CN105653858A - Image omics based lesion tissue auxiliary prognosis system and method - Google Patents
Image omics based lesion tissue auxiliary prognosis system and method Download PDFInfo
- Publication number
- CN105653858A CN105653858A CN201511021413.9A CN201511021413A CN105653858A CN 105653858 A CN105653858 A CN 105653858A CN 201511021413 A CN201511021413 A CN 201511021413A CN 105653858 A CN105653858 A CN 105653858A
- Authority
- CN
- China
- Prior art keywords
- lesion
- data
- image
- prediction
- radiomics
- 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
- 230000003902 lesion Effects 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004393 prognosis Methods 0.000 title description 21
- 230000011218 segmentation Effects 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000004083 survival effect Effects 0.000 claims abstract description 22
- 238000012360 testing method Methods 0.000 claims abstract description 22
- 206010064571 Gene mutation Diseases 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000010827 pathological analysis Methods 0.000 claims abstract description 10
- 210000001519 tissue Anatomy 0.000 claims description 32
- 238000003384 imaging method Methods 0.000 claims description 11
- 206010028980 Neoplasm Diseases 0.000 claims description 10
- 230000007170 pathology Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 4
- 238000001574 biopsy Methods 0.000 claims description 3
- 238000003759 clinical diagnosis Methods 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 210000005228 liver tissue Anatomy 0.000 claims description 2
- 210000004072 lung Anatomy 0.000 claims description 2
- 210000005084 renal tissue Anatomy 0.000 claims description 2
- 201000010536 head and neck cancer Diseases 0.000 description 12
- 208000014829 head and neck neoplasm Diseases 0.000 description 12
- 238000003745 diagnosis Methods 0.000 description 6
- 230000001575 pathological effect Effects 0.000 description 5
- 230000007119 pathological manifestation Effects 0.000 description 5
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 238000004445 quantitative analysis Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009534 blood test Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
Classifications
-
- G06F19/34—
-
- G06F19/321—
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
一种基于影像组学的病变组织辅助预测系统及方法，该方法包括：从大数据量的患者影像数据库中，采用自动或手动的分割方法提取病变部位的影像数据；根据所述病变部位影像的分割结果，分别提取各病变部位的影像表型特征，完成所述患者影像数据库内所有病变部位影像数据的特征提取；基于各病变部位的特征数据和临床信息数据，对所述患者影像数据库中数据进行训练数据集和测试数据集的分类，采用计算机自动识别方法在所述训练数据集进行病变部位的病理分析、临床分期分析、基因突变预测以及生存时间的预测，并在所述测试数据集中实现验证。本发明方法可以对特定的个体分别进行定性以及定量的预测分析，提供可信的预测与分析结果。
A system and method for assisted prediction of diseased tissue based on radiomics, the method comprising: extracting image data of a lesion from a patient image database with a large amount of data using an automatic or manual segmentation method; Segment the results, extract the image phenotype features of each lesion, and complete the feature extraction of all lesion image data in the patient image database; based on the feature data and clinical information data of each lesion, the data in the patient image database Carry out the classification of the training data set and the test data set, adopt the computer automatic recognition method to carry out pathological analysis, clinical staging analysis, gene mutation prediction and survival time prediction of the lesion in the said training data set, and realize in the said test data set verify. The method of the invention can perform qualitative and quantitative prediction analysis on specific individuals respectively, and provide credible prediction and analysis results.
Description
技术领域technical field
本发明涉及疾病诊断辅助技术领域，更具体地涉及一种基于影像组学的病变组织辅助预后系统和方法。The present invention relates to the technical field of disease diagnosis assistance, and more particularly to a system and method for assisting prognosis of diseased tissue based on radiomics.
背景技术Background technique
医学影像作为一种无创的肿瘤早期诊断方法，已被广泛应用于各类癌症的辅助诊断中。目前使用影像信息进行临床辅助诊断往往依靠医生的主观经验，通过影像反映出的病人疾病影像特征给予相应诊断。然而医学影像中仍有待开发的揭示病变分期和预后的有价值信息。As a non-invasive method for early diagnosis of tumors, medical imaging has been widely used in the auxiliary diagnosis of various cancers. At present, the use of image information for clinical auxiliary diagnosis often relies on the subjective experience of doctors, and the corresponding diagnosis is given through the image characteristics of the patient's disease reflected in the image. However, there is still untapped valuable information in medical imaging to reveal lesion staging and prognosis.
不同类型的肿瘤由于其病理特性在影像上的表现迥异，不同的肿瘤影像特征也预示着治疗方式完全不同，并直接影响着预后。目前通过影像手段实现肿瘤的预判都需要医生根据其主观的临床经验、病理切片以及血检等进行详细的检测得到临床检测结果。然而，基于现有的医学影像特征分析研究，某些多维纹理特征能够准确反映病变组织的病理学信息，对于实现个体化医疗具有重要的研究价值，所以一个完备的特征库对于后续关键特征筛选能够提供更全面的数据支持。因此采用计算机方法辅助完成病变的预测分析并给出可信的建议具有极高的实用意义。Different types of tumors have different imaging features due to their pathological characteristics, and different tumor imaging features also indicate completely different treatment methods, which directly affect the prognosis. At present, the prediction of tumors through imaging means requires doctors to conduct detailed tests based on their subjective clinical experience, pathological sections, and blood tests to obtain clinical test results. However, based on the existing medical image feature analysis research, some multi-dimensional texture features can accurately reflect the pathological information of diseased tissues, which has important research value for the realization of individualized medicine, so a complete feature library can be used for subsequent key feature screening. Provide more comprehensive data support. Therefore, it is of great practical significance to use computer methods to assist in the prediction and analysis of lesions and to give credible suggestions.
发明内容Contents of the invention
针对上述技术问题，本发明的目的在于提供一种基于影像组学的病变组织辅助预后系统和方法。In view of the above technical problems, the object of the present invention is to provide a system and method for assisting prognosis of diseased tissue based on radiomics.
为了实现上述目的，作为本发明的一个方面，本发明提供了一种基于影像组学的病变组织辅助预后方法，包括：In order to achieve the above object, as an aspect of the present invention, the present invention provides a radiomics-based assisted prognosis method for diseased tissue, including:
步骤S101，从大数据量的患者影像数据库中，采用自动或手动的分割方法提取病变部位的影像数据；Step S101, extracting the image data of the lesion from the patient image database with a large amount of data by automatic or manual segmentation;
步骤S102，根据所述病变部位影像的分割结果，分别提取各病变部位的影像表型特征，完成所述患者影像数据库内所有病变部位影像数据的特征提取；Step S102, according to the segmentation results of the lesion images, extract the image phenotype features of each lesion respectively, and complete the feature extraction of all lesion image data in the patient image database;
步骤S103，基于各病变部位的特征数据和临床信息数据，对所述患者影像数据库中数据进行训练数据集和测试数据集的分类，采用计算机自动识别方法在所述训练数据集进行病变部位的病理分析、临床分期分析、基因突变预测以及生存时间的预测，并在所述测试数据集中实现验证。Step S103, based on the characteristic data and clinical information data of each lesion, classify the data in the patient image database into a training data set and a test data set, and use computer automatic identification method to perform pathological diagnosis of the lesion in the training data set. Analysis, clinical stage analysis, gene mutation prediction and prediction of survival time, and realize verification in the test data set.
作为本发明的另一个方面，本发明还提供了一种基于影像组学的病变组织辅助预测系统，其特征在于，包括：As another aspect of the present invention, the present invention also provides a radiomics-based auxiliary prediction system for diseased tissue, which is characterized in that it includes:
从大数据量的患者影像数据库中，采用自动或手动的分割方法提取病变部位的影像数据的单元；From a patient image database with a large amount of data, an automatic or manual segmentation method is used to extract the image data unit of the lesion;
根据所述病变部位影像的分割结果，分别提取各病变部位的影像表型特征，完成所述患者影像数据库内所有病变部位影像数据的特征提取的单元；Extracting image phenotype features of each lesion according to the segmentation result of the lesion image, and completing the feature extraction unit of all lesion image data in the patient image database;
基于各病变部位的特征数据和临床信息数据，对所述患者影像数据库中数据进行训练数据集和测试数据集的分类，采用计算机自动识别方法在所述训练数据集进行病变部位的病理分析、临床分期分析、基因突变预测以及生存时间的预测，并在所述测试数据集中实现验证的单元。Based on the characteristic data and clinical information data of each lesion, classify the data in the patient image database into training data sets and test data sets, and use computer automatic recognition methods to perform pathological analysis and clinical diagnosis of lesion in the training data set. Staging analysis, gene mutation prediction, and survival time prediction, and implement a unit of validation in the test data set.
基于上述技术方案可知，本发明的病变组织辅助预后方法能够根据临床影像数据的分割结果，建立病变影像表型特征库，采用计算机自动识别和分别方法将临床病例数据分为训练数据集和测试数据集，在训练数据集里对各类病变的不同病理表现、临床分期、基因突变类型所对应的特征库予以分别训练，从原始表型特征库中计算各个特征的预测、预后贡献度，选择能够正确识别不同病理表现、不同临床分期和不同基因突变类型的关键特征，并使用所获取的关键特征对病变组织进行病理表现、临床分期和基因突变类型和生存期的预测，对特定的个体分别进行定性以及定量的预测分析，提供可信的预测与分析结果。Based on the above technical solution, it can be known that the diseased tissue assisted prognosis method of the present invention can establish a lesion image phenotype feature library according to the segmentation results of clinical image data, and use computer automatic identification and separation methods to divide clinical case data into training data sets and test data In the training data set, the feature libraries corresponding to different pathological manifestations, clinical stages, and gene mutation types of various lesions are trained separately, and the prediction and prognosis contribution of each feature are calculated from the original phenotypic feature library. Correctly identify the key features of different pathological manifestations, different clinical stages and different gene mutation types, and use the acquired key features to predict the pathological manifestations, clinical stages, gene mutation types and survival period of the lesion tissue, and perform specific individual Qualitative and quantitative predictive analysis provides credible forecast and analysis results.
附图说明Description of drawings
图1是本发明的基于影像组学的病变组织辅助预后方法的流程图。Fig. 1 is a flow chart of the radiomics-based assisted prognosis method for diseased tissue of the present invention.
具体实施方式detailed description
为使本发明的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本发明作进一步的详细说明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
本发明公开了一种基于影像组学的病变组织辅助预后方法，其总体构思是：首先采用手动或自动的分割方法定位肿块目标区域影像，完成目标影像数据分割；根据目标影像数据提取肿块的多类型特征，建立完备的表型特征库；根据影像数据库中各个病人的基本临床信息获取患者组织活检结果、基因类型和生存时间等信息，采用计算机自动识别和分类方法对病变组织的病理表现、临床分期、基因突变类型的特征予以分别训练并进行分类，建立可靠的预测预后模型；将其应用于测试数据和以其他独立的数据实现对病理表现、临床分期和基因突变类型的分别预测；对病变总生存期和影像特征进行相关性分析，从而得到预后的生存时间与影像学特征之间关系，对病人给出个体化的定性及定量的预后建议。The invention discloses a method for assisting prognosis of diseased tissue based on radiomics. The overall idea is: firstly, a manual or automatic segmentation method is used to locate the image of the target area of the tumor, and the segmentation of the target image data is completed; According to the basic clinical information of each patient in the image database, the biopsy results, genotype and survival time of the patient were obtained, and the pathological manifestations, clinical manifestations and clinical characteristics of the diseased tissue were analyzed by computer automatic identification and classification methods. The characteristics of stages and gene mutation types are trained and classified separately to establish a reliable prediction and prognosis model; it is applied to test data and other independent data to realize the separate prediction of pathological manifestations, clinical stages and gene mutation types; Correlation analysis was carried out between the overall survival period and the imaging features, so as to obtain the relationship between the prognostic survival time and the imaging features, and provide individualized qualitative and quantitative prognosis suggestions for patients.
本发明的基于影像组学的病变组织辅助预后系统和方法通过计算机软件和算法实现影像和预后的相关性分析，从而揭示预后信息与影像表现之间的关系，输出定量的分析结果；其以一套成熟的计算机软件对输入影像数据进行自动化处理，基于先验模型对输入待处理数据进行个性化分析，从而对病变预后进行辅助指导。该系统和方法并不是直接实现疾病的诊断，而是对影像数据予以定量分析提供个性化辅助分析和参考，进一步给医生的诊断提供数据支持。The radiomics-based lesional tissue-assisted prognosis system and method of the present invention realize the correlation analysis between images and prognosis through computer software and algorithms, thereby revealing the relationship between prognosis information and image performance, and outputting quantitative analysis results; it uses a A set of mature computer software automatically processes the input image data, and performs personalized analysis on the input data to be processed based on the prior model, so as to provide auxiliary guidance for the prognosis of the disease. The system and method do not directly realize the diagnosis of the disease, but provide personalized auxiliary analysis and reference for the quantitative analysis of the image data, and further provide data support for the doctor's diagnosis.
本发明的具体目标如下：(1)实现病变组织病灶区域影像的精确分割，对病变组织进行自动定位和肿瘤影像提取，实现病变部位分割的可重复性和精确性；(2)根据病变组织目标影像进行肿块影像特征提取，深度挖掘各类型影像特征，建立完备的病变组织影像特征数据库；(3)基于大数据化的临床病例数据，结合患者的各临床信息与肿块影像特征，采用计算机自动分类识别算法，实现病变组织的病理分析、临床分期分析以及生存期等预测；并解释病变组织基因突变类型与影像特征的潜在关系，提供定性以及定量的预后建议。The specific objectives of the present invention are as follows: (1) Realize the precise segmentation of lesion area images of lesion tissue, automatically locate lesion tissue and extract tumor images, and realize the repeatability and accuracy of lesion segmentation; (2) According to lesion tissue target Image feature extraction of tumors, deep mining of various types of image features, and establishment of a complete lesion tissue imaging feature database; (3) Based on large-scale clinical case data, combined with clinical information of patients and tumor image features, computer automatic classification is used The recognition algorithm realizes pathological analysis, clinical staging analysis and survival prediction of lesion tissue; it also explains the potential relationship between gene mutation type of lesion tissue and imaging features, and provides qualitative and quantitative prognosis suggestions.
更具体地，本发明的基于影像组学的病变组织辅助预后方法，是一种基于影像组学(Radiomics)的病变组织分析预测辅助方法，如图1所示，包括以下步骤：More specifically, the radiomics-based lesional tissue assisted prognosis method of the present invention is a radiomics-based lesional tissue analysis and prediction auxiliary method, as shown in FIG. 1 , comprising the following steps:
步骤S101，从大数据量的患者影像数据库中，采用自动或手动的分割方法提取病变部位的影像数据；Step S101, extracting the image data of the lesion from the patient image database with a large amount of data by automatic or manual segmentation;
步骤S102，根据所述病变部位影像的分割结果，分别提取各病变部位的影像表型特征，完成所述患者影像数据库内所有病变部位影像数据的特征提取；Step S102, according to the segmentation results of the lesion images, extract the image phenotype features of each lesion respectively, and complete the feature extraction of all lesion image data in the patient image database;
步骤S103，基于各病变部位的特征数据和临床信息数据，对所述患者影像数据库中数据进行训练数据集和测试数据集的分类，采用计算机自动识别方法在所述训练数据集进行病变部位的病理分析、临床分期分析、基因突变预测以及生存时间的预测，并在所述测试数据集中实现验证。Step S103, based on the characteristic data and clinical information data of each lesion, classify the data in the patient image database into a training data set and a test data set, and use computer automatic identification method to perform pathological diagnosis of the lesion in the training data set. Analysis, clinical stage analysis, gene mutation prediction and prediction of survival time, and realize verification in the test data set.
其中，所述影像数据为CT、PET、磁共振或超声波影像设备采集得到的影像数据。Wherein, the image data is image data collected by CT, PET, magnetic resonance or ultrasonic imaging equipment.
其中，所述病变部位包括肺部、肝脏或肾脏组织。Wherein, the lesion site includes lung, liver or kidney tissue.
其中，步骤S101中，所述自动的分割方法是通过计算机实现的基于区域生长的方法、基于水平集的分割方法或基于图割的分割方法。Wherein, in step S101, the automatic segmentation method is a method based on region growing, a segmentation method based on level set or a segmentation method based on graph cut implemented by computer.
其中，步骤S102中，所述影像特征包括：病变部位的形状特征、病变部位的纹理特征和/或病变部位的肿块灰度特征。Wherein, in step S102, the image features include: shape features of the lesion, texture features of the lesion, and/or mass grayscale features of the lesion.
其中，步骤S103所述对患者影像数据库中数据进行训练数据集和测试数据集的分类的步骤包括：Wherein, the steps of classifying the data in the patient image database as training data sets and testing data sets in step S103 include:
采用计算机自动分类识别方法，结合统计学知识和工具，建立并分析影像特征与患者临床信息的统计学相关性模型。Using computer automatic classification and recognition methods, combined with statistical knowledge and tools, a statistical correlation model between image features and patient clinical information was established and analyzed.
其中，步骤S103所述采用计算机自动识别方法在所述训练数据集进行病变部位的病理分析、临床分期分析、基因突变预测以及生存时间的预测的步骤中，所述计算机自动识别方法需要处理的数据包括：所述患者的临床信息、组织活检结果、基因信息及生存时间、患者临床数据、患者所处病理学亚型、临床分期与TNM分期结果、基因突变类型和/或随访生存时间。Wherein, in step S103, in the step of using computer automatic recognition method to perform pathological analysis, clinical staging analysis, gene mutation prediction and survival time prediction of lesion in the training data set, the data that the computer automatic recognition method needs to process Including: the patient's clinical information, tissue biopsy results, gene information and survival time, patient clinical data, patient's pathological subtype, clinical stage and TNM staging results, gene mutation type and/or follow-up survival time.
本发明还公开了一种基于影像组学的病变组织辅助预测系统，包括：The present invention also discloses a lesion tissue auxiliary prediction system based on radiomics, including:
从大数据量的患者影像数据库中，采用自动或手动的分割方法提取病变部位的影像数据的单元；From a patient image database with a large amount of data, an automatic or manual segmentation method is used to extract the image data unit of the lesion;
根据所述病变部位影像的分割结果，分别提取各病变部位的影像表型特征，完成所述患者影像数据库内所有病变部位影像数据的特征提取的单元；Extracting image phenotype features of each lesion according to the segmentation result of the lesion image, and completing the feature extraction unit of all lesion image data in the patient image database;
基于各病变部位的特征数据和临床信息数据，对所述患者影像数据库中数据进行训练数据集和测试数据集的分类，采用计算机自动识别方法在所述训练数据集进行病变部位的病理分析、临床分期分析、基因突变预测以及生存时间的预测，并在所述测试数据集中实现验证的单元。Based on the characteristic data and clinical information data of each lesion, classify the data in the patient image database into training data sets and test data sets, and use computer automatic recognition methods to perform pathological analysis and clinical diagnosis of lesion in the training data set. Staging analysis, gene mutation prediction, and survival time prediction, and implement a unit of validation in the test data set.
其中，所述影像数据为CT、PET、磁共振或超声波影像设备采集得到的影像数据。Wherein, the image data is image data collected by CT, PET, magnetic resonance or ultrasonic imaging equipment.
其中，所述自动的分割方法是通过计算机实现的基于区域生长的方法、基于水平集的分割方法或基于图割的分割方法；所述影像特征包括：病变部位的形状特征、病变部位的纹理特征和/或病变部位的肿块灰度特征。Wherein, the automatic segmentation method is a computer-based method based on region growing, a level set based segmentation method or a graph cut based segmentation method; the image features include: shape features of the lesion, texture features of the lesion and/or the grayscale features of the lesion.
下面结合基于CT影像的头颈癌计算机辅助预后方法对本发明进行详细描述。The present invention will be described in detail below in conjunction with a computer-aided prognosis method for head and neck cancer based on CT images.
步骤S0：数据库确定。回顾性纳入200例经手术病理证实的头颈癌患者CT影像，100例作为训练病例，100例作为验证病例；数据应包含不同TNM分期、病理分期、基因突变类型以及随访生存时间等。图像序列包括：扫描方式：平扫、增强扫描；每种扫描方式包括有常规5mm层厚和1.25mm层厚；包括纵隔窗和软组织窗。Step S0: Database determination. 200 CT images of head and neck cancer patients confirmed by surgery and pathology were retrospectively included, 100 cases were used as training cases, and 100 cases were used as verification cases; the data should include different TNM stages, pathological stages, gene mutation types, and follow-up survival time. The image sequence includes: Scanning methods: plain scan, enhanced scan; each scanning method includes conventional 5mm slice thickness and 1.25mm slice thickness; including mediastinal window and soft tissue window.
步骤S1：对数据库中头颈癌患者的CT图像进行高效、稳定及自动化的分割。采用一种基于区域生长的头颈癌病变区域自动分割方法对数据库中病变组织完成分割。算法以初始种子点为基础采用一种自适应阈值的区域生长自动分割算法，实现病变位置的准确识别，并自适应调整分割参数得到病变区域影像数据。最后采用病变区域的轮廓信息完成图像边界平滑，能够实现分割良好的实时性和鲁棒性。Step S1: Efficient, stable and automatic segmentation of CT images of head and neck cancer patients in the database. A method based on region growing for automatic segmentation of head and neck cancer lesions was used to segment the lesions in the database. Based on the initial seed point, the algorithm adopts an adaptive threshold region growing automatic segmentation algorithm to realize the accurate identification of the lesion location, and adaptively adjusts the segmentation parameters to obtain the image data of the lesion area. Finally, the contour information of the lesion area is used to smooth the image boundary, which can achieve good real-time and robust segmentation.
步骤S2：对分割后的头颈癌CT影像数据进行多类型的特征提取。根据特征所在空间维度不同图像特征可分为一阶统计特征和多维统计特征；根据特征提取时基于的不同方向和不同步长可提取多方向、多尺度的影像特征。重点提取多维度和多方向的纹理特征，从不同尺度提取三维空间中的灰度共生矩阵、游程矩阵等高维纹理特征，建立完备的特征库对于后续关键特征筛选以及预后分析能够提供更全面的数据支持。Step S2: Multi-type feature extraction is performed on the segmented head and neck cancer CT image data. According to the different spatial dimensions of the feature, the image features can be divided into first-order statistical features and multi-dimensional statistical features; according to the different directions and different step lengths based on feature extraction, multi-directional and multi-scale image features can be extracted. Focus on extracting multi-dimensional and multi-directional texture features, extract high-dimensional texture features such as gray-level co-occurrence matrix and run matrix in three-dimensional space from different scales, and establish a complete feature library to provide more comprehensive features for subsequent key feature screening and prognosis analysis data support.
在本实施例中，对所述200例经手术病理证实的头颈癌患者CT影像进行特征量化，提取一阶统计特征、纹理特征、三维形态特征等520个特征，实现所有数据的特征提取。In this embodiment, feature quantification was carried out on the CT images of the 200 head and neck cancer patients confirmed by surgery and pathology, and 520 features such as first-order statistical features, texture features, and three-dimensional morphological features were extracted to realize feature extraction of all data.
步骤S3：采用计算机自动识别和分类方法完成头颈癌患者的预测分析。基于已经完成的数据库内所有影像特征集与患者的临床病理、临床分期、基因突变和随访生存时间等参数，将数据库内不同类型头颈癌数据进行“训练数据集”和“测试数据集”的分类，对训练数据集中不同类别的病变数据分别采用计算机自动识别方法进行模型训练，并将一个完备的训练模型用于测试数据集实现未知病变的分析和预测，得到患者的病理、临床分期、基因信息和生存期的定性以及定量的分析结果。Step S3: Complete the predictive analysis of head and neck cancer patients by using computer automatic identification and classification methods. Based on all image feature sets in the completed database and parameters such as clinicopathology, clinical stage, gene mutation and follow-up survival time of patients, the data of different types of head and neck cancer in the database are classified into "training data set" and "test data set". , using computer automatic recognition method for model training on different types of lesion data in the training data set, and using a complete training model in the test data set to realize the analysis and prediction of unknown lesions, and obtain the patient's pathology, clinical stage, and gene information Qualitative and quantitative analysis results of survival and survival.
在本实施例中，对所述200例经手术病理证实的头颈癌患者CT影像进行分析时发现，纹理特征能够正确区分头颈癌的病理等。对于能够反应病变位置灰度不均匀以及病变表型异质性等特征进行定量分析时，采用游程以及灰度共生矩阵等特征，所使用的头颈癌数据的预后结果与实际的吻合度达到了82％，表示本发明所提出的预后方案能够对头颈癌患者的CT影像进行有效的定量辅助预测。In this embodiment, when analyzing the CT images of the 200 cases of head and neck cancer patients confirmed by surgical pathology, it is found that the texture features can correctly distinguish the pathology of head and neck cancer. For the quantitative analysis of features that can reflect the unevenness of the gray level of the lesion location and the heterogeneity of the lesion phenotype, features such as run length and gray level co-occurrence matrix are used, and the prognostic results of the head and neck cancer data used are in good agreement with the actual results. %, indicating that the prognosis scheme proposed by the present invention can perform effective quantitative auxiliary prediction on CT images of patients with head and neck cancer.
以上所述的具体实施例，对本发明的目的、技术方案和有益效果进行了进一步详细说明，应理解的是，以上所述仅为本发明的具体实施例而已，并不用于限制本发明，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The specific embodiments described above have further described the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention, and are not intended to limit the present invention. Within the spirit and principles of the present invention, any modifications, equivalent replacements, improvements, etc., shall be included in the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511021413.9A CN105653858A (en) | 2015-12-31 | 2015-12-31 | Image omics based lesion tissue auxiliary prognosis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511021413.9A CN105653858A (en) | 2015-12-31 | 2015-12-31 | Image omics based lesion tissue auxiliary prognosis system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105653858A true CN105653858A (en) | 2016-06-08 |
Family
ID=56490039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511021413.9A Pending CN105653858A (en) | 2015-12-31 | 2015-12-31 | Image omics based lesion tissue auxiliary prognosis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105653858A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355023A (en) * | 2016-08-31 | 2017-01-25 | 北京数字精准医疗科技有限公司 | Open quantitative analysis method and system based on medical image |
| CN106815481A (en) * | 2017-01-19 | 2017-06-09 | 中国科学院深圳先进技术研究院 | A kind of life cycle Forecasting Methodology and device based on image group |
| CN107169497A (en) * | 2017-04-14 | 2017-09-15 | 中国科学院苏州生物医学工程技术研究所 | A kind of tumor imaging label extracting method based on gene iconography |
| CN107582097A (en) * | 2017-07-18 | 2018-01-16 | 中山大学附属第医院 | Intelligent aid decision-making system based on multi-mode ultrasound omics |
| WO2018132997A1 (en) * | 2017-01-19 | 2018-07-26 | 中国科学院深圳先进技术研究院 | Radiomics-based survival prediction method and device |
| CN108805892A (en) * | 2018-06-01 | 2018-11-13 | 南方医科大学 | Heterogeneous quantitative depicting method in a kind of PET image nasopharynx carcinoma |
| CN108897984A (en) * | 2018-05-07 | 2018-11-27 | 上海理工大学 | Based on correlation analysis between CT images group feature and lung cancer gene expression |
| WO2018233520A1 (en) * | 2017-06-19 | 2018-12-27 | 京东方科技集团股份有限公司 | Method and device for generating predicted image |
| CN109598266A (en) * | 2018-10-24 | 2019-04-09 | 深圳大学 | Lower-limb deep veins thrombus efficiency of thrombolysis prediction technique and system based on machine learning |
| CN109685810A (en) * | 2018-12-18 | 2019-04-26 | 清华大学 | A kind of recognition methods of Bile fistula lesion and system based on deep learning |
| CN109887600A (en) * | 2019-04-16 | 2019-06-14 | 上海理工大学 | A kind of analysis method of pair of non-small cell lung cancer prognosis Survival |
| CN110197236A (en) * | 2018-10-17 | 2019-09-03 | 中山大学附属第三医院 | A kind of prediction and verification method based on image group to glucocorticoid curative effect |
| CN110391015A (en) * | 2019-06-14 | 2019-10-29 | 广东省人民医院(广东省医学科学院) | A radiomics-based approach to quantify tumor immune status |
| CN110910371A (en) * | 2019-11-22 | 2020-03-24 | 北京理工大学 | Automatic classification method and device for liver tumors based on physiological indicators and image fusion |
| CN111209916A (en) * | 2019-12-31 | 2020-05-29 | 中国科学技术大学 | Focus identification method and system and identification equipment |
| CN111369534A (en) * | 2020-03-05 | 2020-07-03 | 上海市肺科医院（上海市职业病防治院） | Auxiliary system and method for predicting gene mutation in lung cancer pathological image |
| CN111370128A (en) * | 2020-03-05 | 2020-07-03 | 上海市肺科医院（上海市职业病防治院） | Lung cancer patient prognosis prediction system and method |
| CN111429968A (en) * | 2020-03-11 | 2020-07-17 | 至本医疗科技（上海）有限公司 | Method, electronic device, and computer storage medium for predicting tumor type |
| CN111563932A (en) * | 2020-05-18 | 2020-08-21 | 苏州立威新谱生物科技有限公司 | Overlapping coaxial surgical operation control method, system and readable storage medium |
| CN111640503A (en) * | 2020-05-29 | 2020-09-08 | 上海市肺科医院 | Prediction system and method for tumor mutation load of patient with advanced lung cancer |
| CN111657945A (en) * | 2020-06-16 | 2020-09-15 | 中南大学湘雅医院 | Nasopharyngeal carcinoma prognosis auxiliary evaluation method based on enhanced MRI (magnetic resonance imaging) imaging omics |
| CN111772657A (en) * | 2020-07-14 | 2020-10-16 | 丁佳丽 | Artificial intelligence multimode imaging analysis system |
| CN111899214A (en) * | 2020-06-12 | 2020-11-06 | 西安交通大学 | Pathological section scanning analysis device and pathological section scanning method |
| CN112435743A (en) * | 2020-12-09 | 2021-03-02 | 上海市第一人民医院 | Bladder cancer pathological omics intelligent diagnosis method based on machine learning and prognosis model thereof |
| CN112509688A (en) * | 2020-09-25 | 2021-03-16 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
| CN112687385A (en) * | 2019-10-18 | 2021-04-20 | 医渡云（北京）技术有限公司 | Disease stage identification method and device |
| CN113177955A (en) * | 2021-05-10 | 2021-07-27 | 电子科技大学成都学院 | Lung cancer image lesion area dividing method based on improved image segmentation algorithm |
| CN113807394A (en) * | 2021-08-10 | 2021-12-17 | 东莞市人民医院 | Mesenteric fat-based classification method and device for clinical outcomes in Crohn's disease |
| CN116682576A (en) * | 2023-08-02 | 2023-09-01 | 浙江大学 | A liver cancer pathological prognosis system and device based on a double-layer graph convolutional neural network |
| CN117808813A (en) * | 2024-03-01 | 2024-04-02 | 乐恩(北京)医药技术有限公司 | Respiratory system lung nodule tumor cell image detection method and system and storage medium |
| WO2024098387A1 (en) * | 2022-11-11 | 2024-05-16 | 京东方科技集团股份有限公司 | Medical data processing method, medical data analysis method, electronic device, and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101061483A (en) * | 2004-11-19 | 2007-10-24 | 皇家飞利浦电子股份有限公司 | In-situ data collection architecture for computer-aided diagnosis |
| CN101689220A (en) * | 2007-04-05 | 2010-03-31 | 奥利安实验室有限公司 | The system and method that be used for the treatment of, diagnosis and prospective medicine illness takes place |
| CN103200861A (en) * | 2011-11-04 | 2013-07-10 | 松下电器产业株式会社 | Similar case retrieval device and similar case retrieval method |
| WO2014184887A1 (en) * | 2013-05-15 | 2014-11-20 | 株式会社日立製作所 | Image diagnosis support system |
| US20150093007A1 (en) * | 2013-09-30 | 2015-04-02 | Median Technologies | System and method for the classification of measurable lesions in images of the chest |
| CN104933711A (en) * | 2015-06-10 | 2015-09-23 | 南通大学 | Automatic fast segmenting method of tumor pathological image |
| CN105005714A (en) * | 2015-06-18 | 2015-10-28 | 中国科学院自动化研究所 | Non-small cell lung cancer prognosis method based on tumor phenotypic characteristics |
-
2015
- 2015-12-31 CN CN201511021413.9A patent/CN105653858A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101061483A (en) * | 2004-11-19 | 2007-10-24 | 皇家飞利浦电子股份有限公司 | In-situ data collection architecture for computer-aided diagnosis |
| CN101689220A (en) * | 2007-04-05 | 2010-03-31 | 奥利安实验室有限公司 | The system and method that be used for the treatment of, diagnosis and prospective medicine illness takes place |
| CN103200861A (en) * | 2011-11-04 | 2013-07-10 | 松下电器产业株式会社 | Similar case retrieval device and similar case retrieval method |
| WO2014184887A1 (en) * | 2013-05-15 | 2014-11-20 | 株式会社日立製作所 | Image diagnosis support system |
| US20150093007A1 (en) * | 2013-09-30 | 2015-04-02 | Median Technologies | System and method for the classification of measurable lesions in images of the chest |
| CN104933711A (en) * | 2015-06-10 | 2015-09-23 | 南通大学 | Automatic fast segmenting method of tumor pathological image |
| CN105005714A (en) * | 2015-06-18 | 2015-10-28 | 中国科学院自动化研究所 | Non-small cell lung cancer prognosis method based on tumor phenotypic characteristics |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355023A (en) * | 2016-08-31 | 2017-01-25 | 北京数字精准医疗科技有限公司 | Open quantitative analysis method and system based on medical image |
| CN106815481A (en) * | 2017-01-19 | 2017-06-09 | 中国科学院深圳先进技术研究院 | A kind of life cycle Forecasting Methodology and device based on image group |
| WO2018132997A1 (en) * | 2017-01-19 | 2018-07-26 | 中国科学院深圳先进技术研究院 | Radiomics-based survival prediction method and device |
| CN107169497A (en) * | 2017-04-14 | 2017-09-15 | 中国科学院苏州生物医学工程技术研究所 | A kind of tumor imaging label extracting method based on gene iconography |
| CN107169497B (en) * | 2017-04-14 | 2021-06-01 | 中国科学院苏州生物医学工程技术研究所 | A method for tumor image marker extraction based on genetic imaging |
| WO2018233520A1 (en) * | 2017-06-19 | 2018-12-27 | 京东方科技集团股份有限公司 | Method and device for generating predicted image |
| CN107582097A (en) * | 2017-07-18 | 2018-01-16 | 中山大学附属第医院 | Intelligent aid decision-making system based on multi-mode ultrasound omics |
| CN108897984A (en) * | 2018-05-07 | 2018-11-27 | 上海理工大学 | Based on correlation analysis between CT images group feature and lung cancer gene expression |
| CN108805892A (en) * | 2018-06-01 | 2018-11-13 | 南方医科大学 | Heterogeneous quantitative depicting method in a kind of PET image nasopharynx carcinoma |
| CN110197236A (en) * | 2018-10-17 | 2019-09-03 | 中山大学附属第三医院 | A kind of prediction and verification method based on image group to glucocorticoid curative effect |
| CN109598266A (en) * | 2018-10-24 | 2019-04-09 | 深圳大学 | Lower-limb deep veins thrombus efficiency of thrombolysis prediction technique and system based on machine learning |
| CN109685810A (en) * | 2018-12-18 | 2019-04-26 | 清华大学 | A kind of recognition methods of Bile fistula lesion and system based on deep learning |
| CN109887600A (en) * | 2019-04-16 | 2019-06-14 | 上海理工大学 | A kind of analysis method of pair of non-small cell lung cancer prognosis Survival |
| CN110391015B (en) * | 2019-06-14 | 2021-08-13 | 广东省人民医院(广东省医学科学院) | A radiomics-based method to quantify tumor immune status |
| CN110391015A (en) * | 2019-06-14 | 2019-10-29 | 广东省人民医院(广东省医学科学院) | A radiomics-based approach to quantify tumor immune status |
| CN112687385A (en) * | 2019-10-18 | 2021-04-20 | 医渡云（北京）技术有限公司 | Disease stage identification method and device |
| CN110910371A (en) * | 2019-11-22 | 2020-03-24 | 北京理工大学 | Automatic classification method and device for liver tumors based on physiological indicators and image fusion |
| CN111209916A (en) * | 2019-12-31 | 2020-05-29 | 中国科学技术大学 | Focus identification method and system and identification equipment |
| CN111209916B (en) * | 2019-12-31 | 2024-01-23 | 中国科学技术大学 | Focus identification method and system and identification equipment |
| CN111369534A (en) * | 2020-03-05 | 2020-07-03 | 上海市肺科医院（上海市职业病防治院） | Auxiliary system and method for predicting gene mutation in lung cancer pathological image |
| CN111370128A (en) * | 2020-03-05 | 2020-07-03 | 上海市肺科医院（上海市职业病防治院） | Lung cancer patient prognosis prediction system and method |
| CN111429968B (en) * | 2020-03-11 | 2021-06-22 | 至本医疗科技（上海）有限公司 | Method, electronic device, and computer storage medium for predicting tumor type |
| CN111429968A (en) * | 2020-03-11 | 2020-07-17 | 至本医疗科技（上海）有限公司 | Method, electronic device, and computer storage medium for predicting tumor type |
| CN111563932A (en) * | 2020-05-18 | 2020-08-21 | 苏州立威新谱生物科技有限公司 | Overlapping coaxial surgical operation control method, system and readable storage medium |
| CN111640503A (en) * | 2020-05-29 | 2020-09-08 | 上海市肺科医院 | Prediction system and method for tumor mutation load of patient with advanced lung cancer |
| CN111640503B (en) * | 2020-05-29 | 2023-09-26 | 上海市肺科医院 | System and method for predicting tumor mutation load of advanced lung cancer patient |
| CN111899214A (en) * | 2020-06-12 | 2020-11-06 | 西安交通大学 | Pathological section scanning analysis device and pathological section scanning method |
| CN111657945A (en) * | 2020-06-16 | 2020-09-15 | 中南大学湘雅医院 | Nasopharyngeal carcinoma prognosis auxiliary evaluation method based on enhanced MRI (magnetic resonance imaging) imaging omics |
| CN111657945B (en) * | 2020-06-16 | 2023-09-12 | 中南大学湘雅医院 | Nasopharyngeal carcinoma prognosis auxiliary evaluation method based on enhanced MRI image histology |
| CN111772657A (en) * | 2020-07-14 | 2020-10-16 | 丁佳丽 | Artificial intelligence multimode imaging analysis system |
| CN112509688A (en) * | 2020-09-25 | 2021-03-16 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
| CN112509688B (en) * | 2020-09-25 | 2024-06-11 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
| CN112435743A (en) * | 2020-12-09 | 2021-03-02 | 上海市第一人民医院 | Bladder cancer pathological omics intelligent diagnosis method based on machine learning and prognosis model thereof |
| CN113177955A (en) * | 2021-05-10 | 2021-07-27 | 电子科技大学成都学院 | Lung cancer image lesion area dividing method based on improved image segmentation algorithm |
| CN113807394A (en) * | 2021-08-10 | 2021-12-17 | 东莞市人民医院 | Mesenteric fat-based classification method and device for clinical outcomes in Crohn's disease |
| WO2024098387A1 (en) * | 2022-11-11 | 2024-05-16 | 京东方科技集团股份有限公司 | Medical data processing method, medical data analysis method, electronic device, and medium |
| CN116682576B (en) * | 2023-08-02 | 2023-12-19 | 浙江大学 | A liver cancer pathological prognosis system and device based on double-layer graph convolutional neural network |
| CN116682576A (en) * | 2023-08-02 | 2023-09-01 | 浙江大学 | A liver cancer pathological prognosis system and device based on a double-layer graph convolutional neural network |
| CN117808813A (en) * | 2024-03-01 | 2024-04-02 | 乐恩(北京)医药技术有限公司 | Respiratory system lung nodule tumor cell image detection method and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105653858A (en) | Image omics based lesion tissue auxiliary prognosis system and method | |
| Bakas et al. | Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features | |
| CN107582097A (en) | Intelligent aid decision-making system based on multi-mode ultrasound omics | |
| Ali et al. | A systematic review of automated melanoma detection in dermatoscopic images and its ground truth data | |
| CN101742961B (en) | Diagnosis support device and system | |
| CN104616307B (en) | A kind of lung CT image adhesion vascular type nodule detection methods | |
| US9424460B2 (en) | Tumor plus adjacent benign signature (TABS) for quantitative histomorphometry | |
| CN105005714A (en) | Non-small cell lung cancer prognosis method based on tumor phenotypic characteristics | |
| JP2008520317A (en) | System and method for automatically detecting and segmenting tumor boundaries in medical image data | |
| CN111353998A (en) | Tumor diagnosis and treatment prediction model and device based on artificial intelligence | |
| Xu et al. | Using transfer learning on whole slide images to predict tumor mutational burden in bladder cancer patients | |
| JP5456132B2 (en) | Diagnosis support device, diagnosis support device control method, and program thereof | |
| JP2023029283A (en) | cancer prognosis | |
| Li et al. | A novel radiogenomics framework for genomic and image feature correlation using deep learning | |
| CN112819765A (en) | Liver image processing method | |
| CN111027548B (en) | Brain glioma molecular marker nondestructive prediction method and system based on image histology | |
| Ou et al. | Sampling the spatial patterns of cancer: Optimized biopsy procedures for estimating prostate cancer volume and Gleason Score | |
| CN113611404A (en) | Plasma sample cancer early screening method based on ensemble learning | |
| Ma et al. | PHE-SICH-CT-IDS: A benchmark CT image dataset for evaluation semantic segmentation, object detection and radiomic feature extraction of perihematomal edema in spontaneous intracerebral hemorrhage | |
| CN111265234A (en) | Method and system for judging properties of lung mediastinal lymph nodes | |
| CN117594200A (en) | Tumor image auxiliary interpretation system based on image histology knowledge base | |
| Kumar et al. | Innovative breast cancer detection through mammogram analysis | |
| Taranova et al. | RADIOMIC ANALYSIS FOR PREDICTION OF T STAGE PARAMETER (T1-T2) IN LUNG CANCER PATIENTS | |
| CN114121291A (en) | Disease grading prediction method and device, electronic equipment and storage medium | |
| CN112396616A (en) | Osteosarcoma recurrence risk prediction model based on tissue morphology analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160608 |