CN114708428A - Region-of-interest dividing method, device and equipment and readable storage medium - Google Patents
Region-of-interest dividing method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN114708428A CN114708428A CN202210539455.5A CN202210539455A CN114708428A CN 114708428 A CN114708428 A CN 114708428A CN 202210539455 A CN202210539455 A CN 202210539455A CN 114708428 A CN114708428 A CN 114708428A
- Authority
- CN
- China
- Prior art keywords
- clustering
- interest
- image
- region
- clustering result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The application discloses a method, a device and equipment for dividing a region of interest and a readable storage medium. Acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest; dividing the biological tissue slice staining image into a plurality of image blocks; aiming at the number of each interested area, obtaining a first clustering result, a second clustering result and a consistency parameter corresponding to the number of each interested area; determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas; and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions. Based on the scheme, the number of the target interested areas can be quantitatively determined, and therefore the accuracy of the dividing result of the interested areas of the mass spectrum imaging data can be improved.
Description
Technical Field
The present application relates to the field of mass spectrometry imaging data analysis technology, and more particularly, to a method, an apparatus, a device, and a readable storage medium for dividing a region of interest.
Background
Mass Spectrometry Imaging (MSI) is an emerging chemical imaging technique. The mass spectrometry imaging is to separate various chemical components (such as protein, polypeptide, lipid, metabolite, drug and the like) on the surface of a sample and output mass spectrometry imaging data, wherein each pixel in the mass spectrometry imaging data corresponds to a mass spectrogram. Mass spectrometry data analysis is generally divided into two categories, the first being to look for differential compounds (e.g., molecular level changes between healthy and diseased tissue) between different regions of interest in a sample; the second is to look for different compounds between the same regions of interest in different samples (e.g., variation of the same anatomy at the molecular level between control and experimental groups). Therefore, accurately defining the region of interest (ROI) of mass spectrometry imaging data is a basic premise for mass spectrometry imaging data analysis.
At present, a clustering method is mostly adopted to divide an interested region of mass spectrometry imaging data, specifically, based on a basic assumption that different tissue types have different chemical components and the different chemical components generate different mass spectrograms, clustering analysis is performed according to similarity of interstitial spectrograms of pixel points, that is, pixels in the mass spectrometry imaging data are divided into clusters with the same number as the interested region, and each cluster corresponds to one interested region. However, in the existing method for dividing the region of interest of the mass spectrometry imaging data by using the clustering method, because the number of the region of interest is set manually, the accuracy of the division result of the region of interest of the mass spectrometry imaging data may be low.
Therefore, how to improve the accuracy of the division result of the region of interest of the mass spectrometry imaging data becomes a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above problems, the present application provides a method, an apparatus, a device and a readable storage medium for dividing a region of interest, so as to improve the accuracy of a division result of the region of interest of mass spectrometry imaging data.
The specific scheme is as follows:
a method of region of interest partitioning, the method comprising:
acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest;
dividing the biological tissue slice staining image into a plurality of image blocks;
clustering pixels in the mass spectrum imaging data based on the number of the regions of interest according to the number of each region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas;
and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions.
Optionally, the dividing the staining image of the biological tissue section into a plurality of image blocks includes:
and dividing the biological tissue slice staining image into a plurality of image blocks based on the pixel mapping relation between the mass spectrum imaging data and the biological tissue slice staining image, wherein each image block corresponds to one pixel in the mass spectrum imaging data.
Optionally, the clustering, based on the number of the regions of interest, each pixel in the mass spectrometry imaging data to obtain a first clustering result includes:
reducing the dimension of the mass spectrogram of each pixel in the mass spectrometry imaging data to obtain a mass spectrometry spectrogram after dimension reduction;
and clustering each reduced-dimension mass spectrogram based on the number of the interested regions by adopting a clustering algorithm to obtain a first clustering result.
Optionally, the clustering each image block in the biological tissue slice staining image based on the number of the regions of interest to obtain a second clustering result includes:
performing feature extraction on each image block to obtain a tissue morphology feature vector of each image block, wherein each element in the tissue morphology feature vector corresponds to the response intensity of one tissue morphology feature in the image block;
and clustering each image block in the biological tissue slice staining image based on the number of the interested regions and the tissue morphological characteristic vector of each image block to obtain a second clustering result.
Optionally, the performing feature extraction on each image block to obtain a tissue morphology feature vector of each image block includes:
and performing feature extraction on each image block to be processed by using a feature extraction network to obtain a tissue morphology feature vector of each image block to be processed, wherein the feature extraction network is obtained by pre-training a convolutional neural network by using a natural image data set.
Optionally, the clustering, based on the number of the regions of interest and the tissue morphological feature vector of each image block, each image block in the biological tissue slice staining image to obtain a second clustering result includes:
acquiring position information of each image block in the biological tissue slice staining image;
generating a morphological feature data set based on the position information of each image block in the biological tissue slice staining image and the tissue morphological feature vector of each image block;
generating a tissue morphology feature spatial distribution map based on the morphology feature data set, wherein each spatial position point in the tissue morphology feature spatial distribution map corresponds to a tissue morphology feature spectrum;
performing dimensionality reduction on each tissue morphology feature spectrum to obtain a dimensionality-reduced tissue morphology feature spectrum;
and clustering each tissue morphology characteristic spectrum subjected to dimensionality reduction based on the number of the interested regions by adopting a clustering algorithm to obtain a second clustering result.
Optionally, the calculating a consistency parameter of the first clustering result and the second clustering result includes:
calculating Cohen's Kappa coefficients of the first clustering result and the second clustering result as consistency parameters of the first clustering result and the second clustering result.
An apparatus for dividing a region of interest, the apparatus comprising:
the acquisition unit is used for acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest;
the image block dividing unit is used for dividing the biological tissue slice staining image into a plurality of image blocks;
the clustering processing unit is used for clustering each pixel in the mass spectrum imaging data based on the number of the regions of interest aiming at the number of each region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
the number determining unit of the target interested areas is used for determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas;
and the region-of-interest division result determining unit is used for obtaining the region-of-interest division result of the mass spectrometry imaging data according to the first clustering result and the second clustering result corresponding to the number of the target region-of-interest.
A region-of-interest dividing device comprises a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the region of interest division method described above.
A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the region of interest dividing method as described above.
By means of the technical scheme, the application discloses a method, a device and equipment for dividing a region of interest and a readable storage medium. Acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest; dividing the biological tissue slice staining image into a plurality of image blocks; clustering pixels in the mass spectrum imaging data based on the number of the regions of interest according to the number of each region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result, and calculating consistency parameters of the first clustering result and the second clustering result; determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas; and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions. Based on the scheme, the interested regions are divided by respectively adopting different numbers of the interested regions from two aspects of mass spectrum imaging data and a biological tissue slice staining image corresponding to the mass spectrum imaging data, the number of the target interested regions is quantitatively determined based on the consistency of the dividing results of the interested regions of the two aspects, and the accuracy of the interested regions divided by the mass spectrum imaging data based on the number of the target interested regions is highest.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flowchart of a method for dividing a region of interest disclosed in an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for clustering pixels in the mass spectrometry imaging data based on the number of the regions of interest to obtain a first clustering result, disclosed in an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for clustering image blocks in the stained image of a biological tissue slice to obtain a second clustering result based on the number of regions of interest according to an embodiment of the present application;
fig. 4 is an exemplary diagram of a method for dividing a region of interest disclosed in an embodiment of the present application;
fig. 5 is a schematic structural diagram of a device for dividing a region of interest disclosed in an embodiment of the present application;
fig. 6 is a block diagram of a hardware structure of a region of interest dividing apparatus disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Next, the dividing method of the region of interest provided by the present application is described by the following embodiments.
Referring to fig. 1, fig. 1 is a schematic flowchart of a method for dividing a region of interest disclosed in an embodiment of the present application, where the method may include:
step S101: acquiring mass spectrum imaging data of a region to be divided, a biological tissue section staining image corresponding to the mass spectrum imaging data and the number of a plurality of regions of interest.
In the present application, the stained image of the biological tissue section corresponding to the mass spectrometry imaging data may be obtained by various biological imaging methods, such as optical microscope imaging, two-photon imaging, and the like, and the present application is not limited thereto.
The number of the regions of interest is consistent with the category of the subsequent clustering, for example, if the number of the regions of interest is 2, then there are 2 clusters during the subsequent clustering, and if the number of the regions of interest is 3, then there are 3 clusters during the subsequent clustering. In the present application, the number of a plurality of regions of interest may be preset, for example, the number of four regions of interest may be preset, which is 2, 3, 4, and 5 respectively.
It should be noted that the mass spectrometry imaging data of the region of interest to be divided may be obtained by preprocessing the original mass spectrometry imaging data, and the method for preprocessing the original mass spectrometry imaging data may be as follows: the Cardinal2 library was invoked for normalization, spectral smoothing, baseline correction, and spectral peak extraction, collimation, filtering, and binning of mass spectral imaging data.
The stained image of the biological tissue section corresponding to the mass spectrometry imaging data may be obtained by preprocessing an original stained image of the biological tissue section, and the method for preprocessing the original stained image of the biological tissue section may be as follows: and calling a HistomicTK library to perform sample organization-background segmentation, color normalization, color deconvolution and other processing on the microscopic data.
Step S102: and dividing the biological tissue slice staining image into a plurality of image blocks.
In this application, as an implementation manner, the biological tissue slice staining image may be divided into a plurality of image blocks based on a pixel mapping relationship between the mass spectrometry imaging data and the biological tissue slice staining image, where a pixel in each image block corresponds to one pixel in the mass spectrometry imaging data.
The pixel mapping relation between the mass spectrum imaging data and the biological tissue section staining image can be realized by constructing an affine transformation function by using a SimpleITK library.
Step S103: clustering pixels in the mass spectrum imaging data based on the number of the regions of interest according to the number of each region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested regions to obtain a second clustering result; and calculating consistency parameters of the first clustering result and the second clustering result.
It should be noted that the first clustering result is used to indicate a clustering label of each pixel in the mass spectrometry imaging data, and the second clustering result is used to indicate a clustering label of each image block in the biological tissue slice staining image. The purpose of calculating the consistency parameters of the first clustering result and the second clustering result is to realize cross validation between the clustering results.
In this application, as an implementation manner, the coen's Kappa coefficients of the first clustering result and the second clustering result may be calculated as the consistency parameters of the first clustering result and the second clustering result. As another implementable manner, Mutual Information (Mutual Information) of the first clustering result and the second clustering result may be calculated as a consistency parameter of the first clustering result and the second clustering result.
Through the steps, the first clustering result, the second clustering result and the consistency parameter corresponding to the number of each interested area can be obtained.
Step S104: and determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas.
The higher the consistency parameter is, the higher the consistency of the first clustering result and the second clustering result is, the number of the regions of interest corresponding to the maximum consistency parameter is confirmed by two mutually independent biological imaging modalities, and the accuracy is higher.
Step S105: and obtaining the dividing result of the region of interest of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target region of interest.
In this application, as an implementable manner, the first clustering result corresponding to the number of the target region of interest may be used as a division result of the region of interest of the mass spectrometry imaging data.
As another possible implementation manner, in the first clustering result corresponding to the number of the target regions of interest, the clustering label of the pixel having the same clustering label of each image block in the biological tissue slice staining image in the second clustering result corresponding to the number of the target regions of interest in the mass spectrometry imaging data may be output as a result with higher confidence, and in the first clustering result corresponding to the number of the target regions of interest, the clustering label of the pixel having a clustering label different from that of each image block in the biological tissue slice staining image in the second clustering result corresponding to the number of the target regions of interest in the mass spectrometry imaging data may be output as a result with low confidence.
The embodiment discloses a region-of-interest dividing method. Acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest; dividing the biological tissue slice staining image into a plurality of image blocks; for the number of each region of interest, clustering each pixel in the mass spectrum imaging data based on the number of the region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result, and calculating consistency parameters of the first clustering result and the second clustering result; determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas; and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions. Based on the scheme, the interested regions are divided by respectively adopting different numbers of the interested regions from two aspects of mass spectrum imaging data and a biological tissue slice staining image corresponding to the mass spectrum imaging data, the number of the target interested regions is quantitatively determined based on the consistency of the dividing results of the interested regions of the two aspects, and the accuracy of the interested regions divided by the mass spectrum imaging data based on the number of the target interested regions is highest.
In another embodiment of the present application, a process of clustering each pixel in the mass spectrometry imaging data based on the number of the regions of interest to obtain a first clustering result is described in detail.
Referring to fig. 2, fig. 2 is a schematic flowchart of a method for clustering each pixel in the mass spectrometry imaging data based on the number of the regions of interest to obtain a first clustering result, which may include:
step S201: and reducing the dimension of the mass spectrogram of each pixel in the mass spectrometry imaging data to obtain the mass spectrogram after dimension reduction.
In the application, a nonlinear dimension reduction algorithm or a linear dimension reduction algorithm may be used to reduce the dimension of the mass spectrogram of each pixel in the mass spectrometry imaging data, so as to obtain a dimension-reduced mass spectrogram.
The nonlinear dimension reduction algorithm comprises a t-SNE (t-distributed stored neighbor embedding) algorithm, a UMAP (unified transformed Approximation and Projection) algorithm and the like;
linear dimensionality reduction algorithms include a PCA (Principal Component Analysis) algorithm, an NMF (Non-negative matrix factorization), an ICA (independent Component Analysis), and the like.
Step S202: and clustering each reduced-dimension mass spectrogram based on the number of the interested regions by adopting a clustering algorithm to obtain a first clustering result.
In the present application, the clustering algorithm includes: kmeans, hierarchical clustering, density-based clustering, maximum expected clustering using Gaussian mixture models, graph community detection, mean shift clustering.
In another embodiment of the present application, a specific implementation manner of clustering image blocks in the biological tissue slice stain image based on the number of the regions of interest to obtain a second clustering result is described.
Referring to fig. 3, fig. 3 is a schematic flowchart of a method for clustering image blocks in the stained image of a biological tissue slice to obtain a second clustering result based on the number of regions of interest, where the method may include:
step S301: and performing feature extraction on each image block to obtain a tissue morphology feature vector of each image block, wherein each element in the tissue morphology feature vector corresponds to the response intensity of one tissue morphology feature in the image block.
In the present application, the tissue morphological feature vector of each image block may be various computer visual features, such as a gray level co-occurrence matrix, a threshold adjacency statistic, an intensity statistical feature, a feature output by an intermediate layer of a neural network model, and the like, which is not limited in any way in the present application.
As an implementation manner, a feature extraction network may be used to perform feature extraction on each image block to obtain a tissue morphology feature vector of each image block, where the feature extraction network is obtained by pre-training a convolutional neural network with a natural image data set. For example, a convolutional neural network (e.g., DenseNet, ResNet, VGG, etc.) pre-trained on a natural image dataset (e.g., ImageNet) is used as the feature extraction network. The image blocks are used as input after size adjustment and normalization preprocessing, and are transmitted in the convolutional neural network in the forward direction. In a pre-selected intermediate layer (such as conv5_ block32 layer of DenseNet 201), the image blocks of 3 channels are converted into a three-dimensional array with a large number of channels and a small number of pixels, and each channel corresponds to a visual feature, namely a histomorphological feature. And reforming the three-dimensional array into a tissue morphology feature vector through a pooling operation (such as average global pooling), wherein each element in the tissue morphology feature vector corresponds to the response intensity of one morphology feature in the image block.
Step S302: and acquiring the position information of each image block in the biological tissue slice staining image.
Step S303: and generating a morphological feature data set based on the position information of each image block in the biological tissue slice staining image and the tissue morphological feature vector of each image block.
Step S304: and generating a tissue morphology feature spatial distribution map based on the morphology feature data set, wherein each spatial position point in the tissue morphology feature spatial distribution map corresponds to a tissue morphology feature spectrum.
Step S305: and reducing the dimension of each tissue morphology feature spectrum to obtain the tissue morphology feature spectrum after dimension reduction.
In the present application, a nonlinear dimension reduction algorithm or a linear dimension reduction algorithm may be used to perform dimension reduction on each tissue morphology feature spectrum to obtain a dimension-reduced tissue morphology feature spectrum.
The nonlinear dimension reduction algorithm includes t-SNE (t-distributed stored neighbor embedding) algorithm, UMAP (Uniform transformed Approximation and Projection) algorithm and the like;
linear dimensionality reduction algorithms include a PCA (Principal Component Analysis) algorithm, an NMF (Non-negative matrix factorization), an ICA (independent Component Analysis), and the like.
Step S306: and clustering the tissue morphology characteristic spectrums after dimension reduction based on the number of the interested regions by adopting a clustering algorithm to obtain a second clustering result.
In this application, the clustering algorithm may include: kmeans, hierarchical clustering, density-based clustering, maximum expected clustering using Gaussian mixture models, graph community detection, mean shift clustering.
It should be noted that the clustering algorithm used in this step needs to be consistent with the clustering algorithm used in step S202.
For ease of understanding, please refer to fig. 4, in which fig. 4 is a diagram illustrating an example of a region of interest division method disclosed in an embodiment of the present application. As shown in fig. 4, (a) is a schematic diagram of clustering each pixel in the mass spectrometry imaging data based on the number of the regions of interest to obtain a first clustering result, and (b) is a schematic diagram of clustering each image block in the biological tissue slice stain image based on the number of the regions of interest to obtain a second clustering result.
The following describes a region-of-interest dividing apparatus disclosed in an embodiment of the present application, and the region-of-interest dividing apparatus described below and the region-of-interest dividing method described above may be referred to in correspondence with each other.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a device for dividing a region of interest disclosed in an embodiment of the present application. As shown in fig. 5, the apparatus for dividing the region of interest may include:
the acquiring unit 11 is configured to acquire mass spectrometry imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrometry imaging data, and the number of a plurality of regions of interest;
an image block dividing unit 12 for dividing the biological tissue slice staining image into a plurality of image blocks;
the clustering unit 13 is configured to cluster, for the number of each region of interest, each pixel in the mass spectrometry imaging data based on the number of the region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
a target interesting region number determining unit 14, configured to determine that the number of interesting regions corresponding to the maximum consistency parameter is the number of target interesting regions;
and the region-of-interest division result determining unit 15 is configured to obtain a region-of-interest division result of the mass spectrometry imaging data according to the first clustering result and the second clustering result corresponding to the number of the target region-of-interest.
Referring to fig. 6, fig. 6 is a block diagram of a hardware structure of a device for dividing a region of interest provided in an embodiment of the present application, and referring to fig. 6, the hardware structure of the device for dividing a region of interest may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
in the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete mutual communication through the communication bus 4;
the processor 1 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 3 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest;
dividing the biological tissue slice staining image into a plurality of image blocks;
clustering pixels in the mass spectrum imaging data based on the number of the regions of interest according to the number of each region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas;
and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions.
Alternatively, the detailed function and the extended function of the program may be as described above.
Embodiments of the present application further provide a readable storage medium, where a program suitable for being executed by a processor may be stored, where the program is configured to:
acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest;
dividing the biological tissue slice staining image into a plurality of image blocks;
clustering pixels in the mass spectrum imaging data based on the number of the regions of interest according to the number of each region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas;
and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions.
Alternatively, the detailed function and the extended function of the program may be as described above.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for dividing a region of interest, the method comprising:
acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of the plurality of regions of interest;
dividing the biological tissue slice staining image into a plurality of image blocks;
for the number of each region of interest, clustering each pixel in the mass spectrum imaging data based on the number of the region of interest to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas;
and obtaining the division result of the interested region of the mass spectrum imaging data according to the first clustering result and the second clustering result corresponding to the number of the target interested regions.
2. The method of claim 1, wherein the dividing the stained image of the biological tissue section into a plurality of image blocks comprises:
dividing the biological tissue slice staining image into a plurality of image blocks based on the pixel mapping relation between the mass spectrometry imaging data and the biological tissue slice staining image, wherein a pixel in each image block corresponds to one pixel in the mass spectrometry imaging data.
3. The method of claim 1, wherein the clustering the pixels in the mass spectrometry imaging data based on the number of regions of interest to obtain a first clustering result comprises:
reducing the dimension of the mass spectrogram of each pixel in the mass spectrometry imaging data to obtain a mass spectrometry spectrogram after dimension reduction;
and clustering each reduced-dimension mass spectrogram based on the number of the interested regions by adopting a clustering algorithm to obtain a first clustering result.
4. The method according to claim 1, wherein the clustering of each image block in the stained image of the biological tissue slice based on the number of regions of interest to obtain a second clustering result comprises:
performing feature extraction on each image block to obtain a tissue morphology feature vector of each image block, wherein each element in the tissue morphology feature vector corresponds to the response intensity of one tissue morphology feature in the image block;
and clustering each image block in the biological tissue slice staining image based on the number of the interested regions and the tissue morphology characteristic vector of each image block to obtain a second clustering result.
5. The method according to claim 4, wherein the performing feature extraction on each image block to obtain a tissue morphology feature vector of each image block comprises:
and performing feature extraction on each image block to be processed by using a feature extraction network to obtain a tissue morphology feature vector of each image block to be processed, wherein the feature extraction network is obtained by pre-training a convolutional neural network by using a natural image data set.
6. The method according to claim 4, wherein the clustering each image block in the biological tissue slice stain image based on the number of regions of interest and the tissue morphology feature vector of each image block to obtain a second clustering result comprises:
acquiring the position information of each image block in the biological tissue slice staining image;
generating a morphological feature data set based on the position information of each image block in the biological tissue slice staining image and the tissue morphological feature vector of each image block;
generating a tissue morphology feature spatial distribution map based on the morphology feature data set, wherein each spatial position point in the tissue morphology feature spatial distribution map corresponds to a tissue morphology feature spectrum;
performing dimensionality reduction on each tissue morphology feature spectrum to obtain a dimensionality-reduced tissue morphology feature spectrum;
and clustering each tissue morphology characteristic spectrum subjected to dimensionality reduction based on the number of the interested regions by adopting a clustering algorithm to obtain a second clustering result.
7. The method of claim 1, wherein calculating the consistency parameter of the first clustered result and the second clustered result comprises:
calculating Cohen's Kappa coefficients of the first clustering result and the second clustering result as consistency parameters of the first clustering result and the second clustering result.
8. An apparatus for dividing a region of interest, the apparatus comprising:
the acquisition unit is used for acquiring mass spectrum imaging data of a region of interest to be divided, a biological tissue slice staining image corresponding to the mass spectrum imaging data and the number of a plurality of regions of interest;
the image block dividing unit is used for dividing the biological tissue slice staining image into a plurality of image blocks;
the clustering processing unit is used for clustering each pixel in the mass spectrum imaging data based on the number of the interested regions according to the number of each interested region to obtain a first clustering result; clustering each image block in the biological tissue slice staining image based on the number of the interested areas to obtain a second clustering result; calculating consistency parameters of the first clustering result and the second clustering result;
the number determining unit of the target interested areas is used for determining the number of the interested areas corresponding to the maximum consistency parameter as the number of the target interested areas;
and the region-of-interest division result determining unit is used for obtaining the region-of-interest division result of the mass spectrometry imaging data according to the first clustering result and the second clustering result corresponding to the number of the target region-of-interest.
9. The device for dividing the region of interest is characterized by comprising a memory and a processor;
the memory is used for storing programs;
the processor, configured to execute the program, implementing the steps of the region of interest partitioning method according to any one of claims 1 to 7.
10. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the region of interest segmentation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210539455.5A CN114708428A (en) | 2022-05-18 | 2022-05-18 | Region-of-interest dividing method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210539455.5A CN114708428A (en) | 2022-05-18 | 2022-05-18 | Region-of-interest dividing method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114708428A true CN114708428A (en) | 2022-07-05 |
Family
ID=82176216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210539455.5A Pending CN114708428A (en) | 2022-05-18 | 2022-05-18 | Region-of-interest dividing method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114708428A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023221513A1 (en) * | 2022-05-18 | 2023-11-23 | 中国科学院深圳先进技术研究院 | Image partitioning method, apparatus and device, and readable storage medium |
-
2022
- 2022-05-18 CN CN202210539455.5A patent/CN114708428A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023221513A1 (en) * | 2022-05-18 | 2023-11-23 | 中国科学院深圳先进技术研究院 | Image partitioning method, apparatus and device, and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3138959C (en) | Image diagnostic system, and methods of operating thereof | |
| Ruusuvuori et al. | Evaluation of methods for detection of fluorescence labeled subcellular objects in microscope images | |
| Bao et al. | Tree filtering: Efficient structure-preserving smoothing with a minimum spanning tree | |
| Ge et al. | New benchmark for image segmentation evaluation | |
| US7949181B2 (en) | Segmentation of tissue images using color and texture | |
| Ta et al. | Graph-based tools for microscopic cellular image segmentation | |
| US20110216976A1 (en) | Updating Image Segmentation Following User Input | |
| EP1646964B1 (en) | Method and arrangement for determining an object contour | |
| Sbalzarini | Seeing is believing: quantifying is convincing: computational image analysis in biology | |
| CN114841978A (en) | Image partitioning method, device and equipment and readable storage medium | |
| He et al. | iCut: an integrative cut algorithm enables accurate segmentation of touching cells | |
| CN108090913B (en) | Image semantic segmentation method based on object-level Gauss-Markov random field | |
| Mamatha et al. | Graph theory based segmentation of magnetic resonance images for brain tumor detection | |
| CN114708428A (en) | Region-of-interest dividing method, device and equipment and readable storage medium | |
| Berezsky et al. | Segmentation of cytological and histological images of breast cancer cells | |
| US20230096719A1 (en) | Scalable and high precision context-guided segmentation of histological structures including ducts/glands and lumen, cluster of ducts/glands, and individual nuclei in whole slide images of tissue samples from spatial multi-parameter cellular and sub-cellular imaging platforms | |
| Ali et al. | Automatic cancerous tissue classification using discrete wavelet transformation and support vector machine | |
| CN116468923A (en) | Image strengthening method and device based on weighted resampling clustering instability | |
| Zanotelli et al. | A flexible image segmentation pipeline for heterogeneous multiplexed tissue images based on pixel classification | |
| Athanasiadis et al. | Segmentation of complementary DNA microarray images by wavelet-based Markov random field model | |
| Tosta et al. | Fitness functions evaluation for segmentation of lymphoma histological images using genetic algorithm | |
| CN116580397B (en) | Pathological image recognition method, device, equipment and storage medium | |
| Shahul Hameed et al. | P53immunostained cell nuclei segmentation in tissue images of oral squamous cell carcinoma | |
| Mahmoud et al. | Novel feature extraction methodology based on histopathalogical images and subsequent classification by Support Vector Machine | |
| CN117315378B (en) | Grading judgment method for pneumoconiosis and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |