Objective To evaluate the feasibility of diffusion kurtosis imaging (DKI)in the diagnosis and aggressiveness assessment of prostate cancer.Methods The MR data with multi-b-value diffusion-weighted imaging (DWI)of 30 male patients with prostate cancer were retrospectively analyzed.D maps and K maps were generated from the DKI model and ADC maps were obtained using the conventional monoexponential model.Differences in the D,K and ADC values between prostate cancer and benign peripheral zone (PZ)tissues,among tumors with different Gleason scores were analyzed.P<0.05 was considered statistical significance.Results ADC and D values were significantly lower in the prostate cancers than in the benign PZs (P <0.001).K values were significantly greater in the prostate cancers than in the benign PZs (P <0.001).ADC,D and K values were different significantly among the tumors with Glea-son scores of 6,7 and ≥8 (P <0.001,P =0.01 5 and P <0.001,respectively).Conclusion The DKI model can better describe the signal intensity attenuation with b values increasing,which is helpful for diagnosing and grading prostate cancer.K value may be used to quantitatively evaluate the complicated microstructure of prostate cancer.

OBJECTIVE: To compare various models of diffusion-weighted imaging including monoexponential apparent diffusion coefficient (ADC), biexponential (fast diffusion coefficient [Df], slow diffusion coefficient [Ds], and fraction of fast diffusion), stretched-exponential (distributed diffusion coefficient and anomalous exponent term [α]), and kurtosis (mean diffusivity and mean kurtosis [MK]) models in the differentiation of renal solid masses. MATERIALS AND METHODS: A total of 81 patients (56 men and 25 women; mean age, 57 years; age range, 30–69 years) with 18 benign and 63 malignant lesions were imaged using 3T diffusion-weighted MRI. Diffusion model selection was investigated in each lesion using the Akaike information criteria. Mann-Whitney U test and receiver operating characteristic (ROC) analysis were used for statistical evaluations. RESULTS: Goodness-of-fit analysis showed that the stretched-exponential model had the highest voxel percentages in benign and malignant lesions (90.7% and 51.4%, respectively). ADC, Ds, and MK showed significant differences between benign and malignant lesions (p < 0.05) and between low- and high-grade clear cell renal cell carcinoma (ccRCC) (p < 0.05). α was significantly lower in the benign group than in the malignant group (p < 0.05). All diffusion measures showed significant differences between ccRCC and non-ccRCC (p < 0.05) except Df and α (p = 0.143 and 0.112, respectively). α showed the highest diagnostic accuracy in differentiating benign and malignant lesions with an area under the ROC curve of 0.923, but none of the parameters from these advanced models revealed significantly better performance over ADC in discriminating subtypes or grades of renal cell carcinoma (RCC) (p > 0.05). CONCLUSION: Compared with conventional diffusion parameters, α may provide additional information for differentiating benign and malignant renal masses, while ADC remains the most valuable parameter for differentiation of RCC subtypes and for ccRCC grading.
Carcinoma, Renal Cell ; Diffusion ; Female ; Humans ; Magnetic Resonance Imaging ; Male ; ROC Curve

Objective:To evaluate the safety and effectiveness of the accurate puncture during sacral neuromodulation (SNM) guided with 3D printing navigation template based on reconstruction techniques using fusing sacral CT and MRI images.Methods:Totally 42 patients operated with SNM were selected in Renji Hospital, School of Medicine, Shanghai Jiaotong University from July 2016 to August 2017. The patients were randomly divided into control group ( n=22) and experimental group ( n=20) using random number table. The conventional cross-positioning technique under X-ray was used for puncture during SNM in the control group. While in the experimental group, the sacral CT and MRI images were fused for reconstruction and design of the navigation template, printed by 3D technique for the puncture in SNM. The times of punctures, the average time for puncture operation, the time of intraoperative testing of the stimulator device, the minimum onset voltage of the stimulator, the X-ray radiation dose, postoperative curative effect (rate of secondary transformation) and the incidence rate of complications were compared between the two methods using independent-simple t test or χ 2 test. Results:Compared to control group, fewer times of punctures, shorter time needed for puncture operation, shorter time of intraoperative testing of the stimulator, smaller radiation dose and minimum effective voltage were found in the experimental group ( P<0.05). There were 15 and 16 patients who completed the secondary transformation in the control group and experimental group, and there was no significant difference between the two groups (χ2=0.757, P=0.384). There were 3 cases of complications in the control group, including 2 cases of infection and 1 case of bleeding, while no complications in the experimental group. Conclusions:CT and MRI images fusion reconstruction-guided 3D printing navigation template can help perform accurate and safe punctures in SNM. Compared to conventional puncture positioned under X-ray, it can effectively improve the puncture efficiency, and reduce the radiation dose in the operation.

Objective To investigate the feasibility of quantitatively evaluating angiogenesis in liver tumors by using flat detector computed tomography (FDCT) in the angiography suite.Methods The VX2 liver tumor model was established in 25 rabbits,and then FDCT examination was performed for each animal.After reconstructing the blood volume (BV) perfusion map,BV values of the hepatic tumor and parenchyma were measured respectively.All experimental rabbits were sacrificed after FDCT,and the corresponding tumor specimens were collected for measuring microvessel density (MVD) and vascular endothelial growth factor (VEGF) expression level.The relationships of BV values with MVD and VEGF expression in liver tumors were analyzed.Results Of the 25 experimental rabbits,FDCT examination was successfully accomplished in 22(88.0％).Both the hepatic parenchyma and tumor lesions could be clearly visualized on BV perfusion map.The hepatic tumor was characterized by a hyperperfusion rim with a hypoperfusion center,known as rim-like enhancement pattern,on BV perfusion map.BV values bore a close relationship to both MVD grade and VEGF grade (P＜0.05 in both),while MVD grade had a parallel relationship with VEGF grade (r=0.504,P＜ 0.001).Conclusion It is feasible to use FDCT in the angiography suite to quantitatively assess the angiogenesis of liver tumors.It may be helpful for interventional treatment of liver tumors.

Objective To evaluate the relationship between concurrent myocardial bridge at anterior descending branch and the formation of coronary atherosclerosis plaques by using transluminal attenuation gradient (TAG). Methods A total of 198 patients underwent coronary CTA in Renji Hospital of Shanghai Jiaotong University School of Medcine from June 2017 to March 2018 and the results showed the anterior descending myocardial bridge. The data were retrospectively analyzed. All patients completed the coronary CTA with 320?row detector CT. According to the manifestations of myocardial bridge on CTA,the patients were divided into deep and superficial myocardial bridge groups. According to whether the patients were complicated with coronary atherosclerotic plaques, they were divided into isolated myocardial bridge group and myocardial bridge with coronary atherosclerotic plaque group. The thickness and length of myocardial bridge, the volume of coronary atherosclerotic plaques at the site of myocardial bridge, the pre?bridge and post?bridge TAG values, and the K ratio were recorded. Independent sample t test (normal distribution) or Mann?Whitney U test (skewed distribution) was used to compare the difference of measurement data among different groups. χ2 test was used to compare the difference of enumeration data among different groups. Pearson correlation test was used to analyze the correlation among pre?bridge and post?bridge TAG values,K ratio,thickness and length of myocardial bridge and plaque volume. The influence of above indexes on plaque occurrence was analyzed by binary logistic regression analysis. The relationship between main influence indexes and plaque formation was analyzed by receiver operating characteristic curve (ROC). Results Ninety nine patients had isolated myocardial bridge,99 with myocardial bridge and coronary atherosclerotic plaques,27 with superficial myocardial bridge and 171 with deep myocardial bridge. All atherosclerotic plaques occurred in pre?bridge and the mean volume of plaques was (91.6±83.0)mm3. The differences in sex, age, height, body weight and body mass index werenot statistically significant between isolated myocardial bridge group and myocardial bridge with coronary atherosclerotic plaque group (all P>0.05). The difference in pre?bridge TAG value was statistically significant between the isolated myocardial bridge group and myocardial bridge with coronary atherosclerotic plaque group (all P<0.05), but not statistically significant in post?bridge TAG value and K ratio (all P>0.05). The difference in pre?bridge and post?bridge TAG values and K value was not statistically significant between the superficial group and the deep group (all P>0.05). There was a weak negative correlation (r=-0.205,-0.316,-0.339,respectively,P<0.05) between the plaque volume and pre?bridge&post?bridge TAG values and K ratio. The pre?bridge TAG value significantly affected the plaque formation (P=0.014) and the odds ratio was 0.884 (95% CI 0.801 to 0.976). While other factors had no significant effects on plaque formation (all P>0.05). The area under curveof plaque formation promoted by pre?bridge TAG value was 0.582. When the diagnostic critical value was －37.26 HU/mm, the sensitivity and specificity of pre?bridge TAG value in plaque formation were 31.31% and 81.82%, respectively. Conclusion The TAG value of anterior descending bridge is an independent risk factor for plaque occurrence. The abnormal TAG value of anterior descending myocardial bridge can be detected early by CTA.

Objective:To evaluate the diagnostic performance of a radiomics model based on dynamic contrast-enhanced MRI (DCE-MRI) and diffusion weighted imaging (DWI) in small breast cancer (≤ 20 mm in greatest dimension), and to compare the results with those of an experienced radiologist’s interpretation.Methods:A total of 205 small breast lesions in 192 consecutive female patients from June 2016 to January 2018 at Renji Hospital, School of Medicine, Shanghai Jiaotong University, were retrospectively enrolled in the study. All lesions (≤ 20 mm in greatest dimension) were confirmed by surgical pathological results. The lesions were divided into a training set (116 lesions) and an independent test set (89 lesions). Based on preoperative breast DCE-MRI and DWI data, a radiomics model was built using gradient boosting decision tree (GBDT). The GBDT model was applied to the test set for differentiation between malignant and benign small breast lesions. Cases of the test set were also evaluated by an experienced radiologist for benign and malignant diseases differentiation. ROC curve was used to assess the diagnostic performance for the GBDT model and the radiologist evaluation, respectively. Differences in the area under the ROC curve (AUC) were analyzed by the DeLong test. Differences in sensitivity, specificity and accuracy were evaluated by the McNemar test. Kappa values were used to assess the agreement between different evaluation methods.Results:The AUC of the GBDT model (0.950) showed no significant difference from that of the radiologist’s evaluation based on DCE-MRI combing DWI data (0.935) ( Z=0.499, P=0.618). However, it showed the AUC of GBDT model was significantly higher than that of evaluation based on DCE-MRI (0.874) or DWI (0.832) alone ( Z=2.024， P=0.043； Z=2.772， P=0.006). The sensitivity, specificity and accuracy of the best cutoff point of GBDT model were 90.0%, 89.8% and 89.9% respectively. The sensitivity, specificity and accuracy of evaluation based on DCE-MRI combined with DWI were 97.5%, 79.6% and 87.6% respectively. There was no significant difference in diagnostic performance between the two methods (χ 2=0.800,2.286 and 0.083, P>0.05). Conclusions:A radiomics model based on DCE-MRI and DWI images provided good diagnostic performance in small breast cancer. The results of radiomics were favorably comparable with those of experienced radiologist evaluation based on the combination of DCE-MRI and DWI data.

The artificial intelligence based on medical aid diagnosis has been in full swing in these years. How to better and more safely utilize this new technology to improve the diagnostic efficiency and quality of doctors poses new challenges for our hospital management. This paper aims to explore relevant management problems and corresponding solutions from seven aspects:data security, system integration, technical parameters, risks, workflows and diagnosis results by introducing a new intelligent image screening system. After these management problems have been better solved, we found that the intelligent image screening system can improve the diagnostic efficiency and quality of doctors.
Artificial Intelligence ; Hospital Administration

Image registration is of great clinical importance in computer aided diagnosis and surgical planning of liver diseases. Deep learning-based registration methods endow liver computed tomography (CT) image registration with characteristics of real-time and high accuracy. However, existing methods in registering images with large displacement and deformation are faced with the challenge of the texture information variation of the registered image, resulting in subsequent erroneous image processing and clinical diagnosis. To this end, a novel unsupervised registration method based on the texture filtering is proposed in this paper to realize liver CT image registration. Firstly, the texture filtering algorithm based on L0 gradient minimization eliminates the texture information of liver surface in CT images, so that the registration process can only refer to the spatial structure information of two images for registration, thus solving the problem of texture variation. Then, we adopt the cascaded network to register images with large displacement and large deformation, and progressively align the fixed image with the moving one in the spatial structure. In addition, a new registration metric, the histogram correlation coefficient, is proposed to measure the degree of texture variation after registration. Experimental results show that our proposed method achieves high registration accuracy, effectively solves the problem of texture variation in the cascaded network, and improves the registration performance in terms of spatial structure correspondence and anti-folding capability. Therefore, our method helps to improve the performance of medical image registration, and make the registration safely and reliably applied in the computer-aided diagnosis and surgical planning of liver diseases.
Algorithms ; Humans ; Image Processing, Computer-Assisted ; Liver Diseases ; Tomography, X-Ray Computed