A method and system for magnetic resonance spectroscopy image processing

Abstract

The present disclosure relates to a method for processing magnetic resonance spectroscopy images, including: obtaining a first image, where the first image is a magnetic resonance spectroscopy image; selecting, for the spectra of a specific substance, the image pixels whose spectra meet a first condition, and the image pixels meeting the first condition form a first closed curve; outputting a second image, where the second image is an image with the first closed curve. According to the present disclosure, a method for processing magnetic resonance spectroscopy images is provided, which can visually identify regions of interest.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing. Specifically, the present disclosure relates to a method and a system for processing magnetic resonance spectroscopy images. Background Art

[0002] Magnetic Resonance Spectroscopy (MRS) is the only non-invasive technique for determining the chemical composition of a specific tissue region in vivo. It is the perfect combination of magnetic resonance imaging and magnetic resonance spectroscopy technology, and is a new functional analysis and diagnosis method based on magnetic resonance imaging. There are many studies on magnetic resonance spectroscopy of the brain, including cerebral infarction, brain tumors, white matter and gray matter diseases, epilepsy and metabolic diseases, etc. In particular, there are many studies on brain tumors, which have great clinical application value for differentiating brain tumors from non-tumor lesions, differentiating benign and malignant brain tumors, grading malignant tumors, differentiating tumor recurrence from necrosis after surgery, and differentiating primary tumors from metastatic tumors. In addition, it can also differentiate craniopharyngioma from pituitary tumor, intracranial tumors from extracranial tumors, and determine central neurocytoma in the cerebral ventricle. Its application in the heart is mainly in the research of myocardial metabolism such as myocardial ischemia and cardiomyopathy. The main research of liver 31P-MRS includes liver metabolic diseases, hepatitis cirrhosis and liver tumors, etc. MRS can provide metabolic information of prostate tissue to help differentiate prostate cancer from benign prostatic hyperplasia. MRS can also non-invasively detect the metabolites of skeletal muscle phospholipid metabolism and energy metabolism and the intracellular pH value, and study the abnormal changes of phospholipid metabolism and energy metabolism in bone and soft tissue tumors. For magnetic resonance spectroscopy imaging, readability is the direction that the industry pays attention to. Summary of the Invention

[0003] In view of this, the present disclosure provides a method and a system for processing magnetic resonance spectroscopy images.

[0004] According to an exemplary embodiment of the present disclosure, a method for processing a magnetic resonance spectroscopy image, characterized by comprising: obtaining a first image, where the first image is a magnetic resonance spectroscopy image; selecting, for the spectrum of a specific substance, the image pixels whose spectrum meets a first condition, and the image pixels that meet the first condition form a first closed curve; outputting a second image, where the second image is an image with the first closed curve.

[0005] According to an exemplary embodiment of the present disclosure, the specific substance includes one kind, and the first condition is the pixels where the concentration of the specific substance is equal to a first value; or the specific substance includes two kinds, and the first condition is the pixels where the ratio of the concentrations of the two specific substances is equal to a first value.

[0006] According to an exemplary embodiment of the present disclosure, the method further includes: selecting image pixels whose spectra meet a second condition for the spectrum of the specific substance, the image pixels that meet the second condition form a second closed curve, and the second condition is that the concentration of the specific substance or the ratio of the concentrations of the two specific substances is equal to a second value; and the output second image is an image with the second closed curve.

[0007] According to an exemplary embodiment of the present disclosure, the second image is an image obtained by fusing a third image and the first closed curve: the third image is a CT image, a magnetic resonance image, a PET image, an X-ray image, or an ultrasound image.

[0008] According to an exemplary embodiment of the present disclosure, in response to a first operation, the first closed curve is adjusted, and the first operation is: an operation of dragging the first closed curve; and / or an operation of changing the first value.

[0009] According to an exemplary embodiment of the present disclosure, the determination of the first value includes: obtaining a fourth image; registering the first image and the fourth image; determining the first value according to the concentration value of the specific substance or the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image; wherein the fourth image is a CT image, a magnetic resonance image, a PET image, an X-ray image, or an ultrasound image.

[0010] According to an exemplary embodiment of the present disclosure, the determining the first value according to the concentration value of the specific substance or the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image includes: taking the average value of the concentration value of the specific substance / the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image as the first value; or taking the median value of the concentration value of the specific substance / the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image as the first value.

[0011] According to an exemplary embodiment of the present disclosure, the region of interest of the fourth image is obtained by an image recognition algorithm and / or manual calibration.

[0012] According to an exemplary embodiment of the present disclosure, a magnetic resonance spectroscopy image processing device includes: at least one processor; at least one computer storage medium storing a computer program, and the computer program realizes the method of the embodiment of the present disclosure when executed by the at least one processor.

[0013] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method in the embodiments of the present disclosure.

[0014] According to an exemplary embodiment of the present disclosure, a computer program product includes a computer program, wherein the computer program, when executed by a processor, implements the method in the embodiments of the present disclosure.

[0015] According to the magnetic resonance spectroscopy image processing method and system provided by the present disclosure, magnetic resonance spectroscopy images can be presented in a user-friendly manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, so that those of ordinary skill in the art can more clearly understand the above and other features and advantages of the present disclosure. In the drawings:

[0017] Figure 1 is a block diagram of the system architecture of an exemplary embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of the contour lines of a magnetic resonance spectroscopy image of an exemplary embodiment of the present disclosure;

[0019] Figure 3 is another schematic diagram of contour lines of an exemplary embodiment of the present disclosure;

[0020] Figure 4 is another schematic diagram of contour lines of an exemplary embodiment of the present disclosure;

[0021] Figure 5 is an integrated effect diagram of the surgical navigation system and contour lines of an exemplary embodiment of the present disclosure;

[0022] Figure 6 is another integrated effect diagram of the surgical navigation system and contour lines of an exemplary embodiment of the present disclosure.

[0023] Among them, the reference numerals are as follows:

[0024] 1 Imaging workstation 2 Magnetic resonance spectroscopy image processing module 3 Surgical navigation system 4 Image preprocessing 5 Preprocessed image transmission 6 Generate and fuse metabolite contour lines 7 Image transmission with contour lines 8 Default contour line 9 First contour line 10 Second contour line 11 Third contour line 12 Fourth contour line DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following examples are given to further elaborate on the present disclosure in detail. It should be understood that the specific embodiments described herein are only for explaining and interpreting the present disclosure, and are not used to limit the present disclosure.

[0026] In an exemplary embodiment, a method for processing magnetic resonance spectroscopy images includes: obtaining a first image, which is a magnetic resonance spectroscopy image; selecting, for the spectrum of a specific substance, the image pixels whose spectra meet a first condition, and the image pixels meeting the first condition form a first closed curve; and outputting a second image, which is an image with the first closed curve. Magnetic resonance spectroscopy images are often not intuitive enough, so pixels meeting the first condition are identified, and these pixels can form a closed curve around a region of interest. That is, when determining the first condition, the region of interest should be surrounded.

[0027] In an exemplary embodiment, the specific substance includes one type, and the first condition is the pixels where the concentration of the specific substance is equal to a first value; or the specific substance includes two types, and the first condition is the pixels where the ratio of the concentrations of the two specific substances is equal to a first value. Whether to use the concentration of one substance or the ratio of the concentrations of two substances depends on actual needs. In this way, the pixels where the concentration of a specific substance or the ratio of the concentrations of two specific substances is equal to the first value are all selected, forming a closed curve similar to the "contour line" in a map. Generally speaking, in the area within the contour line, the substance concentration or concentration ratio is higher or lower than the first value, which is very useful for observing certain regions of interest. For certain regions of interest, the concentration or concentration ratio of the specific substance is particularly high or particularly low. Circling the "contour line" of the specific concentration or concentration ratio can facilitate the observation of these regions of interest. For details, see Figure 2 , where multiple contour lines are depicted. Taking the default contour line 8 as an example, the closed curve formed by the contour line 8 surrounds an area where the concentration or concentration ratio of the specific substance is greater than or less than the first value, which is the region of interest. This display method highlights the size and shape of the region of interest, facilitating observation.

[0028] In an exemplary embodiment, the method further includes: selecting, for the spectrum of the specific substance, the image pixels whose spectra meet a second condition, and the image pixels meeting the second condition form a second closed curve, where the second condition is the pixels where the concentration of the specific substance or the ratio of the concentrations of two specific substances is equal to a second value; and the output second image is an image with the second closed curve. Still for details, see Figure 2 , where multiple contour lines are depicted. In addition to the default contour line 8, there are a first contour line 9, a second contour line 10, a third contour line 11, and a fourth contour line 12. Each contour line depicts a closed curve where the concentration or concentration ratio of a specific substance is equal to a specific value. Doctors or patients can intuitively see the shapes and sizes of the contour lines for each value and make comparisons. The number of contour lines and the contour line values can both be selected according to the needs of doctors.

[0029] In an exemplary embodiment, the second image is an image obtained by fusing a third image and a first closed curve: the third image is a CT image, a magnetic resonance image, a PET image, an X-ray image, or an ultrasound image. In many scenarios, doctors or users not only need to see the concentration or concentration ratio of a specific substance, but also need to see the anatomical structure image of the human body. The combination of such information will provide users with more intuitive and useful information. For specific reference, see Figures 5 - 6 , the contour line is sent to the surgical navigation system 3, showing the effect of the fusion of the contour line and the MR image. In the scenario of tumor resection, if appropriate contour line values are selected, the contour line can surround the area to be resected. This display method can simultaneously observe the shape of the resection area and the information of other anatomical structures, which is very helpful for doctors' judgment. The image that can form the anatomical structure image can be a CT image, a magnetic resonance image, a PET image, an X-ray image, or an ultrasound image.

[0030] In an exemplary embodiment, in response to a first operation, the first closed curve is adjusted. The first operation is: an operation of dragging the first closed curve; and / or an operation of changing the first value. There may be errors in simply relying on the concentration or concentration ratio of a specific substance to divide the region of interest. The human body situation is often very complex, and doctors' judgments based on a combination of multiple factors and experience are often more accurate. Therefore, this embodiment provides a means for adjusting the closed curve. First, if the user or doctor finds that the position and shape of the closed curve are not ideal, the contour line value can be changed to regenerate a new closed curve until the position and shape of the curve meet the requirements. Second, the local part of the closed curve can also be adjusted. Due to the complexity of the human body situation, the contour line may not meet the requirements locally. Therefore, this embodiment provides a means for dragging the local first closed curve to change the local shape of the closed curve. When dragging the local part, the edge of the anatomical image can be used as an alternative, that is, when the dragged point reaches a position, look for the edge of the anatomical image near this position and display the curve on these edges. If there is no edge near this position, the curve is adjusted to the actual position of the dragging operation.

[0031] In an exemplary embodiment, the determination of the first value includes: obtaining a fourth image; registering the first image and the fourth image; determining the first value according to the specific substance concentration value or the ratio of the two specific substance concentrations of the corresponding first image pixels at the edge of the region of interest in the fourth image; wherein the fourth image is a CT image, a magnetic resonance image, a PET image, an X-ray image or an ultrasound image. In this embodiment, a means for automatically determining the first value is provided. The experience of the doctor is important, but providing the doctor with a preliminary result for further adjustment after the doctor's reference can not only reduce the workload of the doctor, but also possibly obtain more accurate results. In this embodiment, first, a fourth image at the same position as the first image is obtained. The fourth image can represent the anatomical structure at the same position, such as a CT image, a magnetic resonance image, a PET image, an X-ray image or an ultrasound image. Secondly, on the fourth image, image recognition technology, such as an artificial intelligence algorithm, is used to identify the position and shape of the region of interest. For example, when identifying a tumor, the edge of the tumor is identified using an image recognition algorithm. Then, the pixel values in the first image corresponding to the identified edge in the fourth image, that is, the specific substance concentration values, are analyzed, and the first value, that is, the contour value or the threshold, is determined according to these pixel values. In this way, the information of images from different sources is fused, providing the possibility of obtaining more accurate data.

[0032] In an exemplary embodiment, the determination of the first value according to the specific substance concentration value or the ratio of the two specific substance concentrations of the corresponding first image pixels at the edge of the region of interest in the fourth image includes: taking the average value of the specific substance concentration value / the ratio of the two specific substance concentrations of the corresponding first image pixels at the edge of the region of interest in the fourth image as the first value; or taking the median value of the specific substance concentration value / the ratio of the two specific substance concentrations of the corresponding first image pixels at the edge of the region of interest in the fourth image as the first value. This embodiment exemplarily gives a method for determining the first value. After identifying the edge identified in the fourth image and the pixels at the corresponding position in the first image, it may be found that these pixel values are not all equal. Therefore, the average value of these pixels can be calculated as the first value, or the mean value of these pixels can be taken as the first value. When the variance of these pixels is large, pixel values that are far from the mean can also be discarded, leaving pixels whose variance meets the conditions, and then the mean or median value is taken as the first value. Wherein, the region of interest in the fourth image is obtained through an image recognition algorithm and / or manual calibration. Of course, it can also be obtained through manual adjustment and calibration after image recognition.

[0033] In an exemplary embodiment, a magnetic resonance spectroscopy image processing device is provided, including: at least one processor; at least one computer storage medium storing a computer program, and the computer program implements the method of the embodiments of the present disclosure when executed by the at least one processor.

[0034] In an exemplary embodiment, MRS functional imaging is applied to the pre-operative assessment and intraoperative navigation of gliomas, lymphomas, and metastases. This embodiment enables doctors to clearly understand the contour lines such as the peak changes of metabolites during pre-operative assessment, surgical planning, and intraoperative navigation, so as to confirm the degree of cutting during the operation. At the same time, the generated contour lines can be imported into the corresponding navigation system. The embodiment provides intelligent automatic contour drawing for metabolic images of magnetic resonance spectroscopy, and integrates the surgical navigation system, thereby providing processing software for clinical imaging reference for tumor resection surgery. Specifically referring to Figure 1 , the magnetic resonance spectroscopy image processing module 2 (MRS Toolkit) is the main processing module, which can automatically receive nuclear magnetic resonance spectroscopy images from the imaging workstation 1, and help radiologists automatically draw threshold-based contour lines of metabolites at the tumor site on the nuclear magnetic resonance spectroscopy images before surgery. At the same time, the automatically drawn data can be manually adjusted as needed to formulate a surgical plan for the tumor resection range. Then, the generated contour lines and threshold information can be automatically fused into the metabolite image, that is, the metabolite contour line 6 is generated and fused, and the image with the contour line is sent 7 to the surgical navigation system 3. The magnetic resonance spectroscopy image processing module 2 can also automatically analyze and compare the changes in the tumor site in the pre-operative and post-operative images, and provide quantitative indicators for post-operative evaluation. The imaging workstation 1 is a medical image post-processing workstation. The nuclear magnetic resonance spectroscopy image needs to be pre-processed 4 on this workstation to generate the corresponding metabolite image for subsequent automatic drawing and fusion. The imaging workstation 1 also provides basic DICOM services, so that the metabolite image can be sent 5 to the magnetic resonance spectroscopy image processing module 2 through the DICOM service pre-processed image for subsequent image post-processing. The surgical navigation system 3 receives the navigation data processed by the magnetic resonance spectroscopy image processing module 2, enabling doctors to have a clear and intuitive understanding of the tumor site during the operation. In the field of maps, contour lines refer to the closed curves connected by adjacent points with equal elevations on a topographic map. Introducing the concept of contour lines can intuitively mark the active areas of tumors in the tumor metabolism map, enabling doctors to quickly and accurately judge the cutting range of tumors during surgery.

[0035] Calculating contour lines, as a key and core step, has an important impact on subsequent related processing. In this embodiment, the contour lines of the specified image are calculated based on the Marching Squares algorithm, and the coordinates of each contour line are automatically extracted and saved to generate the region of interest (ROI) curve, which is convenient for later contour line drawing and manual deletion or adjustment of the ROI curve on the image. The above algorithm is run on each image in the sequence to generate all contour line ROI data of the sequence and save it in the database for subsequent preview and contour line adjustment.

[0036] In this embodiment, automatic delineation and editing of tumor threshold contour lines based on the characteristic peak ratio of specified metabolites are carried out. The changes before and after treatment can be used as a reference for treatment effect and prognosis. In glioma examination, NAA (a substance that only exists in neurons and their processes, which can reflect the functional state of neurons, and a decrease represents neuron loss) and Cho (a component of cell membrane phospholipid metabolism, which participates in the synthesis and metabolism of cell membranes and is used to evaluate cell proliferation) are utilized. Gliomas will damage neurons, resulting in a decrease in NAA. At the same time, as the damage increases, there is also an increase in cell membrane synthesis and cell repair, so Cho increases. As the malignancy of gliomas increases, NAA significantly decreases and Cho increases negatively. Therefore, the Cho / NAA ratio contributes greatly to the differentiation of high-grade and low-grade gliomas. Generally, it is considered that the Cho / NAA ratio of high-grade tumors > 4, while for WHO grade I and II tumors, the ratio is usually between 2 and 4. According to the characteristics of the metabolic images of the tumor and the needs of surgical resection, radiologists specify different thresholds to be delineated, and then the program will automatically calculate the contour lines according to the corresponding algorithms and display the results on the interface. At the same time, a function for manually adjusting the automatically generated contour lines is also provided, facilitating radiologists to make local fine-tuning of the contour lines. And the system can save the corresponding contour line data, facilitating subsequent comparative analysis of the preoperative and postoperative results. For details, please refer to Figure 2 .

[0037] In Figures 3 - 4 , the contour line data and voxel data are fused with the metabolic images. In order to be able to be fused with the intraoperative navigation system, the structured contour line data and voxel data are respectively fused on the original images through proprietary algorithms, generating two new series respectively. In Figure 3 , the value is the Cho / NAA data value corresponding to this voxel. A voxel is the scanning space volume corresponding to the spectrum.

[0038] In Figures 5 - 6 , it shows the integration with the surgical navigation system 3, enabling the surgeon to view the corresponding contour line data in real time, facilitating the confirmation of the cutting range of the tumor part during the operation. The images used here are magnetic resonance images, which are obtained by fusing the fused ratio sequence with the original magnetic resonance images in the navigation system.

[0039] The exemplary embodiments of the present disclosure have at least the following features:

[0040] (1) In preoperative planning, it can help doctors perform quantitative auxiliary analysis for preoperative surgical planning, and at the same time can formulate high-precision surgical cutting criteria, which is beneficial to the postoperative rehabilitation of patients in the later stage.

[0041] (2) During the operation, the generated contour fusion image can be displayed in real time and provide real-time guidance and reminders for the surgeon regarding the corresponding tumor resection range in the existing navigation system.

[0042] (3) In the postoperative evaluation, it is possible to quantitatively compare multiple pre-operative and post-operative images, effectively evaluate the surgical effect, and facilitate the adjustment of subsequent treatments.

[0043] (4) Through the DICOM standard protocol, the contour data is stored and transmitted using the standard DICOM ROI structure, and different medical information systems are integrated for the transmission of imaging data.

[0044] According to another aspect of the embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the three-dimensional image display method according to any one of the above embodiments of the present disclosure.

[0045] According to another aspect of the embodiments of the present disclosure, there is provided a computer program product including a computer program, wherein the computer program, when executed by a processor, implements the three-dimensional image display method according to any one of the above embodiments of the present disclosure.

[0046] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0047] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0048] In the context of the present disclosure, a computer-readable storage medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the readable storage medium include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0049] It should be understood that the various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and no limitation is made herein.

[0050] Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above methods, systems, and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only defined by the appended claims and their equivalent scope after authorization. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, the steps can be executed in an order different from that described in the present disclosure. Importantly, with the evolution of technology, many of the elements described herein can be replaced by equivalent elements that emerge after the present disclosure.

[0051] In addition, it should be noted that, in the above specific embodiments, the various specific technical features described can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure does not separately describe various possible combinations.

Claims

1. A method for processing magnetic resonance spectroscopy images, characterized in that: It includes: Obtain a first image, where the first image is a magnetic resonance spectroscopy image; For the spectrum of a specific substance, select the image pixels whose spectra meet the first condition, and the image pixels that meet the first condition form a first closed curve; Output a second image, where the second image is an image with the first closed curve; Wherein, the specific substance includes one kind, and the first condition is the pixels where the concentration of the specific substance is equal to the first value; Or The specific substance includes two kinds, and the first condition is the pixels where the ratio of the concentrations of the two specific substances is equal to the first value; Wherein, the second image is an image formed by fusing a third image and the first closed curve: the third image is a CT image, a magnetic resonance image, a PET image, an X-ray image or an ultrasound image.

2. The method for processing magnetic resonance spectroscopy images according to claim 1, the method further includes: For the spectrum of the specific substance, select the image pixels whose spectra meet the second condition, and the image pixels that meet the second condition form a second closed curve, and the second condition is the pixels where the concentration of the specific substance or the ratio of the concentrations of the two specific substances is equal to the second value; and the output second image is an image with the second closed curve.

3. The method for processing magnetic resonance spectroscopy images according to claim 1, in response to a first operation, adjust the first closed curve, and the first operation is: An operation of dragging the first closed curve; And / or An operation of changing the first value.

4. The method for processing magnetic resonance spectroscopy images according to claim 1, wherein the determination of the first value includes: Obtain a fourth image; Register the first image and the fourth image; Determine the first value according to the concentration value of the specific substance or the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image; Wherein, the fourth image is a CT image, a magnetic resonance image, a PET image, an X-ray image or an ultrasound image.

5. The method for processing magnetic resonance spectroscopy images according to claim 4, wherein the determination of the first value according to the concentration value of the specific substance or the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image includes: Taking the average value of the concentration value of the specific substance / the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image as the first value; Or Taking the median value of the concentration value of the specific substance / the ratio of the concentrations of the two specific substances of the corresponding first image pixels at the edge of the region of interest of the fourth image as the first value.

6. The method for processing magnetic resonance spectroscopy images according to claim 4 or 5, wherein the region of interest of the fourth image is obtained by an image recognition algorithm and / or manual calibration.

7. A magnetic resonance spectroscopy image processing device, characterized in that: It includes: At least one processor; At least one computer storage medium storing a computer program which, when executed by the at least one processor, implements the method according to any one of claims 1-6.

8. A computer-readable storage medium storing a computer program, wherein, the computer program, when executed by a processor, implements the method according to any one of claims 1-6.

9. A computer program product comprising a computer program, wherein, the computer program, when executed by a processor, implements the method according to any one of claims 1-6.

Images