WO2022193628A1 - Colon lesion intelligent recognition method and system based on unsupervised transfer picture classification, and medium - Google Patents
Colon lesion intelligent recognition method and system based on unsupervised transfer picture classification, and medium Download PDFInfo
- Publication number
- WO2022193628A1 WO2022193628A1 PCT/CN2021/123276 CN2021123276W WO2022193628A1 WO 2022193628 A1 WO2022193628 A1 WO 2022193628A1 CN 2021123276 W CN2021123276 W CN 2021123276W WO 2022193628 A1 WO2022193628 A1 WO 2022193628A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- colon
- module
- model
- sample
- loss
- Prior art date
Links
- 210000001072 colon Anatomy 0.000 title claims abstract description 114
- 230000003902 lesion Effects 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000012546 transfer Methods 0.000 title claims abstract description 17
- 238000011002 quantification Methods 0.000 claims abstract description 15
- 230000003044 adaptive effect Effects 0.000 claims abstract description 6
- 238000002372 labelling Methods 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 21
- 238000013508 migration Methods 0.000 claims description 8
- 230000005012 migration Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000013139 quantization Methods 0.000 claims description 6
- 208000003200 Adenoma Diseases 0.000 claims description 3
- 206010001233 Adenoma benign Diseases 0.000 claims description 3
- 208000009956 adenocarcinoma Diseases 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 201000010879 mucinous adenocarcinoma Diseases 0.000 claims description 3
- 230000000112 colonic effect Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims 1
- 230000001568 sexual effect Effects 0.000 claims 1
- 238000013526 transfer learning Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 230000001419 dependent effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06T2207/10056—Microscopic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30028—Colon; Small intestine
-
- 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
Definitions
- the invention belongs to the technical field of unsupervised transfer learning and intelligent medical picture classification, and in particular relates to a colon lesion intelligent identification method, system and medium based on unsupervised transfer picture classification.
- the main purpose of the present invention is to overcome the deficiencies of the prior art, and to provide a method, system and medium for intelligent identification of colon lesions based on unsupervised transfer picture classification.
- the present invention provides an intelligent identification method for colon lesions based on unsupervised migration picture classification, comprising the following steps:
- the domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;
- Model deployment and prediction Input the colon microscopic images of the target domain into the trained colon lesion intelligent recognition model, and predict whether lesions will occur according to the model output results.
- the categories of colon microscopic images that define the target area include: normal, adenoma, adenocarcinoma and mucinous adenocarcinoma.
- the classifier of the module get the classification prediction result
- the difficulty quantization module adopts a quantization formula to obtain the difficulty coefficient ⁇ ( xi ) of the training sample x i , which is specifically as follows:
- the domain alignment module adopts the reweighting method to align the loss to obtain the domain alignment loss, which is specifically as follows:
- d ⁇ ( ) is the probability prediction of the sample from the source domain or the target domain by the domain alignment module
- S is the source domain data set
- T is the target domain data set
- ns is the number of samples in the source domain
- n t is the target domain. Number of samples.
- the processing of the prediction results by the method of modeling and manual labeling error probability is specifically as follows: when the model prediction is correct in the training stage but the labeling is wrong, the conversion prediction result is consistent with the labeling, and the prediction stage uses the unmarked The converted prediction results, where the model of the manual labeling error probability method is as follows:
- ⁇ w km ,b km ⁇ are the parameters of the modeling, and f is the prediction result of the model on the sample;
- the classification loss is specifically as follows:
- ⁇ is a hyperparameter that controls the weight of the sample.
- the diversity loss is specifically as follows:
- D KL is the KL divergence
- the training process adopts the gradient descent method for iterative optimization;
- the final loss function is constructed by weighted domain alignment loss, classification loss and diversity loss, and the specific formula is as follows:
- ⁇ is the weight of the domain alignment loss
- ⁇ is the weight of the diversity loss
- the present invention also provides an intelligent identification system for colon lesions based on unsupervised transfer image classification, which is applied to the above-mentioned intelligent identification method for colon lesions based on unsupervised transfer image classification, including a preprocessing module, a model building module, a model training module and a Model prediction module;
- the preprocessing module is used to define the category of colon microscopic images in the target area; collect and process the digital slice images of the colon in the source area, so that the labeling is consistent with the category of colon microscopic images in the target area;
- the model building module builds an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, difficulty quantification module, domain alignment module, noise adaptability module and diversity module;
- the model training module uses the processed source domain colon digital slice images as samples to train the colon lesion intelligent recognition model, specifically:
- the domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;
- the model prediction module deploys the model and makes predictions, inputs the colon microscopic image of the target field into the trained colon lesion intelligent recognition model, and predicts whether the lesion occurs according to the model output result.
- the present invention also provides a storage medium storing a program, and when the program is executed by the processor, the above-mentioned method for intelligent identification of colon lesions based on classification of unsupervised migration pictures is implemented. Compared with the prior art, the present invention has the following advantages and beneficial effects:
- the intelligent identification method of colon lesions proposed by the present invention does not require labeled colon microscopic image samples, and has high robustness to wrong labeling. It uses easily obtained labeled colon digital slice images to train the model, and uses The trained model is used for colon microscopic image prediction, which overcomes the fact that the existing intelligent identification technology of colon lesions relies on the quantity and quality of colon microscopic images that are difficult to obtain. The cost is very high, and the performance is greatly improved when there are errors in the annotation. Decreases and other defects.
- the intelligent identification method of colon lesions proposed by the present invention is based on unsupervised transfer learning, and has low cost, strong robustness and high flexibility.
- FIG. 1 is a schematic diagram of the overall flow of an intelligent identification method for colon lesions based on unsupervised migration picture classification according to an embodiment of the present invention
- FIG. 2 is a schematic diagram of a training process of an intelligent identification model for colon lesions according to an embodiment of the present invention
- FIG. 3 is a schematic diagram of overcoming the influence of incorrect labeling according to an embodiment of the present invention.
- FIG. 4 is a schematic diagram of predicting lesions in colon microscopic images according to an embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of an intelligent identification system for colon lesions based on unsupervised transfer picture classification according to an embodiment of the present invention
- FIG. 6 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.
- this embodiment provides an intelligent identification method for colon lesions based on unsupervised transfer image classification, which includes the following steps:
- S1 Define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field so that the labeling is consistent with the category of colon microscopic images in the target field;
- step S1 the categories of colon microscopic images of the defined target area include "normal”, “adenoma”, “adenocarcinoma” and “mucinous adenocarcinoma”.
- the sub-network module includes a feature extractor and a classifier; the difficulty quantification module is used to obtain the difficulty coefficient; the domain alignment module, the noise adaptability module and the diversity module are used to construct the model.
- the final loss function; the domain alignment module is equivalent to the discriminator, the two sub-network modules are equivalent to the generator, and a generative adversarial network is formed between these two parts.
- step S3 let the i-th training sample be x i ;
- d ⁇ ( ) is the probability prediction of the sample from the source domain or the target domain by the domain alignment module
- S is the source domain data set
- T is the target domain data set
- ns is the number of samples in the source domain
- n t is the target domain. Number of samples
- the noise adaptability module uses the modeling manual labeling error probability method proposed by the present invention to process the prediction result, as shown in Figure 3, and constructs the classification loss;
- modeling manual labeling error probability method to process the prediction results can reduce the damage of manual labeling errors, specifically: when the model prediction is correct in the training stage and the labeling is wrong, the conversion prediction result is consistent with the labeling, and the prediction stage uses Untransformed prediction results, where the model of manual labeling error probability method is as follows:
- ⁇ w km ,b km ⁇ are the parameters of the modeling, and f is the prediction result of the model on the sample;
- the classification loss is specifically as follows:
- ⁇ is a hyperparameter that controls the weight of the model.
- the diversity module adopts KL divergence to measure the similarity between the two sub-network modules, so as to ensure the effect of the integration of the two sub-networks, and construct the diversity loss, as follows:
- D KL is the KL divergence
- the final loss function is constructed by weighted domain alignment loss, classification loss and diversity loss, as follows:
- ⁇ is the weight of the domain alignment loss
- ⁇ is the weight of the diversity loss
- Model deployment and prediction input the colon microscopic image of the target domain into the trained colon lesion intelligent recognition model for prediction, and predict whether a lesion occurs according to the model output result.
- this embodiment provides an intelligent identification system for colon lesions based on unsupervised transfer image classification, including a preprocessing module, a model building module, a model training module and a model prediction module;
- the preprocessing module is used to define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field, so that the labeling is consistent with the category of the colonic microscopic images in the target field;
- the model building module constructs an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, a difficulty quantification module, a domain alignment module, a noise adaptability module and a diversity module;
- the model training module utilizes the processed source domain colon digital slice image as a sample to train a colon lesion intelligent recognition model, specifically:
- the domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;
- the model prediction module is used for deploying the model and making predictions, inputting the colon microscopic image of the target domain into the trained colon lesion intelligent identification model, and predicting whether a lesion occurs according to the model output result.
- the system provided in this embodiment only takes the division of the above-mentioned functional modules as an example.
- the above-mentioned function allocation can be completed by different functional modules as required, that is, the internal structure is divided into Different functional modules are used to complete all or part of the functions described above, and the system is an intelligent identification method for colon lesions based on unsupervised transfer image classification applied to the above embodiment.
- the present embodiment also provides a storage medium storing a program.
- a method for intelligently identifying colon lesions based on unsupervised migration picture classification is implemented, specifically:
- S1 Define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field so that the labeling is consistent with the category of colon microscopic images in the target field;
- the domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module utilizes the feature vector and difficulty coefficient of the sample to construct the domain alignment loss ; the noise adaptability module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss ; The final loss function is used to iteratively optimize the intelligent identification model of colon lesions;
- model deployment and prediction input the colon microscopic image of the target domain into the trained colon lesion intelligent recognition model, and predict whether a lesion occurs according to the model output result.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A colon lesion intelligent recognition method and system based on unsupervised transfer picture classification, and a medium. A model comprising two sub-network modules having the same structure, a difficulty quantification module, a domain alignment module, a noise adaptive module, and a diversity module is constructed for performing intelligent recognition on a colon lesion. There is no need for annotated colon microscopic image samples. The method has high robustness of incorrect annotation, and overcomes the defect in the existing colon lesion intelligent recognition technology that the cost is very high due to the fact that the number and the annotation quality of colon microscopic images which are difficult to obtain are very dependent. At the same time, the colon lesion intelligent recognition method is based on unsupervised transfer learning, and is low in cost, high in robustness, and high in flexibility.
Description
本发明属于无监督迁移学习、智能医疗图片分类的技术领域,具体涉及一种基于无监督迁移图片分类的结肠病变智能识别方法、系统及介质。The invention belongs to the technical field of unsupervised transfer learning and intelligent medical picture classification, and in particular relates to a colon lesion intelligent identification method, system and medium based on unsupervised transfer picture classification.
近年来,人工智能及相关产业正迅速发展壮大,成为学术界、工业界以及世界各国政府关注的焦点,国务院发布了《新一代人工智能发展规划》,突出了人工智能研究和产业的国家战略地位。在结肠病变智能识别领域,结肠显微图像样本不容易获得,而且标注这些样本难度非常大,需要专业和资深的医生人工标注,且不可避免地存在标注错误。现有的方法非常依赖高质量的带标注的结肠显微图像样本,导致成本巨大且难以应用到现实医疗领域。因此,如何减小对带标注的结肠显微图像的依赖是结肠病变智能识别亟待解决的难题。In recent years, artificial intelligence and related industries have been developing rapidly and have become the focus of attention from academia, industry and governments around the world. The State Council issued the "New Generation Artificial Intelligence Development Plan", highlighting the national strategic position of artificial intelligence research and industry. . In the field of intelligent identification of colon lesions, colon microscopic image samples are not easy to obtain, and labeling these samples is very difficult, requiring manual labeling by professional and experienced doctors, and labeling errors are inevitable. Existing methods rely heavily on high-quality annotated colon microscopic image samples, which are costly and difficult to apply to real-world medical applications. Therefore, how to reduce the dependence on the annotated colon microscopic images is an urgent problem to be solved in the intelligent identification of colon lesions.
发明内容SUMMARY OF THE INVENTION
本发明的主要目的在于克服现有技术存在的不足,提供一种基于无监督迁移图片分类的结肠病变智能识别方法、系统及介质。The main purpose of the present invention is to overcome the deficiencies of the prior art, and to provide a method, system and medium for intelligent identification of colon lesions based on unsupervised transfer picture classification.
为了达到上述目的,本发明采用以下技术方案:In order to achieve the above object, the present invention adopts the following technical solutions:
本发明提供了一种基于无监督迁移图片分类的结肠病变智能识别方法,包括下述步骤:The present invention provides an intelligent identification method for colon lesions based on unsupervised migration picture classification, comprising the following steps:
定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;Define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field to make the annotation consistent with the category of colon microscopic images in the target field;
构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、领域对齐模块、噪声适应性模块和多样性模块;Build an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, difficulty quantification module, domain alignment module, noise adaptability module and diversity module;
利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,具体为:Using the processed digital slice images of the colon in the source domain as a sample to train an intelligent recognition model for colon lesions, the details are as follows:
将样本输入所述两个子网络模块,得到样本的分类预测结果和特征向量;Input the sample into the two sub-network modules to obtain the classification prediction result and feature vector of the sample;
将所述样本的分类预测结果输入难度量化模块,得到样本的难度系数;Input the classification prediction result of the sample into the difficulty quantification module to obtain the difficulty coefficient of the sample;
所述领域对齐模块、噪声适应性模块和多样性模块用于构建结肠病变智能识别模型的最终损失函数;其中,所述领域对齐模块利用样本的特征向量和难度系数构建领域对齐损失;所述噪声适应性模块采用建模人工标注错误概率法对预测结果进行处理,并构造分类损失;所述多样性模块采用KL散度以度量两个子网络模块间的相似性,构造多样性损失;所述最终损失函数用于迭代优化结肠病变智能识别模型;The domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;
模型部署及预测,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型,根据模型输出结果预测是否发生病变。Model deployment and prediction: Input the colon microscopic images of the target domain into the trained colon lesion intelligent recognition model, and predict whether lesions will occur according to the model output results.
作为一种优选的技术方案,所述定义目标领域结肠显微图像的类别包括:正常、腺瘤、腺癌和黏液性腺癌。As a preferred technical solution, the categories of colon microscopic images that define the target area include: normal, adenoma, adenocarcinoma and mucinous adenocarcinoma.
作为一种优选的技术方案,训练过程中,设第i个训练样本为x
i;
As a preferred technical solution, in the training process, let the i-th training sample be xi ;
所述样本经过两个子网络模块的特征提取器,得到特征向量P
τ(x
i),其中τ={1,2}表示两个子网络;所述特征向量P
τ(x
i)经过两个子网络模块的分类器,得到分类预测结果
The sample passes through the feature extractors of the two sub-network modules to obtain a feature vector P τ (x i ), where τ={1,2} represents two sub-networks; the feature vector P τ (x i ) passes through the two sub-networks The classifier of the module, get the classification prediction result
作为一种优选的技术方案,所述难度量化模块采用量化公式得到训练样本x
i的难度系数λ(x
i),具体如下式:
As a preferred technical solution, the difficulty quantization module adopts a quantization formula to obtain the difficulty coefficient λ( xi ) of the training sample x i , which is specifically as follows:
其中,
为两个子网络模块的第i个分类预测结果。
in, Predict the result for the ith classification of the two sub-network modules.
作为一种优选的技术方案,所述领域对齐模块采用重加权法对齐损失,得到领域对齐损失,具体如下式:As a preferred technical solution, the domain alignment module adopts the reweighting method to align the loss to obtain the domain alignment loss, which is specifically as follows:
其中,d
τ(·)为领域对齐模块对样本来自源领域或目标领域的概率预测,S为源领域数据集,T为目标领域数据集,n
s为源领域样本数量,n
t为目标领域样本数量。
Among them, d τ ( ) is the probability prediction of the sample from the source domain or the target domain by the domain alignment module, S is the source domain data set, T is the target domain data set, ns is the number of samples in the source domain, and n t is the target domain. Number of samples.
作为一种优选的技术方案,所述采用建模人工标注错误概率法对预测结果进行处理具体为:当训练阶段模型预测正确而标注错误时,转化预测结果与标注一致,而预测阶段则使用未转化的预测结果,其中,人工标注错误概率法的模型如下式:As a preferred technical solution, the processing of the prediction results by the method of modeling and manual labeling error probability is specifically as follows: when the model prediction is correct in the training stage but the labeling is wrong, the conversion prediction result is consistent with the labeling, and the prediction stage uses the unmarked The converted prediction results, where the model of the manual labeling error probability method is as follows:
其中,{w
km,b
km}为建模的参数,f为模型对样本的预测结果;
Among them, {w km ,b km } are the parameters of the modeling, and f is the prediction result of the model on the sample;
所述分类损失具体如下式:The classification loss is specifically as follows:
其中,
为人工标注错误概率法的模型,γ为控制样本权重的一个超参数。
in, is the model of the manual labeling error probability method, and γ is a hyperparameter that controls the weight of the sample.
作为一种优选的技术方案,所述多样性损失,具体如下式:As a preferred technical solution, the diversity loss is specifically as follows:
其中,D
KL为KL散度。
where D KL is the KL divergence.
作为一种优选的技术方案,所述训练过程采用梯度下降法进行迭代优化;所述最终损失函数由领域对齐损失、分类损失和多样性损失加权构建,具体如下式:As a preferred technical solution, the training process adopts the gradient descent method for iterative optimization; the final loss function is constructed by weighted domain alignment loss, classification loss and diversity loss, and the specific formula is as follows:
L=max(-αL
d)+L
c-ηL
div,
L=max(-αL d )+L c -ηL div ,
其中,α为领域对齐损失的权重,η为多样性损失的权重。where α is the weight of the domain alignment loss, and η is the weight of the diversity loss.
本发明还提供了一种基于无监督迁移图片分类的结肠病变智能识别系统,应用于上述的基于无监督迁移图片分类的结肠病变智能识别方法,包括预处理模块、模型构建模块、模型训练模块和模型预测模块;The present invention also provides an intelligent identification system for colon lesions based on unsupervised transfer image classification, which is applied to the above-mentioned intelligent identification method for colon lesions based on unsupervised transfer image classification, including a preprocessing module, a model building module, a model training module and a Model prediction module;
预处理模块用于定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;The preprocessing module is used to define the category of colon microscopic images in the target area; collect and process the digital slice images of the colon in the source area, so that the labeling is consistent with the category of colon microscopic images in the target area;
模型构建模块构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、领域对齐模块、噪声适应性模块和多样性模块;The model building module builds an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, difficulty quantification module, domain alignment module, noise adaptability module and diversity module;
模型训练模块利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,具体为:The model training module uses the processed source domain colon digital slice images as samples to train the colon lesion intelligent recognition model, specifically:
将样本输入所述两个子网络模块,得到样本的分类预测结果和特征向量;Input the sample into the two sub-network modules to obtain the classification prediction result and feature vector of the sample;
将所述样本的分类预测结果输入难度量化模块,得到样本的难度系数;Input the classification prediction result of the sample into the difficulty quantification module to obtain the difficulty coefficient of the sample;
所述领域对齐模块、噪声适应性模块和多样性模块用于构建结肠病变智能识别模型的最终损失函数;其中,所述领域对齐模块利用样本的特征向量和难度系数构建领域对齐损失;所述噪声适应性模块采用建模人工标注错误概率法对预测结果进行处理,并构造分类损失;所述多样性模块采用KL散度以度量两个子网络模块间的相似性,构造多样性损失;所述最终损失函数用于迭代优化结肠病变智能识别模型;The domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;
模型预测模块部署模型以及进行预测,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型,根据模型输出结果预测是否发生病变。The model prediction module deploys the model and makes predictions, inputs the colon microscopic image of the target field into the trained colon lesion intelligent recognition model, and predicts whether the lesion occurs according to the model output result.
本发明还提供了一种存储介质,存储有程序,所述程序被处理器执行时,实现上述的基于无监督迁移图片分类的结肠病变智能识别方法。本发明与现有技术相比,具有如下优点和有益效果:The present invention also provides a storage medium storing a program, and when the program is executed by the processor, the above-mentioned method for intelligent identification of colon lesions based on classification of unsupervised migration pictures is implemented. Compared with the prior art, the present invention has the following advantages and beneficial effects:
(1)本发明提出的结肠病变智能识别方法不需要带标注的结肠显微图像样本,且对错误标注的鲁棒性高,它使用容易获得的带标注的结肠数字切片图像训练模型,并将训练好的模型用于结肠显微图像预测,克服了现有的结肠病变智能识别技术中依赖难以取得的结肠显微图像的数量和标注的质量,成本非常高,且在标注存在错误时性能大大降低等缺陷。(1) The intelligent identification method of colon lesions proposed by the present invention does not require labeled colon microscopic image samples, and has high robustness to wrong labeling. It uses easily obtained labeled colon digital slice images to train the model, and uses The trained model is used for colon microscopic image prediction, which overcomes the fact that the existing intelligent identification technology of colon lesions relies on the quantity and quality of colon microscopic images that are difficult to obtain. The cost is very high, and the performance is greatly improved when there are errors in the annotation. Decreases and other defects.
(2)本发明提出的结肠病变智能识别方法基于无监督迁移学习,成本低,鲁棒性强,灵活性高。(2) The intelligent identification method of colon lesions proposed by the present invention is based on unsupervised transfer learning, and has low cost, strong robustness and high flexibility.
图1是本发明实施例所述基于无监督迁移图片分类的结肠病变智能识别方法整体流程示意图;1 is a schematic diagram of the overall flow of an intelligent identification method for colon lesions based on unsupervised migration picture classification according to an embodiment of the present invention;
图2是本发明实施例所述结肠病变智能识别模型训练过程示意图;2 is a schematic diagram of a training process of an intelligent identification model for colon lesions according to an embodiment of the present invention;
图3是本发明实施例所述克服错误标注影响的示意图;3 is a schematic diagram of overcoming the influence of incorrect labeling according to an embodiment of the present invention;
图4是本发明实施例所述结肠显微图像病变预测示意图;4 is a schematic diagram of predicting lesions in colon microscopic images according to an embodiment of the present invention;
图5是本发明实施例所述基于无监督迁移图片分类的结肠病变智能识别系统的结构示意图;5 is a schematic structural diagram of an intelligent identification system for colon lesions based on unsupervised transfer picture classification according to an embodiment of the present invention;
图6是本发明实施例所述的存储介质的结构示意图。FIG. 6 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.
为了使本技术领域的人员更好地理解本申请方案,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述。显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。In order to make those skilled in the art better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of this application.
实施例一Example 1
如图1所示,本实施例提供了一种基于无监督迁移图片分类的结肠病变智能识别方法,包括以下步骤:As shown in FIG. 1 , this embodiment provides an intelligent identification method for colon lesions based on unsupervised transfer image classification, which includes the following steps:
S1、定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;S1. Define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field so that the labeling is consistent with the category of colon microscopic images in the target field;
更为具体地,步骤S1中,所述定义目标领域结肠显微图像的类别包括“正常”、“腺瘤”、“腺癌”和“黏液性腺癌”。More specifically, in step S1, the categories of colon microscopic images of the defined target area include "normal", "adenoma", "adenocarcinoma" and "mucinous adenocarcinoma".
S2、构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、领域对齐模块、噪声适应性模块和多样性模块;S2. Build an intelligent identification model for colon lesions, including: two sub-network modules with the same structure, a difficulty quantification module, a domain alignment module, a noise adaptability module, and a diversity module;
更为具体地,步骤S2中,子网络模块包括特征提取器和分类器;所述难度量化模块用于得到难度系数;所述领域对齐模块、噪声适应性模块和多样性模块用于构建模型的最终损失函数;领域对齐模块相当于判别器,两个子网络模块相当于生成器,这两个部分之间形成一个生成对抗网络。More specifically, in step S2, the sub-network module includes a feature extractor and a classifier; the difficulty quantification module is used to obtain the difficulty coefficient; the domain alignment module, the noise adaptability module and the diversity module are used to construct the model. The final loss function; the domain alignment module is equivalent to the discriminator, the two sub-network modules are equivalent to the generator, and a generative adversarial network is formed between these two parts.
S3、利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,如图2所示;S3, using the processed source domain colon digital slice image as a sample to train a colon lesion intelligent recognition model, as shown in Figure 2;
更为具体地,步骤S3中,设第i个训练样本为x
i;
More specifically, in step S3, let the i-th training sample be x i ;
S3.1、将样本经过两个子网络模块的特征提取器,得到特征向量P
τ(x
i),其中τ={1,2}表 示两个子网络;所述特征向量P
τ(x
i)经过两个子网络模块的分类器,得到分类预测结果
S3.1. Pass the sample through the feature extractors of two sub-network modules to obtain a feature vector P τ (x i ), where τ={1,2} represents two sub-networks; the feature vector P τ (x i ) passes through Classifier of two sub-network modules to get classification prediction results
S3.2、将所述样本的分类预测结果输入难度量化模块,并采用本发明提出的量化公式得到训练样本x
i的难度系数λ(x
i),具体如下式:
S3.2, input the classification prediction result of the sample into the difficulty quantization module, and adopt the quantization formula proposed by the present invention to obtain the difficulty coefficient λ( xi ) of the training sample x i , specifically as follows:
其中,
为两个子网络模块的第i个分类预测结果;
in, Predict the result for the i-th classification of the two sub-network modules;
S3.3、将样本的特征向量和难度系数输入领域对齐模块的生成对抗网络,采用本发明提出的重加权法对齐损失,构建领域对齐损失,对齐领域特征空间,具体如下式:S3.3. Input the feature vector and difficulty coefficient of the sample into the generative adversarial network of the domain alignment module, adopt the reweighting method proposed by the present invention to align the loss, construct the domain alignment loss, and align the domain feature space, as follows:
其中,d
τ(·)为领域对齐模块对样本来自源领域或目标领域的概率预测,S为源领域数据集,T为目标领域数据集,n
s为源领域样本数量,n
t为目标领域样本数量
Among them, d τ ( ) is the probability prediction of the sample from the source domain or the target domain by the domain alignment module, S is the source domain data set, T is the target domain data set, ns is the number of samples in the source domain, and n t is the target domain. Number of samples
S3.4、噪声适应性模块采用本发明提出的建模人工标注错误概率法对预测结果进行处理,如图3所示,并构造分类损失;S3.4, the noise adaptability module uses the modeling manual labeling error probability method proposed by the present invention to process the prediction result, as shown in Figure 3, and constructs the classification loss;
所述采用建模人工标注错误概率法对预测结果进行处理可减小人工标注错误的损害,具体为:当训练阶段模型预测正确而标注错误时,转化预测结果与标注一致,而预测阶段则使用未转化的预测结果,其中,人工标注错误概率法的模型如下式:The use of the modeling manual labeling error probability method to process the prediction results can reduce the damage of manual labeling errors, specifically: when the model prediction is correct in the training stage and the labeling is wrong, the conversion prediction result is consistent with the labeling, and the prediction stage uses Untransformed prediction results, where the model of manual labeling error probability method is as follows:
其中,{w
km,b
km}为建模的参数,f为模型对样本的预测结果;
Among them, {w km ,b km } are the parameters of the modeling, and f is the prediction result of the model on the sample;
所述分类损失具体如下式:The classification loss is specifically as follows:
其中,
为人工标注错误概率法的模型,γ为控制模型权重的一个超参数。
in, is the model of the manual labeling error probability method, and γ is a hyperparameter that controls the weight of the model.
S3.5、多样性模块采用KL散度以度量两个子网络模块间的相似性,以保证两个子网络集成的效果,构造多样性损失,具体如下式:S3.5. The diversity module adopts KL divergence to measure the similarity between the two sub-network modules, so as to ensure the effect of the integration of the two sub-networks, and construct the diversity loss, as follows:
其中,D
KL为KL散度。
where D KL is the KL divergence.
S3.6、利用最终损失函数迭代优化结肠病变智能识别模型,训练过程采用梯度下降法进行迭代优化,所述最终损失函数由领域对齐损失、分类损失和多样性损失加权构建,具体如下式:S3.6. Use the final loss function to iteratively optimize the colon lesion intelligent recognition model, and use the gradient descent method to iteratively optimize the training process. The final loss function is constructed by weighted domain alignment loss, classification loss and diversity loss, as follows:
L=max(-αL
d)+L
c-ηL
div,
L=max(-αL d )+L c -ηL div ,
其中,α为领域对齐损失的权重,η为多样性损失的权重。where α is the weight of the domain alignment loss, and η is the weight of the diversity loss.
S4、模型部署及预测,如图4所示,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型进行预测,根据模型输出结果预测是否发生病变。S4. Model deployment and prediction, as shown in Figure 4, input the colon microscopic image of the target domain into the trained colon lesion intelligent recognition model for prediction, and predict whether a lesion occurs according to the model output result.
如图5所示,本实施例提供了一种基于无监督迁移图片分类的结肠病变智能识别系统,包括预处理模块、模型构建模块、模型训练模块和模型预测模块;As shown in FIG. 5 , this embodiment provides an intelligent identification system for colon lesions based on unsupervised transfer image classification, including a preprocessing module, a model building module, a model training module and a model prediction module;
所述预处理模块用于定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;The preprocessing module is used to define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field, so that the labeling is consistent with the category of the colonic microscopic images in the target field;
所述模型构建模块构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、领域对齐模块、噪声适应性模块和多样性模块;The model building module constructs an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, a difficulty quantification module, a domain alignment module, a noise adaptability module and a diversity module;
所述模型训练模块利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,具体为:The model training module utilizes the processed source domain colon digital slice image as a sample to train a colon lesion intelligent recognition model, specifically:
将样本输入所述两个子网络模块,得到样本的分类预测结果和特征向量;Input the sample into the two sub-network modules to obtain the classification prediction result and feature vector of the sample;
将所述样本的分类预测结果输入难度量化模块,得到样本的难度系数;Input the classification prediction result of the sample into the difficulty quantification module to obtain the difficulty coefficient of the sample;
所述领域对齐模块、噪声适应性模块和多样性模块用于构建结肠病变智能识别模型的最终损失函数;其中,所述领域对齐模块利用样本的特征向量和难度系数构建领域对齐损失;所述噪声适应性模块采用建模人工标注错误概率法对预测结果进行处理,并构造分类损失;所述多样性模块采用KL散度以度量两个子网络模块间的相似性,构造多样性损失;所述最终损失函数用于迭代优化结肠病变智能识别模型;The domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;
所述模型预测模块用于部署模型以及进行预测,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型,根据模型输出结果预测是否发生病变。The model prediction module is used for deploying the model and making predictions, inputting the colon microscopic image of the target domain into the trained colon lesion intelligent identification model, and predicting whether a lesion occurs according to the model output result.
在此需要说明的是,本实施例提供的系统仅以上述各功能模块的划分进行举例说明,在实际应用中,可以根据需要而将上述功能分配由不同的功能模块完成,即将内部结构划分成不同的功能模块,以完成以上描述的全部或者部分功能,该系统是应用于上述实施例的基于无监督迁移图片分类的结肠病变智能识别方法。It should be noted here that the system provided in this embodiment only takes the division of the above-mentioned functional modules as an example. In practical applications, the above-mentioned function allocation can be completed by different functional modules as required, that is, the internal structure is divided into Different functional modules are used to complete all or part of the functions described above, and the system is an intelligent identification method for colon lesions based on unsupervised transfer image classification applied to the above embodiment.
如图6所示,本实施例还提供了一种存储介质,存储有程序,所述程序被处理器执行时,实现基于无监督迁移图片分类的结肠病变智能识别方法,具体为:As shown in FIG. 6 , the present embodiment also provides a storage medium storing a program. When the program is executed by the processor, a method for intelligently identifying colon lesions based on unsupervised migration picture classification is implemented, specifically:
S1、定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;S1. Define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field so that the labeling is consistent with the category of colon microscopic images in the target field;
S2、构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、 领域对齐模块、噪声适应性模块和多样性模块;S2. Build an intelligent recognition model for colon lesions, including: two sub-network modules with the same structure, a difficulty quantification module, a domain alignment module, a noise adaptability module, and a diversity module;
S3、利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,具体为:S3, using the processed colon digital slice image of the source domain as a sample to train an intelligent recognition model for colon lesions, specifically:
S3.1、将样本输入所述两个子网络模块,得到样本的分类预测结果和特征向量;S3.1. Input the sample into the two sub-network modules to obtain the classification prediction result and feature vector of the sample;
S3.2、将所述样本的分类预测结果输入难度量化模块,得到样本的难度系数;S3.2, input the classification prediction result of the sample into the difficulty quantification module to obtain the difficulty coefficient of the sample;
S3.3、所述领域对齐模块、噪声适应性模块和多样性模块用于构建结肠病变智能识别模型的最终损失函数;其中,所述领域对齐模块利用样本的特征向量和难度系数构建领域对齐损失;所述噪声适应性模块采用建模人工标注错误概率法对预测结果进行处理,并构造分类损失;所述多样性模块采用KL散度以度量两个子网络模块间的相似性,构造多样性损失;所述最终损失函数用于迭代优化结肠病变智能识别模型;S3.3. The domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module utilizes the feature vector and difficulty coefficient of the sample to construct the domain alignment loss ; the noise adaptability module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss ; The final loss function is used to iteratively optimize the intelligent identification model of colon lesions;
S4、模型部署及预测,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型,根据模型输出结果预测是否发生病变。S4, model deployment and prediction, input the colon microscopic image of the target domain into the trained colon lesion intelligent recognition model, and predict whether a lesion occurs according to the model output result.
应当理解,本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中,多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如,如果用硬件来实现,和在另一实施方式中一样,可用本领域公知的下列技术中的任一项或他们的组合来实现:具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路,具有合适的组合逻辑门电路的专用集成电路,可编程门阵列(PGA),现场可编程门阵列(FPGA)等。It should be understood that various parts of this application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.
上述实施例为本发明较佳的实施方式,但本发明的实施方式并不受上述实施例的限制,其他的任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化,均应为等效的置换方式,都包含在本发明的保护范围之内。The above-mentioned embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited by the above-mentioned embodiments, and any other changes, modifications, substitutions, combinations, The simplification should be equivalent replacement manners, which are all included in the protection scope of the present invention.
Claims (10)
- 基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,包括下述步骤:The intelligent identification method of colon lesions based on unsupervised transfer image classification is characterized in that, it comprises the following steps:定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;Define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field to make the annotation consistent with the category of colon microscopic images in the target field;构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、领域对齐模块、噪声适应性模块和多样性模块;Build an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, difficulty quantification module, domain alignment module, noise adaptability module and diversity module;利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,具体为:Using the processed digital slice images of the colon in the source domain as a sample to train an intelligent recognition model for colon lesions, the details are as follows:将样本输入所述两个子网络模块,得到样本的分类预测结果和特征向量;Input the sample into the two sub-network modules to obtain the classification prediction result and feature vector of the sample;将所述样本的分类预测结果输入难度量化模块,得到样本的难度系数;Input the classification prediction result of the sample into the difficulty quantification module to obtain the difficulty coefficient of the sample;所述领域对齐模块、噪声适应性模块和多样性模块用于构建结肠病变智能识别模型的最终损失函数;其中,所述领域对齐模块利用样本的特征向量和难度系数构建领域对齐损失;所述噪声适应性模块采用建模人工标注错误概率法对预测结果进行处理,并构造分类损失;所述多样性模块采用KL散度以度量两个子网络模块间的相似性,构造多样性损失;所述最终损失函数用于迭代优化结肠病变智能识别模型;The domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;模型部署及预测,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型,根据模型输出结果预测是否发生病变。Model deployment and prediction: Input the colon microscopic images of the target domain into the trained colon lesion intelligent recognition model, and predict whether lesions will occur according to the model output results.
- 根据权利要求1所述的基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,所述定义目标领域结肠显微图像的类别包括:正常、腺瘤、腺癌和黏液性腺癌。The method for intelligent identification of colon lesions based on unsupervised transfer image classification according to claim 1, wherein the categories of colon microscopic images in the defined target area include: normal, adenoma, adenocarcinoma and mucinous adenocarcinoma.
- 根据权利要求1所述的基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,训练过程中,设第i个训练样本为x i; The colon lesion intelligent identification method based on unsupervised migration picture classification according to claim 1, is characterized in that, in the training process, let the i-th training sample be xi ;所述样本经过两个子网络模块的特征提取器,得到特征向量P τ(x i),其中τ={1,2}表示两个子网络;所述特征向量P τ(x i)经过两个子网络模块的分类器,得到分类预测结果 The sample passes through the feature extractors of the two sub-network modules to obtain a feature vector P τ (x i ), where τ={1,2} represents two sub-networks; the feature vector P τ (x i ) passes through the two sub-networks The classifier of the module, get the classification prediction result
- 根据权利要求3所述的基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,所述难度量化模块采用量化公式得到训练样本x i的难度系数λ(x i),具体如下式: The colon lesion intelligent identification method based on unsupervised migration picture classification according to claim 3, is characterized in that, described difficulty quantization module adopts quantization formula to obtain the difficulty coefficient λ(x i ) of training sample x i , specifically as follows:
- 根据权利要求4所述的基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,所述领域对齐模块采用重加权法对齐损失,得到领域对齐损失,具体如下式:The method for intelligent identification of colon lesions based on unsupervised migration picture classification according to claim 4, wherein the domain alignment module adopts a reweighting method to align the loss to obtain the domain alignment loss, which is specifically as follows:其中,d τ(·)为领域对齐模块对样本来自源领域或目标领域的概率预测,S为源领域数据集,T为目标领域数据集,n s为源领域样本数量,n t为目标领域样本数量。 Among them, d τ ( ) is the probability prediction of the sample from the source domain or the target domain by the domain alignment module, S is the source domain data set, T is the target domain data set, ns is the number of samples in the source domain, and n t is the target domain. Number of samples.
- 根据权利要求5所述的基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,所述采用建模人工标注错误概率法对预测结果进行处理具体为:当训练阶段模型预测正确而标注错误时,转化预测结果与标注一致,而预测阶段则使用未转化的预测结果,其中,人工标注错误概率法的模型如下式:The method for intelligent identification of colon lesions based on unsupervised transfer picture classification according to claim 5, characterized in that, the method for processing the prediction result by using the modeled manual labeling error probability method is specifically: when the model predicts correctly in the training stage, the labeling is performed. When it is wrong, the converted prediction result is consistent with the annotation, and the untransformed prediction result is used in the prediction stage. The model of the manual annotation error probability method is as follows:其中,{w km,b km}为建模的参数,f为模型对样本的预测结果; Among them, {w km ,b km } are the parameters of the modeling, and f is the prediction result of the model on the sample;所述分类损失具体如下式:The classification loss is specifically as follows:
- 根据权利要求7所述的基于无监督迁移图片分类的结肠病变智能识别方法,其特征在于,所述训练过程采用梯度下降法进行迭代优化;所述最终损失函数由领域对齐损失、分类损失和多样性损失加权构建,具体如下式:The method for intelligent identification of colon lesions based on unsupervised transfer picture classification according to claim 7, wherein the training process adopts gradient descent method for iterative optimization; the final loss function is composed of domain alignment loss, classification loss and diversity The weighted construction of sexual loss is as follows:L=max(-αL d)+L c-ηL div, L=max(-αL d )+L c -ηL div ,其中,α为领域对齐损失的权重,η为多样性损失的权重。where α is the weight of the domain alignment loss, and η is the weight of the diversity loss.
- 基于无监督迁移图片分类的结肠病变智能识别系统,其特征在于,应用于权利要求1-8中任一项所述的基于无监督迁移图片分类的结肠病变智能识别方法,包括预处理模块、模型构建模块、模型训练模块和模型预测模块;An intelligent identification system for colon lesions based on unsupervised transfer picture classification is characterized in that, it is applied to the intelligent identification method for colon lesions based on unsupervised transfer picture classification according to any one of claims 1-8, comprising a preprocessing module, a model Building modules, model training modules and model prediction modules;所述预处理模块用于定义目标领域结肠显微图像的类别;收集并处理源领域结肠数字切片图像,使其标注与目标领域结肠显微图像的类别一致;The preprocessing module is used to define the category of colon microscopic images in the target field; collect and process the digital slice images of the colon in the source field, so that the labeling is consistent with the category of the colonic microscopic images in the target field;所述模型构建模块构建结肠病变智能识别模型,包括:结构相同的两个子网络模块、难度量化模块、领域对齐模块、噪声适应性模块和多样性模块;The model building module constructs an intelligent identification model of colon lesions, including: two sub-network modules with the same structure, a difficulty quantification module, a domain alignment module, a noise adaptability module and a diversity module;所述模型训练模块利用处理后的源领域结肠数字切片图像作为样本训练结肠病变智能识别模型,具体为:The model training module utilizes the processed source domain colon digital slice image as a sample to train a colon lesion intelligent recognition model, specifically:将样本输入所述两个子网络模块,得到样本的分类预测结果和特征向量;Input the sample into the two sub-network modules to obtain the classification prediction result and feature vector of the sample;将所述样本的分类预测结果输入难度量化模块,得到样本的难度系数;Input the classification prediction result of the sample into the difficulty quantification module to obtain the difficulty coefficient of the sample;所述领域对齐模块、噪声适应性模块和多样性模块用于构建结肠病变智能识别模型的最终损失函数;其中,所述领域对齐模块利用样本的特征向量和难度系数构建领域对齐损失;所述噪声适应性模块采用建模人工标注错误概率法对预测结果进行处理,并构造分类损失;所述多样性模块采用KL散度以度量两个子网络模块间的相似性,构造多样性损失;所述最终损失函数用于迭代优化结肠病变智能识别模型;The domain alignment module, the noise adaptability module and the diversity module are used to construct the final loss function of the intelligent identification model of colon lesions; wherein, the domain alignment module constructs the domain alignment loss by using the feature vector and difficulty coefficient of the sample; the noise The adaptive module uses the modeling manual labeling error probability method to process the prediction results, and constructs the classification loss; the diversity module adopts the KL divergence to measure the similarity between the two sub-network modules, and constructs the diversity loss; the final The loss function is used to iteratively optimize the intelligent identification model of colon lesions;所述模型预测模块用于部署模型以及进行预测,将目标领域结肠显微图像输入训练好的结肠病变智能识别模型,根据模型输出结果预测是否发生病变。The model prediction module is used for deploying the model and making predictions, inputting the colon microscopic image of the target domain into the trained colon lesion intelligent identification model, and predicting whether a lesion occurs according to the model output result.
- 一种存储介质,存储有程序,其特征在于,所述程序被处理器执行时,实现权利要求1-8任一项所述的基于无监督迁移图片分类的结肠病变智能识别方法。A storage medium storing a program, characterized in that, when the program is executed by a processor, the method for intelligently identifying colon lesions based on unsupervised migration picture classification according to any one of claims 1-8 is implemented.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110274834.1 | 2021-03-15 | ||
CN202110274834.1A CN113160135A (en) | 2021-03-15 | 2021-03-15 | Intelligent colon lesion identification method, system and medium based on unsupervised migration image classification |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022193628A1 true WO2022193628A1 (en) | 2022-09-22 |
Family
ID=76887254
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/123276 WO2022193628A1 (en) | 2021-03-15 | 2021-10-12 | Colon lesion intelligent recognition method and system based on unsupervised transfer picture classification, and medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113160135A (en) |
WO (1) | WO2022193628A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113160135A (en) * | 2021-03-15 | 2021-07-23 | 华南理工大学 | Intelligent colon lesion identification method, system and medium based on unsupervised migration image classification |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135579A (en) * | 2019-04-08 | 2019-08-16 | 上海交通大学 | Unsupervised field adaptive method, system and medium based on confrontation study |
CN111523621A (en) * | 2020-07-03 | 2020-08-11 | 腾讯科技(深圳)有限公司 | Image recognition method and device, computer equipment and storage medium |
CN111860670A (en) * | 2020-07-28 | 2020-10-30 | 平安科技(深圳)有限公司 | Domain adaptive model training method, image detection method, device, equipment and medium |
WO2020222985A1 (en) * | 2019-04-30 | 2020-11-05 | The Trustees Of Dartmouth College | System and method for attention-based classification of high-resolution microscopy images |
CN113160135A (en) * | 2021-03-15 | 2021-07-23 | 华南理工大学 | Intelligent colon lesion identification method, system and medium based on unsupervised migration image classification |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108198179A (en) * | 2018-01-03 | 2018-06-22 | 华南理工大学 | A kind of CT medical image pulmonary nodule detection methods for generating confrontation network improvement |
CN110717526B (en) * | 2019-09-23 | 2023-06-02 | 华南理工大学 | Unsupervised migration learning method based on graph convolution network |
AU2020103905A4 (en) * | 2020-12-04 | 2021-02-11 | Chongqing Normal University | Unsupervised cross-domain self-adaptive medical image segmentation method based on deep adversarial learning |
-
2021
- 2021-03-15 CN CN202110274834.1A patent/CN113160135A/en active Pending
- 2021-10-12 WO PCT/CN2021/123276 patent/WO2022193628A1/en unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135579A (en) * | 2019-04-08 | 2019-08-16 | 上海交通大学 | Unsupervised field adaptive method, system and medium based on confrontation study |
WO2020222985A1 (en) * | 2019-04-30 | 2020-11-05 | The Trustees Of Dartmouth College | System and method for attention-based classification of high-resolution microscopy images |
CN111523621A (en) * | 2020-07-03 | 2020-08-11 | 腾讯科技(深圳)有限公司 | Image recognition method and device, computer equipment and storage medium |
CN111860670A (en) * | 2020-07-28 | 2020-10-30 | 平安科技(深圳)有限公司 | Domain adaptive model training method, image detection method, device, equipment and medium |
CN113160135A (en) * | 2021-03-15 | 2021-07-23 | 华南理工大学 | Intelligent colon lesion identification method, system and medium based on unsupervised migration image classification |
Non-Patent Citations (1)
Title |
---|
YIFAN ZHANG; YING WEI; QINGYAO WU; PEILIN ZHAO; SHUAICHENG NIU; JUNZHOU HUANG; MINGKUI TAN: "Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 5 July 2020 (2020-07-05), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081722716 * |
Also Published As
Publication number | Publication date |
---|---|
CN113160135A (en) | 2021-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112861995B (en) | Unsupervised few-sample image classification method and system based on model independent meta learning and storage medium | |
WO2021223323A1 (en) | Image content automatic description method based on construction of chinese visual vocabulary list | |
CN106650789B (en) | Image description generation method based on depth LSTM network | |
CN107506822B (en) | Deep neural network method based on space fusion pooling | |
JP7282212B2 (en) | Method for learning deep learning network by AI and learning device using the same | |
JP7158563B2 (en) | Deep model training method and its device, electronic device and storage medium | |
JP7178513B2 (en) | Chinese word segmentation method, device, storage medium and computer equipment based on deep learning | |
JP2021022367A (en) | Image processing method and information processor | |
US20220092407A1 (en) | Transfer learning with machine learning systems | |
EP4018358A1 (en) | Negative sampling algorithm for enhanced image classification | |
CN112307048B (en) | Semantic matching model training method, matching method, device, equipment and storage medium | |
WO2022227214A1 (en) | Classification model training method and apparatus, and terminal device and storage medium | |
CN112232395B (en) | Semi-supervised image classification method for generating countermeasure network based on joint training | |
CN112164077A (en) | Cell example segmentation method based on bottom-up path enhancement | |
WO2022193628A1 (en) | Colon lesion intelligent recognition method and system based on unsupervised transfer picture classification, and medium | |
CN116152554A (en) | Knowledge-guided small sample image recognition system | |
CN114925205B (en) | GCN-GRU text classification method based on contrast learning | |
CN113901991A (en) | 3D point cloud data semi-automatic labeling method and device based on pseudo label | |
CN113450363B (en) | Meta-learning cell nucleus segmentation system and method based on label correction | |
WO2022221991A1 (en) | Image data processing method and apparatus, computer, and storage medium | |
CN112668633B (en) | Adaptive graph migration learning method based on fine granularity field | |
CN117437423A (en) | Weak supervision medical image segmentation method and device based on SAM collaborative learning and cross-layer feature aggregation enhancement | |
WO2023273171A1 (en) | Image processing method and apparatus, device, and storage medium | |
CN113537325B (en) | Deep learning method for image classification based on extracted high-low layer feature logic | |
US11328179B2 (en) | Information processing apparatus and information processing method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21931203 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |