Image target detection method based on multistage judgment

Abstract

The invention relates to an image target detection method based on multistage judgment, which mainly comprises the following steps of: firstly, preprocessing a CT image sequence, and extracting a thoracic cavity region and two cavity regions in the thoracic cavity region; then, two-stage target existence possibility judgment is implemented, the first-stage judgment is basic target screening, the second-stage judgment carries out finer analysis on the screened cavity region through a depth morphological processing and data enhancement technology, and then a ResNet-50 model integrated by a spatial transformation network is utilized to carry out target existence possibility judgment according to the target existence possibility attribute of the cavity region. And the local magnification degree in the image is automatically adjusted to optimize the accuracy of target detection.

Description

Technical Field

[0001] The invention belongs to the field of medical image processing, and in particular relates to a method for detecting a target in a computer tomography (CT) image sequence based on multi-level judgment. Background Art

[0002] Chest computed tomography (CT) is one of the core tools for modern medical diagnosis, especially in identifying and evaluating intrathoracic diseases such as lung lesions. With the advancement of technology, CT scanning has not only increased in speed, but also generated a large amount of image data, which makes early diagnosis and disease monitoring possible. However, as the amount of data increases, how to effectively process and analyze these image data has become a challenge.

[0003] Traditional CT image analysis methods mainly rely on radiologists to make diagnoses through visual inspection, which is not only inefficient but also easily affected by personal experience and judgment. In addition, manual inspection is prone to fatigue when processing large amounts of data, affecting the accuracy of judgment. Therefore, researchers began to explore automated solutions to improve processing efficiency and diagnostic accuracy.

[0004] In recent years, deep learning techniques, especially convolutional neural networks (CNNs), have shown great potential in the field of medical image analysis. They can automatically identify complex patterns in images and provide faster and more accurate analysis results than traditional methods. However, most existing deep learning methods process the entire image without screening, and fail to make full use of key areas in the image, such as specific target areas, resulting in less refined analysis and sometimes introducing unnecessary background noise.

[0005] To address this problem, the present invention proposes an image target detection method based on multi-level judgment, which not only considers the overall image, but also pays special attention to key areas in the chest cavity (such as cavity areas A and B). Through detailed target existence possibility evaluation and the establishment of a deep learning model, the accuracy and efficiency of target detection are greatly improved. This method provides more reliable reference assistance for clinical use by combining advanced image processing technology and deep learning, and is particularly suitable for processing large-scale medical imaging data. Summary of the invention

[0006] In view of the above-mentioned deficiencies of the prior art, the present invention proposes an image target detection method based on multi-level judgment, comprising the following steps:

[0007] Step 1: Perform superpixel-based preprocessing on the CT image to obtain the chest region in the CT image, as well as two cavity regions in the chest region, cavity region A and cavity region B, and perform a first-level judgment to obtain the chest region key monitoring level attributes and the cavity region key monitoring level attributes;

[0008] Step 2: Perform a second-level judgment on the chest area in the CT image, including:

[0009] Step 2.1: Screen and sort the key monitoring level attributes of the cavity area in the chest area in the CT image according to importance, specifically: filter out abnormal images containing the key monitoring level attributes of the cavity area as high-low, medium-high, low-high, and low-medium, and then sort the key monitoring level attributes of the cavity area from high to low according to importance as high-high, high-medium, medium-medium, medium-low, and low-low;

[0010] Step 2.2: setting observation and control attributes for the two cavity areas in the chest area in the CT image, specifically: comparing the key monitoring level attributes of the two cavity areas, marking the cavity area with a higher importance ranking as the observation cavity area, and marking the cavity area with a lower importance ranking as the control cavity area; if the key monitoring level attributes of the two cavity areas are the same, then the two cavity areas are both marked as observation cavity areas;

[0011] Step 2.3: Perform the second level judgment processing according to the marking conditions of cavity area A and cavity area B, specifically: judge whether the marking conditions of cavity area A and cavity area B are the same, if not, execute step 2.3.1; if the same, directly judge the similarity of the two cavity areas;

[0012] Step 2.3.1: Perform deep morphological processing on the observation cavity area and the control cavity area to obtain multiple groups of morphological processing result images;

[0013] Step 2.3.2: Performing data enhancement operation on the morphological processing results of the observation cavity area in each group of morphological processing result images, to obtain multiple groups of enhanced morphological processing result images of the observation cavity area;

[0014] Step 2.3.3: Filter out the enhanced observation cavity area morphological processing results with the highest similarity to the control cavity area morphological processing results in each group of morphological processing result images, and use them as the matches of the control cavity area morphological processing results;

[0015] Step 2.3.4: performing a difference operation on the morphological processing result of the matched enhanced observation cavity area and the morphological processing result of the control cavity area to obtain a difference operation result map;

[0016] Step 2.3.5: Set the threshold thh to perform binarization on the difference operation result image, calculate the ratio Rx of the number of pixel points with a pixel value of 0 to the number of pixel points with a pixel value of 1 in the binarization result image, set the threshold thx, analyze the chest area of ​​the CT image corresponding to the difference operation result image, and obtain the key monitoring level attribute of the cavity area in the CT image;

[0017] Step 3: Based on the key monitoring level attributes of CT images, the ResNet-50 model integrated with the spatial transformer network (STN) is used to perform object detection in CT images.

[0018] Furthermore, in step 1, the CT image is preprocessed based on superpixels, specifically: first, the CT image is normalized, the brightness and contrast are adjusted, and the image noise is reduced using noise reduction technology, and then the image is binarized using the Otsu method to help preliminarily identify the chest area; then, morphological operations are applied to the binary image to further clarify the boundary of the cavity area, and two cavity areas in the chest area are obtained; then, the chest area is converted into a superpixel block, and the superpixel block comprehensively considers the proximity of color, texture and space to ensure that the consistency within each superpixel block is maximized, and the superpixel block is divided into a background superpixel block and a target superpixel block according to the pixel histogram within the superpixel block, and finally, the chest area thresholds th_SP1 and th_SP2 and the cavity area thresholds th_SP3 and th_SP4 are set, and the key monitoring level attributes of the chest area and the two cavity areas are judged based on the regional thresholds to obtain the key monitoring level attributes of the chest area and the cavity area.

[0019] Furthermore, finally, the chest area thresholds th_SP1 and th_SP2 and the cavity area thresholds th_SP3 and th_SP4 are set, and the key monitoring level attributes of the chest area and the two cavity areas are judged based on the regional thresholds to obtain the key monitoring level attributes of the chest area and the cavity area, specifically: first, the ratio of the number of background superpixel blocks and the target superpixel blocks in the chest area is calculated, and then the chest area superpixel fast number ratio is compared with the chest area thresholds th_SP1 and th_SP2, and the chest area key monitoring level attributes are obtained as high, medium and low, respectively; then, the ratio of the number of background superpixel blocks and the target superpixel blocks in the two cavity areas is calculated respectively, and then the cavity area superpixel block number ratio is compared with the cavity area thresholds th_SP3 and th_SP4; and then, according to the key monitoring level attributes of the chest area to which the cavity area belongs, the key monitoring level attributes of the cavity area are fused to obtain high-high, high-medium, high-low, medium-high, medium-medium, medium-low, low-high, low-medium and low-low, respectively.

[0020] Furthermore, in the step 2.3.1, deep morphological processing is performed on the observation cavity area and the control cavity area, specifically: first, a circular structure element with a radius of R pixels is used to continuously erode the image for Rn times, and a circular structure element with the same radius is immediately used for dilation processing after each erosion. After each processing, a set of morphological processing result images including the morphological processing results of the observation cavity area and the morphological processing results of the control cavity area are obtained.

[0021] Furthermore, in the step 2.3.2, data enhancement operation is performed on the morphological processing results of the observation cavity area in each group of morphological processing result images, specifically: first, the morphological processing result images of the observation cavity area are rotated 180 degrees to match the orientation of the control cavity area; then, a slight angle adjustment is made to the rotated result, with the angle ranging from -5 degrees to +5 degrees, and changing by 1 degree each time; and each adjusted result is scaled in series, with the scaling ratio ranging from 0.95 to 1.05, and changing by 0.01 each time. Finally, the morphological processing results of the observation cavity area in each group of morphological processing result images obtain a set of enhanced enhanced morphological processing result images of the observation cavity area.

[0022] Furthermore, in the step 2.3.3, the enhanced observation cavity area morphological processing results with the highest similarity to the control cavity area morphological processing results in each group of morphological processing result images are screened out, specifically: the structural similarity index evaluation method is used to measure the similarity between the enhanced morphological processing results of the observation cavity area and the morphological processing results of the control cavity area, and the enhanced observation cavity area morphological processing results with the highest score are selected as the match of the control cavity area morphological processing results.

[0023] Further, in the step 2.3.5, a threshold value thh is set to perform binarization processing on the difference operation result image, and the ratio Rx of the number of pixel points with a pixel value of 0 and the number of pixel points with a pixel value of 1 in the binarization processing result image is calculated, and a threshold value thx is set, and the chest area of ​​the CT image corresponding to the difference operation result image is analyzed to obtain the key monitoring level of the cavity area in each CT image in the CT image sequence, specifically: when the ratio Rx is greater than thx, the key monitoring level of the cavity area corresponding to the observed cavity area is judged to be high, and a high evaluation is added on the basis of its existing key monitoring level attribute, and then the key monitoring level of the cavity area corresponding to the control cavity area is judged to be medium, and a medium evaluation is added on the basis of its existing key monitoring level attribute; when the ratio Rx is less than thx, the key monitoring level of the cavity area corresponding to the observed cavity area is judged to be medium, and a medium evaluation is added on the basis of its existing key monitoring level attribute, and then the key monitoring level of the cavity area corresponding to the control cavity area is judged to be low, and a low evaluation is added on the basis of its existing key monitoring level attribute.

[0024] Furthermore, in step 3.3, if they are the same, the two cavity areas are directly judged for similarity, specifically: if the two cavity areas are judged to have a high degree of similarity, an evaluation that is the same as the second evaluation in their key monitoring level attributes is added based on their existing key monitoring level attributes.

[0025] Furthermore, in step 3, based on the key monitoring level attributes of the CT image, the ResNet-50 model of the integrated spatial transformation network is used to perform target detection on the CT image, specifically: first, the preprocessed CT image is input into the ResNet-50 model of the integrated spatial transformation network; secondly, according to the key monitoring level attributes of the cavity area, the integrated spatial transformation network module automatically adjusts the local magnification degree of the identified cavity areas A and B in the image through local affine transformation, and again transmits the image adjusted by the integrated spatial transformation network to the subsequent layer of ResNet-50 for feature extraction, and finally performs target detection through the binary classification output layer of the model to determine whether there is a target.

[0026] Furthermore, according to the key monitoring level attributes of the cavity area, the integrated spatial transformation network module automatically adjusts the local magnification degree of the identified cavity areas A and B in the image through local affine transformation, specifically: when the key monitoring level of the cavity areas A and B includes 3 highs, a local magnification of 1.5 times is performed; when it includes 2 highs and 1 medium, a local magnification of 1.4 times is performed; when it includes 1 high and 2 mediums, a local magnification of 1.3 times is performed; when it includes 3 mediums, a local magnification of 1.2 times is performed; when it includes 2 mediums and 1 low, a local magnification of 1.15 times is performed; when it includes 1 medium and 2 lows, a local magnification of 1.1 times is performed; when it includes 3 lows, the original size is maintained without enlargement.

[0027] Compared with the traditional method, the present invention has the following advantages, thereby solving the corresponding technical problems:

[0028] 1. By implementing a two-level target existence possibility judgment, the accuracy and reliability of target area recognition in CT image sequences are significantly improved. First, through the preliminary target existence possibility judgment, the areas that need to be focused on are quickly screened out; then, through a more refined second-level judgment, these initially screened areas are deeply analyzed and verified. This multi-level judgment strategy not only enhances the accuracy of detection, but also optimizes the processing flow, making the method more efficient and accurate when processing large-scale data.

[0029] 2. The method for determining the possibility of the existence of the second-level target includes detailed observation and comparison of the cavity area, attribute analysis, and deep morphological processing. These methods provide a highly refined analysis method. By making a detailed comparison of the observation and comparison cavity areas, and through deep morphological processing and data enhancement operations, the present invention can accurately distinguish tiny differences, thereby providing more accurate positioning and evaluation of existing targets. This kind of detailed regional analysis is often overlooked in traditional methods, and the method of the present invention therefore has a significant advantage in recognition accuracy.

[0030] 3. By integrating the multi-level judgment results into the ResNet-50 model of the spatial transformation network, the present invention can automatically adjust the magnification of the local area according to the different levels of target existence possibility. This adaptive local magnification strategy can ensure that the model focuses more on those areas that may contain key lesions, thereby improving the detection accuracy while also optimizing the learning efficiency and operation efficiency of the model. Through this intelligent image preprocessing, the detection capability of the subsequent deep learning model is greatly enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of an image target detection method based on multi-level judgment; DETAILED DESCRIPTION

[0032] The following will clearly and completely describe the technical solution in the embodiment of the present invention in conjunction with the accompanying drawings in the embodiment of the present invention. The method includes the following steps:

[0033] Step 1: Perform superpixel-based preprocessing on the CT image to obtain the chest region in the CT image, as well as two cavity regions in the chest region, cavity region A and cavity region B, and perform a first-level judgment to obtain the chest region key monitoring level attributes and the cavity region key monitoring level attributes;

[0034] Step 2: Perform a second-level judgment on the chest area in the CT image, including:

[0035] Step 2.1: Screen and sort the key monitoring level attributes of the cavity area in the chest area in the CT image according to importance, specifically: filter out abnormal images containing the key monitoring level attributes of the cavity area as high-low, medium-high, low-high, and low-medium, and then sort the key monitoring level attributes of the cavity area from high to low according to importance as high-high, high-medium, medium-medium, medium-low, and low-low;

[0036] Step 2.2: setting observation and control attributes for the two cavity areas in the chest area in the CT image, specifically: comparing the key monitoring level attributes of the two cavity areas, marking the cavity area with a higher importance ranking as the observation cavity area, and marking the cavity area with a lower importance ranking as the control cavity area; if the key monitoring level attributes of the two cavity areas are the same, then the two cavity areas are both marked as observation cavity areas;

[0037] Step 2.3: Perform the second level judgment processing according to the marking conditions of cavity area A and cavity area B, specifically: judge whether the marking conditions of cavity area A and cavity area B are the same, if not, execute step 2.3.1; if the same, directly judge the similarity of the two cavity areas;

[0038] Step 2.3.1: Perform deep morphological processing on the observation cavity area and the control cavity area to obtain multiple groups of morphological processing result images;

[0039] Step 2.3.2: Performing data enhancement operation on the morphological processing results of the observation cavity area in each group of morphological processing result images, to obtain multiple groups of enhanced morphological processing result images of the observation cavity area;

[0040] Step 2.3.3: Filter out the enhanced observation cavity area morphological processing results with the highest similarity to the control cavity area morphological processing results in each group of morphological processing result images, and use them as the matches of the control cavity area morphological processing results;

[0041] Step 2.3.4: performing a difference operation on the morphological processing result of the matched enhanced observation cavity area and the morphological processing result of the control cavity area to obtain a difference operation result map;

[0042] Step 2.3.5: Set the threshold thh to perform binarization on the difference operation result image, calculate the ratio Rx of the number of pixel points with a pixel value of 0 to the number of pixel points with a pixel value of 1 in the binarization result image, set the threshold thx, analyze the chest area of ​​the CT image corresponding to the difference operation result image, and obtain the key monitoring level attribute of the cavity area in the CT image;

[0043] Step 3: Based on the key monitoring level attributes of CT images, the ResNet-50 model integrated with the spatial transformer network (STN) is used to perform object detection in CT images.

[0044] Furthermore, in step 1, the CT image is preprocessed based on superpixels, specifically: first, the CT image is normalized, the brightness and contrast are adjusted, and the image noise is reduced using noise reduction technology, and then the image is binarized using the Otsu method to help preliminarily identify the chest area; then, morphological operations are applied to the binary image to further clarify the boundary of the cavity area, and two cavity areas in the chest area are obtained; then, the chest area is converted into a superpixel block, and the superpixel block comprehensively considers the proximity of color, texture and space to ensure that the consistency within each superpixel block is maximized, and the superpixel block is divided into a background superpixel block and a target superpixel block according to the pixel histogram within the superpixel block, and finally, the chest area thresholds th_SP1 and th_SP2 and the cavity area thresholds th_SP3 and th_SP4 are set, and the key monitoring level attributes of the chest area and the two cavity areas are judged based on the regional thresholds to obtain the key monitoring level attributes of the chest area and the cavity area.

[0045] Furthermore, finally, the chest area thresholds th_SP1 and th_SP2 and the cavity area thresholds th_SP3 and th_SP4 are set, and the key monitoring level attributes of the chest area and the two cavity areas are judged based on the regional thresholds to obtain the key monitoring level attributes of the chest area and the cavity area, specifically: first, the ratio of the number of background superpixel blocks and the target superpixel blocks in the chest area is calculated, and then the chest area superpixel fast number ratio is compared with the chest area thresholds th_SP1 and th_SP2, and the chest area key monitoring level attributes are obtained as high, medium and low, respectively; then, the ratio of the number of background superpixel blocks and the target superpixel blocks in the two cavity areas is calculated respectively, and then the cavity area superpixel block number ratio is compared with the cavity area thresholds th_SP3 and th_SP4; and then, according to the key monitoring level attributes of the chest area to which the cavity area belongs, the key monitoring level attributes of the cavity area are fused to obtain high-high, high-medium, high-low, medium-high, medium-medium, medium-low, low-high, low-medium and low-low, respectively.

[0046] Furthermore, in the step 2.3.1, deep morphological processing is performed on the observation cavity area and the control cavity area, specifically: first, a circular structure element with a radius of R pixels is used to continuously erode the image for Rn times, and a circular structure element with the same radius is immediately used for dilation processing after each erosion. After each processing, a set of morphological processing result images including the morphological processing results of the observation cavity area and the morphological processing results of the control cavity area are obtained.

[0047] Furthermore, in the step 2.3.2, data enhancement operation is performed on the morphological processing results of the observation cavity area in each group of morphological processing result images, specifically: first, the morphological processing result images of the observation cavity area are rotated 180 degrees to match the orientation of the control cavity area; then, a slight angle adjustment is made to the rotated result, with the angle ranging from -5 degrees to +5 degrees, and changing by 1 degree each time; and each adjusted result is scaled in series, with the scaling ratio ranging from 0.95 to 1.05, and changing by 0.01 each time. Finally, the morphological processing results of the observation cavity area in each group of morphological processing result images obtain a set of enhanced enhanced morphological processing result images of the observation cavity area.

[0048] Furthermore, in the step 2.3.3, the enhanced observation cavity area morphological processing results with the highest similarity to the control cavity area morphological processing results in each group of morphological processing result images are screened out, specifically: the structural similarity index evaluation method is used to measure the similarity between the enhanced morphological processing results of the observation cavity area and the morphological processing results of the control cavity area, and the enhanced observation cavity area morphological processing results with the highest score are selected as the match of the control cavity area morphological processing results.

[0049] Further, in the step 2.3.5, a threshold value thh is set to perform binarization processing on the difference operation result image, and the ratio Rx of the number of pixel points with a pixel value of 0 and the number of pixel points with a pixel value of 1 in the binarization processing result image is calculated, and a threshold value thx is set, and the chest area of ​​the CT image corresponding to the difference operation result image is analyzed to obtain the key monitoring level of the cavity area in each CT image in the CT image sequence, specifically: when the ratio Rx is greater than thx, the key monitoring level of the cavity area corresponding to the observed cavity area is judged to be high, and a high evaluation is added on the basis of its existing key monitoring level attribute, and then the key monitoring level of the cavity area corresponding to the control cavity area is judged to be medium, and a medium evaluation is added on the basis of its existing key monitoring level attribute; when the ratio Rx is less than thx, the key monitoring level of the cavity area corresponding to the observed cavity area is judged to be medium, and a medium evaluation is added on the basis of its existing key monitoring level attribute, and then the key monitoring level of the cavity area corresponding to the control cavity area is judged to be low, and a low evaluation is added on the basis of its existing key monitoring level attribute.

[0050] Furthermore, in step 3.3, if they are the same, the two cavity areas are directly judged for similarity, specifically: if the two cavity areas are judged to have a high degree of similarity, an evaluation that is the same as the second evaluation in their key monitoring level attributes is added based on their existing key monitoring level attributes.

[0051] Furthermore, in step 3, based on the key monitoring level attributes of the CT image, the ResNet-50 model of the integrated spatial transformation network is used to perform target detection on the CT image, specifically: first, the preprocessed CT image is input into the ResNet-50 model of the integrated spatial transformation network; secondly, according to the key monitoring level attributes of the cavity area, the integrated spatial transformation network module automatically adjusts the local magnification degree of the identified cavity areas A and B in the image through local affine transformation, and again transmits the image adjusted by the integrated spatial transformation network to the subsequent layer of ResNet-50 for feature extraction, and finally performs target detection through the binary classification output layer of the model to determine whether there is a target.

[0052] Furthermore, according to the key monitoring level attributes of the cavity area, the integrated spatial transformation network module automatically adjusts the local magnification degree of the identified cavity areas A and B in the image through local affine transformation, specifically: when the key monitoring level of the cavity areas A and B includes 3 highs, a local magnification of 1.5 times is performed; when it includes 2 highs and 1 medium, a local magnification of 1.4 times is performed; when it includes 1 high and 2 mediums, a local magnification of 1.3 times is performed; when it includes 3 mediums, a local magnification of 1.2 times is performed; when it includes 2 mediums and 1 low, a local magnification of 1.15 times is performed; when it includes 1 medium and 2 lows, a local magnification of 1.1 times is performed; when it includes 3 lows, the original size is maintained without enlargement.

[0053] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

Claims

1. A method for detecting an image target based on multi-level judgment, comprising the following steps: Step 1: Perform superpixel-based preprocessing on the CT image to obtain the chest region in the CT image, as well as two cavity regions in the chest region, cavity region A and cavity region B, and perform a first-level judgment to obtain the chest region key monitoring level attributes and the cavity region key monitoring level attributes; Step 2: Perform a second-level judgment on the chest area in the CT image, including: Step 2.1: Screen and sort the key monitoring level attributes of the cavity area in the chest area in the CT image according to importance, specifically: filter out abnormal images containing the key monitoring level attributes of the cavity area as high-low, medium-high, low-high, and low-medium, and then sort the key monitoring level attributes of the cavity area from high to low according to importance as high-high, high-medium, medium-medium, medium-low, and low-low; Step 2.2: setting observation and control attributes for the two cavity areas in the chest area in the CT image, specifically: comparing the key monitoring level attributes of the two cavity areas, marking the cavity area with a higher importance ranking as the observation cavity area, and marking the cavity area with a lower importance ranking as the control cavity area; if the key monitoring level attributes of the two cavity areas are the same, then the two cavity areas are both marked as observation cavity areas; Step 2.3: Perform the second level judgment processing according to the marking conditions of cavity area A and cavity area B, specifically: judge whether the marking conditions of cavity area A and cavity area B are the same, if not, execute step 2.3.1; if the same, directly judge the similarity of the two cavity areas; Step 2.3.1: Perform deep morphological processing on the observation cavity area and the control cavity area to obtain multiple groups of morphological processing result images; Step 2.3.2: Performing data enhancement operation on the morphological processing results of the observation cavity area in each group of morphological processing result images, to obtain multiple groups of enhanced morphological processing result images of the observation cavity area; Step 2.3.3: Filter out the enhanced observation cavity area morphological processing results with the highest similarity to the control cavity area morphological processing results in each group of morphological processing result images, and use them as the matches of the control cavity area morphological processing results; Step 2.3.4: performing a difference operation on the morphological processing result of the matched enhanced observation cavity area and the morphological processing result of the control cavity area to obtain a difference operation result map; Step 2.3.5: Set the threshold thh to perform binarization on the difference operation result image, calculate the ratio Rx of the number of pixel points with a pixel value of 0 to the number of pixel points with a pixel value of 1 in the binarization result image, set the threshold thx, analyze the chest area of ​​the CT image corresponding to the difference operation result image, and obtain the key monitoring level attribute of the cavity area in the CT image; Step 3: Based on the key monitoring level attributes of CT images, the ResNet-50 model integrated with the spatial transformer network (STN) is used to perform object detection in CT images.

2. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In the step 1, the CT image is preprocessed based on superpixels, specifically: first, the CT image is normalized, the brightness and contrast are adjusted, and the image noise is reduced using noise reduction technology, and then the image is binarized using the Otsu method to help preliminarily identify the chest area; Then, morphological operations are applied on the binary image to further clarify the boundary of the cavity area, and two cavity areas in the chest area are obtained; Then the chest area is converted into a superpixel block. The superpixel block comprehensively considers the proximity of color, texture and space to ensure that the consistency within each superpixel block is maximized, and the superpixel block is divided into background superpixel blocks and target superpixel blocks according to the pixel histogram within the superpixel block. Finally, the chest area thresholds th_SP1 and th_SP2 and the cavity area thresholds th_SP3 and th_SP4 are set, and the key monitoring level attributes of the chest area and the two cavity areas are judged based on the regional thresholds to obtain the key monitoring level attributes of the chest area and the cavity area.

3. The image target detection method based on multi-level judgment as claimed in claim 2, characterized in that: Finally, the chest area thresholds th_SP1 and th_SP2 and the cavity area thresholds th_SP3 and th_SP4 are set, and the key monitoring level attributes of the chest area and the two cavity areas are judged based on the regional thresholds to obtain the key monitoring level attributes of the chest area and the cavity area. Specifically, the ratio of the number of background superpixel blocks and the target superpixel blocks in the chest area is first calculated, and then the chest area superpixel fast number ratio is compared with the chest area thresholds th_SP1 and th_SP2 to obtain the chest area key monitoring level attributes of high, medium and low respectively. Then, the ratio of the number of background superpixel blocks and the target superpixel blocks in the two cavity areas is calculated respectively, and then the cavity area superpixel block number ratio is compared with the cavity area thresholds th_SP3 and th_SP4. Then, according to the key monitoring level attributes of the chest area to which the cavity area belongs, the key monitoring level attributes of the cavity area are fused to obtain high-high, high-medium, high-low, medium-high, medium-medium, medium-low, low-high, low-medium and low-low respectively.

4. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In the step 2.3.1, deep morphological processing is performed on the observation cavity area and the control cavity area, specifically: first, a circular structure element with a radius of R pixels is used to continuously erode the image for Rn times, and a circular structure element with the same radius is immediately used to perform expansion processing after each erosion. After each processing, a set of morphological processing result images including the morphological processing results of the observation cavity area and the morphological processing results of the control cavity area are obtained.

5. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In the step 2.3.2, data enhancement operation is performed on the morphological processing results of the observation cavity area in each group of morphological processing result images, specifically: first, the morphological processing result images of the observation cavity area are rotated 180 degrees to match the orientation of the control cavity area; then, a slight angle adjustment is made to the rotated results, with the angle ranging from -5 degrees to +5 degrees, and changing by 1 degree each time; and each adjusted result is scaled in series, with the scaling ratio ranging from 0.95 to 1.05, and changing by 0.01 each time. Finally, the morphological processing results of the observation cavity area in each group of morphological processing result images obtain a set of enhanced enhanced morphological processing result images of the observation cavity area.

6. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In the step 2.3.3, the enhanced observation cavity area morphological processing results with the highest similarity to the control cavity area morphological processing results in each group of morphological processing result images are screened out. Specifically, the similarity between the enhanced morphological processing results of the observation cavity area and the morphological processing results of the control cavity area is measured using a structural similarity index evaluation method, and the enhanced observation cavity area morphological processing result with the highest score is selected as a match for the control cavity area morphological processing result.

7. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In the step 2.3.5, a threshold value thh is set to perform binarization processing on the difference operation result image, and the ratio Rx of the number of pixel points with a pixel value of 0 and the number of pixel points with a pixel value of 1 in the binarization processing result image is calculated, and a threshold value thx is set. The chest area of ​​the CT image corresponding to the difference operation result image is analyzed to obtain the key monitoring level of the cavity area in each CT image in the CT image sequence, specifically: when the ratio Rx is greater than thx, the key monitoring level of the cavity area corresponding to the observed cavity area is judged to be high, and a high evaluation is added on the basis of its existing key monitoring level attribute, and then the key monitoring level of the cavity area corresponding to the control cavity area is judged to be medium, and a medium evaluation is added on the basis of its existing key monitoring level attribute; when the ratio Rx is less than thx, the key monitoring level of the cavity area corresponding to the observed cavity area is judged to be medium, and a medium evaluation is added on the basis of its existing key monitoring level attribute, and then the key monitoring level of the cavity area corresponding to the control cavity area is judged to be low, and a low evaluation is added on the basis of its existing key monitoring level attribute.

8. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In step 3.3, if they are the same, directly perform similarity judgment on the two cavity areas, specifically: judge that the two cavity areas have a high degree of similarity, and add an evaluation that is the same as the second evaluation in its key monitoring level attributes based on its existing key monitoring level attributes.

9. The image target detection method based on multi-level judgment as claimed in claim 1, characterized in that: In the step 3, based on the key monitoring level attribute of the CT image, the ResNet-50 model of the integrated space transformation network is used to perform target detection on the CT image, specifically: first, the preprocessed CT image is input into the ResNet-50 model of the integrated space transformation network; secondly, according to the key monitoring level attribute of the cavity area, the integrated space transformation network module automatically adjusts the local magnification degree of the identified cavity areas A and B in the image through local affine transformation, and then the image adjusted by the integrated space transformation network is transmitted to the subsequent layer of ResNet-50 for feature extraction, and finally the target detection is performed through the binary classification output layer of the model to determine whether the target exists.

10. The image target detection method based on multi-level judgment as claimed in claim 9, characterized in that: According to the key monitoring level attribute of the cavity area, the integrated spatial transformation network module automatically adjusts the local magnification degree of the identified cavity areas A and B in the image through local affine transformation, specifically: when the key monitoring level of the cavity areas A and B includes 3 highs, a local magnification of 1.5 times is performed; when it includes 2 highs and 1 medium, a local magnification of 1.4 times is performed; when it includes 1 high and 2 mediums, a local magnification of 1.3 times is performed; when it includes 3 mediums, a local magnification of 1.2 times is performed; when it includes 2 mediums and 1 low, a local magnification of 1.15 times is performed; when it includes 1 medium and 2 lows, a local magnification of 1.1 times is performed; when it includes 3 lows, the original size is maintained without magnification.

Images