multi-mode image histology feature data is extracted and obtained based on the dynamic image data, the method specifically comprises the following steps: the method comprises the steps of carrying out position registration on dynamic image data of a target object/training object in a radiotherapy period and a radiotherapy target area sketch, and then carrying out global standardization processing and spatial resolution unification processing to obtain a digital image; denoising and statistical equalization processing are carried out on the digital image, a region of interest (ROI) is segmented again, the structure of dynamic image data is constructed, and a multi-mode image histology characteristic dataset of dynamic image data in the whole period of radiotherapy is constructed by adopting various technologies such as wavelet decomposition, texture analysis, principal component analysis and the like; and sequencing the importance degree of each histology feature in the multi-mode image histology feature data set to finish the mining and extraction of the multi-mode image histology features.
It should be noted that, the dynamic image data of the target object/training object is obtained based on different machines, so that the different machines have great differences in terms of image acquisition, reconstruction algorithm, parameter setting and the like; even with the same apparatus, the scanning sequence, pulse sequence, imaging depth, and even the scanner person, etc., have an influence on the image quality. Therefore, in practical application, the embodiment of the application specifically limits the scanning machine and specific parameters, so as to reduce interference factors to the greatest extent, and the technical scheme described in the following specific embodiments can be specifically adopted. Most of the information in the high-dimensional data vector may be redundant information or noise, so in the embodiment of the application, the key feature vector of the data vector is extracted by a wavelet signal processing technology to reduce the dimension of the vector and remove the redundant information.
In addition, in the radiotherapy process of the target object/training object, various dynamic image data representing different physiological information are acquired through various imaging technologies. There are problems such as different image sizes, different spatial resolutions, different layer thicknesses, different numerical indexes, etc. among different images. Therefore, the embodiment of the application realizes the integration of dynamic image data by combining the super-resolution technology and the super-cross-level filling technology in the deep learning so as to establish an effective data structure mechanism and complete the fusion of multi-mode data to obtain the complementation and the deep mining of different-mode image information.
In addition, the target/training subjects will undergo a series of dynamic biochemical index detection, scale scoring and later follow-up during radiotherapy. The whole radiotherapy cycle can form a large amount of clinical data related to diseases and treatments. In the embodiment of the application, signals in different data forms are imported into the artificial neural network through the coupling data model, and the statistical score is adopted to reasonably normalize the related numerical values, so that the artificial intelligent model of the multi-source data can conveniently excavate potential functional characteristics. Thus solving the defect that the clinical problem is difficult to completely explain by a single data type from the point of view of histology.
In addition, by dynamically acquiring various data in the whole period of radiotherapy and extracting a large number of features from the data, medical big data which is constructed and trained by enough artificial intelligence deep learning algorithm is formed. The application realizes the effective fusion of the multi-mode image histology characteristics and the multi-dimensional clinical biological characteristics, and realizes the efficient and accurate mining of the data information by adopting deep learning. The trained deep learning model can reach the professional level of the advanced medical workers to a certain extent, and the output highly experienced result can reflect the accuracy of tumor radiotherapy curative effect prediction and organ-at-risk injury prediction, so that the excessive treatment condition of tumor radiotherapy is effectively reduced, the side effect in the radiotherapy process is lightened, and reliable guidance is provided for the establishment of an individualized accurate treatment scheme.
In practical application, the radiotherapy data processing result includes: a near-term efficacy prediction result and a far-term efficacy prediction result; wherein the recent efficacy prediction result includes: objective remission rate prediction results and disease control rate prediction results; the long-term efficacy prediction results comprise a progression-free lifetime prediction result, a remission duration prediction result and a total lifetime prediction result; the organ damage prediction result includes: EORTC (electronic monitoring system) scale-head and neck special scale information, acute toxicity grading standard-CTCAE v5.0 information, RTOG late radiation injury grading standard information, pain VRS scale information, brain cognitive function MMSE scale information and hearing-vision scale information of a target object.
In practical application, the embodiment of the application can also carry out clinical verification and model correction on the radiotherapy data after obtaining the processing result of the radiotherapy data so as to facilitate the convergence of the model in subsequent application. Namely: performing follow-up visit on a target object, performing radiation damage evaluation on the target object by adopting an artificial intelligence technology to obtain a verification data training set of the target object, and performing verification training on a radiotherapy data processing model by utilizing the verification data training set; by iterating the steps continuously, the consistency of clinical observation is used as the final convergence standard of the radiotherapy data processing model.
In summary, the application provides a multi-level, multi-factor and multi-time-point intelligent comprehensive radiotherapy data processing method covering clinical data, biological sample characteristics and multi-mode image histology characteristics of a target object. The discrimination rules of tumor control and radiation injury are found and verified by dynamically acquiring and acquiring relevant data and characteristics in the whole period of radiation therapy and fitting the relation between the change trend of the characteristics of the group science and the radiation therapy curative effect and the damage of the organs by using a deep learning model. Compared with the prior art, the application dynamically collects the related data of the radiotherapy in the whole period of the radiotherapy and carries out corresponding treatment so as to effectively predict the curative effect of the radiotherapy and the damage of organs under the noninvasive condition; in practical application, the prediction result obtained through the treatment provides a theoretical basis for the later-stage actual radiotherapy, so that a better curative effect can be obtained at a lower risk, and reliable technical guidance is provided for the establishment of an individualized accurate treatment scheme.
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
Step 1: acquiring a basic data set (also called a clinical data set) of a target object, for dynamically evaluating a radiotherapy curative effect and damage to a organs at risk in a radiotherapy period;
step 2: dynamically acquiring a clinical biological sample of the target subject during a radiotherapy cycle to extract a first set of biometric data (also referred to as clinical biometric) from the clinical biological sample;
step 3: acquiring dynamic image data of a target object in a radiotherapy period, and extracting and obtaining a multi-mode image histology characteristic data set (also called multi-mode image histology characteristic) from the dynamic image data;
step 4: integrating the clinical biological characteristics and the multi-mode image histology characteristics, and establishing a radiotherapy data processing model based on the integrated data;
step 5: and constructing a training set and a verification set based on the clinical data set, the clinical biological characteristics and the multi-modal influence group study characteristics so as to train, verify and correct the radiotherapy data processing model.
It should be noted that, in step S1, the target clinical data set includes target basic data and tumor-related data, and the target basic data includes, but is not limited to, target age, sex, body mass index, concomitant diseases, smoking history, ECOG score, PG-SGA score, NRS2002 score; tumor-related data include, but are not limited to, primary tumor site, invasive sub-anatomical structure, pathological type, TNM stage (UICC 8) th ) Primary tumor volume;
in step S1, dynamically evaluating the radiotherapy efficacy and the damage of the organs at risk in the radiotherapy period, namely dynamically evaluating the radiotherapy efficacy before the start of the radiotherapy, after the end of the 5 th radiotherapy, after the end of the 15 th radiotherapy, after the end of the whole-treatment radiotherapy, 3 months after the end of the whole-treatment radiotherapy and 6 months after the end of the whole-treatment radiotherapy, and evaluating the damage of the organs at risk by adopting the RECSIT1.1 standard and adopting the damage evaluation scale;
alternatively, when the method of the present application is applied to radiotherapy data processing of head and neck tumors, the lesion assessment scales include, but are not limited to, EORTC scales-head and neck dedicated scales, common acute toxicity grading criteria (CTCAE v 5.0), RTOG late radiation lesion grading criteria, pain VRS scales, brain cognitive function MMSE scales, and hearing and vision scales.
In step S2, a clinical biological sample dynamically collected during a radiotherapy period, including a tumor fresh tissue sample or a wax block, and a serum sample of a target subject is collected before the start of radiotherapy, after the end of radiotherapy at 5 th, after the end of radiotherapy at 15 th, after the end of radiotherapy in whole course, 3 months after the end of radiotherapy in whole course, and 6 months after the end of radiotherapy in whole course;
in step S2, the clinical biological characteristics extracted from the dynamically collected clinical biological sample refer to dynamic measurement of peripheral blood biomarkers before the start of radiotherapy, after the end of radiotherapy at time 5, after the end of radiotherapy at time 15, after the end of radiotherapy in full course, 3 months after the end of radiotherapy in full course and 6 months after the end of radiotherapy in full course; wherein peripheral blood biomarkers include, but are not limited to, EBV titer, blood convention, biochemistry, cellular immunity, CRP, growth hormone, thyroid hormone;
in step S3, the dynamic image data in the radiotherapy cycle refers to CT, MRI and DWI scanning of the target object before the start of radiotherapy, after the end of the 5 th radiotherapy, after the end of the 15 th radiotherapy, after the end of the whole-treatment radiotherapy, 3 months after the end of the whole-treatment radiotherapy and 6 months after the end of the whole-treatment radiotherapy, and PET-CT scanning of the target object before the start of radiotherapy and at the end of the whole-treatment radiotherapy, and collecting image data of tumors and normal organs;
In step S3, the multi-modal image histology features extracted from the dynamic image data include determining tumor and positive lymph node volumes before the start of radiotherapy, after the end of radiotherapy 5 th time, after the end of radiotherapy 15 th time, after the end of radiotherapy full treatment, 3 months after the end of radiotherapy full treatment and 6 months after the end of radiotherapy full treatment, and measuring ADC values and SUV values of tumor and positive lymph nodes;
in step S3, the extraction of the multi-modal image histology features includes the following steps:
s31, carrying out position registration on dynamic image data in a radiotherapy period of a target object and a radiotherapy target area sketch;
s32, carrying out global standardization and spatial resolution standardization on dynamic image data;
s33, denoising the digital image;
s34, digital image statistical equalization;
s35, re-segmentation of a region of interest (ROI) is carried out, and structure construction of dynamic image data is carried out;
s36, constructing a multi-mode image histology characteristic data set of dynamic image data in the whole period of radiotherapy by adopting a plurality of technologies such as wavelet decomposition, texture analysis, principal component analysis and the like; and sequencing the importance degree of each histology feature in the multi-mode image histology feature data set to finish the mining and extraction of the multi-mode image histology features.
In step S4, the super-resolution technique and the super-cross-level filling technique are adopted to integrate the dynamic image data in the radiotherapy period, and the cross-domain data association is adopted to integrate the clinical biological characteristics and the multi-mode image group characteristics;
Optionally, in step S4, a radiotherapy data processing model is used to predict the efficacy of radiotherapy. Predicting the radiotherapy curative effect comprises the steps of adopting an artificial intelligent deep learning model to intelligently calculate the integrated information of the clinical biological characteristics and the multi-mode image histology characteristics acquired in the radiotherapy period; in the training stage, model training is carried out by taking a dynamic evaluation standard of the radiotherapy efficacy of the target object in the radiotherapy period as a model convergence direction; and in the use stage of training completion, outputting a radiotherapy curative effect prediction result by the model.
Optionally, in step S4, a radiotherapy data processing model is used to predict the organ-at-risk injury. Predicting the damage of the organs comprises the steps of adopting an artificial intelligent deep learning model to intelligently calculate the integrated information of the clinical biological characteristics and the multi-mode image histology characteristics acquired in the radiotherapy period; in the training stage, model training is carried out by taking a target object organ-at-risk damage evaluation standard in a radiotherapy period as a model convergence direction; and in the use stage of training completion, outputting a damage prediction result of the organs at risk by the model.
In step S5, the clinical verification and model correction includes:
performing follow-up visit on a target object, performing radiation damage evaluation on the target object by adopting an artificial intelligence technology to obtain a verification data training set of the target object, and performing verification training on a radiotherapy data processing model by utilizing the verification data training set; by iterating the steps continuously, the consistency of clinical observation is used as the final convergence standard of the radiotherapy data processing model.
Example 2
Step 1: acquiring a basic data set (also called a clinical data set) of a target object, for dynamically evaluating a radiotherapy curative effect and damage to a organs at risk in a radiotherapy period;
step 2: dynamically acquiring a clinical biological sample of the target subject during a radiotherapy cycle to extract a first set of biometric data (also referred to as clinical biometric) from the clinical biological sample;
step 3: acquiring dynamic image data of a target object in a radiotherapy period, and extracting and obtaining a multi-mode image histology characteristic data set (also called multi-mode image histology characteristic) from the dynamic image data;
step 4: integrating the clinical biological characteristics and the multi-mode image histology characteristics, and establishing a radiotherapy data processing model based on the integrated data;
step 5: and constructing a training set and a verification set based on the clinical data set, the clinical biological characteristics and the multi-modal influence group study characteristics so as to train, verify and correct the radiotherapy data processing model.
The clinical data set comprises target object basic data and tumor related data; target subject profile includes, but is not limited to, target subject age, gender, body mass index, concomitant disease, smoking history, ECOG score, PG-SGA score, NRS2002 score; tumor-related data include, but are not limited to, primary tumor site, invasive sub-anatomical structure, pathological type, TNM stage (UICC 8) th ) Primary tumor volume;
optionally, in step S1, the target subject clinical data set further comprises treatment regimen information; treatment regimen information includes chemotherapy regimen and dose, radiotherapy target volume delineation principles, radiotherapy target volume dose and normal organ dose limits.
Optionally, when the present application is applied to radiotherapy data processing of head and neck tumors, in step S1, the target clinical data set further includes target tumor and organ-at-risk dosimetry data including, but not limited to, measurement of DVH parameters (Dmean, D50, V5, V10, V15, V20, V25, V30, V35, V40, V45, V50) of brain stem, spinal cord, optic nerve, optic cross, temporal lobe, pituitary, mandible, temporomandibular joint, crystalline, eyeball, brachial plexus, parotid, submaxillary gland, oral cavity, cochlea, larynx, pharyngeal contractile, esophagus, trachea, thyroid;
in step S1, the dynamic evaluation of the radiotherapy curative effect and the crisis organ injury in the radiotherapy period refers to the dynamic evaluation of the radiotherapy curative effect by adopting the RECSIT1.1 standard before the start of the radiotherapy, the end of the 5 th radiotherapy, the end of the 15 th radiotherapy, the end of the whole-course radiotherapy, 3 months after the end of the whole-course radiotherapy and 6 months after the end of the whole-course radiotherapy, and the evaluation of the crisis organ injury by adopting the injury evaluation scale.
Further, dynamic evaluation of radiotherapy efficacy includes recent efficacy evaluation and long-term efficacy evaluation; wherein, the Objective Remission Rate (ORR) of recent efficacy assessment is the percentage of Complete Remission (CR) +partial remission (PR); disease Control Rate (DCR) is defined as the percentage of Complete Remission (CR) +partial remission (PR) +disease Stabilization (SD); the long-term efficacy assessment included Progression Free Survival (PFS), duration of remission (DOR), total survival (OS).
Optionally, dynamically assessing the organ-at-risk injury includes screening for high risk factors associated with the organ-at-risk injury of the target subject following radiation therapy: and analyzing the correlation between the basic characteristics, the test result, the dosimetry correlation characteristics of tumors and organs at risk, the treatment scheme and the like of the target object and the damage of the organs at risk after treatment by adopting single-factor Logistic regression analysis, searching possible high-risk factors, performing multi-factor analysis on the possible high-risk factors by adopting a Binary Logistic forward stepwise regression method, and screening out independent prediction factors with statistical significance.
Alternatively, when the present application is applied to radiotherapy data processing of head and neck tumors, the lesion assessment scales include, but are not limited to, EORTC scales-head and neck specific scales, common acute toxicity grading criteria (CTCAE v 5.0), RTOG late radiation injury grading criteria, pain VRS scales, brain cognitive function MMSE scales, and hearing and vision scales.
In step S2, a clinical biological sample dynamically collected during a radiotherapy period, including a tumor fresh tissue sample or a wax block, and a serum sample of a target subject is collected before the start of radiotherapy, after the end of radiotherapy at 5 th, after the end of radiotherapy at 15 th, after the end of radiotherapy in whole course, 3 months after the end of radiotherapy in whole course, and 6 months after the end of radiotherapy in whole course;
in step S2, the clinical biological characteristics extracted from the dynamically collected clinical biological sample refer to the tumor and positive lymph node volume, the ADC value and SUV value of the tumor and positive lymph node, and the peripheral blood biomarker, before the start of radiotherapy, after the end of radiotherapy at time 5, after the end of radiotherapy at time 15, after the end of radiotherapy in whole course, 3 months after the end of radiotherapy in whole course, and 6 months after the end of radiotherapy in whole course; wherein peripheral blood biomarkers include, but are not limited to, EBV titer, blood convention, biochemistry, cellular immunity, CRP, growth hormone, thyroid hormone;
further, the step of extracting peripheral blood biomarkers from a dynamically collected clinical biological sample comprises: collecting target subject fasting venous blood, centrifuging for 12min at 3000r/min with a centrifugal radius of 15cm, separating to obtain serum, and storing at-80deg.C; flow cytometry was used to detect dynamic changes in the numbers of peripheral blood neutrophils, lymphocytes, cd3+ T lymphocytes, cd4+ T lymphocytes, cd8+ T lymphocytes.
Optionally, when the application is applied to radiotherapy data processing of head and neck tumors, extracting clinical biological characteristics from a dynamically acquired clinical biological sample further comprises extracting pathological characteristics of the head and neck tumors, including extracting tumor tissue slices: collecting paraffin samples of tissue before treatment of head and neck tumor target object, continuously slicing with thickness of 3 μm, baking at 60deg.C for > 2 hr, dewaxing in xylene for 3 times (10 min/time), hydrating with gradient ethanol, and washing with distilled water for 5min; extracting immunohistochemical characteristics: immunohistochemical detection was performed on an automatic staining platform using P16 antibody, EGFR antibody, VEGFR antibody, lysyl oxidase-like protein antibody.
In step S3, the dynamic image data in the radiotherapy cycle refers to CT, MRI, and DWI scanning of the target object before the start of radiotherapy, after the end of 5 th radiotherapy, after the end of 15 th radiotherapy, after the end of full-treatment radiotherapy, 3 months after the end of full-treatment radiotherapy, and 6 months after the end of full-treatment radiotherapy, and PET-CT scanning of the target object before the start of radiotherapy and at the end of full-treatment radiotherapy, and collecting image data of tumor and normal organs.
Optionally, when the application is applied to radiotherapy data processing of head and neck tumors, the scanning parameters of dynamic image data in a radiotherapy period are defined as follows:
CT scanning parameters: CT scanning adopts Philips BigBore, and the canthus line is perpendicular to the table top; after the leveling scanning, selecting the lesion to be added with multi-layer enhanced scanning. The contrast agent is iohexol and the enhanced scan starts a first layer scan at 65s after the start of the injection of the contrast agent. The scanning layer thickness and the layer spacing are 3mm;
MRI scan parameters: MRI scanning magnetic resonance imaging scanning was performed using GE3.0T MRI and eight-channel head and neck combined coils. All target subjects were subjected to conventional MRI and DWI examinations. Conventional MRI includes axial, coronal, and sagittal positions T1WI, T2WI. The scanning range is up to the top of the cranium and down to 2cm below the collarbone. With spin echo planar echo sequence (SE-EPI), in order to minimize the effect of diffusion anisotropy, diffusion sensitive gradients are applied in three directions X, Y, Z;
DWI scan parameters: TR6000ms, TE 90ms, layer thickness 5mm, interval 1mm, matrix 128X128, field 24X24, excitation times 2 times, diffusion sensitivity factor 0, 500, 800s/mm2, scan time 3 min 43 s; because the resolution of the ADC image is lower, the boundary of the anatomical position of the tissue organ is poor, errors are easy to generate when a region of interest (ROI) is marked, in order to reduce the errors, the positioning scanning range, the layer thickness and the interval are consistent with the DWI before the DWI is firstly performed by T2WI positioning scanning, so that the images of the ADC image can be overlapped and fused on the ADC image, and the positioning and the measurement of the gland are more accurate. All target objects scan the line in a static state and DWI scan;
PET-CT imaging: the target subjects were checked for fasted on the same day for >6h, and height, body mass and blood glucose were measured before the check. After the target object is intravenous injected with 18F-FDG 3.7-4.4MBq/kg, the rest is quietly performed for 40-60min, and limb movement and acousto-optic stimulation are avoided. The target object is supine on the examination bed after urine is drained before PET-CT examination, the arms are lifted, and the scanning range is from the top of the head to the upper sections of femur on both sides. Firstly, whole body CT scanning is performed, the scanning parameters are that the voltage is 120kV, the current is 160-220mAs, the layer thickness is 5mm, and then PET scanning is performed. And carrying out image reconstruction on the PET data through an iterative reconstruction method after CT attenuation correction, and finally obtaining PET tomographic images of transverse position, coronal position and sagittal position and PET-CT fusion images.
In step S3, the multi-modal image histology features extracted from the dynamic image data include determining tumor and positive lymph node volumes before the start of radiotherapy, after the end of radiotherapy 5 th time, after the end of radiotherapy 15 th time, after the end of radiotherapy full treatment, 3 months after the end of radiotherapy full treatment and 6 months after the end of radiotherapy full treatment, and measuring ADC values and SUV values of tumor and positive lymph nodes;
further, the extraction of the multi-modal image histology features includes the steps of:
s31, carrying out position registration on dynamic image data in a radiotherapy period of a target object and a radiotherapy target area sketch;
S32, carrying out global standardization and spatial resolution standardization on dynamic image data;
s33, denoising the digital image;
s34, digital image statistical equalization;
s35, re-segmentation of a region of interest (ROI) is carried out, and structure construction of dynamic image data is carried out;
s36, constructing a multi-mode image histology characteristic data set of dynamic image data in the whole period of radiotherapy by adopting a plurality of technologies such as wavelet decomposition, texture analysis, principal component analysis and the like; and sequencing the importance degree of each histology feature in the multi-mode image histology feature data set to finish the mining and extraction of the multi-mode image histology features.
In step S4, the super-resolution technique and the super-cross-level filling technique are adopted to integrate the dynamic image data in the radiotherapy period, and the cross-domain data association is adopted to integrate the clinical biological characteristics and the multi-mode image group characteristics;
optionally, in step S4, clinical biological features and multi-mode image histology features in different data forms are imported into the artificial neural network through the coupled data model, and normalization of relevant values is performed by adopting statistical scores, so that mining of potential functional features of the artificial intelligent model of the multi-source data is completed;
Optionally, in step S4, a radiotherapy data processing model is used to predict the efficacy of radiotherapy. Predicting the radiotherapy curative effect comprises the steps of adopting an artificial intelligent deep learning model to intelligently calculate the integrated information of the clinical biological characteristics and the multi-mode image histology characteristics acquired in the radiotherapy period; in the training stage, model training is carried out by taking a dynamic evaluation standard of the radiotherapy efficacy of the target object in the radiotherapy period as a model convergence direction; and in the use stage of training completion, outputting a radiotherapy curative effect prediction result by the model.
Optionally, in step S4, a radiotherapy data processing model is used to predict the organ-at-risk injury. Predicting the damage of the organs comprises the steps of adopting an artificial intelligent deep learning model to intelligently calculate the integrated information of the clinical biological characteristics and the multi-mode image histology characteristics acquired in the radiotherapy period; in the training stage, model training is carried out by taking a target object organ-at-risk damage evaluation standard in a radiotherapy period as a model convergence direction; and in the use stage of training completion, outputting a damage prediction result of the organs at risk by the model.
In step S5, the clinical verification and model correction includes:
performing follow-up visit on a target object, performing radiation damage evaluation on the target object by adopting an artificial intelligence technology to obtain a verification data training set of the target object, and performing verification training on a radiotherapy data processing model by utilizing the verification data training set; by iterating the steps continuously, the consistency of clinical observation is used as the final convergence standard of the radiotherapy data processing model.
Example 3
Step S1, dynamically collecting physiological detection data of a target object in a radiotherapy period, and extracting multidimensional metabolic characteristics from the dynamically collected physiological detection data; dynamically evaluating the curative effect of the radiotherapy and the damage of the organs at risk in a radiotherapy period;
step S2, dynamically collecting clinical biological samples of a target object in a radiotherapy period, and extracting clinical biological characteristics from the dynamically collected clinical biological samples;
s3, acquiring dynamic image data in a radiotherapy period of a target object, and extracting multi-mode image histology characteristics from the dynamic image data;
s4, integrating clinical biological characteristics and multi-mode image histology characteristics, and establishing a radiotherapy data processing model based on the multi-mode image histology;
and S5, constructing multi-mode histology data of the clinical data set, the clinical biological characteristics and the multi-mode influence histology characteristics, and performing clinical verification and model correction based on the radiotherapy data processing model in the step S4 to guide the personalized treatment of the target object.
In step S1, the step of extracting the multidimensional metabolic feature from the physiological test data includes:
s11, checking and sorting physiological detection data of the target objects in the group, and listing the maximum common data unit;
S12, introducing technologies such as metabonomics, proteomics and the like, improving the metabolite detection dimension of the target object, and expanding an effective data set;
s13, carrying out normalization arrangement on the data;
s14, screening and eliminating invalid data such as null data, data with a super threshold range and abnormal data;
s15, taking the target object organ-at-risk injury evaluation standard as a model convergence direction, performing artificial neural network training, and screening valuable metabolic indexes.
Optionally, in step S4, the radiotherapy data processing model is used for predicting an organ-at-risk injury, comprising: carrying out data structure reconstruction on multidimensional influence histology features and multidimensional metabolism features according to different stages of radiotherapy; taking DenseNet as a network prototype, adding a data embedding layer, and carrying out input fusion input of different structures; taking the previous stage of radiotherapy as model input, taking the latter stage as model output target, taking the staged damage evaluation result of the organs at risk as control variable, and carrying out network training; and taking the full-stage fusion data as model input, taking the final secondary damage evaluation result as model output, and carrying out damage evaluation training of the radiotherapy data processing model.
Except for the above technical matters, the technical solution provided in embodiment 3 is basically the same as the technical solution described in embodiment 1, and will not be described in detail here.
Referring to fig. 3, based on the same inventive concept, the embodiment of the present application provides that: a radiotherapy data processing apparatus, comprising:
the information acquisition module is used for acquiring a characteristic data set of the target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set;
the prediction module is used for inputting the feature data set into a radiotherapy data processing model after normalization processing so as to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results; the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
It should be noted that, each module in the radiotherapy data processing apparatus in this embodiment corresponds to each step in the radiotherapy data processing method in the foregoing embodiment one by one, so the specific implementation manner and the achieved technical effect of this embodiment may refer to the implementation manner of the foregoing radiotherapy data processing method, and will not be described herein again.
Furthermore, in an embodiment, the present application also provides an electronic device, where the electronic device includes a processor, a memory, and an acquisition computer program stored in the memory, where the acquisition computer program is executed by the processor to implement the steps of the method in the foregoing embodiment.
Furthermore, in an embodiment, the present application also provides an acquisition machine storage medium, on which an acquisition machine program is stored, which when executed by a processor, implements the steps of the method in the previous embodiment.
In some embodiments, the acquisition machine readable storage medium may be FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM, among others; but may be a variety of devices including one or any combination of the above memories. The acquisition machine may be various acquisition devices including intelligent terminals and servers.
In some embodiments, the executable instructions may be in the form of programs, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and they may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in an acquisition environment.
As an example, the executable instructions may, but need not, correspond to files in a file system, may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a hypertext markup language (HTML, hyper Text Markup Language) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
As an example, the executable instructions may be deployed to be executed on one acquisition device or on multiple acquisition devices located at one site, or, alternatively, on multiple acquisition devices distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. read-only memory/random-access memory, magnetic disk, optical disk), comprising instructions for causing a multimedia terminal device (which may be a mobile phone, an acquisition machine, a television receiver, or a network device, etc.) to perform the method according to the embodiments of the present application.
The foregoing disclosure is merely illustrative of some embodiments of the present application and it is not to be construed as limiting the scope of the application, as a person of ordinary skill in the art will appreciate that all or part of the above-described embodiments may be practiced with equivalent variations which fall within the scope of the application as defined in the appended claims.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A method for processing radiotherapy data, comprising the steps of:
acquiring a characteristic data set of a target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set;
after the feature data set is subjected to normalization processing, inputting the feature data set into a radiotherapy data processing model to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results;
the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
2. The method of claim 1, wherein the full cycle of radiation therapy comprises before the beginning of radiation therapy, after the end of radiation therapy at time 5, after the end of radiation therapy at time 15, after the end of radiation therapy at full treatment period, 3 months after the end of radiation therapy at full treatment period, and 6 months after the end of radiation therapy at full treatment period.
3. The radiotherapy data processing method according to claim 2, wherein the dynamically acquired characteristic data in the whole period of radiotherapy of the training subject comprises:
in the whole period of radiotherapy of a training object, biological samples of the training object are collected and detected to obtain basic data and biological characteristic data of the training object;
in the whole period of radiotherapy of a training object, image scanning is carried out on the training object so as to obtain dynamic image data of the target part and normal parts around the target part; based on the dynamic image data, multi-mode image histology feature data are obtained.
4. The method of claim 3, wherein the step of performing image scanning on the training subject during the whole period of the radiotherapy of the training subject to obtain dynamic image data of the target region and normal regions around the target region comprises:
In the whole period of radiotherapy of a training object, image scanning is carried out on each part of the training object so as to obtain dynamic image data of a target part and normal parts around the target part;
and integrating the dynamic image data of the target part and the normal part around the target part based on a super resolution technology and a super-cross-level filling technology to obtain effective dynamic image data.
5. The radiotherapy data processing method of claim 3, wherein the base data comprises: basic information data and tumor-related data of a training object; wherein the basic information data includes: age data, gender data, body mass index data, concomitant disease data, smoking history data, ECOG scoring data, PG-SGA scoring data, and NRS2002 scoring data; the tumor-related data includes: training tumor-related data of the subject; the tumor-related data comprises primary tumor site data, invasive sub-anatomical structure data, pathology type data, TNM stage-UICC 8 th Data and primary tumor volume data.
6. The radiotherapy data processing method of claim 3, wherein the biometric data comprises: EBV titer data, blood routine data, biochemical index data, cellular immunity data, C-reactive protein data, and hormone data of the training subjects;
The dynamic image data includes: training image data of a tumor area of a subject and image data of a normal organ;
the multi-modal image histology feature data comprises: volume data of tumor and positive lymph nodes, magnetic resonance data of tumor and positive lymph nodes, and SUV values of tumor and positive lymph nodes of the subject were trained.
7. The radiotherapy data processing method according to claim 3, wherein the radiotherapy data processing result comprises: a near-term efficacy prediction result and a far-term efficacy prediction result; wherein the recent efficacy prediction result includes: objective remission rate prediction results and disease control rate prediction results; the long-term efficacy prediction results comprise a progression-free lifetime prediction result, a remission duration prediction result and a total lifetime prediction result;
the organ damage prediction result includes: EORTC (electronic monitoring system) scale-head and neck special scale information, acute toxicity grading standard-CTCAE v5.0 information, RTOG late radiation injury grading standard information, pain VRS scale information, brain cognitive function MMSE scale information and hearing-vision scale information of a target object.
8. A radiotherapy data processing apparatus, comprising:
The information acquisition module is used for acquiring a characteristic data set of the target object; wherein the feature data set comprises a base data set, a first biological feature data set and a multi-modal image histology feature data set;
the prediction module is used for inputting the feature data set into a radiotherapy data processing model after normalization processing so as to obtain a prediction result; wherein the prediction results comprise radiotherapy data processing results and organ damage prediction results; the radiotherapy data processing model is obtained by training a training data set, and a radiotherapy curative effect dynamic evaluation standard in the whole period of radiotherapy is taken as a model convergence direction; the training data set comprises various feature data which are dynamically acquired in the whole period of radiotherapy of a training object, wherein the feature data comprise basic data, first biological feature data and multi-mode image histology feature data.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the radiotherapy data processing method according to any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, the computer program being executable by a processor to perform the radiotherapy data processing method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310738298.5A CN116721761A (en) | 2023-06-20 | 2023-06-20 | Radiotherapy data processing method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310738298.5A CN116721761A (en) | 2023-06-20 | 2023-06-20 | Radiotherapy data processing method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116721761A true CN116721761A (en) | 2023-09-08 |
Family
ID=87875015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310738298.5A Pending CN116721761A (en) | 2023-06-20 | 2023-06-20 | Radiotherapy data processing method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116721761A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117238484A (en) * | 2023-11-13 | 2023-12-15 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Intelligent diagnosis and treatment device, electronic equipment and storage medium |
| CN117238488A (en) * | 2023-11-16 | 2023-12-15 | 四川省肿瘤医院 | Rectal cancer radiotherapy reaction analysis method and system based on image analysis |
| CN117274235A (en) * | 2023-11-09 | 2023-12-22 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Determination device for radiotherapy curative effect, electronic equipment and storage medium |
| CN117408905A (en) * | 2023-12-08 | 2024-01-16 | 四川省肿瘤医院 | Medical image fusion method based on multi-modal feature extraction |
-
2023
- 2023-06-20 CN CN202310738298.5A patent/CN116721761A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274235A (en) * | 2023-11-09 | 2023-12-22 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Determination device for radiotherapy curative effect, electronic equipment and storage medium |
| CN117274235B (en) * | 2023-11-09 | 2024-02-27 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Determination device for radiotherapy curative effect, electronic equipment and storage medium |
| CN117238484A (en) * | 2023-11-13 | 2023-12-15 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Intelligent diagnosis and treatment device, electronic equipment and storage medium |
| CN117238484B (en) * | 2023-11-13 | 2024-02-27 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Intelligent diagnosis and treatment device, electronic equipment and storage medium |
| CN117238488A (en) * | 2023-11-16 | 2023-12-15 | 四川省肿瘤医院 | Rectal cancer radiotherapy reaction analysis method and system based on image analysis |
| CN117238488B (en) * | 2023-11-16 | 2024-01-30 | 四川省肿瘤医院 | Rectal cancer radiotherapy reaction analysis method and system based on image analysis |
| CN117408905A (en) * | 2023-12-08 | 2024-01-16 | 四川省肿瘤医院 | Medical image fusion method based on multi-modal feature extraction |
| CN117408905B (en) * | 2023-12-08 | 2024-02-13 | 四川省肿瘤医院 | Medical image fusion method based on multi-modal feature extraction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116721761A (en) | Radiotherapy data processing method, system, equipment and medium | |
| US11023785B2 (en) | Sparse MRI data collection and classification using machine learning | |
| CN109741346A (en) | Area-of-interest exacting method, device, equipment and storage medium | |
| CN109938764A (en) | A kind of adaptive multiple location scan imaging method and its system based on deep learning | |
| US11615535B2 (en) | Systems and methods for image processing | |
| CN108629785B (en) | Three-dimensional magnetic resonance pancreas image segmentation method based on self-learning | |
| CN106096636A (en) | A kind of Advancement Type mild cognition impairment recognition methods based on neuroimaging | |
| CN109919254B (en) | Breast density classification method, system, readable storage medium and computer device | |
| CN108257132A (en) | A kind of method of the CT image quality measures based on machine learning | |
| CN109215040B (en) | Breast tumor segmentation method based on multi-scale weighted learning | |
| WO2018045066A1 (en) | Quantitative differentiation of inflammation from solid tumors, heart and nerve injury | |
| CN108765368A (en) | MRI lesion locations detection method, device, computer equipment and storage medium | |
| DE102017221830A1 (en) | Characterization of a disruptive body within an examination object based on a medical image data set | |
| CN109124660A (en) | The postoperative risk checking method of gastrointestinal stromal tumor and system based on deep learning | |
| CN112839577A (en) | Method for adjusting brain function connection correlation value, system for adjusting brain function connection correlation value, method for coordinating brain activity classifier, system for coordinating brain activity classifier, and brain activity biomarker system | |
| CN110874860A (en) | Target extraction method of symmetric supervision model based on mixed loss function | |
| CN116784820A (en) | Brain function network construction method and system based on seed point connection | |
| CN110021022A (en) | A kind of thyroid gland nuclear medical image diagnostic method based on deep learning | |
| De Nunzio et al. | Robust intensity standardization in brain magnetic resonance images | |
| Yo et al. | Quantifying brain connectivity: a comparative tractography study | |
| US10964074B2 (en) | System for harmonizing medical image presentation | |
| CN113989551A (en) | Alzheimer disease classification method based on improved ResNet network | |
| TW201941220A (en) | Diagnosis support device, program, learned model, and learning device | |
| Koch et al. | Evaluating reproducibility and subject-specificity of microstructure-informed connectivity | |
| WO2020056196A1 (en) | Fully automated personalized body composition profile |
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 |