CN110956629A

CN110956629A - Method for measuring morphological parameters of myotube cells and providing interactive interface of myotube cells

Info

Publication number: CN110956629A
Application number: CN201911299861.3A
Authority: CN
Inventors: 王新宇; 丁国鹏; 张永合; 陈奕帆; 郭明; 支帅; 毛青筠; 陈昕
Original assignee: Shanghai Engineering Center for Microsatellites; Innovation Academy for Microsatellites of CAS
Current assignee: Shanghai Engineering Center for Microsatellites; Innovation Academy for Microsatellites of CAS
Priority date: 2019-12-17
Filing date: 2019-12-17
Publication date: 2020-04-03
Anticipated expiration: 2039-12-17
Also published as: CN110956629B

Abstract

The invention provides a method for measuring myotube cell morphological parameters and providing an interactive interface thereof, wherein the interactive interface comprises a result display area for displaying an operation result and an operation area, the measurement and statistical analysis of the myotube cell morphological parameters can be realized by clicking each function button of the operation area, and the method for measuring the myotube cell morphological parameters comprises image segmentation based on deep learning, myotube cell screening and morphological parameter measurement.

Description

Method for measuring morphological parameters of myotube cells and providing interactive interface of myotube cells

Technical Field

The invention relates to the field of life science, in particular to a measuring technology of myotube cell morphological parameters.

Background

The long-term weightlessness flight of astronauts has great influence on the physiological functions of the astronauts, and the long-term weightlessness can cause disuse atrophy of muscles of the astronauts for resisting gravity. The countermeasure of muscle atrophy in the space microgravity environment is still a difficult problem to be solved by the space medicine. For on-orbit detection and real-time data analysis of myotube cell states, the research which can explore the influence of space environments such as microgravity, radiation and the like on myotube cell development is an important subject for preventing and treating the muscular atrophy of spacemen.

At present, researchers mainly observe myotube cell images through naked eyes for analyzing myotube cell state data, then select myotube cells with obvious characteristics, and further manually measure the width of the widest part of the myotube cells. On one hand, the method cannot measure the area parameters of the myotube cells, on the other hand, the method is limited by subjective judgment of scientific researchers, the average width and the widest width of the myotube cells cannot be objectively obtained, and meanwhile, the on-track detection of the state of the myotube cells and the analysis of real-time data cannot be realized.

Disclosure of Invention

In order to overcome some or all of the defects in the prior art, the invention provides a method for measuring the morphological parameters of the myotube cells, so as to realize on-track detection and real-time data analysis of the cell states of the myotube cells. A method of measuring a myotube cell morphological parameter, comprising:

preprocessing the myotube cell image;

screening myotube cells;

calculating morphological parameters of myotube cells obtained by screening; and

statistical analysis was performed on myotube cell morphological parameters.

Further, the preprocessing comprises image segmentation, binarization and connected domain division.

Further, the image segmentation is realized by adopting a method based on a deep learning network.

Further, the image segmentation method based on the deep learning network adopts a 12-layer U-net learning network for learning.

Further, the screening of the myotube cells comprises deleting myotube cells with an area smaller than a threshold value.

Further, the calculation of the myotube cell morphological parameters includes calculating the average width, the widest width and the area of each myotube cell.

Further, the statistical analysis of the myotube cell morphological parameters includes statistical distribution of the average width, the widest width and the area of the myotube cells.

Another aspect of the present invention provides a method for providing an interactive interface for myotube morphological parameter measurement, so that a non-professional can also perform myotube morphological parameter measurement quickly. A method for providing an interactive interface for measuring morphological parameters of myotube cells comprises a result display area and an operation area, wherein the result display area is used for displaying operation results, the operation results comprise a segmented image, a cell average width distribution graph, a cell widest width distribution graph and a cell area distribution graph, and the operation area comprises:

providing a 'picture selection' button, and clicking the 'picture selection' button to select the myotube cell image to be detected;

providing a label for displaying a picture address, wherein the label is used for displaying the image address of the selected myotube cell image to be detected;

providing a 'click segmentation image' button, and clicking the 'click segmentation image' button to perform cell segmentation of myotube cells on the selected myotube cell image to be detected based on a deep learning network;

providing an address button for selecting a storage result, and clicking the address button for selecting the storage result to select an address for storing a segmented image morphological parameter result;

providing a label for displaying a storage result address, and displaying the storage address of the segmented image morphological parameter result;

providing a button for measuring the cell morphological parameters by clicking, wherein the cell morphological parameters can be measured by clicking the button for measuring the cell morphological parameters;

providing a label indicating completion of the measurement of the cellular morphological parameter and the time required for the operation to be completed and displaying the length of time it takes for the measurement of the cellular morphological parameter;

providing a button for selecting data to be processed, and clicking the button for selecting data to be processed to select morphological parameter data of a plurality of myotube cell images for myotube cell morphological parameter statistics;

providing a cell average width distribution diagram button, and counting the cell average width distribution by clicking the cell average width distribution diagram button;

providing a 'cell widest width distribution diagram' button, and counting the distribution of the widest width of the cell by clicking the 'cell widest width distribution diagram' button; and

a "cell area map" button is provided, and a single click of the "cell area map" button allows statistics of the cell area distribution.

According to the method for measuring the morphological parameters of the myotube cells and providing the interactive interface of the myotube cells, provided by the invention, a large number of myotube cell images in different states under different doses of medicaments at different moments are collected, a label is printed under the guidance of scientific researchers to form a specific data set, and a 12-layer U-net learning network is established for learning, so that the area, the average width and the widest width of the cells can be obtained without being limited by priori knowledge, the related parameter information is stored in a corresponding folder, online statistical analysis can be carried out, and the on-track detection and real-time data analysis of the morphological parameters of the myotube cells are realized. Meanwhile, the interactive interface provided by the invention is simple and easy to operate, and common operators can operate the interactive interface.

Drawings

To further clarify the above and other advantages and features of embodiments of the present invention, a more particular description of embodiments of the present invention will be rendered by reference to the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. In the drawings, the same or corresponding parts will be denoted by the same or similar reference numerals for clarity.

FIG. 1 is a flow chart of a method for measuring myotube cell morphological parameters according to an embodiment of the invention;

FIG. 2 illustrates a flow diagram of a deep learning network training method according to an embodiment of the invention;

FIG. 3 is a schematic diagram of an interactive interface of a method for measuring morphological parameters of myotubes according to an embodiment of the invention;

FIG. 4 is a schematic view of the operation area of the interface of a method for measuring the morphological parameters of myotubes according to an embodiment of the present invention;

FIG. 5 is a graph showing the segmentation results of a myotube cell image according to an embodiment of the present invention;

FIG. 6 is a graph showing the results of the distribution of the mean width of myotube cells according to one embodiment of the present invention;

FIG. 7 is a graph showing the results of one embodiment of the invention for myotube cell widest width distribution; and

FIG. 8 is a graph showing the results of myotube cell area distribution according to one embodiment of the present invention.

Detailed Description

In the following description, the present invention is described with reference to examples. One skilled in the relevant art will recognize, however, that the embodiments may be practiced without one or more of the specific details, or with other alternative and/or additional methods, materials, or components. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the invention. Similarly, for purposes of explanation, specific numbers, materials and configurations are set forth in order to provide a thorough understanding of the embodiments of the invention. However, the invention is not limited to these specific details. Further, it should be understood that the embodiments shown in the figures are illustrative representations and are not necessarily drawn to scale.

Reference in the specification to "one embodiment" or "the embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment.

It should be noted that the embodiment of the present invention describes the process steps in a specific order, however, this is only for the purpose of illustrating the specific embodiment, and does not limit the sequence of the steps. Rather, in various embodiments of the present invention, the order of the steps may be adjusted according to process adjustments.

Fig. 1 shows a flowchart of a method for measuring myotube cell morphological parameters according to an embodiment of the invention. As shown in fig. 1, a method for measuring myotube cell morphological parameters includes:

step 101, deep learning network training, as shown in fig. 2, includes:

step 201, labeling the myotube cell image, marking the myotube cell and binarizing the labeled myotube cell to form a label;

202, enabling the labels to correspond to myocyte cells one by one to form a data set;

and

step 203, training a learning network, building a 12-layer U-net network by adopting the data set, and training a deep learning network with the myotube cell image as input and the corresponding label as output to obtain a deep learning network architecture and parameters;

step 102, preprocessing the myotube cell image, comprising:

image segmentation, namely inputting the myotube cell image to be detected into the deep learning network to obtain a corresponding myotube cell segmentation image;

binarization processing, namely performing binarization on the myotube cell segmentation image, and performing morphological operation on the binarized image; and

dividing a connected domain, namely dividing the binarized image into the connected domains and calculating the area of each connected domain, wherein the area of each connected domain corresponds to the area of a myotube cell;

103, screening myotube cells, screening the myotube cells according to the area of the myotube cells, deleting the myotube cells with the area not reaching the threshold value, collecting the contour of the rest myotube cells, determining the top point of the cells, and dividing the contour of the cells into two cell edges;

104, calculating morphological parameters of the myotube cells obtained by screening, calculating tangent lines and normal lines of all points on one edge of the myotube cells obtained by screening, determining intersection points of the normal lines of all points on the edge of the myotube cells and the edge of the other myotube cell, calculating the distance between each point and the corresponding intersection point to be used as the width of the myotube cells at each point, and respectively calculating the average width, the widest width and the area of each myotube cell according to the width of the myotube cells at each point; and

and 105, performing statistical analysis on the myotube cell morphological parameters, measuring the morphological parameters of the multiple myotube cell images to obtain the morphological parameters of multiple myotube cells in the multiple myotube cell images, and performing statistics on the average width, the widest width and the area of the multiple myotube cells to obtain the average width distribution, the widest width distribution and the area distribution of the myotube cells.

FIG. 3 is a schematic interactive interface diagram of a method for measuring myotube cell morphological parameters provided by the invention. As shown in fig. 3, an interactive interface of a method for measuring morphological parameters of myotube cells includes a result display area 301 and an operation area 302, where the result display area 301 is used to display operation results including a segmented image, a cell average width distribution map, a cell widest width distribution map and a cell area distribution map, and as shown in fig. 4, the operation area 302 includes:

a 'select picture' button 311, and the myotube cell image to be detected can be selected by clicking the 'select picture' button 311;

a label 321 for displaying a picture address, configured to display the image address of the selected myotube cell image to be detected;

the image segmentation button 312 is clicked, and the cell segmentation of the myotube cells can be realized on the selected myotube cell image to be detected based on the deep learning network by clicking the image segmentation button 312;

the address button 313 for selecting the storage result is clicked, and the address for selecting the storage result 313 can be used for selecting the address for storing the morphological parameter result of the divided image;

a label 322 for displaying a storage address of the segmented image morphological parameter result, configured to display the storage address of the segmented image morphological parameter result;

the "cell morphology parameter measurement by clicking" button 314, the "cell morphology parameter measurement by clicking" button 314 can be carried out;

a label 323 for indicating completion of the measurement of the cellular morphological parameter and the time required for the operation to be completed and displaying the length of time taken for the measurement of the cellular morphological parameter;

the 'data to be processed is selected' button 315, and the 'data to be processed is selected' button 315 by clicking, so that the morphological parameter data of a plurality of myotube cell images can be selected for myotube cell morphological parameter statistics;

a "cell average width distribution map" button 316, and counting of the cell average width distribution can be performed by clicking the "cell average width distribution map" button 316;

a "cell widest width distribution map" button 317, and counting of the cell widest width distribution can be performed by clicking the "cell widest width distribution map" button 317; and

the "cell area distribution map" button 318 is clicked, and the cell area distribution can be counted by clicking the "cell area distribution map" button 318.

When measuring the morphological parameters of the myotube cells, firstly clicking the 'select picture' button 311 to select the image to be measured, the address of the image is displayed in the label 321 for displaying the picture address, then clicking the 'click on the split image' button 312 to split the image to be measured, as shown in fig. 5, the image split result is displayed in the result display area 301, next clicking the 'select save result address' button 313 to select the save address of the split image morphological parameter result, the save address is used for saving the cellular morphological parameter information in the measured myotube cell image, the cellular morphological parameter information is in the form of Excel and image, the save address is displayed in the label 322 for displaying the save result address, next clicking the 'click on the measure cellular morphological parameter' button 314, the measurement of the morphological parameters of the image to be measured is started, and after the measurement is completed, the time taken for the measurement is displayed in the label 323 indicating the completion of the measurement of the cellular morphological parameters and the required time. And repeating the process to measure the plurality of images to be measured. After the measurement of the morphological parameters of the multiple images of the myotube cells is completed, the morphological parameters of the multiple images of the myotube cells are counted, the "select data to be processed" button 315 is clicked, the morphological parameter data of the multiple images of the myotube cells are selected, and then the "cell average width distribution map" button 316 is clicked, the cell average width distribution of the selected multiple images of the myotube cells is counted, as shown in fig. 6, and the distribution map of the cell average width distribution is displayed in the result display area 301. If the "cell widest width distribution map" button 317 is clicked, the cell widest width distribution of the selected multiple myotube cell images can be counted, as shown in fig. 7, and the distribution map of the cell widest width distribution is displayed in the result display area 301; the cell area distribution of the selected images of the plurality of myotube cells can be counted by clicking the "cell area distribution map" button 318, as shown in fig. 8, and the distribution map of the cell area distribution is displayed in the result display area 301.

While various embodiments of the present invention have been described above, it should be understood that they have been presented by way of example only, and not limitation. It will be apparent to persons skilled in the relevant art that various combinations, modifications, and changes can be made thereto without departing from the spirit and scope of the invention. Thus, the breadth and scope of the present invention disclosed herein should not be limited by any of the above-described exemplary embodiments, but should be defined only in accordance with the following claims and their equivalents.

Claims

1. A method for measuring myotube cell morphological parameters is characterized by comprising the following steps:

pre-processing the myotube cell image, comprising:

segmenting the myotube cell image by adopting an image segmentation method based on a deep learning network;

carrying out binarization processing on the segmented image to obtain a binarization myotube cell image; and

carrying out connected domain division on the binaryzation myotube cell image, and calculating the area of each connected domain;

screening myotube cells according to the area of the connected domain; and

and calculating the morphological parameters of the myotube cells obtained by screening.

2. The method of claim 1, wherein the deep learning network-based image segmentation method employs a 12-layer U-net learning network.

3. The method of claim 1, wherein the screening of myotube cells comprises deleting myotube cells having an area less than a threshold.

4. The method of claim 1, wherein the calculation of the myotube cell morphological parameters comprises calculating an average width, a widest width and an area of each myotube cell.

5. The method of claim 4, wherein the calculation of the average width and the widest width comprises:

collecting the contour of the screened myotube cell, determining the top point of the cell, and dividing the contour of the cell into two cell edges;

calculating the tangent and the normal of each point on the edge of any myotube cell, determining the intersection point of the normal of each point on the edge of the cell and the edge of another myotube cell, and calculating the distance between each point and the corresponding intersection point, wherein the distance is the width of the myotube cell at each point; and

calculating the average width and the widest width of each myotube cell according to the width of the myotube cell at each point.

6. The method of claim 1, further comprising performing a statistical analysis of myotube cell morphology parameters.

7. The method of claim 6, wherein the statistical analysis of the myotube cell morphological parameters comprises statistical distribution of mean width, widest width and area of the myotube cells.

8. A method for providing a myotube cell morphology parameter measurement interaction interface, comprising:

providing a result display area configured to display the operation result including the segmented image, the cell average width distribution map, the cell widest width distribution map, and the cell area distribution map; and

providing an operating field comprising:

providing a label displaying a picture address, configured to display an image address of the selected myotube cell image to be tested;

providing a label for displaying a saving result address, wherein the label is configured to display the saving address of the segmented image morphological parameter result;

providing a label that indicates completion of measuring the cellular morphological parameter and a time required, configured to indicate a length of time it takes for the operation to be completed and display the measurement of the cellular morphological parameter;