WO2020211530A1 - Model training method and apparatus for detection on fundus image, method and apparatus for detection on fundus image, computer device, and medium - Google Patents
Model training method and apparatus for detection on fundus image, method and apparatus for detection on fundus image, computer device, and medium Download PDFInfo
- Publication number
- WO2020211530A1 WO2020211530A1 PCT/CN2020/076501 CN2020076501W WO2020211530A1 WO 2020211530 A1 WO2020211530 A1 WO 2020211530A1 CN 2020076501 W CN2020076501 W CN 2020076501W WO 2020211530 A1 WO2020211530 A1 WO 2020211530A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- superpixels
- fundus
- pixel
- network
- neural network
- Prior art date
Links
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
-
- 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
- G06T2207/30041—Eye; Retina; Ophthalmic
Definitions
- the present disclosure relates to the field of computer vision information, and in particular to a model training method for detecting fundus pictures, a method and device for detecting fundus pictures.
- the fundus is the tissue in the back of the eyeball, and the picture of the fundus is the fundus picture.
- Fundus pictures can be used to diagnose fundus diseases such as glaucoma and fundus macular degeneration, and can also provide reference for the diagnosis of diabetes, hypertension and other diseases.
- the embodiments of the present disclosure provide a model training method for detecting fundus pictures, a method and device for detecting fundus pictures.
- an embodiment of the present disclosure provides a model training method for detecting fundus pictures, including: dividing each of the N fundus pictures in the fundus image training set into M superpixels; N and M are both positive integers; according to the M ⁇ N superpixels, a first network model is obtained through training; the first network model is used to identify each input superpixel as a key pixel during output Or background pixels; training to obtain a second network model according to the superpixels belonging to the key pixels in the M ⁇ N superpixels; the second network model is used to input each superpixel in the output When marked as diseased or non-pathological.
- training to obtain the first network model based on the M ⁇ N superpixels includes: constructing a deep neural network; each time at least one of the M ⁇ N superpixels is selected and input In the deep neural network; wherein, each of the M ⁇ N superpixels has been previously marked as a key pixel or a background pixel; and the output result of the deep neural network is compared with the superpixel in advance Compare the marking results of the deep neural network and train the network parameters of the deep neural network until the deep neural network identifies the superpixel as a key pixel or the correct rate of the background pixel is greater than or equal to the first Threshold to obtain the first network model.
- the deep neural network is a deep belief network.
- training to obtain a second network model according to the superpixels belonging to the key pixels in the M ⁇ N superpixels includes: constructing a convolutional neural network; each time selecting the M ⁇ N superpixels , At least one of the superpixels among all the superpixels belonging to the key pixel is input into the convolutional neural network; wherein each of the superpixels belonging to the key pixel has been previously marked as diseased or non-pathological; Compare the output result of the convolutional neural network with the pre-marked results of the superpixels belonging to key pixels, and train the network parameters of the convolutional neural network until the loss value of the convolutional neural network is less than or equal to The second threshold is used to obtain the second network model; the output result of the convolutional neural network includes the identification of the superpixel as diseased or non-pathological.
- the convolutional neural network is a combination of a residual network and an Inception network.
- the model training method for detecting fundus pictures further includes: Perform pre-processing; the pre-processing includes at least one of rotation, shearing, distortion, scaling, adjusting color difference, and reducing resolution.
- the embodiments of the present disclosure also provide a method for detecting fundus pictures, including: dividing the fundus picture to be detected into P superpixels, and obtaining the addresses corresponding to the P superpixels one-to-one; Input superpixels into the first network model to obtain the P superpixels identified as key pixels or background pixels; input the superpixels identified as key pixels into the second network model to obtain The non-lesion pixel is identified as the super pixel of the key pixel; according to the address corresponding to the super pixel identified as the key pixel and the lesion pixel, the position of the super pixel is found in the fundus image to be detected, and The position is marked on the fundus picture to be detected.
- the method for detecting the fundus image further includes: pre-processing the fundus image to be detected Processing;
- the preprocessing includes: at least one of cropping and scaling.
- the first network model is obtained through the following training process: constructing a deep neural network; each time at least one of the M ⁇ N superpixels is selected and input into the deep neural network; where M ⁇ N superpixels are obtained by dividing each of the N fundus pictures in the fundus picture training set into M superpixels, each of the M ⁇ N superpixels The super pixel has been pre-marked as a key pixel or background pixel; the output result of the deep neural network is compared with the pre-marked result of the super pixel, and the network parameters of the deep neural network are trained until the deep neural network When the network outputs the super pixel, the accuracy of the super pixel is identified as a key pixel or the background pixel is greater than or equal to a first threshold to obtain the first network model.
- the deep neural network is a deep belief network.
- the second network model is obtained through the following training process: constructing a convolutional neural network; each time selecting M ⁇ N superpixels, at least one of the superpixels belonging to the key pixels , Input into the convolutional neural network; wherein, the M ⁇ N superpixels are obtained by dividing each of the N fundus pictures in the fundus picture training set into M superpixels, Wherein, each of the superpixels belonging to the key pixel has been previously marked as a diseased pixel or a non-pathological pixel; the output result of the convolutional neural network is compared with the pre-marked result of the superpixel belonging to the key pixel, Train the network parameters of the convolutional neural network until the loss value of the convolutional neural network is less than or equal to the second threshold to obtain the second network model; the output result of the convolutional neural network includes The pixels are identified as lesion pixels or non-lesion pixels.
- the convolutional neural network is a combination of a residual network and an Inception network.
- the embodiments of the present disclosure also provide a computer device, including a memory and a processor; the memory stores a computer program that can be run on the processor; when the processor executes the computer program, The aforementioned model training method for detecting fundus pictures or the aforementioned method for detecting fundus pictures.
- embodiments of the present disclosure also provide a computer device, including a processor, which implements the aforementioned model training method for detecting fundus pictures or the aforementioned method for detecting fundus pictures when the processor executes a computer program.
- the embodiments of the present disclosure also provide a computer-readable medium storing a computer program that, when executed by a processor, implements the aforementioned model training method for detecting fundus pictures or the aforementioned fundus pictures The detection method.
- an embodiment of the present invention also provides a model training device for detecting fundus pictures, including: a segmentation module configured to divide each of the N fundus pictures in the fundus picture training set, Are M superpixels; N and M are both positive integers; the training module is configured to train according to the M ⁇ N superpixels to obtain a first network model; the first network model is used to use each input The super pixels are identified as key pixels or background pixels when output; the training module is also configured to train to obtain a second network model according to the super pixels marked as key pixels; the second network model is used to input Each of the superpixels is marked as diseased or non-pathological when output.
- an embodiment of the present invention also provides a detection device for a fundus picture, including: a segmentation module configured to divide the fundus picture to be detected into M superpixels; and an acquisition module configured to acquire the P superpixels One-to-one correspondence address; the obtaining module is also configured to input the P superpixels into the first network model, thereby obtaining the P superpixels identified as key pixels or background pixels; the obtaining module is also configured to The superpixels identified as key pixels are input into the second network model, so as to obtain the superpixels identified as key pixels, which are identified as diseased pixels or non-lesion pixels; the identification module is configured to be configured according to the identified key pixels and identified as The address corresponding to the super pixel of the diseased pixel, the position of the super pixel is found in the fundus picture to be detected, and the position is marked on the fundus picture to be detected.
- FIG. 1 is a flowchart of a model training method for detecting fundus pictures according to an embodiment of the disclosure
- FIG. 2 is a flowchart of yet another model training method for detecting fundus pictures according to an embodiment of the disclosure
- FIG. 3 is a flowchart of another model training method for detecting fundus pictures according to an embodiment of the disclosure
- FIG. 4 is a flowchart of yet another model training method for detecting fundus pictures provided by an embodiment of the disclosure
- FIG. 5 is a flowchart of another model training method for detecting fundus pictures according to an embodiment of the disclosure.
- FIG. 6 is a schematic structural diagram of a model training device for detecting fundus pictures according to an embodiment of the disclosure
- FIG. 7 is a flowchart of a method for detecting fundus pictures according to an embodiment of the disclosure.
- FIG. 8 is a flowchart of yet another method for detecting fundus pictures according to an embodiment of the present disclosure.
- FIG. 9 is a schematic structural diagram of a detection device for fundus pictures provided by an embodiment of the disclosure.
- FIG. 10 is a schematic structural diagram of a computer device provided by an embodiment of the disclosure.
- the embodiment of the present disclosure provides a model training method for detecting fundus pictures, as shown in FIG. 1, including:
- the fundus image training set refers to a collection of multiple fundus images used to train the model.
- the number of fundus pictures in the fundus picture training set can be set as needed.
- Super pixels refer to irregular pixel blocks with a certain visual significance composed of adjacent pixels with similar texture, color, brightness and other characteristics.
- a small number of super pixels can replace a large number of pixels to express the characteristics of the fundus picture, which reduces the complexity of subsequent processing of the fundus picture.
- a fundus picture is divided into M superpixels, that is, a large number of pixels in a fundus picture are replaced with M superpixels, which reduces the complexity of the fundus picture.
- each fundus picture is divided into M superpixels, so that the complexity of all fundus pictures is reduced and reduced to the same degree.
- the method of dividing each fundus picture into M superpixels is called superpixel division.
- the principle of the superpixel segmentation method is based on a clustering algorithm, that is, the clustering algorithm is used for the segmentation of fundus pictures.
- M pixels are uniformly selected as the initial cluster centers.
- For the remaining pixels according to the distance between the remaining pixels and these cluster centers, according to the principle of nearest neighbor, respectively Assign to the closest cluster.
- a first network model is obtained through training; the first network model is used to identify each input superpixel as a key pixel or a background pixel during output.
- M ⁇ N superpixels need to be input in batches, and the number of superpixels input each time can be set as required.
- the super pixels that best reflect the content of the fundus pictures are called key pixels, and the remaining super pixels are called background pixels. Distinguishing between key pixels and background pixels for all superpixels can eliminate the interference of background pixels in the fundus picture, which is close to the user's detection intention, which is beneficial to the improvement of detection performance.
- a second network model is obtained by training; the second network model is used to identify each input superpixel as a diseased or non-pathological when outputting.
- key pixels when training the second network model, key pixels also need to be input in batches, and the number of key pixels input each time can be set according to needs.
- the key pixel that best reflects the information of the fundus lesion is marked as a lesion, and the remaining key pixels are marked as non-lesion. Distinguishing the key pixels between lesions and non-lesions can eliminate the interference of non-lesion super-pixels in fundus pictures and realize the user's detection intention.
- the embodiment of the present application provides a model training method for detecting fundus pictures.
- the first network model is trained by using the superpixels to train the first network model by dividing the fundus pictures in the fundus image training set into multiple superpixels.
- the super pixels can be identified as key pixels or background pixels.
- use key pixels to train the second network model so that the second network model can identify the key pixels as lesions or non-lesions in subsequent applications, so that the trained model can recognize lesions through the above simple training method Fast speed and high accuracy rate.
- the above-mentioned model training method for detecting fundus pictures further includes :
- the first preprocessing includes at least one of rotation, shearing, distortion, scaling, adjusting color difference, and reducing resolution.
- Rotation is to randomly rotate the fundus picture by a certain angle with the center or a certain vertex as the origin; cutting is to randomly select a part of the image; distortion is to apply a random four-point perspective transformation to the image; scaling is to unify the size of the fundus picture; To adjust the color difference is to randomly process the hue and saturation of the fundus picture.
- the model Before training the model, perform the first preprocessing on the fundus picture to correct the content of the fundus picture, which can expand the fundus picture training set, so that the trained model can process images taken under various shooting conditions and improve model recognition Accuracy.
- the trained model will have a more accurate recognition effect during the actual detection of fundus lesions.
- the model training method for detecting fundus pictures also includes:
- the background pixels output by the first network model are deleted, and only key pixels are retained for subsequent processing, which reduces the amount of calculation and can increase the calculation speed.
- the first network model is obtained by training according to M ⁇ N superpixels in S20, as shown in FIG. 4, which includes:
- the deep neural network in S201 is a deep belief network (Deep Belief Network, DBN).
- DBN Deep Belief Network
- the deep belief network includes multiple stacked Restricted Boltzmann Machines (RBM).
- RBM Restricted Boltzmann Machines
- the structural principle of the restricted Boltzmann machine comes from the Boltzmann distribution in physics. Among them, each restricted Boltzmann machine has two layers of neurons. One layer is called the Visible Layer, which is composed of Visible Units and is used for input; the other layer is called Hidden Layer. , Composed of Hidden Units, used for detection. Both the explicit element and the hidden element are binary variables, that is, their state takes the value 0 or 1. In each layer of neurons, there is no connection within the layer, and the layers are fully connected.
- the hidden layer of the lower restricted Boltzmann machine serves as the visible layer of the higher restricted Boltzmann machine, which is the upper layer of restricted glass. Erzmann machine input data.
- the number of restricted Boltzmann machines stacked into a deep belief network can be set as required, which is not limited in the present disclosure.
- each superpixel may be pre-marked by manual marking.
- the deep neural network is a deep belief network
- the following provides a method of training the first network model based on M ⁇ N superpixels to clearly describe its implementation process.
- the hidden layer of the first restricted Boltzmann machine is used as the visible layer of the second restricted Boltzmann machine, features are extracted, and the weights are updated. And so on.
- unsupervised training refers to each restricted Boltzmann machine.
- the data input to the explicit layer does not need to be manually labeled.
- the main steps of the Contrastive Divergence (CD) method include setting the explicit state of the restricted Boltzmann machine according to the superpixel, and calculating the hidden state by using the conditional probability of the hidden layer under the explicit condition; After the state of the hidden element is determined, the state of the next layer is calculated according to the conditional probability of the explicit layer under the condition of the hidden layer, the explicit layer is reconstructed, and sampling is repeated until the model parameters converge.
- CD Contrastive Divergence
- the output result of the deep belief network is compared with the artificial labeling result, and the correct rate of all superpixels identified as key pixels or background pixels through the deep belief network is calculated.
- the accuracy rate is very low, you can use the Error Back Propagation (BP) algorithm to calculate the mean square error of the deep belief network, and continuously adjust the network parameters to make the mean square error of the deep belief network less than or equal to the set value
- BP Error Back Propagation
- the second network model is obtained by training according to superpixels belonging to key pixels among the M ⁇ N superpixels in S30, as shown in FIG. 5, which includes:
- the convolutional neural network model is a multi-layer structure learning algorithm that uses the relative spatial positions and weights in the picture to reduce the number of network weights to improve the performance of complex network training.
- convolutional neural network When convolutional neural network is trained, it is a machine learning model that learns under supervision.
- the convolutional neural network is a combination of the residual network and the Inception network.
- the residual network constructed by jump connection technology, breaks the convention that the output of the S-1 layer of the traditional neural network can only be input to the S layer, so that the output of a certain layer can directly cross several layers as a later layer input of.
- the stacking of multiple residual networks can reduce the number of network parameters, reduce the amount of calculation, and increase the calculation speed.
- the Inception network is a network with a parallel structure. Through an asymmetric convolution kernel structure, it can reduce the amount of calculation and increase the speed of calculation while ensuring that the information loss is small enough.
- At least one superpixel among all the superpixels belonging to the key pixel is selected each time among the M ⁇ N superpixels, and input into the convolutional neural network; wherein, each superpixel belonging to the key pixel has been previously marked as a lesion Or non-pathological.
- each superpixel belonging to a key pixel may be pre-marked by manual marking.
- the output result of the convolutional neural network includes identifying superpixels as diseased or non-pathological.
- the convolutional neural network is the combination of the residual network and the Inception network
- the following provides a method for training the second network model based on the superpixels belonging to the key pixels in the M ⁇ N superpixels to make it clear Describe its realization process.
- the number of residual networks included in the convolutional neural network and the number of Inception networks can be set as required, and the present disclosure does not limit this.
- the output result of the convolutional neural network is compared with the artificial labeling result, and the loss value of all superpixels belonging to the key pixel is calculated.
- the loss value is large, back propagation can be used to adjust the network parameters until the loss value is less than or equal to the second threshold, thereby obtaining a convolutional neural network.
- the main function of the convolutional neural network is to divide the superpixels belonging to the key pixels into lesions or non-lesions, which is used as a classification model.
- the loss function for calculating the loss value uses the cross entropy (Cross Entroy Loss) loss function.
- y i represents the probability distribution of artificial labeling results
- y i ' represents the probability distribution of the output results of the convolutional neural network.
- Cross entropy describes the distance between two probability distributions. The larger the cross entropy, the greater the difference between the two. The smaller the cross entropy, the closer the two are.
- the embodiment of the present disclosure also provides a computer device, as shown in FIG. 10, including a memory 100 and a processor 200; the memory 100 stores a computer program that can run on the processor 200; the processor 200 executes the computer program to realize the above Model training method for detecting fundus pictures.
- Memory may include, but is not limited to, disk drives, optical storage devices, solid-state storage devices, floppy disks, flexible disks, hard disks, tapes or any other magnetic media, compact disks or any other optical media, ROM (read only memory), RAM (random Access memory), cache memory and/or any other memory chip or cartridge, and/or any other medium from which the processor can read data, instructions and/or code.
- the processor may be any type of processor, and may include, but is not limited to, one or more general-purpose processors and/or one or more special-purpose processors (such as special-purpose processing chips).
- the computer device may not include the memory 100.
- Computer equipment can retrieve computer programs by accessing external or remote storage.
- the embodiment of the present disclosure also provides a computer-readable medium storing a computer program, and the computer program is executed by a processor to implement the above-mentioned model training method for detecting fundus pictures.
- the embodiment of the present invention also provides a model training device for detecting fundus pictures, as shown in FIG. 6, including:
- the dividing module 10 is configured to divide each fundus picture in the N fundus pictures in the fundus picture training set into M superpixels; N and M are both positive integers.
- the training module 20 is configured to train a first network model according to M ⁇ N superpixels; the first network model is used to identify each input superpixel as a key pixel or a background pixel when outputting.
- the training module 20 is also configured to train to obtain a second network model according to the superpixels that have been marked as key pixels; the second network model is used to identify each superpixel input as a diseased or non-pathological when outputting.
- the embodiment of the present application provides a model training device for detecting fundus pictures.
- the fundus pictures in the fundus image training set are divided into multiple superpixels through the segmentation module, and then the training module is used to train the first network using the superpixels.
- the model enables the first network model to recognize superpixels as key pixels or background pixels, and continues to use the training module to train the second network model using key pixels, so that the second network model can recognize that the key pixels are lesions or non-lesions, thereby
- a model that can quickly recognize lesions in fundus pictures with good recognition effect and high accuracy can be trained.
- the embodiment of the present disclosure also provides a method for detecting fundus pictures, as shown in FIG. 7, including:
- S200 Input the P superpixels into the first network model obtained by the above-mentioned model training method for detecting fundus pictures, so as to obtain superpixels identified as key pixels.
- S300 Input superpixels identified as key pixels into the second network model obtained by the above-mentioned model training method for detecting fundus pictures, so as to obtain superpixels identified as key pixels and with lesions.
- S400 Find the position of the superpixel in the fundus picture to be detected according to the address corresponding to the superpixel identified as the key pixel and the lesion, and mark the position on the fundus picture to be detected.
- an address L corresponding to a superpixel identified as a key pixel and a diseased superpixel is used as a seed pixel. According to the address L, it is retrieved whether the superpixels at adjacent addresses L-1 and L+1 are also key pixels and Lesions.
- the super pixel at address L-1 or L+1 as the seed pixel to find whether the super pixel at the neighboring address of the seed pixel is a key pixel and diseased, and so on, until the super pixel at the neighboring address If none of the key pixels is a key pixel and the lesion is a lesion, then one search ends, and all the adjacent key pixels and superpixels of the lesion found before are merged and identified as positions. Then continue to traverse the next unidentified super pixel that belongs to the key pixel and the lesion.
- the mark when marking the location of the lesion on the fundus picture to be detected, can be a circle, a dot, a check mark, etc., as long as the human eye can distinguish it from the fundus picture, and its shape and color are not limited in the present disclosure. .
- the embodiments provided in the present disclosure provide a method for detecting fundus pictures.
- the first network model obtained by training is used to identify the superpixels, and the key pixels are obtained.
- the key pixels are input into the second network model obtained by training, the key pixels are identified, the superpixels of the lesions are obtained, and then according to the address of the superpixel, the position of the superpixel is found and marked in the fundus image. Therefore, the above method can quickly and accurately detect the pathological changes in the fundus picture, and when applied, it can assist the doctor in the rapid diagnosis and reduce the probability of misdiagnosis and missed diagnosis.
- the model training method for detecting the fundus image further includes:
- a second preprocessing is performed on the fundus picture to unify the size of the fundus picture, reduce adverse effects, and improve the accuracy of detection.
- the embodiment of the present disclosure also provides a computer device, as shown in FIG. 10, including a memory 100 and a processor 200; the memory 100 stores a computer program that can run on the processor 200; the processor 200 executes the computer program to realize the above Detection method of fundus pictures.
- the embodiment of the present disclosure also provides a computer-readable medium storing a computer program, and the computer program is executed by a processor to implement the above-mentioned method for detecting fundus pictures.
- An embodiment of the present invention also provides a device for detecting fundus pictures, as shown in FIG. 9, including:
- the segmentation module 10 is configured to segment the fundus image to be detected into M superpixels.
- the obtaining module 30 is configured to obtain the addresses corresponding to the P superpixels one to one.
- the obtaining module 30 is further configured to input the P superpixels into the first network model obtained by the above-mentioned model training method for detecting fundus pictures, so as to obtain superpixels identified as key pixels.
- the acquiring module 30 is further configured to input the superpixels identified as key pixels into the second network model obtained by the above-mentioned model training method for detecting fundus pictures, so as to acquire the superpixels identified as key pixels and having lesions. Pixels.
- the identification module 40 is configured to find the position of the super pixel in the fundus image to be detected according to the address corresponding to the super pixel identified as a key pixel and the lesion, and to identify the position on the fundus image to be detected.
Abstract
Description
Claims (17)
- 一种用于检测眼底图片的模型训练方法,包括:A model training method for detecting fundus pictures includes:将眼底图片训练集的N个眼底图片中的每个所述眼底图片,分割为M个超像素;N和M均为正整数;Divide each of the N fundus pictures in the fundus picture training set into M superpixels; N and M are both positive integers;根据M×N个所述超像素,训练得到第一网络模型;所述第一网络模型用于将输入的每个所述超像素,在输出时标识为关键像素或背景像素;Training to obtain a first network model according to the M×N superpixels; the first network model is used to identify each input superpixel as a key pixel or a background pixel during output;根据M×N个所述超像素中属于关键像素的所述超像素,训练得到第二网络模型;所述第二网络模型用于将输入的每个所述超像素,在输出时标识为病变或非病变。According to the superpixels belonging to the key pixels in the M×N superpixels, a second network model is obtained through training; the second network model is used to identify each of the input superpixels as a lesion when outputting Or non-pathological.
- 根据权利要求1所述的用于检测眼底图片的模型训练方法,其中,根据M×N个所述超像素,训练得到第一网络模型,包括:The model training method for detecting fundus pictures according to claim 1, wherein training the first network model according to the M×N superpixels comprises:构建深层神经网络;Build a deep neural network;每次选取M×N个所述超像素中的至少一个所述超像素,输入所述深层神经网络中;其中,M×N个所述超像素中的每个所述超像素已预先被标记为关键像素或背景像素;Each time at least one of the M×N superpixels is selected and input into the deep neural network; wherein, each of the M×N superpixels has been previously marked Are key pixels or background pixels;将所述深层神经网络的输出结果与所述超像素预先的标记结果进行比较,训练所述深层神经网络的网络参数,直至所述深层神经网络在输出所述超像素时,将所述超像素标识为关键像素或者背景像素的正确率大于或等于第一阈值,得到所述第一网络模型。The output result of the deep neural network is compared with the pre-labeled result of the super pixel, and the network parameters of the deep neural network are trained until the deep neural network outputs the super pixel, the super pixel The correct rate of the identified key pixel or background pixel is greater than or equal to the first threshold, and the first network model is obtained.
- 根据权利要求2所述的用于检测眼底图片的模型训练方法,其中,所述深层神经网络为深度信念网络。The model training method for detecting fundus pictures according to claim 2, wherein the deep neural network is a deep belief network.
- 根据权利要求1-3任一项所述的用于检测眼底图片的模型训练方法,其中,根据M×N个所述超像素中属于关键像素的所述超像素,训练得到第二网络模型,包括:The model training method for detecting fundus pictures according to any one of claims 1 to 3, wherein the second network model is obtained by training according to the superpixels belonging to the key pixels among the M×N superpixels, include:构建卷积神经网络;Build a convolutional neural network;每次选取M×N个所述超像素中,属于关键像素的所有所述超像素中的至少一个所述超像素,输入所述卷积神经网络中;其中,属于关键像素的每个所述超像素已预先被标记为病变或非病变;Each time the M×N superpixels are selected, at least one of the superpixels belonging to the key pixel is input into the convolutional neural network; wherein, each of the key pixels is Super pixels have been pre-marked as lesions or non-lesions;将所述卷积神经网络的输出结果与属于关键像素的所述超像素预先的标记结果进行比较,训练所述卷积神经网络的网络参数,直至所述卷积神经网络的损失值小于或等于第二阈值,得到所述第二网络模型;所述卷积神经网络的输出结果包括将所述超像素标识为病变或非病变。Compare the output result of the convolutional neural network with the pre-marked results of the superpixels belonging to key pixels, and train the network parameters of the convolutional neural network until the loss value of the convolutional neural network is less than or equal to The second threshold is used to obtain the second network model; the output result of the convolutional neural network includes the identification of the superpixel as diseased or non-pathological.
- 根据权利要求4所述的用于检测眼底图片的模型训练方法,其中,所述卷积神经网络为残差网络和Inception网络的结合。The model training method for detecting fundus pictures according to claim 4, wherein the convolutional neural network is a combination of a residual network and an Inception network.
- 根据权利要求1所述的用于检测眼底图片的模型训练方法,其中,将眼底图片训练集的N个眼底图片中的每个所述眼底图片,分割为M个超像素之前,所述用于检测眼底图片的模型训练方法还包括:The model training method for detecting fundus pictures according to claim 1, wherein before dividing each of the N fundus pictures in the fundus picture training set into M superpixels, the The model training method for detecting fundus pictures also includes:对所述眼底图片进行预处理;Preprocessing the fundus picture;所述预处理,包括:旋转、剪切、扭曲、缩放、调整色差、降低分辨率中的至少一种。The preprocessing includes at least one of rotation, shearing, distortion, scaling, adjusting color difference, and reducing resolution.
- 一种眼底图片的检测方法,包括:A method for detecting fundus pictures includes:将待检测眼底图片分割为P个超像素,并获取所述P个超像素一一对应的地址;Dividing the fundus image to be detected into P superpixels, and obtaining addresses corresponding to the P superpixels one-to-one;将所述P个超像素输入第一网络模型中,从而获取标识为关键像素或背景像素的所述P个超像素;Input the P superpixels into the first network model to obtain the P superpixels identified as key pixels or background pixels;将标识为关键像素的所述超像素输入第二网络模型中,从而获取标识为病变像素或非病变像素的标识为关键像素的所述超像素;Input the superpixels identified as key pixels into the second network model, thereby obtaining the superpixels identified as diseased pixels or non-pathological pixels as key pixels;根据标识为关键像素且标识为病变像素的所述超像素对应的地址,在所述待检测眼底图片找到所述超像素的位置,并在所述待检测眼底图片上标识出该位置。According to the address corresponding to the super pixel identified as a key pixel and identified as a diseased pixel, the position of the super pixel is found in the fundus picture to be detected, and the position is marked on the fundus picture to be detected.
- 根据权利要求7所述的眼底图片的检测方法,其中,将待检测眼底图片分割为P个超像素,并获取P个所述超像素一一对应的地址之前,所述眼底图片的检测方法还包括:The method for detecting a fundus picture according to claim 7, wherein before dividing the fundus picture to be detected into P superpixels, and obtaining the addresses corresponding to the P superpixels one-to-one, the detection method for the fundus picture further include:对所述待检测眼底图片进行预处理;Preprocessing the fundus image to be detected;所述预处理,包括:剪切和缩放中的至少一种。The preprocessing includes at least one of cropping and scaling.
- 根据权利要求7所述的眼底图片的检测方法,其中,第一网络模型是通过如下训练处理获得的:The method for detecting fundus pictures according to claim 7, wherein the first network model is obtained through the following training process:构建深层神经网络;Build a deep neural network;每次选取M×N个超像素中的至少一个所述超像素,输入所述深层神经网络中;其中,M×N个所述超像素是通过将眼底图片训练集的N个眼底图片中的每个所述眼底图片分割为M个超像素而获得的,M×N个所述超像素中的每个所述超像素已预先被标记为关键像素或背景像素;Each time at least one of the M×N superpixels is selected and input into the deep neural network; wherein, the M×N superpixels are selected from the N fundus pictures in the fundus picture training set. Each of the fundus images is obtained by dividing each of the fundus pictures into M superpixels, each of the M×N superpixels has been previously marked as a key pixel or a background pixel;将所述深层神经网络的输出结果与所述超像素预先的标记结果进行比较,训练所述深层神经网络的网络参数,直至所述深层神经网络在输出所述超像素时,将所述超像素标识为关键像素或者背景像素的正确率大于或等于第一阈值,得到 所述第一网络模型。The output result of the deep neural network is compared with the pre-labeled result of the super pixel, and the network parameters of the deep neural network are trained until the deep neural network outputs the super pixel, the super pixel The correct rate of the identified key pixel or background pixel is greater than or equal to the first threshold, and the first network model is obtained.
- 根据权利要求9所述的眼底图片的检测方法,其中,所述深层神经网络为深度信念网络。The method for detecting fundus pictures according to claim 9, wherein the deep neural network is a deep belief network.
- 根据权利要求7所述的眼底图片的检测方法,其中,第二网络模型是通过如下训练处理获得的:8. The method for detecting fundus pictures according to claim 7, wherein the second network model is obtained through the following training processing:构建卷积神经网络;Build a convolutional neural network;每次选取M×N个超像素中,属于关键像素的所有所述超像素中的至少一个所述超像素,输入所述卷积神经网络中;其中,M×N个所述超像素是通过将眼底图片训练集的N个眼底图片中的每个所述眼底图片分割为M个超像素而获得的,其中,属于关键像素的每个所述超像素已预先被标记为病变像素或非病变像素;Each time M×N superpixels are selected, at least one of the superpixels belonging to the key pixel is input into the convolutional neural network; wherein, the M×N superpixels are passed through Obtained by dividing each of the N fundus pictures in the fundus picture training set into M superpixels, wherein each of the superpixels belonging to the key pixel has been previously marked as a lesion pixel or a non-lesion pixel Pixel将所述卷积神经网络的输出结果与属于关键像素的所述超像素预先的标记结果进行比较,训练所述卷积神经网络的网络参数,直至所述卷积神经网络的损失值小于或等于第二阈值,得到所述第二网络模型;所述卷积神经网络的输出结果包括将所述超像素标识为病变像素或非病变像素。Compare the output result of the convolutional neural network with the pre-marked results of the superpixels belonging to key pixels, and train the network parameters of the convolutional neural network until the loss value of the convolutional neural network is less than or equal to The second threshold is used to obtain the second network model; the output result of the convolutional neural network includes identifying the superpixel as a diseased pixel or a non-pathological pixel.
- 根据权利要求11所述的眼底图片的检测方法,其中,所述卷积神经网络为残差网络和Inception网络的结合。The method for detecting fundus pictures according to claim 11, wherein the convolutional neural network is a combination of a residual network and an Inception network.
- 一种计算机设备,包括存储器和处理器;所述存储器中存储可在所述处理器上运行的计算机程序;所述处理器执行所述计算机程序时实现如权利要求1-6任一项所述的用于检测眼底图片的模型训练方法或如权利要求7-8任一项所述的眼底图片的检测方法。A computer device, comprising a memory and a processor; the memory stores a computer program that can be run on the processor; when the processor executes the computer program, the implementation of any one of claims 1-6 The model training method for detecting fundus pictures or the method for detecting fundus pictures according to any one of claims 7-8.
- 一种计算机设备,包括处理器,所述处理器执行计算机程序时实现如权利要求1-6任一项所述的用于检测眼底图片的模型训练方法或如权利要求7-8任一项所述的眼底图片的检测方法。A computer device, comprising a processor, which implements the model training method for detecting fundus pictures according to any one of claims 1-6 or the method according to any one of claims 7-8 when executing a computer program The detection method of fundus pictures described.
- 一种计算机可读介质,其存储有计算机程序,所述计算机程序被处理器执行时实现如权利要求1-6任一项所述的用于检测眼底图片的模型训练方法或如权利要求7-8任一项所述的眼底图片的检测方法。A computer-readable medium, which stores a computer program that, when executed by a processor, implements the model training method for detecting fundus pictures according to any one of claims 1-6 or according to claim 7- 8. The detection method of any of the fundus pictures.
- 一种用于检测眼底图片的模型训练装置,包括:A model training device for detecting fundus pictures includes:分割模块,配置为将眼底图片训练集的N个眼底图片中的每个所述眼底图片,分割为M个超像素;N和M均为正整数;A segmentation module, configured to divide each of the N fundus pictures in the fundus picture training set into M superpixels; N and M are both positive integers;训练模块,配置为根据M×N个所述超像素,训练得到第一网络模型;所述第一网络模型用于将输入的每个所述超像素,在输出时标识为关键像素或背景像素;The training module is configured to train to obtain a first network model according to the M×N superpixels; the first network model is used to identify each input superpixel as a key pixel or a background pixel when outputting ;训练模块,还配置为根据已标记为关键像素的所述超像素,训练得到第二网络模型;所述第二网络模型用于将输入的每个所述超像素,在输出时标识为病变或非病变。The training module is further configured to train to obtain a second network model according to the superpixels that have been marked as key pixels; the second network model is used to identify each of the input superpixels as lesions or Non-pathological.
- 一种眼底图片的检测装置,包括:A detection device for fundus pictures includes:分割模块,配置为将待检测眼底图片分割为M个超像素;A segmentation module, configured to segment the fundus image to be detected into M superpixels;获取模块,配置为获取所述P个超像素一一对应的地址;An obtaining module configured to obtain the addresses corresponding to the P superpixels one-to-one;获取模块,还配置为将所述P个超像素输入第一网络模型中,从而获取标识为关键像素或背景像素的所述P个超像素;The obtaining module is further configured to input the P superpixels into the first network model, so as to obtain the P superpixels identified as key pixels or background pixels;获取模块,还配置为将标识为关键像素的所述超像素输入第二网络模型中,从而获取标识为病变像素或非病变像素的标识为关键像素的所述超像素;The acquiring module is further configured to input the superpixels identified as key pixels into the second network model, so as to acquire the superpixels identified as diseased pixels or non-pathological pixels as key pixels;标识模块,配置为根据标识为关键像素且标识为病变像素的所述超像素对应的地址,在所述待检测眼底图片找到所述超像素的位置,并在所述待检测眼底图片上标识出该位置。The identification module is configured to find the position of the super pixel in the fundus picture to be detected according to the address corresponding to the super pixel that is identified as a key pixel and a diseased pixel, and to mark it on the fundus picture to be detected The location.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910320422.X | 2019-04-19 | ||
CN201910320422.XA CN110070531B (en) | 2019-04-19 | 2019-04-19 | Model training method for detecting fundus picture, and fundus picture detection method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020211530A1 true WO2020211530A1 (en) | 2020-10-22 |
Family
ID=67368200
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/076501 WO2020211530A1 (en) | 2019-04-19 | 2020-02-25 | Model training method and apparatus for detection on fundus image, method and apparatus for detection on fundus image, computer device, and medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110070531B (en) |
WO (1) | WO2020211530A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926596A (en) * | 2021-02-10 | 2021-06-08 | 北京邮电大学 | Real-time superpixel segmentation method and system based on recurrent neural network |
CN114693670A (en) * | 2022-04-24 | 2022-07-01 | 西京学院 | Ultrasonic detection method for weld defects of longitudinal submerged arc welded pipe based on multi-scale U-Net |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110070531B (en) * | 2019-04-19 | 2021-05-07 | 京东方科技集团股份有限公司 | Model training method for detecting fundus picture, and fundus picture detection method and device |
CN111046835A (en) * | 2019-12-24 | 2020-04-21 | 杭州求是创新健康科技有限公司 | Eyeground illumination multiple disease detection system based on regional feature set neural network |
CN111402246A (en) * | 2020-03-20 | 2020-07-10 | 北京工业大学 | Eye ground image classification method based on combined network |
CN111716368A (en) * | 2020-06-29 | 2020-09-29 | 重庆市柏玮熠科技有限公司 | Intelligent matching checking robot |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140050391A1 (en) * | 2012-08-17 | 2014-02-20 | Nec Laboratories America, Inc. | Image segmentation for large-scale fine-grained recognition |
US9443314B1 (en) * | 2012-03-29 | 2016-09-13 | Google Inc. | Hierarchical conditional random field model for labeling and segmenting images |
CN106599805A (en) * | 2016-12-01 | 2017-04-26 | 华中科技大学 | Supervised data driving-based monocular video depth estimating method |
CN106934816A (en) * | 2017-03-23 | 2017-07-07 | 中南大学 | A kind of eye fundus image Segmentation Method of Retinal Blood Vessels based on ELM |
CN110070531A (en) * | 2019-04-19 | 2019-07-30 | 京东方科技集团股份有限公司 | For detecting the model training method of eyeground picture, the detection method and device of eyeground picture |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040122672A1 (en) * | 2002-12-18 | 2004-06-24 | Jean-Francois Bonastre | Gaussian model-based dynamic time warping system and method for speech processing |
CN104517116A (en) * | 2013-09-30 | 2015-04-15 | 北京三星通信技术研究有限公司 | Device and method for confirming object region in image |
CN107016677B (en) * | 2017-03-24 | 2020-01-17 | 北京工业大学 | Cloud picture segmentation method based on FCN and CNN |
CN107194929B (en) * | 2017-06-21 | 2020-09-15 | 太原理工大学 | Method for tracking region of interest of lung CT image |
-
2019
- 2019-04-19 CN CN201910320422.XA patent/CN110070531B/en active Active
-
2020
- 2020-02-25 WO PCT/CN2020/076501 patent/WO2020211530A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9443314B1 (en) * | 2012-03-29 | 2016-09-13 | Google Inc. | Hierarchical conditional random field model for labeling and segmenting images |
US20140050391A1 (en) * | 2012-08-17 | 2014-02-20 | Nec Laboratories America, Inc. | Image segmentation for large-scale fine-grained recognition |
CN106599805A (en) * | 2016-12-01 | 2017-04-26 | 华中科技大学 | Supervised data driving-based monocular video depth estimating method |
CN106934816A (en) * | 2017-03-23 | 2017-07-07 | 中南大学 | A kind of eye fundus image Segmentation Method of Retinal Blood Vessels based on ELM |
CN110070531A (en) * | 2019-04-19 | 2019-07-30 | 京东方科技集团股份有限公司 | For detecting the model training method of eyeground picture, the detection method and device of eyeground picture |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926596A (en) * | 2021-02-10 | 2021-06-08 | 北京邮电大学 | Real-time superpixel segmentation method and system based on recurrent neural network |
CN114693670A (en) * | 2022-04-24 | 2022-07-01 | 西京学院 | Ultrasonic detection method for weld defects of longitudinal submerged arc welded pipe based on multi-scale U-Net |
Also Published As
Publication number | Publication date |
---|---|
CN110070531B (en) | 2021-05-07 |
CN110070531A (en) | 2019-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020211530A1 (en) | Model training method and apparatus for detection on fundus image, method and apparatus for detection on fundus image, computer device, and medium | |
CN110232383B (en) | Focus image recognition method and focus image recognition system based on deep learning model | |
CN110599448B (en) | Migratory learning lung lesion tissue detection system based on MaskScoring R-CNN network | |
CN109325942B (en) | Fundus image structure segmentation method based on full convolution neural network | |
CN111985536B (en) | Based on weak supervised learning gastroscopic pathology image Classification method | |
WO2020087960A1 (en) | Image recognition method and device, terminal apparatus, and medical system | |
JP2022528539A (en) | Quality evaluation in video endoscopy | |
CN109886946B (en) | Deep learning-based early senile maculopathy weakening supervision and classification method | |
CN112396605B (en) | Network training method and device, image recognition method and electronic equipment | |
CN113012163A (en) | Retina blood vessel segmentation method, equipment and storage medium based on multi-scale attention network | |
Zhang et al. | Attention-based multi-model ensemble for automatic cataract detection in B-scan eye ultrasound images | |
CN114372951A (en) | Nasopharyngeal carcinoma positioning and segmenting method and system based on image segmentation convolutional neural network | |
CN114092450A (en) | Real-time image segmentation method, system and device based on gastroscopy video | |
CN115375711A (en) | Image segmentation method of global context attention network based on multi-scale fusion | |
CN113643261B (en) | Lung disease diagnosis method based on frequency attention network | |
CN113781489B (en) | Polyp image semantic segmentation method and device | |
Miao et al. | Classification of Diabetic Retinopathy Based on Multiscale Hybrid Attention Mechanism and Residual Algorithm | |
Guergueb et al. | A Review of Deep Learning Techniques for Glaucoma Detection | |
CN112634291A (en) | Automatic burn wound area segmentation method based on neural network | |
CN117036288A (en) | Tumor subtype diagnosis method for full-slice pathological image | |
Lin et al. | Res-UNet based optic disk segmentation in retinal image | |
CN116091446A (en) | Method, system, medium and equipment for detecting abnormality of esophageal endoscope image | |
Jayachandran et al. | Retinal vessels segmentation of colour fundus images using two stages cascades convolutional neural networks | |
CN112734769B (en) | Medical image segmentation and quantitative analysis method based on interactive information guided deep learning method, computer device and storage medium | |
CN114708236B (en) | Thyroid nodule benign and malignant classification method based on TSN and SSN in ultrasonic image |
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: 20792180 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20792180 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20792180 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 10.05.2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20792180 Country of ref document: EP Kind code of ref document: A1 |