A method for removing a couch plate in CT images

Abstract

The present invention relates to the technical field of medical image processing, and specifically discloses a method for removing a couch plate in a CT image, which includes: acquiring a CT image; calculating the optimal elliptical region of the CT image; performing image processing on the image of the optimal elliptical region to obtain a plurality of connected regions; integrating the plurality of connected regions according to a preset threshold requirement to obtain a region, and obtaining a CT image after couch removal according to the integrated region. The method for removing a couch plate in a CT image provided by the present invention extracts the effective region in the image to achieve the purpose of couch removal, and has the advantages of high efficiency and good effect.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly relates to a method for removing a couch plate from a CT image. Background Art

[0002] With the development of medical imaging technology, CT images are becoming clearer and providing greater convenience for doctors. However, in CT imaging technology, the couch plate will exist in the image. When doctors use a three-dimensional image post-processing workstation for diagnosis, the couch plate will cause interference to it (obscuring human body parts), reducing the doctor's work efficiency. In addition, as an indispensable data in deep learning research, the couch plate in CT images will increase the computational amount and training time of the model, and also affect the accuracy of the results. To sum up, it is necessary to automatically remove the couch plate from CT images.

[0003] Currently, the method of removing the couch plate sometimes relies on manual or semi-automatic operations by doctors, which is laborious and prone to fatigue. And common segmentation methods such as thresholding, median filtering, and region growing methods are often used for removing the couch plate. Due to the diversity of the couch plate and its irregular display in the image, a single method cannot obtain better results. The median filtering method is suitable for removing linear structures, but most couch plates are non-linear structures, so this method is not applicable. The region growing method is applied in the patent documents with patent application numbers 201610313298.0 and 201410438472.5. The difference is that the pre-processing for obtaining the growth seed points is different. However, for the parts where the couch plates are adhered or where the couch plates are irregularly displayed, the region growing method will have certain drawbacks and is also time-consuming. Summary of the Invention

[0004] The present invention provides a method for removing a couch plate from a CT image, which solves the problems such as low efficiency and poor effect in removing the couch plate in the related art.

[0005] As an aspect of the present invention, there is provided a method for removing a couch plate from a CT image, which includes:

[0006] Obtain a CT image;

[0007] Calculate the optimal elliptical region of the CT image;

[0008] Perform image processing on the image of the optimal elliptical region to obtain a plurality of connected regions;

[0009] Integrate the plurality of connected regions according to a preset threshold requirement to obtain a region, and obtain a CT image without the couch plate according to the integrated region.

[0010] Further, the calculating the optimal elliptical region of the CT image includes:

[0011] Perform binarization processing on the CT image to obtain a binary image;

[0012] Perform edge detection and morphological operations on the binary image to obtain the largest binary image in the image set;

[0013] Calculate the major axis, minor axis and the centroid of the largest binary image to obtain the optimal elliptical region.

[0014] Further, the performing binarization processing on the CT image to obtain a binary image includes:

[0015] Perform binarization processing on the CT image using a first threshold to obtain a binary image.

[0016] Further, the performing edge detection and morphological operations on the binary image to obtain the largest binary image in the image set includes:

[0017] Perform opening operation on the binary image;

[0018] Perform edge detection and closing operation on the binary image after the opening operation to obtain the closed contour of the region in the binary image;

[0019] Perform hole filling processing on the binary image after obtaining the closed contour to obtain the largest binary image in the image set.

[0020] Further, the calculating the major axis, minor axis and the centroid of the largest binary image to obtain the optimal elliptical region includes:

[0021] Calculate the centroid of the largest binary image;

[0022] Obtain the smallest circumscribed rectangle of the largest binary image;

[0023] Compare the smallest circumscribed rectangle with the thresholds of the major and minor axes to determine the major axis and minor axis of the optimal elliptical region;

[0024] Obtain the optimal elliptical region according to the major axis, minor axis and the centroid of the largest binary image.

[0025] Further, the performing image processing on the image of the optimal elliptical region to obtain a plurality of connected regions includes:

[0026] Perform binarization processing on the image of the optimal elliptical region to obtain a binary image;

[0027] Perform processing on the binary image to obtain a plurality of connected regions.

[0028] Further, the performing binarization processing on the image of the optimal elliptical region to obtain a binary image includes:

[0029] Perform binarization processing on the optimal elliptical region using a second threshold to obtain a binary image.

[0030] Furthermore, processing the binary image to obtain multiple connected regions includes:

[0031] Perform edge detection and "cross" processing on the binary image to obtain multiple connected regions.

[0032] Furthermore, performing edge detection and "cross" processing on the binary image to obtain multiple connected regions includes:

[0033] Perform edge detection on the binary image to obtain an edge detection result;

[0034] Perform "cross" processing on the edge detection result to connect the discontinuous points and obtain multiple processed regions;

[0035] Judge whether the edges of each processed region are connected;

[0036] If so, perform closing operation and hole filling processing on the processed region to obtain multiple connected regions;

[0037] If not, perform closing operation and hole filling processing after closing the unclosed places on the edge of the processed region.

[0038] Furthermore, integrating multiple connected regions into one region according to a preset threshold requirement, and obtaining a CT image after removing the bed board based on the integrated region includes:

[0039] Compare each connected region with an area threshold;

[0040] Integrate all connected regions that meet the condition of having an area greater than the area threshold into one region;

[0041] Obtain a CT image after removing the bed board based on the integrated region.

[0042] The method for removing the bed board in the CT image provided by the present invention, compared with the prior art, adopts an opposite idea. Since there are many types of bed boards and their shapes are irregular, it is difficult to directly process the bed board. Therefore, the embodiments of the present invention extract the effective regions in the image to achieve the purpose of removing the bed board. In addition, since the image processing in the present invention is performed on a two-dimensional image, the calculation time is short and the speed is fast. Most of the bed boards can be removed by the elliptical processing method, reducing the post-processing calculation amount. Therefore, the method for removing the bed board in the CT image provided by the embodiments of the present invention can efficiently and quickly remove the bed board in the CT image, thereby improving the working efficiency of doctors. Description of the Drawings

[0043] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present invention, but do not constitute a limitation to the present invention. In the accompanying drawings:

[0044] Figure 1 It is a flowchart of the method for removing the bed board in the CT image provided by the present invention.

[0045] Figure 2 It is a schematic diagram of the original CT image provided by the present invention.

[0046] Figure 3 It is a flowchart of the specific implementation of the method for removing the bed board in the CT image provided by the present invention.

[0047] Figure 4 It is the CT image after elliptical processing provided by the present invention.

[0048] Figure 5 It is the image after Canny edge detection provided by the present invention.

[0049] Figure 6 It is the image after the final binary processing provided by the present invention.

[0050] Figure 7 It is the CT image after removing the bed provided by the present invention.

[0051] Figure 8 It is a comparison diagram of one angle of the three-dimensional reconstruction results of removing the bed board and not removing the bed board provided by the present invention.

[0052] Figure 9 It is a comparison diagram of another angle of the three-dimensional reconstruction results of removing the bed board and not removing the bed board provided by the present invention.

[0053] Figure 10 It is a comparison diagram of another angle of the three-dimensional reconstruction results of removing the bed board and not removing the bed board provided by the present invention. Specific Embodiments

[0054] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0055] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0056] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to implement the embodiments of the present invention described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0057] In this embodiment, a method for removing a couch plate from a CT image is provided. Figure 1 is a flowchart of the method for removing a couch plate from a CT image provided according to an embodiment of the present invention, as Figure 1 shown, including:

[0058] S110. Obtain a CT image;

[0059] As Figure 2 shown, it is the obtained original CT image. It should be understood that the original CT image is also a grayscale value image.

[0060] S120. Calculate the optimal elliptical region of the CT image;

[0061] In the embodiment of the present invention, as Figure 3 shown, it may specifically include:

[0062] S121. Perform binarization processing on the CT image to obtain a binary image;

[0063] For example, the CT image can be binarized using a first threshold to obtain a binary image.

[0064] In the embodiment of the present invention, the first threshold may specifically be 800.

[0065] S122. Perform edge detection and morphological operations on the binary image to obtain the largest binary image in the image set;

[0066] In the embodiments of the present invention, it may specifically include:

[0067] Perform an opening operation on the binary image;

[0068] Perform edge detection and closing operation on the binary image after the opening operation to obtain the closed contour of the region in the binary image;

[0069] Perform hole filling on the binary image after obtaining the closed contour to obtain the largest binary image in the image set.

[0070] It should be understood that performing an opening operation on the obtained binary image eliminates the noise points in the binary image. Then, perform edge detection on the above-obtained result to obtain the closed contour of the region in the binary image. Since the contour obtained by edge detection is not necessarily closed, a closing operation is performed later to further ensure that the obtained contour is closed. Perform hole filling on the closed contour to obtain the largest binary image.

[0071] Preferably, the edge detection performed here can be specifically implemented by using the Sobel edge detection algorithm.

[0072] S123. Obtain the major axis, minor axis, and the centroid of the largest binary image to obtain the optimal elliptical region.

[0073] In the embodiments of the present invention, according to the above processing, obtain the largest binary image in the image set and calculate its regional centroid. Subsequently, obtain the smallest circumscribed rectangle of the above largest binary image, determine the major axis a and minor axis b, and compare them with the major axis threshold A (which can be taken as 245 here) and minor axis threshold B (which can be taken as 200 here). If it is less than the threshold, a and b are retained; if it is greater than the threshold, a and b are respectively assigned as A and B to remove the redundant bed plates and reduce the post-processing calculation amount.

[0074] More specifically, it includes:

[0075] Calculate the centroid of the largest binary image;

[0076] Obtain the smallest circumscribed rectangle of the largest binary image;

[0077] Compare according to the smallest circumscribed rectangle and the thresholds of the major axis and minor axis to determine the major axis and minor axis of the optimal elliptical region;

[0078] Obtain the optimal elliptical region according to the major axis, minor axis, and the centroid of the largest binary image.

[0079] As Figure 4 shown, it is the obtained optimal elliptical region. Process the image according to the obtained centroid and major axis a, minor axis b, retain the image inside the ellipse, and set the outside of the ellipse to 0, that is, most of the bed plates are removed.

[0080] S130. Perform image processing on the image of the optimal elliptical region to obtain multiple connected regions;

[0081] In an embodiment of the present invention, it may specifically include:

[0082] S131. Perform binarization processing on the image of the optimal elliptical region to obtain a binary image;

[0083] In an embodiment of the present invention, the optimal elliptical region is binarized using a second threshold to obtain a binary image.

[0084] S132. Process the binary image to obtain multiple connected regions.

[0085] In an embodiment of the present invention, edge detection and "cross" processing are performed on the binary image to obtain multiple connected regions.

[0086] More specifically, the edge detection and "cross" processing of the binary image to obtain multiple connected regions includes:

[0087] Perform edge detection on the binary image to obtain an edge detection result, as Figure 5 shown;

[0088] Perform "cross" processing on the edge detection result to connect the discontinuous points to obtain multiple processed regions;

[0089] Judge whether the edges of each processed region are connected;

[0090] If so, perform closing operation and hole filling processing on the processed region to obtain multiple connected regions;

[0091] If not, perform closing processing on the unclosed places of the edge of the processed region and then perform closing operation and hole filling processing.

[0092] It should be understood that the obtained image is binarized according to the second threshold to obtain a binary image, and connected regions are obtained through edge detection and "cross" processing. To prevent the situation that individual images exceed the image size and cause no connected regions, it is necessary to judge the edge detection image and close the continuously unclosed places, and perform closing operation and hole filling on it.

[0093] Preferably, the edge detection performed here can be specifically implemented using the Canny edge detection algorithm.

[0094] S140. Integrate multiple connected regions according to preset threshold requirements to obtain a region, and obtain a CT image after removing the bed according to the integrated region.

[0095] In the embodiments of the present invention, it specifically includes:

[0096] Compare each connected region with an area threshold;

[0097] Integrate all connected regions that satisfy the area being greater than the area threshold into one region, as Figure 6 shown;

[0098] Obtain the CT image after removing the bed board according to the integrated region, as Figure 7 shown.

[0099] It should be understood that by screening the connected regions through the aspect ratio (L1, L2) (where L1 can take 0.3 and L2 can take 3) and the area threshold D (where it can take 1200), integrating the connected regions with an area greater than D into one region, and performing an AND operation on the integrated region and the image after obtaining the optimal elliptical region ( Figure 4 shown), the CT image after removing the bed board is obtained, as Figure 7 shown.

[0100] Figures 8 to 10 For the comparison of the schematic diagram of the result of three-dimensional reconstruction of the image after removing the bed board and the schematic diagram of the result of three-dimensional reconstruction of the image without removing the bed board by using the method for removing the bed board in the CT image provided by the embodiments of the present invention, where the three-dimensional images reconstructed without removing the bed board are on the left side, and the three-dimensional images reconstructed from the images after removing the bed board are on the right side.

[0101] In summary, compared with the prior art, the method for removing the bed board in the CT image provided by the embodiments of the present invention adopts an opposite idea. Since there are many types of bed boards and their shapes are irregular, it is difficult to directly process the bed board. Therefore, the embodiments of the present invention extract the effective regions in the image to achieve the purpose of removing the bed board. In addition, since the image processing in the present invention is performed on two-dimensional images, the calculation time is short and the speed is fast. Most of the bed board can be removed through the elliptical processing method, reducing the post-processing calculation amount. Therefore, the method for removing the bed board in the CT image provided by the embodiments of the present invention can efficiently and quickly remove the bed board in the CT image, thereby improving the working efficiency of doctors.

[0102] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principle of the present invention, and the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also regarded as the protection scope of the present invention.

Claims

1. A method for removing a couch plate in a CT image, characterized in that, Including: Obtain a CT image; Calculate the optimal elliptical region of the CT image; Perform image processing on the image of the optimal elliptical region to obtain multiple connected regions; Integrate multiple connected regions according to preset threshold requirements to obtain a region, and obtain the CT image after removing the bed based on the integrated region; Among them, calculating the optimal elliptical region of the CT image includes: Perform binarization processing on the CT image to obtain a binary image; Perform edge detection and morphological operations on the binary image to obtain the largest binary image in the image set; Obtain the major axis, minor axis, and centroid of the largest binary image to obtain the optimal elliptical region; The performing image processing on the image of the optimal elliptical region to obtain multiple connected regions includes: Perform binarization processing on the image of the optimal elliptical region to obtain a binary image; Perform edge detection and "cross" processing on the binary image to obtain multiple connected regions.

2. The method for removing a couch plate in a CT image according to claim 1, characterized in that, The performing binarization processing on the CT image to obtain a binary image includes: Perform binarization processing on the CT image using a first threshold to obtain a binary image.

3. The method for removing a couch plate in a CT image according to claim 1, wherein The performing edge detection and morphological operations on the binary image to obtain the largest binary image in the image set includes: Perform opening operation on the binary image; Perform edge detection and closing operation on the binary image after the opening operation to obtain the closed contour of the region in the binary image; Perform hole filling processing on the binary image after obtaining the closed contour to obtain the largest binary image in the image set.

4. The method for removing the couch in the CT image according to claim 1, wherein The obtaining the major axis, minor axis, and centroid of the largest binary image to obtain the optimal elliptical region includes: Obtain the centroid of the largest binary image; Obtain the minimum circumscribed rectangle of the largest binary image; Compare the minimum circumscribed rectangle with the thresholds of the major and minor axes to determine the major axis and minor axis of the optimal elliptical region; Obtain the optimal elliptical region according to the major axis, minor axis, and centroid of the largest binary image.

5. The method for removing a couch in a CT image according to claim 1, characterized in that, The performing binarization processing on the image of the optimal elliptical region to obtain a binary image includes: Perform binarization processing on the optimal elliptical region using a second threshold to obtain a binary image.

6. The method for removing the couch in the CT image according to claim 1, characterized in that, The performing edge detection and "cross" processing on the binary image to obtain multiple connected regions includes: Perform edge detection on the binary image to obtain an edge detection result; Perform "cross" processing on the edge detection result to connect the discontinuous points to obtain multiple processed regions; Judge whether the edges of each processed region are connected; If so, perform closing operation and hole filling processing on the processed region to obtain multiple connected regions; If not, perform closing operation and hole filling processing after closing the unclosed places of the edges of the processed region.

7. The method for removing the couch in the CT image according to claim 1, wherein The integrating multiple connected regions according to preset threshold requirements to obtain a region, and obtaining the CT image after removing the bed based on the integrated region includes: Compare each connected region with an area threshold; Integrate all connected regions that meet the condition that the area is greater than the area threshold into a region; Obtain the CT image after removing the bed based on the integrated region.

Images