WO2021253732A1 - Procédé et appareil de traitement d'image médicale, dispositif informatique et support d'enregistrement - Google Patents

Procédé et appareil de traitement d'image médicale, dispositif informatique et support d'enregistrement Download PDF

Info

Publication number
WO2021253732A1
WO2021253732A1 PCT/CN2020/133036 CN2020133036W WO2021253732A1 WO 2021253732 A1 WO2021253732 A1 WO 2021253732A1 CN 2020133036 W CN2020133036 W CN 2020133036W WO 2021253732 A1 WO2021253732 A1 WO 2021253732A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
medical
area
medical image
original
Prior art date
Application number
PCT/CN2020/133036
Other languages
English (en)
Chinese (zh)
Inventor
沈嘉浩
宋珂
Original Assignee
飞依诺科技(苏州)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 飞依诺科技(苏州)有限公司 filed Critical 飞依诺科技(苏州)有限公司
Publication of WO2021253732A1 publication Critical patent/WO2021253732A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20132—Image cropping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30048—Heart; Cardiac
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30056—Liver; Hepatic

Definitions

  • This application relates to the technical field of medical equipment, and in particular to a processing method, device, computer equipment, and storage medium for medical images.
  • DICOM Digital Imaging and Communications in Medicine
  • DICOM medical images are characterized by high image resolution and high image quality. But at the same time, the amount of data is huge, and there will be some difficulties in its archiving, transmission and management. Therefore, in many cases, DICOM medical images are saved as compressed images with extraneous information, and the saved medical images contain medical images and sensitive information that is not a medical image (such as patient number, examination time) , Check location and other personal privacy information).
  • a method for processing medical images includes:
  • the binarized image of the original medical image includes a plurality of connected regions
  • the obtaining the local entropy grayscale image of the original medical image includes:
  • the gray-scale image of the original medical image is traversed by using a conversion matrix of a preset size to obtain the gray-scale image of the local entropy of the original medical image.
  • the traversing the grayscale image of the original medical image by using a conversion matrix of a preset size to obtain the local entropy grayscale image of the original medical image includes:
  • the local entropy matrix is normalized to obtain the local entropy grayscale image of the original medical image.
  • the performing image segmentation on the local entropy grayscale image to obtain the binarized image of the original medical image includes:
  • An open operation is performed on the binarized image of the local entropy grayscale image to obtain the binarized image of the original medical image.
  • the determining the connected area corresponding to the medical ontology area in the plurality of connected areas according to the area of each of the connected areas includes:
  • the connected area with the largest area is determined as the connected area corresponding to the medical ontology area.
  • the connected area is provided with corresponding corner coordinates; the extraction of the medical image of the medical ontology area from the original medical image according to the connected area corresponding to the medical ontology area includes :
  • the original medical image is cropped according to the corner coordinates of the connected region corresponding to the medical body region to obtain the medical image of the medical body region.
  • the original medical image is an ultrasound image including sensitive information
  • the medical image of the medical body region is an ultrasound image generated when an ultrasound probe scans a target part.
  • a medical image processing device includes:
  • the first acquisition module is used to acquire the local entropy grayscale image of the original medical image, the original medical image including the medical ontology area;
  • An image segmentation module configured to perform image segmentation on the local entropy grayscale image to obtain a binarized image of the original medical image; the binarized image of the original medical image includes a plurality of connected regions;
  • An area determining module configured to determine the connected area corresponding to the medical ontology area among the multiple connected areas according to the area of each of the connected areas;
  • the image extraction module is used to extract the image of the medical ontology area from the original medical image according to the connected area corresponding to the medical ontology area.
  • a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the medical image processing method described in any one of the foregoing when the computer program is executed.
  • the above-mentioned medical image processing method, device, computer equipment and storage medium obtain the local entropy gray image of the original medical image, the original medical image includes the medical ontology area; perform image segmentation on the local entropy gray image to obtain The binarized image of the original medical image, and determine multiple connected regions in the binarized image; thereby determining the connected region corresponding to the medical ontology region according to the area of each connected region; further, due to the binary If the chemical image corresponds to the original medical image, then according to the connected area corresponding to the medical ontology area, the medical image of the medical ontology area can be accurately and completely extracted from the original medical image, and sensitive information in the medical image can be accurately and completely extracted. Desensitization.
  • FIG. 1 is a schematic flowchart of a method for processing medical images in an embodiment
  • Fig. 2a is a schematic flowchart of step S102 in an embodiment
  • Figure 2b is a schematic diagram of a flow of local entropy extraction in an embodiment
  • Fig. 4 is a schematic diagram of a flow of local entropy extraction in another embodiment
  • FIG. 3 is a schematic flowchart of step S206 in an embodiment
  • Fig. 4a is a schematic flowchart of step S104 in an embodiment
  • Figure 4b is a schematic view of the process of the corrosion operation in an embodiment
  • Figure 4c is a schematic flow chart of an expansion operation in an embodiment
  • Figure 5a is a schematic flowchart of an ultrasound image processing method in an embodiment
  • 5b to 5c are schematic diagrams of original ultrasound images in an embodiment
  • Figure 5d is a schematic diagram of a local entropy grayscale image in an embodiment
  • Figure 5e is a schematic diagram of a binarized image in an embodiment
  • Figure 5f is a schematic diagram of a binarized image after an open operation in an embodiment
  • Figure 5g is a schematic diagram of the ultrasound body region (the largest connected region) in an embodiment
  • 5h to 5i are schematic diagrams of ultrasound body images extracted in an embodiment
  • Figure 6 is a structural block diagram of a medical image processing device in an embodiment
  • Fig. 7 is an internal structure diagram of a computer device in an embodiment.
  • a method for processing medical images includes the following steps:
  • S102 Obtain a local entropy grayscale image of the original medical image, where the original medical image includes the medical ontology region.
  • the original medical image is a medical image image obtained through medical imaging technologies such as computed tomography (CT), nuclear magnetic resonance (MRI), ultrasound imaging (US), digital silhouette angiography (DSA), etc., which include medical ontology images And sensitive information that is not part of the medical ontology image.
  • the medical ontology image is an image obtained by scanning a part of interest.
  • the medical ontology area is a partial area in the original medical image corresponding to the patient's area of interest.
  • the imaging device After obtaining the medical ontology image corresponding to the part of interest, the imaging device generates and displays sensitive information based on personal privacy information such as the patient number, examination time, and examination location to generate the original medical image.
  • the part of interest can be body organs such as the uterus and the heart.
  • the original medical image may be an image saved in the form of a DICOM (Digital imaging and Communications in Medicine, medical imaging imaging and communication standard) medical image compressed and with extraneous information.
  • the format of the original medical image may be
  • the local entropy gray-scale image of the original medical image is obtained from a computer locally or a computer device connected in communication with the computer.
  • the local entropy gray-scale image refers to the gray-scale image obtained by performing local entropy calculation on the gray-scale image corresponding to the original medical image and updating the gray value of each pixel in the original medical image.
  • the local entropy refers to the entropy calculated within the limited N*N (such as 5*5) range of the digital image.
  • the entropy of a digital image is a special statistical form, which reflects the amount of information contained in the aggregation features of the gray-scale distribution in the image.
  • the entropy expression of a gray-scale digital image is:
  • i is the gray value of the pixel
  • p i is the probability that the pixel value i appears in the entire digital image.
  • S104 Perform image segmentation on the local entropy grayscale image to obtain a binarized image of the original medical image.
  • image segmentation refers to the technology and process of dividing an image into several specific regions with unique properties and extracting regions of interest or target parts.
  • the medical ontology image is extracted from the original medical image.
  • the gray value of each pixel in the binarized image is 0 or 255, and the entire image presents an obvious black and white effect.
  • Connected components generally refer to an image area composed of adjacent pixels that have the same pixel value.
  • the binarized image of the original medical image includes multiple connected regions. The area of each connected area may be different or equal.
  • the segmentation threshold is set according to the gray value of each pixel in the local entropy gray image, and the gray value of each pixel in the local entropy gray image is updated, such as updating If it is 0 or 255, it realizes image segmentation of the local entropy grayscale image of the original medical image to obtain the binarized image of the original medical image.
  • the connected area in the binarized image is determined according to the gray value of each pixel in the binarized image.
  • the original medical image contains the medical ontology area corresponding to the medical ontology image and the sensitive area corresponding to the sensitive information.
  • the medical body area and the sensitive area respectively correspond to their own connected areas. Since the medical ontology area and the sensitive area have areas of different sizes in the original medical image, the connected area corresponding to the medical ontology area can be determined from the multiple connected areas of the binarized image according to the area of the connected area.
  • the connected area corresponding to the medical ontology area is determined among the multiple connected areas of the binarized image, thereby determining the position or distribution of the medical ontology area in the binarized image. Because the binarized image corresponds to the original medical image, the position or distribution of the medical ontology area in the original medical image can be known, so that the medical image of the medical ontology area can be extracted from the original medical image.
  • the original medical image includes the medical ontology area; performing image segmentation on the local entropy gray image to obtain the binary image of the original medical image, and determine Multiple connected regions in the binarized image; thereby determining the connected region corresponding to the medical ontology region according to the area of each connected region; further, since the binarized image corresponds to the original medical image, the connected region corresponding to the medical ontology region , It can accurately and completely extract the medical image of the medical ontology area from the original medical image, and desensitize the sensitive information in the medical image. Further, the extracted medical image contains complete medical image information, which solves the technical problem of the lack of medical image information in the traditional technology.
  • step S102 obtaining the local entropy grayscale image of the original medical image includes the following steps:
  • S204 Perform grayscale processing on the original medical image to obtain a grayscale image of the original medical image
  • S206 Traverse the grayscale image of the original medical image by using the conversion matrix of the preset size to obtain the local entropy grayscale image of the original medical image.
  • the conversion matrix is a N*N matrix with a preset size, which is used to delineate the range of N*N in the grayscale image of the original medical image, and calculate the local entropy value in the range of N*N.
  • the original medical image is obtained from the computer locally or from a computer device that is in communication with the computer.
  • the original medical image may have colors.
  • the original medical image is gray-scale processed to obtain the gray-scale image of the original medical image.
  • the local entropy of the original medical image is extracted according to the pixel value of each pixel within the range of the 5*5 conversion matrix, thereby using the 5*5 conversion matrix Traverse the gray-scale image of the original medical image to obtain the local entropy gray-scale image of the original medical image.
  • the grayscale image of the original medical image is obtained by performing grayscale processing on the original medical image; and the grayscale image of the original medical image is traversed using a conversion matrix of a preset size to obtain the local entropy grayscale of the original medical image
  • the image can highlight the medical ontology area and sensitive area in the original medical image, which provides a basis for the subsequent extraction of the medical ontology image.
  • step S206 the gray-scale image of the original medical image is traversed by using a conversion matrix of a preset size to obtain the gray-scale image of local entropy of the original medical image, which includes:
  • the pixel value of each pixel within the range of the N*N conversion matrix is calculated, and the conversion matrix is obtained within the range of N*N.
  • the local entropy value Use the local entropy in the N*N range to update the gray value of the pixel at the center of the N*N matrix, and so on, use the N*N conversion matrix to traverse the gray image of the original medical image to obtain the local entropy matrix. Further, normalize the region entropy matrix to a preset gray value such as (0 value 255), and set it to be eight bits deep for each pixel, that is, a single-channel, eight-bit deep region is obtained Entropy grayscale image. It is understandable that the size of N is an empirical value and can be selected according to actual conditions.
  • the conversion matrix is used to traverse the grayscale image of the original medical image, and the local entropy of each pixel corresponding to the conversion matrix in the grayscale image is calculated; the grayscale of the pixel corresponding to the center position of the conversion matrix in the grayscale image is calculated The value is updated to the calculated local entropy value to obtain the local entropy matrix; the local entropy matrix is normalized to obtain the local entropy grayscale image of the original medical image.
  • the medical ontology area and sensitive area can be further highlighted in the original medical image to ensure the accuracy and completeness of the extraction of the medical ontology image.
  • step S104 image segmentation is performed on the local entropy grayscale image to obtain a binary image of the original medical image, including:
  • S402 Perform image threshold segmentation on the local entropy gray image to obtain a binarized image of the local entropy gray image;
  • S404 Perform an open operation on the binarized image of the local entropy grayscale image to obtain the binarized image of the original medical image.
  • the image threshold segmentation can use the Otsu method (OTSU method).
  • Otsu method Otsu method
  • the Dajin Law is well known to the art staff, so I won’t repeat it here.
  • the open operation includes the process of first corroding and then expanding the image, which is an operation performed on the binarized image to change the size, thickness, and adhesion of the image, thereby optimizing the outline of the binarized image.
  • the corrosion operation is to corrode the edges of the object.
  • the specific operation method is that the M*N rectangle is used as a template to process each pixel in the image as follows: pixel x is at the center of the template, traverse all other pixels covered by the template according to the size of the template, and modify the value of pixel x to all The smallest value in a pixel.
  • the result of this operation is to corrode the prominent points on the periphery of the image.
  • the expansion operation expands the outline of the image.
  • the operation method is similar to the corrosion operation.
  • the M*N rectangle is used as a template to traverse each pixel of the image. The difference is that the value of the modified pixel is not the smallest value among all pixels, but the largest value. The result of this operation will connect and extend the prominent points on the periphery of the image.
  • the segmentation threshold is set according to the gray value of each pixel in the local entropy gray image, and the gray value of each pixel in the local entropy gray image is updated, such as updating If it is 0 or 255, it realizes the image threshold segmentation of the local entropy grayscale image of the original medical image to obtain the binarized image of the original medical image. Further, in order to optimize the contours in the binarized image, the binarized image of the local entropy grayscale image is first eroded and then expanded to obtain the binarized image of the original medical image, which is based on each of the binarized images. The gray value of the pixel determines the connected area in the binarized image.
  • the binarized image of the local entropy gray image is obtained, which realizes the prominent display of the medical ontology area and the sensitive area in the original medical image, and further controls
  • the binarized image of the local entropy grayscale image performs the open operation to obtain the binarized image of the original medical image, optimize the contour in the binarized image, and ensure the accuracy of the connected region, so that the original medical image can be accurately and completely obtained from the original medical image.
  • the medical image of the medical ontology area is extracted from the image, and the sensitive information in the medical image is desensitized.
  • determining the connected area corresponding to the medical ontology area among the multiple connected areas includes: among the multiple connected areas, determining the connected area with the largest area as the connected area corresponding to the medical ontology area Connected areas.
  • the medical ontology area is the area with the largest area in the original medical image. Therefore, among the multiple connected regions, the connected region with the largest area is determined as the connected region corresponding to the medical ontology region.
  • the connected area is provided with corresponding corner coordinates.
  • extracting the medical image of the medical ontology area from the original medical image includes: cutting the original medical image according to the corner coordinates of the connected area corresponding to the medical ontology area to obtain the medicine of the medical ontology area image.
  • the corner points are the vertices of the polygonal shape of the connected region.
  • the connected area has corner coordinates in the binarized image of the original medical image, and the binarized image corresponds to the original medical image. It can be seen that the position of the medical ontology area in the original medical image is explained by taking the connected area of the quadrilateral as an example.
  • Each pixel in the area corresponds to a coordinate value, from which the maximum x-axis coordinate value x1 and the minimum x-axis coordinate value x2 are respectively obtained, and the maximum y-axis coordinate value y1 and the minimum y-axis coordinate value y2 are obtained.
  • the corner coordinates are (x1, y1), (x1, y2), (x2, y1), (x2, y2).
  • the position of the medical ontology area in the original medical image is determined, so that the original medical image is cropped according to the position of the medical ontology area in the original medical image to obtain the medical ontology Medical image of the area.
  • the shape of the connected area is a rectangle
  • the corner coordinates are the coordinates of the four vertices of the rectangle
  • the area within the rectangular frame is the medical ontology area
  • the medical ontology is extracted from the original medical image based on the four vertices of the rectangle. Medical image of the area.
  • the original medical image is an ultrasound image including sensitive information
  • the medical image of the medical body region is an ultrasound image generated when the ultrasound probe scans the target part.
  • the ultrasound image is generated by processing the echo collected by the ultrasound probe.
  • the medical image is explained by taking an ultrasound image as an example.
  • the medical image processing method includes the following steps:
  • the original ultrasound image includes an ultrasound body region 510.
  • the ultrasound body area corresponds to the target area scanned by the ultrasound probe.
  • the ultrasound image in the ultrasound body region 510 is a “pure” ultrasound body image required for scientific research.
  • the original ultrasound image also includes a sensitive area 520, in which sensitive information such as the time and location of the patient's examination are displayed.
  • S504 Perform grayscale processing on the original ultrasound image to obtain a grayscale image of the original ultrasound image.
  • S506 Use the conversion matrix to traverse the grayscale image of the original ultrasound image, and calculate the local entropy value of each pixel corresponding to the conversion matrix in the grayscale image.
  • S510 Normalize the local entropy matrix to obtain a local entropy grayscale image of the original ultrasound image (as shown in FIG. 5d).
  • S512 Perform image threshold segmentation on the local entropy gray image to obtain a binarized image of the local entropy gray image (as shown in FIG. 5e).
  • S514 Perform an open operation on the binarized image of the local entropy grayscale image to obtain the binarized image of the original ultrasound image (as shown in FIG. 5f).
  • the binarized image of the original ultrasound image includes multiple connected regions
  • the connected area with the largest area is determined as the connected area corresponding to the ultrasound body area and extracted (as shown in FIG. 5g).
  • the connected area is provided with corresponding corner coordinates.
  • S518 According to the corner coordinates of the connected area corresponding to the ultrasound body region, crop the original ultrasound image to obtain the ultrasound body image of the ultrasound body region (as shown in Fig. 5h and Fig. 5i).
  • the ultrasound body image of the ultrasound body region is the ultrasound image generated when the ultrasound probe scans the target part.
  • the ultrasound equipment includes an ultrasound display terminal and an ultrasound probe.
  • the ultrasonic display terminal applies an electrical signal to the ultrasonic probe through the ultrasonic cable so that the ultrasonic probe emits ultrasonic waves to the target site to be detected.
  • the ultrasonic probe receives the echo signal reflected by the target part and feeds the echo signal back to the ultrasonic display terminal through the ultrasonic cable.
  • the ultrasonic display terminal can generate the ultrasonic body image of the target part according to the echo signal.
  • the ultrasonic display terminal will respond according to the patient
  • the private information generates sensitive information. It is understandable that the sensitive information has nothing to do with the ultrasound emitted by the ultrasound probe.
  • the target part is a part of interest of the physician, such as liver, pancreas, uterus, etc.
  • the original ultrasound image is quickly segmented through the local entropy matrix, and the ultrasound image body area is completely segmented.
  • the obtained ultrasound body image not only contains complete ultrasound image information, and the ultrasound body image does not include any sensitive information.
  • a medical image processing device including: a first acquisition module 602, an image segmentation module 604, an area determination module 606, and an image extraction module 608, wherein:
  • the first acquisition module 602 is configured to acquire a local entropy grayscale image of an original medical image, the original medical image including a medical ontology region;
  • the image segmentation module 604 is configured to perform image segmentation on the local entropy grayscale image to obtain a binarized image of the original medical image; the binarized image of the original medical image includes a plurality of connected regions;
  • the area determining module 606 is configured to determine the connected area corresponding to the medical ontology area among the multiple connected areas according to the area of each of the connected areas;
  • the image extraction module 608 is configured to extract the image of the medical ontology region from the original medical image according to the connected regions corresponding to the medical ontology region.
  • the first acquisition module 602 includes a second acquisition module, a grayscale processing module, and an image traversal module; wherein:
  • the second acquisition module is used to acquire the original medical image
  • a grayscale processing module configured to perform grayscale processing on the original medical image to obtain a grayscale image of the original medical image
  • the image traversal module is used to traverse the grayscale image of the original medical image by using a conversion matrix of a preset size to obtain the local entropy grayscale image of the original medical image.
  • the image traversal module includes a local entropy calculation module, a gray value update module, and a normalization module; among them:
  • a local entropy calculation module configured to use the conversion matrix to traverse the grayscale image of the original medical image, and calculate the local entropy value of each pixel corresponding to the conversion matrix in the grayscale image;
  • a gray value update module configured to update the gray value of the pixel corresponding to the center position of the conversion matrix in the gray image to the calculated local entropy value to obtain the local entropy matrix
  • the normalization module is used to normalize the local entropy matrix to obtain the local entropy grayscale image of the original medical image.
  • the image segmentation module 604 is further configured to perform image threshold segmentation on the local entropy grayscale image to obtain a binarized image of the local entropy grayscale image;
  • the binarized image performs an open operation operation to obtain the binarized image of the original medical image.
  • the area determining module 606 is further configured to determine the connected area with the largest area among the multiple connected areas as the connected area corresponding to the medical ontology area.
  • the connected area is provided with corresponding corner coordinates; the image extraction module 608 is further configured to crop the original medical image according to the corner coordinates of the connected area corresponding to the medical ontology area, Obtain the medical image of the medical ontology area.
  • the original medical image is an ultrasound image including sensitive information
  • the medical image of the medical body region is an ultrasound image generated when an ultrasound probe scans a target part.
  • Each module in the above-mentioned medical image processing device can be implemented in whole or in part by software, hardware, and a combination thereof.
  • the foregoing modules may be embedded in the form of hardware or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the foregoing modules.
  • a computer device is provided.
  • the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 7.
  • the computer equipment includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus.
  • the processor of the computer device is used to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system and a computer program.
  • the internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium.
  • the communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator's network, NFC (near field communication) or other technologies.
  • the computer program is executed by the processor to realize a medical image processing method.
  • the display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, or it can be a button, trackball or touchpad set on the housing of the computer equipment , It can also be an external keyboard, touchpad, or mouse.
  • FIG. 7 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
  • a computer device including a memory and a processor, and a computer program is stored in the memory.
  • the processor executes the computer program, the following steps are implemented: obtaining a partial entropy grayscale image of an original medical image,
  • the original medical image includes the medical ontology region; image segmentation is performed on the local entropy gray image to obtain a binarized image of the original medical image;
  • the binarized image of the original medical image includes a plurality of connected regions;
  • the area of the connected area determining the connected area corresponding to the medical ontology area among the multiple connected areas; extracting the medical ontology area from the original medical image according to the connected area corresponding to the medical ontology area Medical image.
  • the processor further implements the following steps when executing the computer program: acquiring an original medical image; performing gray-scale processing on the original medical image to obtain a gray-scale image of the original medical image; using a preset size conversion The matrix traverses the grayscale image of the original medical image to obtain the local entropy grayscale image of the original medical image.
  • the processor further implements the following steps when executing the computer program: traverse the grayscale image of the original medical image by using the conversion matrix, and calculate the value of each pixel corresponding to the conversion matrix in the grayscale image. Local entropy value; update the gray value of the pixel corresponding to the center position of the conversion matrix in the gray image to the calculated local entropy value to obtain the local entropy matrix; normalize the local entropy matrix, Obtain the local entropy grayscale image of the original medical image.
  • the processor further implements the following steps when executing the computer program: image threshold segmentation is performed on the local entropy gray image to obtain a binarized image of the local entropy gray image; The binarized image of the degree image is subjected to an open operation operation to obtain the binarized image of the original medical image.
  • the processor further implements the following step when executing the computer program: among the multiple connected areas, the connected area with the largest area is determined as the connected area corresponding to the medical ontology area.
  • the connected area is provided with corresponding corner coordinates; the processor further implements the following steps when executing the computer program: according to the corner coordinates of the connected area corresponding to the medical ontology area, compare the original medical image Cutting is performed to obtain the medical image of the medical body region.
  • the original medical image is an ultrasound image including sensitive information
  • the medical image of the medical body region is an ultrasound image generated when an ultrasound probe scans a target part.
  • a computer-readable storage medium on which a computer program is stored.
  • the following steps are implemented: Obtain a local entropy grayscale image of an original medical image, the original medical image Including the medical ontology region; performing image segmentation on the local entropy grayscale image to obtain a binarized image of the original medical image; the binarized image of the original medical image includes a plurality of connected regions; The area of the region, the connected region corresponding to the medical ontology region is determined among the multiple connected regions; the medical image of the medical ontology region is extracted from the original medical image according to the connected region corresponding to the medical ontology region .
  • the following steps are also implemented: obtaining an original medical image; performing gray-scale processing on the original medical image to obtain a gray-scale image of the original medical image; using a preset size
  • the conversion matrix traverses the grayscale image of the original medical image to obtain the local entropy grayscale image of the original medical image.
  • the following steps are also implemented: use the conversion matrix to traverse the grayscale image of the original medical image, and calculate each pixel corresponding to the conversion matrix in the grayscale image Update the gray value of the pixel corresponding to the center position of the conversion matrix in the gray image to the calculated local entropy value to obtain the local entropy matrix; normalize the local entropy matrix , To obtain the local entropy grayscale image of the original medical image.
  • image threshold segmentation is performed on the local entropy gray image to obtain a binarized image of the local entropy gray image;
  • the binarized image of the gray-scale image performs an open operation to obtain the binarized image of the original medical image.
  • the following step is further implemented: among the multiple connected areas, the connected area with the largest area is determined as the connected area corresponding to the medical ontology area.
  • the connected area is provided with corresponding corner coordinates; when the computer program is executed by the processor, the following steps are further implemented: according to the corner coordinates of the connected area corresponding to the medical ontology area, compare the original medical The image is cropped to obtain the medical image of the medical ontology area.
  • the original medical image is an ultrasound image including sensitive information
  • the medical image of the medical body region is an ultrasound image generated when an ultrasound probe scans a target part.
  • Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical storage.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM may be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

Procédé et appareil de traitement d'image médicale, dispositif informatique et support d'enregistrement. Le procédé comprend : l'obtention d'une image d'échelle de gris d'entropie locale d'une image médicale d'origine, l'image médicale d'origine comprenant une région d'ontologie médicale (S102) ; la réalisation d'une segmentation d'image sur l'image d'échelle de gris d'entropie locale pour obtenir une image binaire de l'image médicale d'origine (S104) ; la détermination d'une pluralité de régions de communication dans l'image binaire, et en fonction des zones des régions de communication, la détermination d'une région de communication correspondant à la région d'ontologie médicale (S106) ; et en fonction de la région de communication correspondant à la région d'ontologie médicale, l'extraction précise et complète d'une image médicale de la région d'ontologie médicale à partir de l'image médicale d'origine (S108). Par conséquent, la désensibilisation d'informations sensibles dans une image médicale est réalisée.
PCT/CN2020/133036 2020-06-18 2020-12-01 Procédé et appareil de traitement d'image médicale, dispositif informatique et support d'enregistrement WO2021253732A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010561269.2 2020-06-18
CN202010561269.2A CN113822839B (zh) 2020-06-18 2020-06-18 医学图像的处理方法、装置、计算机设备和存储介质

Publications (1)

Publication Number Publication Date
WO2021253732A1 true WO2021253732A1 (fr) 2021-12-23

Family

ID=78911885

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/133036 WO2021253732A1 (fr) 2020-06-18 2020-12-01 Procédé et appareil de traitement d'image médicale, dispositif informatique et support d'enregistrement

Country Status (2)

Country Link
CN (1) CN113822839B (fr)
WO (1) WO2021253732A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116630256A (zh) * 2023-05-15 2023-08-22 什维新智医疗科技(上海)有限公司 一种超声造影图像识别方法、系统、电子设备及存储介质
CN116935493A (zh) * 2023-09-13 2023-10-24 成都市青羊大数据有限责任公司 一种教育管理系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024119323A1 (fr) * 2022-12-05 2024-06-13 深圳华大生命科学研究院 Procédé de segmentation de tissu pour image d'échantillon, système, dispositif et support

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106295588A (zh) * 2016-08-17 2017-01-04 电子科技大学 一种白带显微图像中白细胞的自动识别方法
CN107845098A (zh) * 2017-11-14 2018-03-27 南京理工大学 基于随机森林和模糊聚类的肝癌图像全自动分割方法
CN107909590A (zh) * 2017-11-15 2018-04-13 北京工业大学 一种基于Snake改进算法的IVUS图像外膜边缘分割方法
CN108765409A (zh) * 2018-06-01 2018-11-06 电子科技大学 一种基于ct图像的候选结节的筛选方法
WO2019041590A1 (fr) * 2017-08-31 2019-03-07 中国科学院微电子研究所 Procédé de détection de bord à l'aide d'un angle arbitraire
CN110378924A (zh) * 2019-07-19 2019-10-25 合肥学院 基于局部熵的水平集图像分割方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103914856A (zh) * 2014-04-14 2014-07-09 贵州电网公司输电运行检修分公司 一种基于熵值的运动目标检测方法
CN104376260B (zh) * 2014-11-20 2017-06-30 东华大学 一种基于香农信息熵的恶意代码可视化分析方法
CN105427320B (zh) * 2015-11-30 2018-07-06 威海北洋电气集团股份有限公司 一种图像分割提取方法
CN106373138B (zh) * 2016-08-30 2019-07-02 海纳医信（北京）软件科技有限责任公司 用于提取牙弓曲线的图像处理方法和装置
CN106815853B (zh) * 2016-12-14 2020-06-05 海纳医信（北京）软件科技有限责任公司 对眼底图像中视网膜血管的分割方法和装置
CN107229910A (zh) * 2017-05-18 2017-10-03 北京环境特性研究所 一种遥感图像结冰湖泊检测方法及其系统
CN107239666B (zh) * 2017-06-09 2020-10-09 孟群 一种对医疗影像数据进行脱敏处理的方法及系统
CN108629773B (zh) * 2018-05-10 2021-06-18 北京红云智胜科技有限公司 建立训练识别心脏血管类型的卷积神经网络数据集的方法
CN108765335B (zh) * 2018-05-25 2022-08-02 电子科技大学 一种基于遥感图像的森林火灾检测方法
CN108765406A (zh) * 2018-05-31 2018-11-06 电子科技大学 一种基于红外遥感图像的雪山检测方法
CN109063740A (zh) * 2018-07-05 2018-12-21 高镜尧 超声影像关键目标的检测模型构建及检测方法、装置
CN110288594B (zh) * 2019-07-02 2021-06-04 河北农业大学 一种植物冠层结构性状分析方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106295588A (zh) * 2016-08-17 2017-01-04 电子科技大学 一种白带显微图像中白细胞的自动识别方法
WO2019041590A1 (fr) * 2017-08-31 2019-03-07 中国科学院微电子研究所 Procédé de détection de bord à l'aide d'un angle arbitraire
CN107845098A (zh) * 2017-11-14 2018-03-27 南京理工大学 基于随机森林和模糊聚类的肝癌图像全自动分割方法
CN107909590A (zh) * 2017-11-15 2018-04-13 北京工业大学 一种基于Snake改进算法的IVUS图像外膜边缘分割方法
CN108765409A (zh) * 2018-06-01 2018-11-06 电子科技大学 一种基于ct图像的候选结节的筛选方法
CN110378924A (zh) * 2019-07-19 2019-10-25 合肥学院 基于局部熵的水平集图像分割方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116630256A (zh) * 2023-05-15 2023-08-22 什维新智医疗科技(上海)有限公司 一种超声造影图像识别方法、系统、电子设备及存储介质
CN116935493A (zh) * 2023-09-13 2023-10-24 成都市青羊大数据有限责任公司 一种教育管理系统
CN116935493B (zh) * 2023-09-13 2024-01-02 成都市青羊大数据有限责任公司 一种教育管理系统

Also Published As

Publication number Publication date
CN113822839A (zh) 2021-12-21
CN113822839B (zh) 2024-01-23

Similar Documents

Publication Publication Date Title
WO2021253732A1 (fr) Procédé et appareil de traitement d'image médicale, dispositif informatique et support d'enregistrement
WO2020224406A1 (fr) Procédé de classification d'image, support d'informations lisible par ordinateur et dispositif informatique
Kalpathy-Cramer et al. Radiomics of lung nodules: a multi-institutional study of robustness and agreement of quantitative imaging features
US11633146B2 (en) Automated co-registration of prostate MRI data
CN111932520A (zh) 医学图像显示方法、查看设备以及计算机设备
US8401285B1 (en) Methods, apparatuses, and computer program products for controlling luminance of non-tissue objects within an image
US9058650B2 (en) Methods, apparatuses, and computer program products for identifying a region of interest within a mammogram image
US11276490B2 (en) Method and apparatus for classification of lesion based on learning data applying one or more augmentation methods in lesion information augmented patch of medical image
US11676273B2 (en) Methods and systems for displaying image
CN115965750B (zh) 血管重建方法、装置、计算机设备和可读存储介质
CN115272250B (zh) 确定病灶位置方法、装置、计算机设备和存储介质
CN111951272A (zh) 脑部影像的分割方法、装置、计算机设备和可读存储介质
CN114092475A (zh) 病灶长径确定方法、图像标注方法、装置及计算机设备
CN110570425B (zh) 一种基于深度强化学习算法的肺结节分析方法及装置
CN112102235A (zh) 人体部位识别方法、计算机设备和存储介质
US20220277175A1 (en) Method and system for training and deploying an artificial intelligence model on pre-scan converted ultrasound image data
CN113962958B (zh) 一种征象检测方法及装置
CN106530386B (zh) 医学图像的体绘制方法及其系统
CN114723723A (zh) 医学影像处理方法、计算机设备和存储介质
CN114820483A (zh) 图像检测方法、装置及计算机设备
JP7105918B2 (ja) 領域特定装置、方法およびプログラム
CN115393246A (zh) 图像分割系统及图像分割方法
EP4102456A1 (fr) Programme de calcul; procédé de calcul et dispositif de calcul
US20240119592A1 (en) Information processing apparatus, information processing method, and program
US20240202924A1 (en) Image processing apparatus, image processing method, and image processing program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20940920

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20940920

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20940920

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 27/06/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20940920

Country of ref document: EP

Kind code of ref document: A1