Method, equipment and program product for predicting adrenal lesion based on chest CT (Computed Tomography)

Abstract

The invention relates to the field of intelligent medical treatment, in particular to a method, equipment and a program product for predicting an adrenal lesion based on chest CT (Computed Tomography). Comprising the following steps: S1, acquiring chest CT data; s2, transmitting the chest CT data to a segmentation network for segmentation to obtain a region of interest; and S3, transmitting the region of interest to a classifier for prediction to obtain a prediction result that the adrenal gland is normal or abnormal. Normality or abnormity of the adrenal gland can be predicted through chest CT, a new and convenient way is provided, and the method has good clinical value.

Description

Technical Field

[0001] The present application relates to the field of intelligent medical care, and specifically to a method, device, program product, and computer-readable storage medium for predicting adrenal lesions based on chest CT. Background Art

[0002] Adrenal diseases account for about 5% of patients with hypertension. However, with the advancement of testing technology and doctors' increased awareness of secondary hypertension, it is now believed that the proportion of adrenal hypertension has risen to more than 20%, especially in patients with refractory hypertension, the proportion is even more than 30%. Most adrenal diseases can be prevented, controlled, or even cured by surgical resection. Therefore, early screening for adrenal disease is important for reducing complications and improving quality of life.

[0003] However, there is currently no effective screening method for adrenal diseases. Due to the small size and deep location of the adrenal glands, ultrasound examinations often have difficulty accurately detecting the adrenal region. Although the detection rate of abdominal enhanced CT is high, it is expensive, has a large amount of radiation, and there is a risk of contrast agent allergy, and the examination procedures are relatively complicated. These unfavorable factors have led to many cases not being diagnosed in time, thus affecting the detection rate and treatment effect of adrenal diseases, causing patients to often face the serious consequences of hypertension when they seek medical treatment. Summary of the invention

[0004] In response to the above problems, the present invention proposes a method for predicting adrenal lesions based on chest CT. As a routine physical examination item, chest CT scans from the apex to the base of the lungs. In addition to being able to detect lung diseases such as lung nodules, it can also identify adrenal abnormalities. Using chest CT to screen for adrenal nodules can not only reduce radiation dose, but also reduce medical costs, becoming a "kill two birds with one stone" preferred screening strategy. And with the continuous advancement of artificial intelligence technology in the field of medical imaging, the development of specialized software based on deep learning models for screening adrenal nodules in chest CT can effectively reduce medical costs and improve work efficiency, thereby providing more people with timely and accurate medical services. The method for predicting adrenal lesions based on chest CT specifically includes:

[0005] S1. Obtain chest CT data;

[0006] S2, inputting the chest CT data into a segmentation network for segmentation to obtain a region of interest;

[0007] S3. Inputting the region of interest into a classifier for prediction to obtain a prediction result of whether the adrenal gland is normal or abnormal.

[0008] Furthermore, the chest CT includes one or more of the following: low-dose chest CT, plain scan CT, enhanced CT, and high-resolution CT;

[0009] Optionally, the chest CT is a low-dose CT;

[0010] Optionally, the segmentation includes one or more of the following: a two-dimensional segmentation network, a three-dimensional segmentation network;

[0011] Optionally, the two-dimensional segmentation network includes one or more of the following: UNet, FCN, SegNet, Enet, DeepLabV3+, DSN;

[0012] Optionally, the three-dimensional segmentation network includes one or more of the following: 3D Vnet, 3D UNet, 3D FCN, AtlasNet, DenseVoxNet, nnUNet, 3D ResNet / ResNeXt.

[0013] The S2 is replaced by S2': the chest CT data is input into a segmentation network for segmentation to obtain a target region, regional expansion is performed based on the target region to generate a regional bounding box, and segmentation is performed based on the regional bounding box to obtain a region of interest.

[0014] The training process of the three-dimensional segmentation network is:

[0015] Obtain chest CT dataset and adrenal gland region labels;

[0016] Inputting the data set and the label into the three-dimensional segmentation network to be trained to obtain a region recognition result;

[0017] Compare the region recognition results with the adrenal region labels to obtain the loss function;

[0018] The three-dimensional segmentation network is optimized based on the loss function, and the above steps are repeated until the loss function remains unchanged to obtain the three-dimensional segmentation network.

[0019] The three-dimensional segmentation network performs region of interest segmentation through 3D Vnet, which includes an encoder and a decoder. The chest CT data is downsampled N times by the encoder and a feature map obtained by each downsampling is output, where N is a natural number greater than 1. The feature map obtained by the Nth downsampling is input to the decoder, and the decoder performs N upsampling to obtain the region of interest, and the feature map obtained by downsampling is input to the decoder through a jump connection.

[0020] The classifier makes predictions through a pre-trained deep learning network;

[0021] Optionally, the pre-trained deep learning network includes one or more of the following: Med3D, MTCNN, DenseVNet, DGCNN, VoteNet, ShellNet;

[0022] Optionally, the pre-trained deep learning network is a Med3D deep learning network;

[0023] Optionally, the decoding module of the Med3D deep learning network is replaced by L convolution modules and a fully connected layer, L is a natural number greater than 1, and the convolution module includes a maximum pooling layer and a convolution layer;

[0024] Optionally, the training process of the pre-trained deep learning network is:

[0025] Obtaining a set of regions of interest and labels of normal or abnormal adrenal glands;

[0026] The region of interest set and the normal or abnormal labels of the adrenal glands are input into a pre-trained deep learning network to be trained to obtain a pre-trained deep learning network, wherein the pre-trained deep learning network is parameter adjusted and weight optimized according to the input data.

[0027] The method further comprises data preprocessing, wherein the chest CT data is preprocessed to obtain processed data, and the processed data is input into a three-dimensional segmentation network;

[0028] Optionally, the data preprocessing includes: data enhancement, data resampling, and data standardization.

[0029] The object of the present invention is to provide a computer product, including a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement the above-mentioned method for predicting adrenal lesions based on chest CT.

[0030] The object of the present invention is to provide a computer device, including a memory, a processor, and a computer program or instructions stored in the memory, wherein the computer program or instructions are executed by the processor to implement the above-mentioned method for predicting adrenal lesions based on chest CT.

[0031] The object of the present invention is a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the above-mentioned method for predicting adrenal lesions based on chest CT.

[0032] Advantages of the present invention:

[0033] 1. Chest CT has been routinely used for health examinations and lung cancer screening for community populations, and its scanning range covers the adrenal region. The present invention uses chest CT to detect incidental adrenal lesions, thereby improving the detection rate of adrenal abnormalities without increasing medical expenses and radiation doses.

[0034] 2. The present invention uses artificial intelligence deep learning technology to achieve automatic segmentation and classification of chest CT, assisting clinicians to automatically evaluate the adrenal region after scanning. When abnormalities are detected, the doctor is prompted to conduct further examinations, reducing the doctor's workload and improving work efficiency.

[0035] 3. Adrenal diseases may lead to secondary hypertension and refractory hypertension, but some patients fail to receive further treatment due to missed diagnosis, which leads to serious complications. The present invention aims to improve the detection rate of adrenal abnormalities, achieve early diagnosis and treatment, and thus reduce long-term complications, which has significant clinical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A schematic flow chart of a method for predicting adrenal lesions based on chest CT provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a system for predicting adrenal lesions based on chest CT provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a device for predicting adrenal lesions based on chest CT provided by an embodiment of the present invention;

[0040] Figure 4Schematic diagram of non-enhanced CT adrenal abnormality provided in an embodiment of the present invention, the abnormal area of ​​the adrenal region is indicated by an arrow. (A) Adrenal adenoma: local soft tissue density lesions in the adrenal region, roughly circular, with clear and uniform boundaries, and an average CT value of 0-10HU. (B) Non-specific mass or nodule in the adrenal region: local soft tissue lesions in the adrenal region, with clear or unclear boundaries, and a CT value of 10-40HU. (C) Adrenal myelolipoma: local fat density lesions in the adrenal region, with a CT value range of -20 to -100HU. (D) Cystic lesions in the adrenal region: local water density lesions in the adrenal region, roughly circular, with clear boundaries, and a CT value of approximately 0HU. (E) Adrenal calcification: single or multiple high-density lesions in the adrenal region, usually small, appearing as dots, lines or plaques, with clear boundaries, may involve the entire adrenal gland, and the CT value exceeds 100HU. (F) Postoperative changes in the adrenal area: normal adrenal glands are not clearly visible, and short linear high-density objects can be seen locally, which are postoperative metal sutures or clips. (G) Adrenal hemorrhage: The acute phase is manifested by diffuse enlargement and increased density of the adrenal glands, with a CT value of 50-80HU. (H) Diffuse adrenal hyperplasia: diffuse enlargement of the adrenal glands, which can be an increase in the volume and thickness of the entire adrenal gland, or an increase in the volume of the medial or lateral limbs. The boundaries are clear, there is no focal abnormal density, and no masses or nodules are formed. (I) Adrenal nodular hyperplasia: one or more nodules appear in the adrenal glands, with equal or slightly lower density. The shape of the adrenal glands is irregular and can occur in any part of the adrenal glands. They can exist in a single adrenal gland or both adrenal glands;

[0041] Figure 5 A data flow diagram provided for an embodiment of the present invention;

[0042] Figure 6 Evaluation indicators of the segmentation model provided in the embodiment of the present invention, A represents the DSC results of the test set, internal validation set and external validation set. The first row shows the DSC value of the left adrenal gland, which is divided into a normal group and an abnormal group. The second row provides the DSC value of the right adrenal gland, using the same classification method; the third row shows the DSC values ​​of all adrenal glands; the first column lists the DSC values ​​of the left and right adrenal glands in the test set; the second column details the DSC values ​​in the internal validation cohort; the third column shows the DSC values ​​of all adrenal glands; B represents volume similarity (VS), and C represents the average Hausdorff distance (HD) statistic; In Val: internal validation; Exter Val: external validation; DSC: Dice similarity coefficient; VS: volume similarity; Hd: Hausdorff distance;

[0043] Figure 7The model training results provided by the embodiments of the present invention; AC shows the confusion matrix of the AI ​​model in the test set, internal validation set, and external validation set. DF represents the confusion matrix of the radiology report in the test set, internal validation set, and external validation set. GI gives the ROC curves of the AI ​​model and the radiology report in the test set, internal validation set, and external validation set. JL shows the PR curves of the AI ​​model and the radiology report in the test set, internal validation set, and external validation set. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0045] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The sequence numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0046] Figure 1 A schematic diagram of a method for predicting adrenal lesions based on chest CT provided by an embodiment of the present invention specifically includes:

[0047] S1: Acquire chest CT data;

[0048] In one embodiment, the chest CT includes one or more of the following: low-dose chest CT, plain scan CT, enhanced CT, and high-resolution CT.

[0049] In one embodiment, the chest CT is a low-dose CT.

[0050] In one embodiment, the concept of low-dose CT: when other conditions remain unchanged, the tube current is reduced to reduce radiation, while ensuring the image diagnosis requirements. The radiation dose is about 1 / 5 of that of ordinary CT, about 1 mSv. Low-dose CT is not a special machine, but it changes the parameters of an ordinary CT machine (generally a 64-row CT). While reducing the radiation dose, it also loses some clarity, so it is mainly used for screening people at high risk of lung cancer. LDCT, also known as low-dose spiral CT, is 1 / 4-1 / 3 of the radiation dose of ordinary CT, so it has a higher safety factor and is more suitable for physical examinations. Cheap: LDCT is relatively cheaper than ordinary CT. Low resolution: The image resolution of LDCT is lower than that of ordinary CT.

[0051] In one embodiment, the method further comprises data preprocessing, wherein the chest CT data is preprocessed to obtain processed data, and the processed data is input into a three-dimensional segmentation network;

[0052] Optionally, the data preprocessing includes: data enhancement, data resampling, and data standardization.

[0053] In a specific embodiment, the data of the present invention includes four different cohorts. Cohort A is from Hospital 1 and includes chest LDCT scans collected between March 2018 and December 2021. Given the limited number of abnormal cases in Cohort A, in order to increase the sample size of patients with adrenal abnormalities, Cohort B was also included, including patients from Hospital 1 who underwent abdominal CT scans from October 2021 to December 2021 and whose radiology reports showed adrenal abnormalities. The data from Cohorts A and B were used for the development of the AI ​​model. In addition, Cohort C from Hospital 1 includes consecutive chest LDCT scans from July 2022 to April 2023. Cohort D is from Hospital 2 and has the same inclusion criteria as Cohort C. Cohorts C and D are designated for internal and external validation of the AI ​​model.

[0054] Exclusion criteria included cases where CT images could not be uploaded, duplicate patient examinations, visualization obscured by significant upper abdominal artifacts, and cases where the adrenal glands could not be identified on CT images. Incomplete coverage of the adrenal glands on chest CT images was also excluded. For patients to be included in this study, complete visualization of the bilateral adrenal glands within a maximum slice thickness of 5 mm was required. In total, this study included 2574, 1205, 3681, and 779 patients in the four cohorts, respectively, with no patient overlap between them.

[0055] In one specific embodiment, all CT images were acquired by 12 scanners produced by 5 different manufacturers. The model development cohort was obtained from scanners from 4 vendors, and the internal validation cohort was obtained from scanners from 3 vendors. The external validation cohort was obtained from scanners from two vendors. The tube current of the model development data set was 133.0 (IQR: 101.0-300.0) mA, the peak tube voltage was 100 (IQR: 100-120) kV, and the scanning slice thickness was 5.00 (IQR: 5.00-5.00) mm. For the internal validation group, the tube current was 98.0 (IQR: 77.0-120.0) mA, the peak tube voltage was 100 (IQR: 100-100) kV, and the scanning slice thickness was 5.00 (IQR: 5.00-5.00) mm. The tube current of the external validation cohort was 78.0 (IQR: 65.0-92.5) mA, the tube voltage peak was 120 (IQR: 110-120) kV, and the scanning slice thickness was 1.50 (IQR: 1.50-1.50) mm. The differences in all scanning parameters between the model development cohort, internal validation cohort, and external validation cohort were statistically significant (all P < 0.001).

[0056] In one embodiment, two experienced urological radiologists independently read and analyze the CT images to determine whether there are abnormalities in the adrenal glands. The evaluation criteria for adrenal abnormalities focus on whether there are isolated or combined density and morphological abnormalities in the adrenal glands, such as Figure 4 Abnormal adrenal density included calcification, hemorrhage, cysts, fatty infiltration, or density lower than normal adrenal tissue. Morphological abnormalities included diffuse adrenal enlargement, multiple nodules, solitary nodules or masses, and changes suggestive of previous surgical intervention. When the two experts disagreed, consensus was reached through joint consultation.

[0057] S2: Inputting the chest CT data into a segmentation network for segmentation to obtain a region of interest;

[0058] In one embodiment, the segmentation includes one or more of the following: a two-dimensional segmentation network, a three-dimensional segmentation network.

[0059] In one embodiment, the two-dimensional segmentation network includes one or more of the following: UNet, FCN, SegNet, Enet, DeepLabV3+, DSN.

[0060] In one embodiment, the training process of the two-dimensional segmentation network is:

[0061] Obtain chest CT dataset and adrenal gland region labels;

[0062] Inputting the data set and the label into the two-dimensional segmentation network to be trained to obtain a region recognition result;

[0063] Compare the region recognition results with the adrenal region labels to obtain the loss function;

[0064] The two-dimensional segmentation network is optimized based on the loss function, and the above steps are repeated until the loss function remains unchanged to obtain a two-dimensional segmentation network.

[0065] In one embodiment, the three-dimensional segmentation network includes one or more of the following: 3D Vnet, 3DUNet, 3DFCN, AtlasNet, DenseVoxNet, nnUNet, 3D ResNet / ResNeXt.

[0066] In one embodiment, the training process of the 3D segmentation network is:

[0067] Obtain chest CT dataset and adrenal gland region labels;

[0068] Inputting the data set and the label into the three-dimensional segmentation network to be trained to obtain a region recognition result;

[0069] Compare the region recognition results with the adrenal region labels to obtain the loss function;

[0070] The three-dimensional segmentation network is optimized based on the loss function, and the above steps are repeated until the loss function remains unchanged to obtain the three-dimensional segmentation network.

[0071] In one embodiment, the three-dimensional segmentation network performs region of interest segmentation through 3D Vnet, and the 3D Vnet includes an encoder and a decoder. The chest CT data is downsampled N times by the encoder and the feature map obtained by each downsampling is output, where N is a natural number greater than 1. The feature map obtained by the Nth downsampling is input to the decoder, and the decoder performs N-time upsampling on the feature map after the Nth encoding to obtain the region of interest, and the downsampled feature map is input to the decoder through a jump connection. The encoder and the decoder perform a jump connection to fuse the feature map, and the feature dimension of the encoding layer of the jump connection is the same as the feature dimension of the decoding layer.

[0072] In one embodiment, S2 is replaced by S2': the chest CT data is input into a segmentation network for segmentation to obtain a target region, region expansion is performed based on the target region to generate a region bounding box, and segmentation is performed based on the region bounding box to obtain a region of interest.

[0073] In a specific embodiment, the workflow of the deep learning algorithm of the present invention is as follows: Figure 5As shown, it includes two main stages: adrenal segmentation and adrenal classification. The first stage involves the segmentation of the adrenal glands, where the 3D VNet deep learning network is utilized. The input data consists of a complete CT image (A) and bilateral adrenal regions labeled by experts (B). The output of the segmentation model is the bilateral adrenal region prediction (C). The second stage is the classification of the adrenal glands, using the Med3D deep learning model. The adrenal gland region predicted from the segmentation model is used as a mask (D) to crop the CT image, producing the adrenal gland bounding box (E), which then becomes the input of the Med3D model. The classification label of the adrenal gland is marked as normal or abnormal (F). The cropped CT image and its label are used as input for the Med3D model, and the output is the probability that the adrenal gland is abnormal (G).

[0074] All training processes were completed on NVIDIA Tesla P100 16G GPU. The algorithm was coded in Python3.6, PyTorch 0.4.1, OpenCV 3.4.0.12, NumPy 1.16.2, and SimpleITK 1.2.0. The deep learning model was developed using the model development dataset, which was randomly divided into three subsets: training set, validation set, and test set, with an approximate ratio of 8:1:1. To ensure the integrity of the evaluation, the data of the same patient were assigned to a separate subset. During the training process, the training set was used for gradient descent optimization, and the validation set was used for hyperparameter tuning and model selection. The test set was reserved to evaluate the performance of the model after training.

[0075] In the first step, a three-dimensional deep neural network called 3D VNet was used. The network consists of an encoder and a decoder to accurately locate the location of the bilateral adrenal glands. The encoder performs 4 downsampling operations to construct feature maps, which are then fused in the decoder through skip connections. The decoder upsamples from the variables and concatenates them with the previous encoder feature maps. The input of 3D VNet consists of the entire CT images, which are preprocessed before being fed into the network. To ensure that the shape and voxel spacing of the data are consistent, the images are resampled to a fixed resolution of 256×192×96 (x×y×z). The window width is set to 300 and the window center is set to 30. In addition, the voxel values ​​are normalized by z-score normalization. The training set data is augmented by applying random rotations (up to 10°), introducing random noise, and performing parallel translations within the range of [-0.1, 0.1] pixels on the horizontal and vertical axes. The loss function of 3D VNet is the Dice loss, which is well suited to address the imbalanced classes often encountered in medical imaging. The Dice coefficient D is defined as:

[0076]

[0077] Where A represents the predicted segmentation and B represents the true value. The Dice loss LDice is defined as:

[0078]

[0079] Where pi is the predicted probability of each voxel and gi is the true label.

[0080] S3: Inputting the region of interest into a classifier for prediction to obtain a prediction result of whether the adrenal gland is normal or abnormal.

[0081] In one embodiment, the classifier makes predictions via a pre-trained deep learning network;

[0082] The pre-trained deep learning network includes one or more of the following: Med3D, MTCNN, DenseVNet, DGCNN, VoteNet, and ShellNet.

[0083] In one embodiment, the pre-trained deep learning network is a Med3D deep learning network; the decoding module of the Med3D deep learning network is replaced by L convolution modules and a fully connected layer, L is a natural number greater than 1, and the convolution module includes a maximum pooling layer and a convolution layer.

[0084] In one embodiment, the training process of the pre-trained deep learning network is:

[0085] Obtaining a set of regions of interest and labels of normal or abnormal adrenal glands;

[0086] The region of interest set and the normal or abnormal labels of the adrenal glands are input into a pre-trained deep learning network to be trained to obtain a pre-trained deep learning network, wherein the pre-trained deep learning network is parameter adjusted and weight optimized according to the input data.

[0087] In one embodiment, the present invention proposes automatic segmentation of the entire adrenal gland without manual intervention, which, coupled with automatic classification, can accurately identify adrenal abnormalities. This approach has advantages over the labor-intensive process of interpreting LDCT scans and may help reduce the rate at which radiologists overlook adrenal abnormalities. Therefore, the purpose of this study is to explore the feasibility of automatic segmentation and classification of the adrenal gland using a deep learning model to detect adrenal abnormalities in LDCT imaging.

[0088] In one specific embodiment, in the second step, the present invention employs a deep learning network called Med3D. This framework uses the power of transfer learning to analyze 3D medical images. Med3D includes a 3D convolutional neural network pre-trained on a wide range of medical image datasets. For the present invention's application, the present invention fine-tunes this pre-trained model. Through transfer learning, the weights of the encoder are used to extract features from the image. The present invention retains the encoder component and replaces the decoder (deconvolution part) of the network with the convolutional layers and fully connected layers in the classification network architecture. The structure of the classification convolutional layer is as follows: 1) a maximum pooling layer with a stride of 2; 2) a convolutional layer with a kernel size of 3; 3) another maximum pooling layer with a stride of 2; 4) another second convolutional layer with a kernel size of 3. The fully connected layer of the classification network consists of 128 neurons that integrate and classify the image features. The output is then calculated and the classification result is presented through a SoftMax function, which generates a probability distribution for different categories. The input to the second stage is the bounding box derived from the adrenal mask extracted in the first step. These masks are used to crop bounding boxes from the entire CT image in preparation for the input to the second stage. Med3D then predicts that each adrenal gland is either normal or abnormal. The output of the second stage is a probability score indicating the likelihood of abnormality, with values ​​ranging from 0 to 1. The loss function used by Med3D is the binary cross entropy loss, which is defined as follows:

[0089] L BCE =-[ylog(p)+(1-y)log(1-p)]

[0090] Where y is the true label (0 or 1) and p is the predicted probability that the instance is in class 1.

[0091] The present invention uses the Adam optimizer with a learning rate of 0.01-0.0001 to update the parameters of the network. To prevent overfitting, early stopping is implemented, and the final model is selected based on the criterion that the loss does not decrease in 50 consecutive iterations.

[0092] In a specific embodiment, the performance of the model on the test set was evaluated from the model development data set, the internal validation cohort, and the external validation cohort. For adrenal segmentation, the Dice score (DSC), volume similarity (VS), and average Hausdorff distance (HD) were used to evaluate the performance of the model. For adrenal classification, evaluation indicators such as the receiver operating characteristic (ROC) curve, the precision-recall rate (PR) curve, and the confusion matrix were used. The present invention also collected the radiology reports of these patients and extracted the description of the adrenal glands from the reports. The output of the model and the radiology report were compared with the actual situation. The present invention uses integrated discrimination improvement (IDI) to evaluate the AI ​​model and improves the diagnostic accuracy of the radiology report.

[0093] In a specific embodiment, statistical analysis was performed using R4.1.3 software. Normally distributed continuous variables were expressed as mean ± standard deviation, and non-normally distributed variables were expressed as median (interquartile range, IQR). Categorical variables were reported as frequency and percentage. The Kolmogorov-Smirnov (KS) test was used to assess the normality of the distribution, and the F test was used to assess the homogeneity of variance. The Mann-Whitney U test or the Kruskal-Wallis test was used for comparisons between groups with non-normally distributed data or unequal variances. Multiple comparisons were corrected using the Bonferroni method. The DeLong test was used for comparison of AUC. The Z statistic was used to test whether the IDI was significantly different from 0. A P value less than 0.05 was considered statistically significant.

[0094] In one specific example, Table 1 presents detailed demographic data and adrenal status.

[0095] In the model development dataset, the median age was 60.0 years ((IQR: 49.0-69.0)), of which 2199 (58.2%) were male. There were 2268 cases with normal bilateral adrenal glands (60.0%), 759 cases with abnormal left adrenal glands (20.1%), 217 cases with abnormal right adrenal glands (5.7%), 475 cases with abnormal bilateral adrenal glands (12.6%), and 60 cases with incomplete adrenal scans (1.6%). In the internal validation cohort, the median age was 47.0 years ((IQR: 37.0-60.0)), of which 1814 (49.3%) were male. There were 3602 cases (97.9%) with normal adrenal glands, 46 cases (1.2%) with abnormal left adrenal glands, 17 cases (0.5%) with abnormal right adrenal glands, 2 cases (0.1%) with abnormal bilateral adrenal glands, and 14 cases (0.4%) with adrenal insufficiency. The median age of the external validation cohort was 60.0 years (IQR: 48.0-69.0), of which 503 cases (64.6%) were male. There were 646 cases (82.9%) with normal adrenal glands, 105 cases (13.5%) with abnormal left adrenal glands, 14 cases (1.8%) with abnormal right adrenal glands, 8 cases (1.0%) with abnormal bilateral adrenal glands, and 6 cases (0.8%) with adrenal insufficiency. The adrenal morphology, diameter, volume, and CT value were statistically analyzed. All clinical parameters were statistically significant among the three groups (P<0.05).

[0096] Table 1

[0097]

[0098]

[0099] In a specific embodiment, the DSC, VS and HD values ​​of each data set and the results of the statistical tests are detailed in Tables 2 and Figure 6 . The DSC values ​​of the test data set, internal validation set, and external validation set were 0.839 (IQR: 0.783-0.871), 0.870 (IQR: 0.819 -0.902), and 0.799 (IQR: 0.729-0.849), respectively. The differences in DSC values ​​among the three groups were statistically significant (P<0.05). The VS values ​​of each group were 0.947 (IQR: 0.893-0.973), 0.952 (IQR: 0.910-0.978), and 0.914 (IQR: 0.840-0.963), respectively. The differences in VS values ​​among the three groups were statistically significant (P<0.05). The average HD values ​​were 0.226 mm (IQR: 0.158-0.374), 0.163 mm (IQR: 0.0989-0.302), and 0.354 mm (IQR: 0.223-0.616), respectively. The differences in HD values ​​among the three groups were statistically significant (P<0.05). Focusing on the DSC value, the present invention further compared the performance of the AI ​​model in segmenting normal and abnormal adrenal glands. In the test set, internal validation cohort, and external cohort, the median DSC of abnormal adrenal glands was smaller than that of normal adrenal glands (all P<0.05).

[0100] In addition, the present invention also compared the performance of the AI ​​model in segmenting the left and right adrenal glands. In the test set, the median DSC value of the right side was greater than that of the left side, and in the internal validation cohort, the median DSC value of the left side was greater than that of the right side (P<0.001). In the external validation cohort, there was no statistically significant difference in the median DSC values ​​of the left and right adrenal glands (P=0.511).

[0101] Figure 7 The confusion matrix, ROC curve, and PR curve of the AI ​​model and radiology report for adrenal gland classification in the test set, internal validation set, and external validation set are given. Table 3 lists the AUC values, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, and negative likelihood ratio of the classification in the three datasets in detail. The DeLong test was used to compare the AUC values ​​of the AI ​​model and radiology report on each dataset, and the results are shown in Table 4.

[0102] Table 2

[0103]

[0104]

[0105] P 1: Statistical test results of the difference in DSC values ​​between normal adrenal glands and abnormal adrenal glands or between left and right adrenal glands. 2 : Statistical test results of the difference in VS values ​​between the left and right adrenal glands or between normal and abnormal adrenal glands. 3 : Statistical test results of the difference in HD values ​​between normal and abnormal adrenal glands or between the left and right adrenal glands. P 4 : Statistical test results of the differences in DSCs, VSs, and HDs among the test set, internal validation set, and external validation set.

[0106] Table 3

[0107]

[0108]

[0109] Table 4

[0110]

[0111] The AUC values ​​of the ROC curve of the AI ​​model in the test set, internal validation set, and external validation set were 0.956 (95% CI: 0.941-0.972), 0.942 (95% CI: 0.906-0.978), and 0.977 (95% CI: 0.956-0.997), respectively. The AUC values ​​of the radiology reports in the three data sets were 0.889 (95% CI: 0.861-0.916), 0.705 (95% CI: 0.650-0.760), and 0.551 (95% CI: 0.525-0.576), respectively. In the three data sets (all P < 0.05), the AUC values ​​of the AI ​​model were significantly greater than those of the radiology reports.

[0112] Given the severe imbalance in the number of normal and abnormal adrenal glands in the internal and external validation cohorts, the PR curve was further used to evaluate the classification ability of the AI ​​model and radiology reports. The PR AUC values ​​of the AI ​​model and radiology reports in the test set were 0.913 and 0.809, respectively, in the internal validation cohort were 0.753 and 0.708, respectively, and in the external validation cohort were 0.927 and 0.591, respectively, with statistically significant differences (P<0.05).

[0113] The IDI was used to study the enhancement effect of the AI ​​model on the radiology report. Taking the radiology report as the reference, the net reclassification index (NRI) of the AI ​​model relative to the radiology report in the test set, internal validation cohort, and external validation cohort was -0.172 (95% CI: -0.261, -0.084), -0.821 (95% CI: -1.039 to -0.602), and 0.685 (95% CI: 0.610-0.761), respectively, all P < 0.001. The IDI of the AI ​​model relative to the radiology report was -0.130 (95% CI: -0.197, -0.063) in the test set, 0.221 (95% CI: 0.066 -0.376) in the internal validation cohort, and 0.590 (95% CI: 0.523-0.657) in the external validation cohort, all P < 0.05.

[0114] Studies have reported that adrenal abnormalities are common but often overlooked in radiology reports, highlighting the need for increased awareness in radiology. The AI ​​model proposed in this study can automatically detect abnormalities in the adrenal region from LDCT images with an AUC of 0.942-0.977, which exceeds the detection capability of radiology reports (AUC: 0.551-0.889, P<0.05). This suggests that the AI ​​model of the present invention can assist radiologists in their work. The envisioned application scenario is that the AI ​​model acts as the first reader to assist radiologists in automatically evaluating scans after LDCT is completed. If the AI ​​model identifies an abnormality, it can alert radiologists to the adrenal glands during image interpretation and reporting.

[0115] In recent years, with the development of deep learning technology, the accurate delineation of abdominal organs in medical images has achieved remarkable results. However, automatic segmentation of adrenal glands remains challenging due to their small size, unclear boundaries with surrounding tissues, and large variations in shape and position. Our study focuses on adrenal gland segmentation in chest LDCT images, which usually have lower image quality, thus increasing the difficulty of the task. Nevertheless, our study obtained competitive DSC values ​​for 9,606 adrenal glands in different validation sets, ranging from 0.799 to 0.870, which is consistent with previous research results.

[0116] The present study differs from the above studies in three main aspects. First, the present invention focuses on images from chest LDCT scans. Secondly, a larger data set was used during training, more extensive validation was performed, and the results of the AI ​​model of the present invention were compared with radiology reports, demonstrating the potential clinical benefits of using the AI ​​model. The validation cohort of the present invention includes an internal validation cohort (7523 adrenal glands) and an external validation cohort (1545 adrenal glands). The model showed robust classification performance in both cohorts, with a sensitivity of 0.821-0.964, a specificity of 0.927-0.994, a ROC AUC of 0.942-0.977, and a PR AUC of 0.753-0.927. In both internal and external validation cohorts, the AI ​​model was significantly superior to radiology reports in detecting adrenal abnormalities. Third, the present study divided the adrenal glands into two categories: normal and abnormal, rather than the normal vs. mass-containing adrenal glands or normal vs. hyperplasia classifications used in previous studies. The definition of abnormality in the present invention includes various morphological and density abnormalities of the adrenal gland, which is more in line with clinical practice.

[0117] In our study, the incidence of adrenal abnormalities was 1.8% in the internal validation cohort (65 of 3681 patients) and 15.4% in the external validation cohort (127 of 779 patients with follow-up). This significant difference in incidence is likely attributable to demographic differences between the cohorts, with the number of older patients in the external cohort (median age 60.0 years, IQR: 48.0-69.0) being higher than in the internal cohort (median age 47.0 years, IQR: 37.0-60.0), a difference that was statistically significant (P < 0.001).

[0118] The AI ​​model proposed in this paper is designed to accurately detect these adrenal abnormalities. Its application in future large-sample studies could enhance the understanding of the incidence of adrenal abnormalities and may serve as a preliminary screening tool for community health assessment, making a valuable contribution to the field.

[0119] The disclosed embodiments of the present invention further provide a computer program product or system, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for predicting adrenal lesions based on chest CT.

[0120] Figure 2 The schematic diagram of the system for predicting adrenal lesions based on chest CT provided by an embodiment of the present invention specifically includes:

[0121] Acquisition unit: acquire chest CT data;

[0122] Segmentation unit: inputting the chest CT data into a segmentation network for segmentation to obtain a region of interest;

[0123] Prediction unit: input the region of interest into the classifier for prediction to obtain a prediction result of whether the adrenal gland is normal or abnormal.

[0124] Figure 3 A schematic diagram of a device for predicting adrenal lesions based on chest CT provided by an embodiment of the present invention specifically includes:

[0125] A memory and a processor; the memory is used to store program instructions; the processor is used to call program instructions, and when the program instructions are executed, any one of the above-mentioned methods for predicting adrenal lesions based on chest CT is performed.

[0126] The disclosed embodiments of the present invention further provide a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, is any one of the above-mentioned methods for predicting adrenal lesions based on chest CT.

[0127] The verification results of this verification example show that assigning inherent weights to indications can improve the performance of the method relative to the default settings. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways.

[0128] For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0129] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be implemented by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned medium storage can be a read-only memory, a disk or an optical disk, etc.

[0130] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting adrenal lesions based on chest CT, characterized in that: include: S1. Obtain chest CT data; S2, inputting the chest CT data into a segmentation network for segmentation to obtain a region of interest; S3. Inputting the region of interest into a classifier for prediction to obtain a prediction result of whether the adrenal gland is normal or abnormal.

2. The method for predicting adrenal lesions based on chest CT according to claim 1, characterized in that: The chest CT includes one or more of the following: low-dose chest CT, plain scan CT, enhanced CT, and high-resolution CT; Optionally, the chest CT is a low-dose CT; Optionally, the segmentation network includes one or more of the following: a two-dimensional segmentation network, a three-dimensional segmentation network; Optionally, the two-dimensional segmentation network includes one or more of the following: UNet, FCN, SegNet, Enet, DeepLabV3+, DSN; Optionally, the three-dimensional segmentation network includes one or more of the following: 3D Vnet, 3D UNet, 3D FCN, AtlasNet, DenseVoxNet, nnUNet, 3D ResNet / ResNeXt.

3. The method for predicting adrenal lesions based on chest CT according to claim 1, characterized in that: The S2 is replaced by S2': the chest CT data is input into a segmentation network for segmentation to obtain a target region, regional expansion is performed based on the target region to generate a regional bounding box, and segmentation is performed based on the regional bounding box to obtain a region of interest.

4. The method for predicting adrenal lesions based on chest CT according to claim 2, characterized in that: The training process of the three-dimensional segmentation network is: Obtain chest CT dataset and adrenal gland region labels; Inputting the data set and the label into the three-dimensional segmentation network to be trained to obtain a region recognition result; Compare the region recognition results with the adrenal region labels to obtain the loss function; The three-dimensional segmentation network is optimized based on the loss function, and the above steps are repeated until the loss function remains unchanged to obtain the three-dimensional segmentation network.

5. The method for predicting adrenal lesions based on chest CT according to claim 2, characterized in that: The three-dimensional segmentation network performs region of interest segmentation through 3D Vnet, which includes an encoder and a decoder. The chest CT data is downsampled N times by the encoder and a feature map obtained by each downsampling is output, where N is a natural number greater than 1. The feature map obtained by the Nth downsampling is input to the decoder, and the decoder performs N upsampling to obtain the region of interest, and the feature map obtained by downsampling is input to the decoder through a jump connection.

6. The method for predicting adrenal lesions based on chest CT according to claim 1, characterized in that: The classifier makes predictions through a pre-trained deep learning network; Optionally, the pre-trained deep learning network includes one or more of the following: Med3D, MTCNN, DenseVNet, DGCNN, VoteNet, ShellNet; Optionally, the pre-trained deep learning network is a Med3D deep learning network; Optionally, the decoding module of the Med3D deep learning network is replaced by L convolution modules and a fully connected layer, L is a natural number greater than 1, and the convolution module includes a maximum pooling layer and a convolution layer; Optionally, the training process of the pre-trained deep learning network is: Obtaining a set of regions of interest and labels of normal or abnormal adrenal glands; The region of interest set and the normal or abnormal labels of the adrenal glands are input into a pre-trained deep learning network to be trained to obtain a pre-trained deep learning network, wherein the pre-trained deep learning network is parameter adjusted and weight optimized according to the input data.

7. The method for predicting adrenal lesions based on chest CT according to claim 1, characterized in that: The method further comprises data preprocessing, wherein the chest CT data is preprocessed to obtain processed data, and the processed data is input into a three-dimensional segmentation network; Optionally, the data preprocessing includes: data enhancement, data resampling, and data standardization.

8. A computer product comprising a computer program or instructions, characterized in that The computer program or instructions are executed by a processor to implement the method for predicting adrenal lesions based on chest CT as described in any one of claims 1 to 7.

9. A computer device comprising a memory, a processor and a computer program or instruction stored in the memory, characterized in that: The computer program or instructions are executed by a processor to implement the method for predicting adrenal lesions based on chest CT as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instructions are executed by a processor to implement the method for predicting adrenal lesions based on chest CT as described in any one of claims 1 to 7.

Images