CN115471440A - Ultrasonic cardiogram analysis system based on space mapping - Google Patents

Abstract

The present disclosure provides an echocardiogram analysis system based on spatial mapping, comprising: a data acquisition module configured to: obtaining an echocardiogram; a pre-processing module configured to: preprocessing the obtained echocardiogram; an image processing module configured to: obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model; the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are subjected to partition and measurement task association through a space mapping module, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time; the heart apex blood ejection device can automatically segment the myocardium, the left ventricle and the left atrium in the two apical chambers and the four apical chambers, and directly output the left ventricle volume and the ejection fraction in the contraction and relaxation periods.

Description

Ultrasonic cardiogram analysis system based on space mapping

Technical Field

The present disclosure relates to the field of medical image processing technologies, and in particular, to an echocardiogram analysis system based on spatial mapping.

Background

The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.

In clinical applications, the use of echocardiography for cardiac function assessment is the primary basis for physicians to diagnose heart disease. By performing left atrium segmentation and measurement on paired apical views (apical two-chamber and apical four-chamber), important medical indexes such as left ventricle volume change and ejection fraction can be calculated.

The inventor finds that at present, clinicians need to manually segment the left ventricle contour, the working efficiency and the repeatability are low, and the rapid echocardiogram segmentation cannot be realized; and currently, the left atrium segmentation result, the left ventricle volume change and the ejection fraction value result can not be obtained simultaneously according to the echocardiogram.

Disclosure of Invention

In order to solve the deficiencies of the prior art, the present disclosure provides an echocardiogram processing system based on spatial mapping, which can automatically segment the myocardium, the left ventricle and the left atrium in the apical two-chamber and apical four-chamber, and directly output the left ventricle volume and ejection fraction in the systolic and diastolic periods.

In order to achieve the purpose, the following technical scheme is adopted in the disclosure:

a first aspect of the present disclosure provides an echocardiography analysis system based on spatial mapping.

An echocardiography analysis system based on spatial mapping, comprising:

a data acquisition module configured to: obtaining an echocardiogram;

a pre-processing module configured to: preprocessing the obtained echocardiogram;

an image processing module configured to: obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

Furthermore, in the SegQ-Net network model, the segmentation characteristic diagram and the measurement characteristic diagram respectively pass through the segmentation module and the measurement module to output segmentation results and measurement results.

Further, the encoder-decoder partition network uses UNet + + as a base network.

Further, the spatial mapping module adopts Non-local and channel compression-excitation operations, so that the input characteristic maps of the two tasks keep the same spatial input mode.

Further, the echocardiographic segmentation results include myocardium, left ventricle and left atrium segmentation results.

Further, the cardiac function numerical results include systolic and/or diastolic left ventricular volume and ejection fraction numerical measurements.

Further, the acquired medical image is preprocessed, and the preprocessing comprises the following processes:

flipping the input image and the corresponding label map with a probability of 0.5;

cropping the given image to random size and aspect ratio;

and adjusting the cropped image to a given size.

Further, echocardiography is a medical image of apical two-chamber and apical four-chamber.

A second aspect of the present disclosure provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, performs the steps of:

obtaining an echocardiogram;

preprocessing the obtained echocardiogram;

obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

A third aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor executes the program to implement the following steps:

obtaining an echocardiogram;

preprocessing the obtained echocardiogram;

obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

Compared with the prior art, the beneficial effect of this disclosure is:

1. the system, medium, or electronic device of the present disclosure can automatically segment the myocardium, left ventricle, and left atrium chambers in apical two and apical four chambers, and directly output the left ventricle volume and ejection fraction during systole and diastole.

2. According to the system, the medium or the electronic device, the spatial mapping module adopts Non-local and channel compression-excitation operations, so that the input characteristic diagrams of the two tasks keep the same spatial input mode, and spatial information in the tasks can be fully connected and measured.

Advantages of additional aspects of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.

Fig. 1 is a schematic diagram of an experimental data set provided in example 1 of the present disclosure.

Fig. 2 is a schematic flowchart of a working method of the echocardiography analysis system based on spatial mapping according to embodiment 1 of the present disclosure.

Detailed Description

The present disclosure is further described with reference to the following drawings and examples.

It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.

The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

Example 1:

an embodiment 1 of the present disclosure provides an echocardiogram analysis system based on spatial mapping, including:

a data acquisition module configured to: obtaining an echocardiogram;

a pre-processing module configured to: preprocessing the acquired echocardiogram;

an image processing module configured to: and obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model.

Specifically, the method comprises the following steps:

collecting medical images of a central apex two-chamber and a central apex four-chamber of an echocardiogram by taking a patient as a unit, and labeling the inner membrane and the outer membrane of the left atrium to obtain experimental data;

preprocessing experimental data to obtain a data set required by an experiment;

inputting the experimental data set into a SegQ-Net network for training, wherein the output of the network is an echocardiogram myocardium, a left ventricle and a left atrium segmentation result and a systolic period and a diastolic period left ventricle volume and ejection fraction numerical value result.

Firstly, corresponding equipment is utilized to acquire an echocardiogram image, and the echocardiogram image of each experimental object is acquired under the support of hospital data. After the images are collected, the collected images are processed to be made into an experimental data set.

The process of constructing the experimental data set is shown in fig. 1 and comprises: three parts of data acquisition, data annotation and data enhancement pretreatment;

the data acquisition comprises acquiring two different echocardiography images of a patient, firstly selecting DICOM images of an apical two-chamber and an apical four-chamber from the echocardiography by taking the patient as a unit and converting the images into a PNG format.

It should be noted that the data provided by the present embodiment is all data obtained from a legal source.

In the data annotation, the PNG image is manually annotated by LabelMe, the outlines of the inner membrane and the outer membrane of the left atrium are respectively drawn point by point during annotation, and an original drawing (img.png) and a label drawing (label.png) are read from a generated JSON file to serve as an experimental data set.

The method for enhancing and preprocessing the data of the segmented data set comprises the following steps:

(1) And (4) random overturning: flipping the input image and the corresponding label with a probability of 0.5;

(2) Random cutting: cropping the given image to random size and aspect ratio;

(3) Adjusting the size: the input image is resized to a given size.

The measurement data set needs to extract measurement indexes (left ventricular systolic volume, left ventricular diastolic volume and left ventricular ejection fraction) and corresponding numerical results, and the measurement indexes are stored in a txt file by taking a patient as a unit.

And inputting the experimental data set into a SegQ-Net network to obtain an echocardiogram left atrium segmentation result and a measurement result. The specific calculation flow is as follows:

as shown in FIG. 2, an input image x is passed through an encoder θ (-) and a decoder

The encoder characteristic obtained after is f ₁ (= θ (x)) and

f ₁ and f ₂ Obtaining a segmentation feature map F after inputting the space mapping module phi (-) ₁ And measuring the characteristic diagram F ₂ And then the final segmentation result and the final measurement result are obtained through the segmentation module and the measurement module respectively.

In this embodiment, segQ-Net uses the encoder-decoder partition network as a skeleton network, and the encoder output and the decoder output are associated with each other through a space mapping module for partition and measurement tasks, and output partition and measurement feature maps. And the segmentation and measurement characteristic graphs are respectively output segmentation and measurement results through the segmentation and measurement module. The encoder-decoder adopts UNet + + as a basic network, and the spatial mapping module adopts Non-local and channel compression-excitation operations, so that the input characteristic diagrams of the two tasks keep the same spatial input mode, and spatial information in the segmentation and measurement tasks is fully connected.

Example 2:

an embodiment 2 of the present disclosure provides a computer-readable storage medium on which a program is stored, the program implementing the steps of, when executed by a processor:

obtaining an echocardiogram;

preprocessing the obtained echocardiogram;

obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

Example 3:

a third aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor executes the program to implement the following steps:

obtaining an echocardiogram;

preprocessing the obtained echocardiogram;

obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are associated with a partition and measurement task through a space mapping module, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (10)

1. An echocardiography analysis system based on spatial mapping, characterized by: the method comprises the following steps:

a data acquisition module configured to: obtaining an echocardiogram;

a pre-processing module configured to: preprocessing the obtained echocardiogram;

an image processing module configured to: obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

2. The spatial mapping based echocardiography analysis system of claim 1, wherein:

in the SegQ-Net network model, the segmentation characteristic diagram and the measurement characteristic diagram are respectively output a segmentation result and a measurement result through a segmentation module and a measurement module.

3. The spatial mapping-based echocardiography analysis system of claim 1, wherein:

the encoder-decoder split network uses UNet + + as a base network.

4. The spatial mapping based echocardiography analysis system of claim 1, wherein:

the spatial mapping module adopts Non-local and channel compression-excitation operations, so that the input characteristic maps of the two tasks keep the same spatial input mode.

5. The spatial mapping based echocardiography analysis system of claim 1, wherein:

the echocardiographic segmentation results include myocardium, left ventricle, and left atrium segmentation results.

6. The spatial mapping based echocardiography analysis system of claim 1, wherein:

the cardiac function numerical results include systolic and/or diastolic left ventricular volume and ejection fraction numerical measurements.

7. The spatial mapping based echocardiography analysis system of claim 1, wherein:

preprocessing the acquired medical image, comprising the following processes:

flipping the input image and the corresponding label map with a probability of 0.5;

cropping the given image to random size and aspect ratio;

and adjusting the cropped image to a given size.

8. The spatial mapping based echocardiography analysis system of claim 1, wherein:

echocardiography is a medical image of the apical two-chamber and apical four-chamber.

9. A computer-readable storage medium on which a program is stored, the program realizing the steps of, when executed by a processor:

obtaining an echocardiogram;

preprocessing the obtained echocardiogram;

obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

10. An electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor implements the following steps when executing the program:

obtaining an echocardiogram;

preprocessing the obtained echocardiogram;

obtaining an echocardiogram segmentation result and a cardiac function numerical value measurement result according to the preprocessed echocardiogram and a preset SegQ-Net network model;

the SegQ-Net network model takes an encoder-decoder partition network as a skeleton network, the encoder output and the decoder output are related to each other through a space mapping module for partitioning and measuring tasks, and a partition characteristic diagram and a measurement characteristic diagram are output at the same time.

Images