ISSN 1004-4140
CN 11-3017/P

2021 Vol. 30, No. 6

CT Theory
Segmentation of Liver Tumors Based on Bottleneck Residual Attention Mechanism U-net
DONG Xiaoying, CHEN Ping
2021, 30(6): 661-670. doi: 10.15953/j.1004-4140.2021.30.06.01
Abstract(424) PDF(85)
The segmentation of liver tumors is difficult due to the large amount of noise contained in medical CT images and the uneven size, location and tissue density of liver tumors similar to adjacent organs. The existing traditional full-convolutional neural network (FCN) method can achieve liver tumor segmentation by assigning category labels to each pixel in the input CT image, but the problems of small target missing or fuzzy target boundary segmentation still occur in the segmentation accuracy. In order to solve these problems, we propose a bottleneck residual attention mechanism U-net (BRA U-net) segmentation method for liver tumors. By introducing bottleneck residual modules, we can greatly reduce the computational load in very deep networks while solving the gradient disappearance problem. In addition, stacked attention modules can increase the proportion of effective features. In this paper, the proposed framework was tested on the public MICCAI2017 liver tumor segmentation dataset, and the dice similarity coefficient value reached 0.788, higher than other comparative segmentation networks. The generality of the proposed method was verified by using the 3D-IRCADb dataset. The results show that the proposed method has good segmentation effect and can provide a reliable basis for clinical diagnosis.
Study on Magnetic Analogy Fitting Inversion of Two-dimensional IP Data Using Central Gradient Array
ZHAO Zhan, QIANG Jianke, ZHU Yuzhen
2021, 30(6): 671-679. doi: 10.15953/j.1004-4140.2021.30.06.02
Abstract(203) PDF(25)
In this paper, the dual-frequency IP response of underground polarized ellipsoids with central gradient array on the surface is studied through Cole-Cole model, so as to learn about the characteristics of polarizability engendered by polarized bodies with different parameters, which is convenient for the construction of interactive modeling later. According to the theoretical derivation, the induced polarization anomaly generated by any geological body with induced polarization characteristics on the surface can be approximated as a three-dimensional spatial integral of an underground electric dipole. This integral form is consistent with the forward calculation formula of the magnetic field, which means that we can interpret the induced polarization anomaly by the same method applied in interpreting the magnetic anomaly; it is called Pseudo-Magnetic Interpretation Method (PMIM). As long as the model changes in real time according to the prior information, which will make the curve obtained by IP forward modeling approximate to the measured IP curve, when the fitting difference is less than the mean square error, we regard the last approximate model as the real model, so as to obtain the spatial parameters such as top buried depth, dip angle and geometric size of the underground polarizer. The test of field data shows that human-computer interaction method which merges with some prior information holds more rationality than automatic inversion.
Application of Amplitude Compensation Method Based on Phase Control in Reservoir Prediction of Bohai B Oilfield
WEI Hong, SONG Junting, TIAN Tao, ZHANG Pengzhi
2021, 30(6): 681-690. doi: 10.15953/j.1004-4140.2021.30.06.03
Abstract(210) PDF(40)
The main target layer of Bohai B Oilfield is the Dongying Formation, which is 50-80 meters away from the bottom of the overlying Guantao Formation. There are one or more sets of high-speed, high-density and limited-distributed conglomerates developing at the bottom of the Guantao Formation, they cause energy loss, weaken the seismic response of the underlying reservoir and seriously affect the identification of the true range of the reservoir. For this reason, in this paper, starting with the theory of seismic wave propagation, firstly, we analyze the reflection and transmission loss effects of conglomerate-induced energy. Secondly, based on the forward simulation, the degree of energy loss caused by the conglomerate is analyzed, which is the same cumulative thickness. With more layers of conglomerate come greater losses. Based on the forward simulation results and the well-earthquake combination, we describe the plane distribution range of the three seismic phases, which are single set of conglomerates, multiple sets of conglomerate and non-conglomerate rock. Furthermore, combined with seismic attributes, we perform quantitative analysis on the plane distribution range of the energy loss of the reservoir. Then we extract the energy compensation factors of different seismic phases, and propose the phase-controlled energy compensation method for corresponding amplitude compensation. That is, the energy loss caused by single set of conglomerate is mainly compensated by reflection coefficients while the energy loss caused by multiple sets of conglomerate is mainly compensated by transmission coefficients repeatedly. Finally, we quantitatively eliminate the energy shielding influence of the overlying Guantao formation conglomerate on the underlying Dongying formation reservoir, portray the true plane range of the reservoir, and obtain drilling success, which fully proves the validity of this research and realizes accurate prediction of potential area.
Industrical CT
Characterization of Pore Distribution of the Anthracite Coal Sample Based on Synchrotron Radiation X-ray CT
WANG Runhua, WANG Haipeng, LI Jianli, WANG Jinxiu, LI Kunjie, Y. S. Yang
2021, 30(6): 691-700. doi: 10.15953/j.1004-4140.2021.30.06.04
Abstract(252) PDF(42)
Synchrotron Radiation X-ray was performed on the anthracite coal sample from Sihe Mine in Qinshui Basin at beam energy of 24 keV, then CT slices of the sample were obtained by reconstructing the projections images. The CT slices of the sample were analyzed by adopting the methods of the digital terrain model (DTM) and the data-constrained modelling (DCM) respectively. The results showed that, as for the coal sample used in this paper, the porosity calculated by DTM was close to that measured by combination of the true density and the apparent relative density method. Yet, the porosity obtained by the threshold segmentation method based on the threshold determined by DTM was quite different from the porosity calculated by DTM. The porosity calculated by DCM was consistent with the porosity calculated by DTM and the experimental results. By taking the partial volume effect of the CT imaging process into considration, the DCM obtained the distribution information of pores whose size were smaller than that of the CT voxel size, which expanded the characterization length scale of CT imaging technique to some extent. The DCM calculated results indicated that most pores in the coal sample mostly coexisted as partially occupied CT voxels with coal matrix or mineral compositionsl.
The Pseudo-color Mapping Model of Spect Reconstruction Data Based on Adjustable Dual-vector Parameters
SUN Yuyang, JIANG Han, ZHENG Yongguo, CHEN Ming, HU Xiaokun, LI Gang
2021, 30(6): 701-708. doi: 10.15953/j.1004-4140.2021.30.06.05
Abstract(263) PDF(35)
SPECT performs imaging on the γ-ray emitted by radioactive particles implanted in the patient's body. The gray information of SPECT image represents counts of γ-ray, which can correspond to the radiation dose value of γ-ray after transformation. In order to observe the dose distribution near the lesion clinically, it is necessary to perform pseudo-color processing on SPECT images, which are then fused with CT images. However, the SPECT/CT pseudo-color processing of conventional processing software is difficult to provide sufficient dose detail resolution, which cannot meet the needs of clinical diagnosis and treatment. For the requirement of γ radiation dose distribution details in the treatment of brain tumors, we present a pseudo-color mapping model with adjustable dual-vector parameters, which is based on DICOM data of SPECT imaging and can bulid a multi-level mapping relationship.The proposed method can not only control the pseudo-color display area, but also adjust the multi-segment details of the dose display. Results of numerical experiments by Python show that the proposed mapping method can display the dose area and data range of interest in SPECT images more clearly and accurately. After being fused with the CT image, they can significantly enhance the layering of dose distribution in the SPECT/CT focus area,, and accurately display the information of particle space and radiation dose distribution. The proposed method can provide a reliable basis for the judgment of clinical efficacy.
Medical Imaging and Image Processing
Evaluation of Detection and Diagnostic Efficiency of Pulmonary Nodules by Chest CT Based on Artificial Intelligence
LIU Na, ZHAO Zhengkai, ZOU Jiayu, LI Yi, LIU Jian
2021, 30(6): 709-715. doi: 10.15953/j.1004-4140.2021.30.06.06
Abstract(218) PDF(52)
Objective: To evaluate the value of artificial intelligence (AI) based on deep learning in the detection and diagnosis of chest CT pulmonary nodules. Methods: A total of 172 patients with pulmonary nodules diagnosed by surgery in our hospital from June 2018 to April 2020 were collected, and a total of 204 nodules were surgically resected. 172 cases of preoperative high-resolution chest CT images were imported into the artificial intelligence recognition system, then artificial intelligence (AI) and radiologists detected and diagnosed the pulmonary nodules respectively, and we compared the sensitivity, positive predictive value and false positive rate between the two diagnostic methods. Using the pathological results as the gold standard for diagnosis, the sensitivity, specificity and area under the receiver operating characteristic (ROC) curve of AI and radiologists in the diagnosis of malignant pulmonary nodules were compared. Results: A total of 796 true nodules were detected in the 172 cases of high-resolution chest CT images. The sensitivity of AI and radiologists in detecting nodules was respectively 90.5% and 75.0%, the positive predictive value was respectively 74.5% and 99.7%, and the number of false positive nodules was respectively 247 and 2.As for the surgically resected 204 nodules, the sensitivity of AI, radiologist and AI-radiologist combination in diagnosing malignant pulmonary nodules was respectively 93.3%, 78.5% and 98.6%, the specificity was respectively 34.8%, 79.7% and 79.7%, and the area under the receiver operating characteristic (ROC) curve for the diagnosis of malignant pulmonary nodules by AI, radiologist and AI-radiologist combination was respectively 0.641, 0.791 and 0.819. Conclusion: The sensitivity of AI in detecting pulmonary nodules is significantly higher than that of radiologists, yet the false positive rate of AI is also higher. The efficiency of AI-radiologist combination in diagnosing malignant pulmonary nodules is higher than that of AI or radiologists separately. Therefore, we recommend that AI and radiologists should collaborate to detect and diagnose pulmonary nodules, which can reduce the rate of missed diagnosis and improve the diagnosis accuracy.
Evaluation of the Severity Degree of Esophageal Varices in Cirrhosis Based on Radiomics Features of Hepatic Segment CT Imaging
LI Min, LIU Changchun, ZHANG Zhe, ZHOU Nan, ZHANG Jianzeng, XU Hui, YAN Yuchang, ZHAO Liqin
2021, 30(6): 717-726. doi: 10.15953/j.1004-4140.2021.30.06.07
Abstract(170) PDF(25)
Objective: To investigate the value of CT imaging radiomics features of different hepatic segments in predicting the severity of esophageal varices in cirrhotic patients. Methods: A total of 143 cirrhotic patients with portal hypertension and EV who were clinically confirmed and underwent gastroscopy from February 2018 to February 2021 were retrospectively selected. According to the severity of EV under gastroscopy, they were divided into severe group (61 cases) and non-severe group (82 cases). All patients received enhanced liver CT examination within 2 weeks before gastroscopy examination. The images of portal vein phase were selected and Shukun Radiomics V94 software was applied to extract the image radiomics features of caudate lobe, left lateral lobe, left inner lobe and right lobe (posterior upper segment + anterior upper segment) of liver at the level of bifurcations of portal vein in axial image according to Couinaud segmentation. Models to predict EV degree of different segments were established respectively. The value of radiomic features of different liver segments in predicting EV severity were compared. Results: Both severe and non-severe esophageal varices could be identified by the radiomics models established for predicting EV degree based on the CT imaging features of different hepatic segments in cirrhotic patients. The AUC values of the training set and verification set of the model of upper right lobe were:0.85 (0.78~0.92), 0.79 (0.64~0.93), respectively. That of caudate lobe, left lateral lobe, left inner lobe model training set and validation set were 0.78 (0.69~0.87) and 0.62 (0.44~0.79), 0.80 (0.71~0.88) and 0.64 (0.46~0.82), and 0.71 (0.61~0.81) and 0.73 (0.58~0.88), respectively. The AUC values of training set and validation set were the highest in the right lobe of liver model. Conclusion: All the CT images based radiomics features of different hepatic segments in cirrhotic patients could distinguish severe EV, among which the model of right hepatic lobe produces the best results.
The Analysis of Factors Influencing the Peak Time of Head and Neck CTA
FENG Chen, FANG Yu, ZHANG Dechuan, MEI Xiuting, YU Wanjun
2021, 30(6): 727-733. doi: 10.15953/j.1004-4140.2021.30.06.08
Objective: To explore the factors influencing the peak time of head and neck CTA. Methods: The basic factors (gender, age, height, weight, heart rate, systolic blood pressure, diastolic blood pressure) and contrast medium injection parameters (flow rate, total amount of injection) during Test-Bolus injection were prospectively and randomly collected from 120 subjects with head and neck CTA. The peak time of head and neck CTA was obtained by Test-Bolus injection method at the cervical 4/5 level. The related factors influencing the peak time were analyzed using multiple regression mathematical method. Results: The peak time of female subjects (13.88±2.03)s was faster than that of male subjects (15.87±2.35)s, there was significant difference between genders. The peak time varied remarkably with factors such as age, height, and heart rate, which showed a certain linear relationship, with slopes of 0.043, 0.101 and -0.086 respectively, indicating that they were the main factors influencing the peak time of head and neck CTA. There was also significant difference between body weight and peak time, yet it turned out not the main factor through multiple regression analysis. There was no significant difference in systolic blood pressure, diastolic blood pressure and peak time. Although the contrast medium parameters of test-Bolus injection had certain effect on peak time, the difference was not significant. Conclusion: Gender, age, height and heart rate were the main factors influencing the peak time of head and neck CTA, and there was certain linear relationship with the peak time. The specific relationship provides a theoretical basis for optimizing the clinical scanning program for head and neck CTA.
A Preliminary Analysis of Using the Sinogram-affirmed Iterative Reconstruction Strength Levels based on the Original Data of Low-dose Chest CT to Evaluate Different Types of Small Pulmonary Nodules
CAO Juntao, CHEN Qiqi, HU Ming, XU Ting, TU Jianchun, ZHANG Huan
2021, 30(6): 735-742. doi: 10.15953/j.1004-4140.2021.30.06.09
Abstract(168) PDF(21)
Objective: We intend to explore the Corresponding relations between the Sinogram-affirmed iterative reconstruction (SAFIRE) strength levels and the optimized display of different types (solid, partially solid, and pure ground glass) of small pulmonary nodules in low-dose chest CT (LDCT). Materials and methods: We analyzed 105 small pulmonary nodules in 101 patients who underwent LDCT from September 2020 to January 2021 and also met the criteria for small pulmonary nodules. Based on nodule composition, they were divided into the solid nodule Group (n=27), the partially solid nodule group (n=37) and the pure ground glass nodule group (n=41). First we adopted the one-way analysis of variance, Chi-square test or Kruskal-Wallis H test to analyze the general data in groups, then took the filtered back projection algorithm (FBP, B50f) as the reference to compare the difference in objective image quality (including noise value, CT value of small pulmonary nodules, SNR and CNR) and subjective image quality in groups under different SAFIRE modes (I50f and I70f, strength levels 1 to 5 respectively).Results: 1 There was no significant difference in gender, body mass index, and nodule distribution in three groups. The age and length of the nodules in the pure ground-glass nodule group were smaller than those in the solid and partial solid nodule groups; 2 The image noise values in SAFIRE I50f 1-5 and I70f-5 were lower than that in FBP B50f while SAFIRE I50f-5 showed the lowest noise value. There was no significant difference in CT values of small pulmonary nodules in the three groups under different modes, the SNR and CNR of small pulmonary nodules in SAFIRE I50f-5 were higher than those of FBP B50f and other SAFIRE modes; 3 SAFIRE I50f 3~5 of solid and partial solid pulmonary nodule groups obtained higher subjective scores than that of FBP B50f and other SAFIRE modes except I70f-5. SAFIRE I50f-4 of pure ground glass nodule group obtained a higher subjective score than those of FBP B50f and other SAFIRE modes except I50f-3 and I50f-5, and there was no significant difference in the subjective scores in three groups under this mode (P=0.428). Conclusion: SAFIRE I50f-4 performed well and displayed a balanced effect in the objective and subjective evaluation of solid, partial solid and pure ground glass small pulmonary nodules in LDCT. We suggest it can be applied to evaluate different types of small pulmonary nodules in LDCT.
Study on Predicting and Evaluating Clinical Classification of COVID-19 Pneumonia by Artificial Intelligence CT Quantitative Analysis
LIU Li, CHEN Hong, ZHONG Wei, WEI Dongmei, SONG Yongli, LI Huixin, ZHOU Xin, GAO Xiaolong
2021, 30(6): 743-751. doi: 10.15953/j.1004-4140.2021.30.06.10
Abstract(144) PDF(25)
Objective: To evaluate the correlation of CT artificial intelligence quantitative analysis in prediction and evaluation of clinical classification of COVID-19 pneumonia. Methods: The clinical and CT imaging data of 46 patients with COVID-19 treated in the hospital from February 1st, 2019 to January 20th, 2021 was retrospectively analyzed. We compared the correlation between the total lung infection volume, grinding glass density volume (GGO volume), solid density volume (SO volume) and clinical classification when artificial intelligence (AI) quantitative analysis was applied. Results: Among the 26 cases of common type, 16 cases of severe type and 4 cases of critical type, the main clinical manifestations were fever, cough and fatigue. Severe and critical types were more common in elder patients. The CT manifestations of three clinical types of pulmonary lesions were mainly GGO; total lung infection volume, GGO volume, SO volume in common type were smaller than that in patients of severe/critical type. Spearman grade correlation analysis showed significant correlation between total lung infection volume, GGO volume, and SO volume with clinical classification (0.86, 0.87, 0.84). Conclusion: The artificial intelligence CT quantitative index analysis (infection volume, GGO volume, SO volume) holds much correlation with clinical classification of COVID-19 pneumonia.
Spectral CT
Clinical Value of Double Low Examination Technique Based on KARL 3D Iterative Reconstruction Algorithm in Bronchial Artery Imaging
JIANG Yi, QIN Lixin, TIAN Kui, SHA Jinlu, ZHOU Chunhua
2021, 30(6): 753-760. doi: 10.15953/j.1004-4140.2021.30.06.11
Abstract(177) PDF(14)
Objective: We intend to explore the clinical value of double-low (low tube electrodepressed contrast agent dosage) examination technique which is based on KARL 3D iterative reconstruction when applied in bronchial artery imaging. Methods: We performed retrospective analysis on the clinical imaging data of 60 patients with hemoptysis treated in Wuhan Pulmonary Hospital from July to September 2020. 30 patients were randomly selected to use plan A while the rest 30 adopted plan B. In group A, 120 kV and 80 mL contrast agent dosage were used for FBP image reconstruction; in group B, 100 kV and 65mL contrast agent dosage were used for KARL 3D grade 5 and FBP image reconstruction respectively. We compared the subjective grade, objective evaluation and radiation dose difference of the image quality between the two groups. Results: There was no statistically significant difference in KARLl 3D grade 5 reconstruction image qualities between the two groups, and both groups met the diagnostic requirements of CTA. Compared with the FBP image, we found that the noise of the KARLl 3D level 5 reconstruction images in group B decreased and the image quality improved, the difference held statistical meaning. The effective dose of group B was lower than that of group A, and the difference held statistical meaning. Conclusion: The bronchial artery images obtained by using low tube voltage and low contrast agent dosage based on KARL 3D iterative reconstruction algorithm can meet the diagnostic requirements and in the mean time reduce the radiation dose and contrast agent dosage used on the patients.
Medical CT
Diagnostic Value of MSCT in Extrapancreatic Nerve Infiltration of Pancreatic Cancer
CHEN Yuexi
2021, 30(6): 761-767. doi: 10.15953/j.1004-4140.2021.30.06.12
Abstract(171) PDF(14)
Objective: To investigate the diagnostic value of multi-slice spiral CT (MSCT) in extrapancreatic nerve infiltration of pancreatic cancer. Methods: We compared the morphology, size and CT value of celiac ganglia between 20 patients with pancreatic carcinoma and 50 healthy people. Taking the pathological results as the standard, we analyzed the sensitivity, specificity, accuracy of MSCT in diagnosing the celiac ganglia invasion. Results: In the pancreatic cancer group, the shape of abdominal ganglion was coarse strip, and the fat gap between the tumor and the abdominal ganglion was unclear. The shape of abdominal ganglion in healthy control group was fine strip or small nodular, and the surrounding fat gap was clear. The long diameter and short diameter of bilateral abdominal ganglions in the pancreatic cancer group were higher than those in the healthy group, while the three-phase CT values of left abdominal ganglion in the pancreatic cancer group were higher than those in the healthy group. Compared with the pathological results, the sensitivity, specificity and accuracy of CT in the diagnosis of abdominal ganglion invasion in pancreatic cancer were 80%, 60% and 75%, respectively. Conclusion: MSCT holds high diagnostic value for extrapancreatic nerve infiltration, which can clearly show the morphology, size and CT value of abdominal ganglion. The circumstances of thick-strip enlargement of abdominal ganglion, unclear fat gap and occurrence of obvious enhancement indicate the nerve invasion of the existing tumor.
The Application Value of Accurate Diagnosis of CT Image of Skull Base Fractures based on Convolutional Neural Network
HUANG Dongyun, XIA Jun, LIN Yuwen, CHEN Jiakuan, CHEN Haibin
2021, 30(6): 769-776. doi: 10.15953/j.1004-4140.2021.30.06.13
Abstract(110) PDF(13)
Objective: To explore the application value of convolutional neural network (CNN) in CT diagnosis of skull base fractures. Methods: The skull CT image data of 3100 patients with skull base fractures and 2 467 normal patients was collected retrospectively. After the standard nanofiltration and actual model calculation, the skull base CT image data of 2 488 patients with skull base fractures and 1 628 normal patients were selected. The CT images were labeled and randomly assigned into training set and test set. The skull area discrimination algorithm model and skull base fractures detection algorithm model were established by CNN, then we performed verification on the models through skull base area discrimination, skull fractures and skull base fractures in the test. The detection indexes included precision, recall and average diagnosis time consumption. We carried out comparisons of diagnostic efficacy with the artificial group (junior radiologist) test. Results: We carried out test comparisons on the steady models obtained by CNN algorithm, the results showed that the accuracy of the whole skull base fractures (including the anterior, middle and posterior skull base fractures) was less than 0.5, which was lower than that of the artificial group (all higher than 0.63); The recall rate > 0.89 was better than that of the artificial group (all < 0.8); The average diagnosis time was (3.12±67)s, significantly less than that of artificial group. In the area test of skull base fractures, the accuracy rate was anterior skull base > middle skull base > posterior skull base while the recall rate was middle skull base > posterior skull base > anterior skull base. Conclusion: The algorithm model of skull base fractures based on CNN is superior to the artificial test results in recall rate and diagnosis time consumption for CT diagnosis of skull base fractures in patients with craniocerebral trauma, which has certain value in assisting clinical diagnosis, reducing missed diagnosis and diagnosis time consumption.
Study on the Value of Individualized Contrast Agent Injection Scheme in Improving the Biosafety of Pulmonary Artery CTA
WANG Yongsheng, WANG Chensi, LU Haoyu, TIAN Xiangbao, ZHUANG Qixin
2021, 30(6): 777-783. doi: 10.15953/j.1004-4140.2021.30.06.14
Abstract(147) PDF(13)
Objective: To study the value of individualized contrast medium injection scheme in improving the biosafety of pulmonary artery CTA. Materials and methods: 50 patients clinically suspected of pulmonary embolism from January 2018 to June 2020 were randomly assigned into groups A and B. Group A was the routinely group, the injection scheme was 20mL of normal saline, 50 mL of contrast agent and 30 mL of saline, with the injection rate of 4.5 mL/s. Group B was the individualized group, and the injection scheme was 20 mL of normal saline, (contrast medium dosage=weight×0.6 mL) and 30 mL of normal saline, the injection rate of contrast medium=dosage of contrast agent/10 s while the injection rate of physiological saline was 4.5 mL/s. We adopted t-test of independent samples to compare the data of age, height, weight, dosage and rate of contrast agent injection, CT value of main pulmonary artery and left and right pulmonary arteries and subjective evaluation of image quality between the two groups. Kappa test was used to evaluate the consistency of subjective evaluation of the image quality between the two doctors. Results: There was no statistical significance in the difference of age, height and weight between the two groups; the difference between the two groups in the dosage and rate of contrast mediumt injection was statistically significant; there was no statistical significance in CT value of main pulmonary artery and left and right pulmonary arteries and subjective evaluation of image quality between the two groups; Kappa test indicated that the two doctors held high consistency in subjective evaluation of image quality, with Kappa=0.80. Conclusion: On the premise of ensuring the quality of CTA images of pulmonary artery, personalized injection scheme can effectively reduce the dosage of contrast medium and slow down the injection rate for patients with weight less than 75 kg, thus reduces the potential risk of biological safety for patients.
Advances in CT and MRI Monitoring of Crohn's Disease
CHEN Yunhui, YANG Yaying, PENG Chao, HU Juan
2021, 30(6): 785-791. doi: 10.15953/j.ctta.2021-001

Crohn's disease, with alternating phases of activity and remission holds the characteristics of a long course, complex evolution and extensive involvement,, which have a huge impact on the life quality of patients. How to accurately and comprehensively identify and assess the onset, progression and regression of the disease, such as whether it is in the active phase, the nature of intestinal strictures, and the presence of other systemic lesions, is particularly important to guide treatment. Evaluation modalities that rely solely on clinical indicators or endoscopy are increasingly recognized as flawed by studies. With increased disease awareness and rapid development of examination modalities, the role of medical imaging in this disease cannot be ignored. In this paper we will focus on the value of CT and MRI for monitoring Crohn's disease in active, fibrosis, intestinal luminal strictures, abscess/fistulas, and extragastrointestinal lesions, and also introduce the application of related advanced technologies.