Medical image processing method and device, computer device and storage medium

Abstract

The application relates to a medical image processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining target projection images of a scanning object at preset projection angles; the target projection images are obtained by scanning the scanning object at the projection angles by using a first scanning device; obtaining projection contour images of the scanning object at the projection angles based on the target projection images; reconstructing by using the projection contour images to obtain an external contour image of the scanning object; determining an attenuation coefficient of the scanning object according to the external contour image of the scanning object; the attenuation coefficient is used for attenuation correction of a to-be-corrected image of the scanning object; the to-be-corrected image is obtained by scanning the scanning object by using a second scanning device; the second scanning device is different from the first scanning device. The method can improve the efficiency of attenuation correction of the to-be-corrected image of the scanning object.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a medical image processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] As an important component of nuclear medicine imaging, SPECT (single photon emission computed tomography) and PET (positron emission tomography), examination methods that utilize radioactive nuclides to capture radiation information generated inside the scanned object, play a vital role in clinical disease diagnosis and preclinical drug testing. To obtain higher quality SPECT or PET reconstructed images, the attenuation of gamma rays during penetration of the scanned object can be corrected using images obtained from X-ray computed tomography equipment, such as CT (computed tomography).

[0003] However, in related technologies, the sampling time required by CT equipment to sample CT images with a sufficiently high signal-to-noise ratio is relatively long, resulting in low efficiency when performing attenuation correction on the images to be corrected. Summary of the Invention

[0004] Therefore, it is necessary to provide a medical image processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the efficiency of attenuation correction in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a medical image processing method. The method includes:

[0006] Obtain target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object at the projection angles using a first scanning device;

[0007] Based on each of the target projection images, the projection contour image of the scanned object at each of the projection angles is obtained;

[0008] The external contour image corresponding to the scanned object is obtained by reconstructing the projected contour images.

[0009] Based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

[0010] In one embodiment, the first scanning device is used to obtain the target projection image by using radiation to penetrate the scanned object; the second scanning device is used to reconstruct the tomographic imaging signal of the scanned object by using the radiation information generated inside the scanned object, and obtain the image to be corrected.

[0011] In one embodiment, the target projection image is obtained by scanning the object disposed in the scanning chamber using the first scanning device; obtaining the projection contour image of the object at each projection angle based on each target projection image includes:

[0012] Acquire the scanning cabin projection image corresponding to each of the projection angles; the scanning cabin projection image is obtained by scanning the scanning cabin individually at the projection angle using the first scanning device.

[0013] Subtract the target projection image with the same projection angle from the scanning chamber projection image to obtain the subtracted projection image of the scanned object at each of the projection angles.

[0014] The subtracted projection images corresponding to each projection angle are used as the projection contour images corresponding to each projection angle.

[0015] In one embodiment, subtracting the target projection image with the same projection angle from the scanning chamber projection image to obtain the subtracted projection image of the scanned object at each of the projection angles includes:

[0016] For any of the projection angles, in the target projection image and the scanning cabin projection image corresponding to the projection angle, determine the first pixel value and the second pixel value corresponding to the same pixel position in the target projection image and the scanning cabin projection image.

[0017] Subtract the first pixel value and the second pixel value corresponding to the same pixel position to obtain the target pixel value corresponding to the same pixel position;

[0018] Based on the target pixel value corresponding to the same pixel position, determine the subtracted projection image of the scanned object at any projection angle.

[0019] In one embodiment, acquiring the target projection image of the scanned object at each preset projection angle includes:

[0020] Obtain an initial projected image of the object being scanned using the scanning device at each of the stated projection angles;

[0021] The initial projection images are regularized to obtain the regularized projection images of the scanned object at each projection angle.

[0022] Logarithmic processing is performed on each of the regularized projection images to obtain the target projection image of the scanned object at each of the projection angles.

[0023] In one embodiment, the process of reconstructing the projected contour images to obtain the external contour image corresponding to the scanned object includes:

[0024] The back-projection algorithm is used to reconstruct the projected contour images to obtain the reconstructed image of the target corresponding to the scanned object.

[0025] The reconstructed image of the target is segmented to obtain the external contour image corresponding to the scanned object.

[0026] In one embodiment, segmenting the reconstructed image of the target to obtain the external contour image corresponding to the scanned object includes:

[0027] Determine the contour pixels corresponding to the scanned object in the reconstructed image of the target;

[0028] The contour region of the scanned object in the reconstructed image of the target is determined based on each of the contour pixels;

[0029] The reconstructed image of the target is segmented based on the contour region to obtain the external contour image corresponding to the scanned object.

[0030] In one embodiment, determining the attenuation coefficient corresponding to the scanned object based on the external contour image corresponding to the scanned object includes:

[0031] Obtain the mapping relationship between the external contour image and the attenuation coefficient;

[0032] Based on the mapping relationship, an attenuation coefficient matching the external contour image corresponding to the scanned object is determined, and the attenuation coefficient corresponding to the scanned object is obtained.

[0033] Secondly, this application also provides a medical image processing apparatus. The apparatus includes:

[0034] The acquisition module is used to acquire target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object at the projection angles using a first scanning device;

[0035] The first determining module is used to obtain the projection contour image of the scanned object at each projection angle based on each of the target projection images;

[0036] The reconstruction module is used to reconstruct the external contour image corresponding to the scanned object by applying the projected contour images.

[0037] The second determining module is used to determine the attenuation coefficient corresponding to the scanned object based on the external contour image corresponding to the scanned object; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

[0038] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0039] Obtain target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object at the projection angles using a first scanning device;

[0040] Based on each of the target projection images, the projection contour image of the scanned object at each of the projection angles is obtained;

[0041] The external contour image corresponding to the scanned object is obtained by reconstructing the projected contour images.

[0042] Based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

[0043] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0044] Obtain target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object at the projection angles using a first scanning device;

[0045] Based on each of the target projection images, the projection contour image of the scanned object at each of the projection angles is obtained;

[0046] The external contour image corresponding to the scanned object is obtained by reconstructing the projected contour images.

[0047] Based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

[0048] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0049] Obtain target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object at the projection angles using a first scanning device;

[0050] Based on each of the target projection images, the projection contour image of the scanned object at each of the projection angles is obtained;

[0051] The external contour image corresponding to the scanned object is obtained by reconstructing the projected contour images.

[0052] Based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

[0053] The aforementioned medical image processing method, apparatus, computer equipment, storage medium, and computer program product acquire target projection images of a scanned object at preset projection angles; wherein, the target projection images are obtained by scanning the scanned object using a first scanning device at the projection angles; based on each target projection image, a projection contour image of the scanned object at each projection angle is obtained; the projection contour images are reconstructed using each projection contour image to obtain an external contour image corresponding to the scanned object; and based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; wherein, the attenuation coefficient is used to attenuate and correct the image to be corrected corresponding to the scanned object; wherein, the image to be corrected is obtained by scanning the scanned object using a second scanning device. The image is obtained by scanning; wherein the second scanning device is different from the first scanning device; thus, the external contour image of the scanned object is obtained by reconstructing the projection image of the scanned object at a preset projection angle, and the number of projection images required to reconstruct the external contour image is much less than the number of projection images required to reconstruct the internal structure image, thereby reducing the sampling time required by the first scanning device to obtain the projection image and improving the sampling efficiency when obtaining the projection image; at the same time, image reconstruction can be performed with fewer projection images, which can improve the image reconstruction efficiency; thereby shortening the time required to obtain the attenuation coefficient for attenuation correction of the image to be corrected based on the reconstructed image, effectively improving the efficiency of attenuation correction of the image to be corrected corresponding to the scanned object. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating a medical image processing method in one embodiment;

[0055] Figure 2 This is a flowchart illustrating the steps of obtaining the projected contour images of the scanned object at various projection angles in one embodiment.

[0056] Figure 3 This is a schematic diagram of a target projection image and a scanning cabin projection image obtained by a first scanning device at a certain projection angle in one embodiment.

[0057] Figure 4 This is a flowchart illustrating a medical image processing method in another embodiment;

[0058] Figure 5 This is a flowchart illustrating another medical image processing method in one embodiment;

[0059] Figure 6 This is a structural block diagram of a medical image processing device in one embodiment;

[0060] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0063] In one embodiment, such as Figure 1 As shown, a medical image processing method is provided, applied to computer equipment. In practical applications, the computer equipment can be a user terminal, or it can be implemented using a standalone server or a server cluster consisting of multiple servers. The user terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.

[0064] In this embodiment, the method includes the following steps:

[0065] Step S110: Obtain the target projection image of the scanned object at each preset projection angle.

[0066] The scanned object can be a living organism (such as a patient or animal).

[0067] The target projection image is obtained by scanning the object using the first scanning device at the projection angle.

[0068] The angular intervals between each projection angle can be equal.

[0069] In practice, the first scanning device can use radiation to scan the object at preset projection angles to obtain the target projection image of the object at each preset projection angle, so that the computer device can acquire each target projection image.

[0070] Step S120: Based on the projection images of each target, obtain the projection contour images of the scanned object at each projection angle.

[0071] In practice, the computer device can identify the contour of the scanned object in each target projection image based on the target projection image, and obtain the projection contour image of the scanned object at each projection angle.

[0072] Step S130: Reconstruct the external contour image of the scanned object by applying each projected contour image.

[0073] In practice, computer equipment can use a back projection algorithm to reconstruct the external contour image corresponding to the scanned object by applying each projected contour image.

[0074] Step S140: Determine the attenuation coefficient corresponding to the scanned object based on the external contour image of the scanned object.

[0075] The attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object.

[0076] The image to be corrected is obtained by scanning the object using a second scanning device.

[0077] The second scanning device is different from the first scanning device.

[0078] In practice, the second scanning device can utilize the radiation information generated inside the scanned object by a radioactive nuclide to obtain the image to be corrected corresponding to the scanned object, which can then be acquired by the computer device. After acquiring the image to be corrected and the external contour image of the scanned object, the computer device can determine the attenuation coefficient corresponding to the gamma-ray energy level of the scanned object through the mapping relationship between the external contour image and the attenuation coefficient, thereby obtaining the attenuation coefficient corresponding to the scanned object. Based on the attenuation coefficient, an attenuation correction map is determined, and attenuation correction is performed on the image to be corrected based on this attenuation correction map.

[0079] In the aforementioned medical image processing method, target projection images of the scanned object are acquired at preset projection angles; wherein, the target projection images are obtained by scanning the scanned object using a first scanning device at the preset projection angles; based on each target projection image, projection contour images of the scanned object at each projection angle are obtained; reconstruction is performed using each projection contour image to obtain the external contour image corresponding to the scanned object; based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; wherein, the attenuation coefficient is used to attenuate and correct the image to be corrected corresponding to the scanned object; wherein, the image to be corrected is obtained by scanning the scanned object using a second scanning device; wherein, The second scanning device differs from the first scanning device. Thus, by reconstructing the projected image of the scanned object at a preset projection angle, the external contour image of the scanned object is obtained. The number of projected images required to reconstruct the external contour image is far fewer than the number required to reconstruct the internal structure image, thereby reducing the sampling time required by the first scanning device to obtain the projected image and improving the sampling efficiency when obtaining the projected image. Simultaneously, image reconstruction using fewer projected images can improve image reconstruction efficiency. This, in turn, shortens the time required to obtain the attenuation coefficient for attenuation correction of the image to be corrected based on the reconstructed image, effectively improving the efficiency of attenuation correction of the image to be corrected corresponding to the scanned object.

[0080] In one embodiment, a first scanning device is used to obtain a target projection image by using radiation to penetrate the scanned object; a second scanning device is used to reconstruct the tomographic imaging signal of the scanned object by using the radiation information generated inside the scanned object, thereby obtaining an image to be corrected.

[0081] The first scanning device is a CT (Computed Tomography) device, such as a conventional X-ray CT device or a photon counting CT device.

[0082] The second scanning device can be a SPECT (single photon emission computed tomography) device or a PET (positron emission computed tomography) device.

[0083] In practice, the first scanning device can use radiation to penetrate the scanning object to obtain the target projection image of the scanning object at each preset projection angle; when the first scanning device is a photon counting CT device, the target projection image of the scanning object acquired by the photon counting CT device can be used to obtain a reconstructed image of the scanning object with higher precision and lower noise.

[0084] After a radioactive isotope drug is injected into the target body, a second scanning device can utilize the radiation information (gamma rays) generated by the radioactive decay of the drug within the target body to reconstruct the tomographic imaging signal of the target body, obtaining the corresponding image to be corrected for acquisition by a computer. Specifically, the second scanning device achieves imaging through gamma rays. When the second scanning device is a PET scanner, the gamma rays are generated by the annihilation radiation caused by the positrons emitted by the target drug (such as a radioactive isotope drug) combining with the negative electrons in the tissue within the target body. When the second scanning device is a SPECT scanner, the gamma rays are generated by the radioactive decay of the drug within the target body. The attenuation caused by the gamma rays during penetration of the target body must be corrected. Based on the attenuation coefficient corresponding to the target body, an attenuation correction map can be determined for PET or SPECT reconstruction, and this attenuation correction map is used to perform attenuation correction on the image to be corrected.

[0085] In this embodiment, the first scanning device is used to obtain a target projection image by using radiation to penetrate the scanning object; the second scanning device is used to reconstruct the tomographic imaging signal of the scanning object by using the radiation information generated inside the scanning object to obtain the image to be corrected; thus, by using radiation to penetrate the scanning object, a highly accurate external contour image of the scanning object can be reconstructed, so as to accurately predict the attenuation coefficient of the scanning object based on the external contour image, and accurately perform attenuation correction on the image to be corrected corresponding to the scanning object.

[0086] In one embodiment, such as Figure 2 As shown, step S120 obtains the projected contour image of the scanned object at each projection angle based on the projected images of each target, including:

[0087] Step S210: Obtain the scanning cabin projection images corresponding to each projection angle.

[0088] The target projection image is obtained by scanning the object placed in the scanning chamber using the first scanning device at preset projection angles.

[0089] The projected images of the scanning cabin are obtained by scanning the scanning cabin individually using the first scanning device at preset projection angles.

[0090] The first scanning device is also used to obtain the scanning chamber projection image corresponding to each preset projection angle by using radiation to penetrate the scanning chamber.

[0091] In a specific implementation, the first scanning device can use radiation to scan the object set in the scanning chamber at preset projection angles to obtain the target projection image of the object at each preset projection angle. At the same time, the first scanning device can also use radiation to scan the scanning chamber separately at preset projection angles to obtain the scanning chamber projection image at each preset projection angle. In this way, the computer device can obtain the target projection image of the object at each preset projection angle, as well as the scanning chamber projection image at each preset projection angle.

[0092] Step S220: Subtract the target projection image with the same projection angle from the scanning chamber projection image to obtain the subtracted projection image of the scanned object at each projection angle.

[0093] In practice, since the target projection image is obtained by scanning the object set in the scanning chamber, the target projection image contains the attenuation information of the scanning chamber on the X-rays and the attenuation information of the scanning sample on the X-rays. In order to eliminate the influence of the scanning chamber in the target projection image at each projection angle, the computer device can obtain the target projection image and the scanning chamber projection image at the same projection angle based on the target projection image and the scanning chamber projection image at each projection angle. The target projection image and the scanning chamber projection image at the same projection angle are then subtracted to obtain the subtracted projection image of the scanned object at each projection angle, thereby eliminating the influence of the scanning chamber.

[0094] For the convenience of those skilled in the art, Figure 3 A schematic diagram is provided showing the target projection image and the scanning chamber projection image obtained by a first scanning device at a certain projection angle.

[0095] like Figure 3As shown, the “…” line represents the scanning chamber projection image; the “————” line represents the target projection image; the horizontal axis represents the pixel position of a certain row of pixels in the scanning chamber projection image and the target projection image; the vertical axis represents the normalized gray value; 301 is the scanning object; 302 is the scanning chamber; 3031 is the first parallel X-ray; 3032 is the second parallel X-ray; 3033 is the third parallel X-ray; 3034 is the fourth parallel X-ray; 304, located between the second parallel X-ray 3032 and the third parallel X-ray 3033, is the image data of the scanning chamber projection image at the corresponding pixel position; 305, located between the second parallel X-ray 3032 and the third parallel X-ray 3033, is the image data of the target projection image at the corresponding pixel position. It can be seen that, at pixel positions other than the pixel position where the scanned sample is located (i.e., the pixel position between the second parallel X-ray 3032 and the third parallel X-ray 3033), the grayscale value of the scanned chamber projection image obtained by scanning the scanned chamber alone is the same as that of the target projection image obtained by scanning the scanned object set in the scanned chamber; at the pixel position where the scanned sample is located, since the target projection image is obtained by scanning the scanned object set in the scanned chamber, the grayscale value of the scanned chamber projection image obtained by scanning the scanned chamber alone is different from that of the target projection image.

[0096] Step S230: Subtract the corresponding projection images at each projection angle and use them as the corresponding projection contour images at each projection angle.

[0097] In practice, after the computer device obtains the subtracted projection images of the scanned object at each projection angle, the subtracted projection images contain the difference information between the target projection image and the scanning chamber projection image, that is, the projection image area corresponding to the scanned object. Therefore, the computer device can use the subtracted projection images of the scanned object at each projection angle as the projection contour images of the scanned object at each projection angle.

[0098] In practical applications, computer equipment can also perform threshold segmentation on each subtracted projection image using a thresholding method, extracting the projection image region corresponding to the scanned object from each subtracted projection image to obtain the projection contour image of the scanned object at each projection angle.

[0099] In this embodiment, the target projection image is obtained by scanning the object placed inside the scanning chamber using a first scanning device at a projection angle. The scanning chamber projection image is obtained by acquiring the corresponding projection images of the scanning chamber at each projection angle. The target projection image at the same projection angle is subtracted from the scanning chamber projection image to obtain the subtracted projection image of the scanned object at each projection angle. Finally, the subtracted projection images of the scanned object at each projection angle are used as the projection contour images of the scanned object at each projection angle. Since the target projection image is obtained by scanning the object placed inside the scanning chamber, it contains not only the attenuation information of the scanning chamber but also the attenuation information of the scanned sample. By subtracting the target projection image from the scanning chamber projection image, the influence of the scanning chamber in the target projection image can be eliminated, thus accurately obtaining the attenuation coefficient corresponding to the scanned object based on the subtracted projection image.

[0100] In one embodiment, subtracting the target projection image and the scanning chamber projection image at the same projection angle to obtain the subtracted projection image of the scanned object at each projection angle includes: for any projection angle, determining the first pixel value and the second pixel value corresponding to the same pixel position in the target projection image and the scanning chamber projection image at any projection angle; subtracting the first pixel value and the second pixel value corresponding to each same pixel position to obtain the target pixel value corresponding to each same pixel position; and determining the subtracted projection image of the scanned object at any projection angle based on the target pixel value corresponding to each same pixel position.

[0101] In practice, when the computer device subtracts the target projection image and the scanning chamber projection image at the same projection angle to obtain the subtracted projection image of the scanned object at each projection angle, for any projection angle, the computer device needs to determine the pixel value corresponding to the same pixel position in the target projection image and the corresponding pixel value in the scanning chamber projection image. The pixel value corresponding to the same pixel position in the target projection image is taken as the first pixel value, and the pixel value corresponding to the same pixel position in the scanning chamber projection image is taken as the second pixel value, thus obtaining a one-to-one correspondence between the first and second pixel values ​​at each same pixel position. Then, the computer device subtracts the first and second pixel values ​​corresponding to the same pixel position, and uses the subtracted pixel value as the target pixel value corresponding to each same pixel position. In this way, the subtracted projection image of the scanned object at any projection angle can be determined based on the target pixel values ​​corresponding to each same pixel position.

[0102] The technical solution of this embodiment, for any projection angle, determines the first pixel value and the second pixel value corresponding to the same pixel position in the target projection image and the scanning chamber projection image, respectively; subtracts the first pixel value and the second pixel value corresponding to each same pixel position to obtain the target pixel value corresponding to each same pixel position; and determines the subtracted projection image of the scanned object at any projection angle based on the target pixel value corresponding to each same pixel position. Thus, for any projection angle, by obtaining the subtraction value between the first pixel value and the second pixel value corresponding to the same pixel position in the target projection image and the scanning chamber projection image, the difference information between the target projection image and the scanning chamber projection image can be accurately detected, thereby accurately obtaining the subtracted projection image of the scanned object at any projection angle.

[0103] In one embodiment, obtaining the target projection image of the scanned object at each preset projection angle includes: obtaining the initial projection image obtained by the first scanning device scanning the scanned object at each projection angle; performing regularization processing on each initial projection image to obtain the regularized projection image of the scanned object at each projection angle; and performing logarithmic processing on each regularized projection image to obtain the target projection image of the scanned object at each projection angle.

[0104] In specific implementation, the first scanning device can use radiation to scan the object set in the scanning chamber at preset projection angles to obtain the initial projection image of the object at each preset projection angle. The computer device can then obtain the initial projection image of the object. The initial projection image is then regularized to obtain the regularized post-processed image at each projection angle, which is used as the regularized projection image of the object at each projection angle. Additionally, the regularized projection image is logarithmically processed. This logarithmic processing can be based on e (a natural constant with a value of approximately 2.718281828459045) to obtain the logarithmically processed image at each projection angle, which is used as the target projection image of the object at each projection angle.

[0105] It is understandable that the initial scanning cabin projection image obtained by the first scanning device scanning the scanning cabin individually according to each preset projection angle also needs to be regularized to obtain the regularized scanning cabin projection image corresponding to each projection angle; and the logarithmic processing is performed on each regularized scanning cabin projection image to obtain the scanning cabin projection image corresponding to each projection angle.

[0106] The technical solution of this embodiment involves acquiring initial projection images of the object being scanned by a first scanning device at various projection angles; performing regularization processing on each initial projection image to obtain a regularized projection image of the object at each projection angle; and performing logarithmic processing on each regularized projection image to obtain a target projection image of the object at each projection angle. Thus, since the initial projection image may contain noise, be blurry, or have defects, regularization processing can denoise the initial projection image, improving the image quality of the projection image. Simultaneously, by performing logarithmic processing on the regularized projection image, the low grayscale value portion of the regularized projection image can be expanded, thereby improving the contrast of the darker areas of the regularized projection image, effectively enhancing the dark details of the image, and thus improving the image quality of the target projection image.

[0107] In one embodiment, reconstructing the external contour image corresponding to the scanned object using each projected contour image includes: using a back-projection algorithm to reconstruct the target image corresponding to the scanned object using each projected contour image; and segmenting the target image to obtain the external contour image corresponding to the scanned object.

[0108] The back projection algorithm can be, but is not limited to, filtered back projection, direct back projection, inverse Fourier transform, and other back projection algorithms.

[0109] In practice, the computer device can employ a back-projection algorithm to reconstruct the scanned object using the corresponding projected contour images at various projection angles, resulting in a reconstructed CT image, which serves as the target reconstructed image corresponding to the scanned object. Then, the computer device can identify the contour corresponding to the scanned object in the target reconstructed image to segment the image and obtain the external contour image corresponding to the scanned object.

[0110] The technical solution of this embodiment uses a back-projection algorithm to reconstruct the target image corresponding to the scanned object by applying each projected contour image. The reconstructed target image is then segmented to obtain the external contour image corresponding to the scanned object. In this way, the reconstructed image is directly obtained through the back-projection algorithm, and the external contour image corresponding to the scanned object is obtained by segmenting the reconstructed image. The computational load required is small, which can quickly obtain the external contour image corresponding to the scanned object, improve the efficiency of obtaining the external contour image, and thus shorten the time required to obtain the attenuation coefficient for attenuation correction of the image to be corrected based on the external contour image. This further improves the attenuation correction efficiency for the image to be corrected corresponding to the scanned object.

[0111] In one embodiment, segmenting the reconstructed image of the target to obtain the external contour image corresponding to the scanned object includes: determining the contour pixels corresponding to the scanned object in the reconstructed image of the target; determining the contour region corresponding to the scanned object in the reconstructed image of the target based on each contour pixel; and segmenting the reconstructed image of the target based on the contour region to obtain the external contour image corresponding to the scanned object.

[0112] In the specific implementation, during the process of segmenting the reconstructed image of the target to obtain the external contour image corresponding to the scanned object, the computer device can determine the contour pixels corresponding to the scanned object in the reconstructed image of the target through a contour detection algorithm. Based on each contour pixel corresponding to the scanned object in the reconstructed image of the target, the contour region corresponding to the scanned object in the reconstructed image of the target can be determined. Finally, the computer device can segment the reconstructed image of the target based on the contour region, extract the contour corresponding to the target object in the reconstructed image of the target, and obtain the external contour image corresponding to the scanned object.

[0113] The technical solution of this embodiment involves determining the contour pixels corresponding to the scanned object in the reconstructed image of the target; determining the contour region corresponding to the scanned object in the reconstructed image of the target based on each contour pixel; and segmenting the reconstructed image of the target based on the contour region to obtain the outer contour image corresponding to the scanned object. In this way, the outer contour image corresponding to the scanned object can be accurately segmented in the reconstructed image of the target based on the contour region corresponding to the scanned object, so as to obtain the attenuation coefficient corresponding to the scanned object.

[0114] In one embodiment, determining the attenuation coefficient corresponding to the scanned object based on the external contour image of the scanned object includes: obtaining the mapping relationship between the external contour image and the attenuation coefficient; determining the attenuation coefficient that matches the external contour image of the scanned object based on the mapping relationship, thereby obtaining the attenuation coefficient corresponding to the scanned object.

[0115] The attenuation coefficient is the attenuation coefficient corresponding to the gamma-ray energy level.

[0116] In practice, during the process of determining the attenuation coefficient of the scanned object based on its external contour image, the computer device can obtain the mapping relationship between the external contour image and the attenuation coefficient. This mapping relationship can be determined based on a pre-trained deep learning network model or prior knowledge. Through this mapping relationship, the computer device can determine the attenuation coefficient that matches the external contour image of the scanned object, thus obtaining the attenuation coefficient corresponding to the scanned object, i.e., the attenuation coefficient of the scanned object at the gamma-ray energy level.

[0117] The technical solution of this embodiment obtains the mapping relationship between the external contour image and the attenuation coefficient; based on the mapping relationship, it determines the attenuation coefficient that matches the external contour image corresponding to the scanned object, and obtains the attenuation coefficient corresponding to the scanned object; thus, based on this mapping relationship, the attenuation coefficient that matches the external contour image corresponding to the scanned object can be quickly determined, thereby improving the efficiency of obtaining the attenuation coefficient.

[0118] In another embodiment, such as Figure 4 As shown, a medical image processing method is provided, and the method is illustrated using an application to a computer device as an example. The method includes the following steps:

[0119] Step S410: Obtain the target projection image of the scanned object at each preset projection angle.

[0120] Step S420: Obtain the scanning cabin projection images corresponding to each projection angle.

[0121] Step S430: Subtract the target projection image with the same projection angle from the scanning chamber projection image to obtain the subtracted projection image of the scanned object at each projection angle.

[0122] Step S440: Subtract the corresponding projection images at each projection angle and use them as the corresponding projection contour images at each projection angle.

[0123] Step S450: The back projection algorithm is used to reconstruct the target image corresponding to the scanned object by applying each projection contour image.

[0124] Step S460: Segment the reconstructed image of the target to obtain the external contour image corresponding to the scanned object.

[0125] Step S470: Determine the attenuation coefficient corresponding to the scanned object based on the external contour image of the scanned object.

[0126] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a medical image processing method described above.

[0127] For the convenience of those skilled in the art, Figure 5 A flowchart illustrating another medical image processing method is provided, using the application of this method to a computer device as an example, including the following steps:

[0128] Step S510: Obtain the sine curve of the scanned object at a preset projection angle.

[0129] The sine curve is obtained from the target projection image of the scanned object at each preset projection angle.

[0130] The target projection image is obtained by the photon counting CT device scanning the object set in the scanning chamber at a preset projection angle.

[0131] In practice, the computer device can acquire the target projection image of the scanned object at a preset projection angle, sort the target projection images according to the corresponding projection angle size, obtain the sorted target projection images, and synthesize a sine graph based on the sorted target projection images to obtain the sine graph of the scanned object at the preset projection angle.

[0132] Step S520: Preprocess the sine curve to obtain the projected contour image of the scanned object at the projection angle.

[0133] In practice, the photon counting CT scanner can scan the scanning chamber individually at preset projection angles, obtaining projection images of the scanning chamber at each preset projection angle. After acquiring the projection images of the scanning chamber at each projection angle, the computer equipment sorts the projection images of the scanning chamber according to the size of the corresponding projection angle and synthesizes a sine curve of the scanning chamber at the preset projection angle. The computer equipment obtains the projection contour image of the scanned object at the projection angle by subtracting the sine curve from the sine curve of the scanning chamber.

[0134] Step S530: The back projection algorithm is used to reconstruct the projected contour image to obtain the reconstructed image of the target corresponding to the scanned object.

[0135] Step S540: Segment the reconstructed image of the target to obtain the external contour image corresponding to the scanned object.

[0136] Step S550: Determine the attenuation coefficient corresponding to the scanned object based on the external contour image of the scanned object.

[0137] The attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object.

[0138] The image to be corrected is obtained by scanning the object using a second scanning device.

[0139] The second scanning device is a SPECT (single photon emission computed tomography) device.

[0140] In practice, the CT reconstructed images used for SPECT attenuation correction do not need to have the same high image quality as conventional CT reconstructed images; that is, the CT reconstructed images used for SPECT attenuation correction do not need to be a completely accurate internal structure diagram of the scanned object. Therefore, this method only needs to acquire sine waves obtained by a photon-counting CT device at a small number of preset projection angles. The sine waves are preprocessed to obtain the external contour image corresponding to the scanned object. Based on prior knowledge or a deep learning network, the attenuation coefficient corresponding to the scanned object at the gamma-ray energy level is determined from the external contour image. Attenuation correction is then performed on the image to be corrected acquired by the SPECT device according to this attenuation coefficient.

[0141] The technical solution of this embodiment does not require attenuation correction of the image to be corrected acquired by the SPECT device through a completely accurate internal structure diagram of the scanned object. It only needs to acquire the external contour image of the scanned object. The number of projection images required to reconstruct the external contour image is far less than the number of projection images required to reconstruct the internal structure image. Therefore, due to the reduction of projection images, the image reconstruction efficiency can be effectively improved when reconstructing the image based on the projection images.

[0142] Meanwhile, because the physical properties of the photon counting detector in a photon counting CT scanner limit the intensity of the X-ray source during sampling, a longer exposure time is required to sample a target projection image with a sufficiently high signal-to-noise ratio. However, due to the reduced number of required projection images, the sampling time required by the photon counting CT scanner in this solution is significantly reduced, effectively improving the sampling efficiency of the photon counting CT scanner.

[0143] Furthermore, since the number of required projected images is reduced, the amount of radiation absorbed by the scanned object is also reduced during the scanning process of the photon counting CT equipment. This solution is also applicable to image attenuation correction of SPECT or PET equipment combined with conventional X-ray CT equipment.

[0144] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0145] Based on the same inventive concept, this application also provides a medical image processing apparatus for implementing the medical image processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more medical image processing apparatus embodiments provided below can be found in the limitations of a medical image processing method described above, and will not be repeated here.

[0146] In one embodiment, such as Figure 6 As shown, a medical image processing apparatus is provided, comprising: an acquisition module 610, a first determination module 620, a reconstruction module 630, and a second determination module 640, wherein:

[0147] The acquisition module 610 is used to acquire target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object at the projection angles using a first scanning device.

[0148] The first determining module 620 is used to obtain the projection contour image of the scanned object at each projection angle based on each of the target projection images.

[0149] The reconstruction module 630 is used to reconstruct the external contour image corresponding to the scanned object by applying the projected contour images.

[0150] The second determining module 640 is used to determine the attenuation coefficient corresponding to the scanned object based on the external contour image corresponding to the scanned object; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

[0151] In one embodiment, the first scanning device is used to obtain the target projection image by using radiation to penetrate the scanned object; the second scanning device is used to reconstruct the tomographic imaging signal of the scanned object by using the radiation information generated inside the scanned object, and obtain the image to be corrected.

[0152] In one embodiment, the target projection image is obtained by scanning the object placed in the scanning chamber using the first scanning device at the projection angle; the first determining module 620 is specifically used to obtain the scanning chamber projection image corresponding to each projection angle; the scanning chamber projection image is obtained by scanning the scanning chamber individually using the first scanning device at the projection angle; the target projection image with the same projection angle is subtracted from the scanning chamber projection image to obtain the subtracted projection image of the object corresponding to each projection angle; the subtracted projection image corresponding to each projection angle is used as the projection contour image corresponding to each projection angle.

[0153] In one embodiment, the first determining module 620 is specifically configured to, for any projection angle, determine, in the target projection image and the scanning cabin projection image corresponding to the same pixel position, a first pixel value in the target projection image and a second pixel value in the scanning cabin projection image; subtract the first pixel value and the second pixel value corresponding to each of the same pixel positions to obtain the target pixel value corresponding to each of the same pixel positions; and determine the subtracted projection image of the scanning object at any projection angle based on the target pixel value corresponding to each of the same pixel positions.

[0154] In one embodiment, the acquisition module 610 is specifically used to acquire initial projection images obtained by scanning the scanned object using the first scanning device at each of the projection angles; perform regularization processing on each of the initial projection images to obtain regularized projection images of the scanned object at each of the projection angles; and perform logarithmic processing on each of the regularized projection images to obtain target projection images of the scanned object at each of the projection angles.

[0155] In one embodiment, the reconstruction module 630 is specifically used to reconstruct the projected contour images using a back-projection algorithm to obtain the target reconstructed image corresponding to the scanned object; and to segment the target reconstructed image to obtain the external contour image corresponding to the scanned object.

[0156] In one embodiment, the reconstruction module 630 is specifically configured to: determine the contour pixels corresponding to the scanned object in the reconstructed image of the target; determine the contour region corresponding to the scanned object in the reconstructed image of the target based on each contour pixel; and segment the reconstructed image of the target based on the contour region to obtain the outer contour image corresponding to the scanned object.

[0157] In one embodiment, the second determining module 640 is specifically used to obtain the mapping relationship between the external contour image and the attenuation coefficient; and to determine the attenuation coefficient that matches the external contour image corresponding to the scanned object based on the mapping relationship, thereby obtaining the attenuation coefficient corresponding to the scanned object.

[0158] The various modules in the aforementioned medical image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0159] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a medical image processing method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0160] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0161] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0162] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0163] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0165] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0166] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A medical image processing method, characterized in that, The method includes: Acquire target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object set in the scanning chamber using a first scanning device at the projection angles; Based on each of the target projection images, a projection contour image of the scanned object at each of the projection angles is obtained; wherein, a scanning cabin projection image at each of the projection angles is obtained; the scanning cabin projection image is obtained by scanning the scanning cabin separately using the first scanning device at each of the projection angles; the target projection images with the same projection angles are subtracted from the scanning cabin projection images to obtain the subtracted projection images of the scanned object at each of the projection angles; the subtracted projection images at each of the projection angles are used as the projection contour images at each of the projection angles. The external contour image corresponding to the scanned object is obtained by reconstructing the projected contour images. Based on the external contour image corresponding to the scanned object, an attenuation coefficient corresponding to the scanned object is determined; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

2. The method according to claim 1, characterized in that, The first scanning device is used to obtain the target projection image by using radiation to penetrate the scanned object; the second scanning device is used to reconstruct the tomographic imaging signal of the scanned object by using the radiation information generated inside the scanned object, and obtain the image to be corrected.

3. The method according to claim 1, characterized in that, The step of subtracting the target projection image with the same projection angle from the scanning chamber projection image to obtain the subtracted projection image of the scanned object at each of the projection angles includes: For any of the projection angles, in the target projection image and the scanning cabin projection image corresponding to any projection angle, determine the first pixel value and the second pixel value corresponding to the same pixel position in the target projection image and the scanning cabin projection image. Subtract the first pixel value and the second pixel value corresponding to the same pixel position to obtain the target pixel value corresponding to the same pixel position; Based on the target pixel value corresponding to the same pixel position, determine the subtracted projection image of the scanned object at any projection angle.

4. The method according to claim 1, characterized in that, The method of reconstructing the projected contour images to obtain the external contour image corresponding to the scanned object includes: The back-projection algorithm is used to reconstruct the projected contour images to obtain the reconstructed image of the target corresponding to the scanned object. The reconstructed image of the target is segmented to obtain the external contour image corresponding to the scanned object.

5. The method according to claim 4, characterized in that, The step of segmenting the reconstructed image of the target to obtain the external contour image corresponding to the scanned object includes: Determine the contour pixels corresponding to the scanned object in the reconstructed image of the target; The contour region of the scanned object in the reconstructed image of the target is determined based on each of the contour pixels; The reconstructed image of the target is segmented based on the contour region to obtain the external contour image corresponding to the scanned object.

6. The method according to claim 1, characterized in that, The step of determining the attenuation coefficient corresponding to the scanned object based on the external contour image of the scanned object includes: Obtain the mapping relationship between the external contour image and the attenuation coefficient; Based on the mapping relationship, an attenuation coefficient matching the external contour image corresponding to the scanned object is determined, and the attenuation coefficient corresponding to the scanned object is obtained.

7. A medical image processing device, characterized in that, The device includes: The acquisition module is used to acquire target projection images of the scanned object at preset projection angles; the target projection images are obtained by scanning the scanned object set in the scanning chamber using a first scanning device at the projection angles; The first determining module is used to obtain a projection contour image of the scanned object at each projection angle based on each of the target projection images; wherein, the scanning cabin projection image at each of the projection angles is obtained; the scanning cabin projection image is obtained by scanning the scanning cabin individually using the first scanning device at each projection angle; the target projection images with the same projection angle are subtracted from the scanning cabin projection images to obtain the subtracted projection images of the scanned object at each of the projection angles; and the subtracted projection images at each of the projection angles are used as the projection contour images at each of the projection angles. The reconstruction module is used to reconstruct the external contour image corresponding to the scanned object by applying the projected contour images. The second determining module is used to determine the attenuation coefficient corresponding to the scanned object based on the external contour image corresponding to the scanned object; the attenuation coefficient is used to perform attenuation correction on the image to be corrected corresponding to the scanned object; the image to be corrected is obtained by scanning the scanned object using a second scanning device; the second scanning device is different from the first scanning device.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images