Objective:To explore the construction of an evaluation model for aortic root anatomy and calcium burden in patients with bicuspid aortic valve (BAV) stenosis before transcatheter aortic valve replacement (TAVR) based on deep learning (DL) algorithms.Methods:A retrospective collection of 362 BAV stenosis patients who underwent TAVR from September 2023 to May 2024 was performed. All patients underwent cardiac CT angiography. The patients were divided into training group ( n=104), internal validation group ( n=206), and external validation group ( n=52). A DL model was trained on the training dataset to assess aortic root anatomy and calcification burden. The evaluation included the segmentation accuracy of the algorithm, the measurement performance of key anatomical structures (i.e., valve leaflets and type-1 and type-2 fusion raphe), and calcification burden, as well as the measurement efficiency. Overall segmentation performance was assessed using the average Dice coefficient (ADC). The fine-scale segmentation quality was validated by the 95th-percentile Hausdorff distance (HD-95) and the average symmetric surface distance (ASSD). The consistency of the measurement results was assessed using the Pearson correlation coefficient and the intraclass correlation coefficient ( ICC) with a two-way mixed model for absolute agreement. In addition, the total time and total mouse movement distance required for manual assessment versus the DL model on the validation datasets were recorded and compared. Results:The algorithm demonstrated excellent segmentation performance on aortic root anatomical targets, achieving outstanding consistency within both internal and external validation datasets (0.955

Objective:To explore the construction of an evaluation model for aortic root anatomy and calcium burden in patients with bicuspid aortic valve (BAV) stenosis before transcatheter aortic valve replacement (TAVR) based on deep learning (DL) algorithms.Methods:A retrospective collection of 362 BAV stenosis patients who underwent TAVR from September 2023 to May 2024 was performed. All patients underwent cardiac CT angiography. The patients were divided into training group ( n=104), internal validation group ( n=206), and external validation group ( n=52). A DL model was trained on the training dataset to assess aortic root anatomy and calcification burden. The evaluation included the segmentation accuracy of the algorithm, the measurement performance of key anatomical structures (i.e., valve leaflets and type-1 and type-2 fusion raphe), and calcification burden, as well as the measurement efficiency. Overall segmentation performance was assessed using the average Dice coefficient (ADC). The fine-scale segmentation quality was validated by the 95th-percentile Hausdorff distance (HD-95) and the average symmetric surface distance (ASSD). The consistency of the measurement results was assessed using the Pearson correlation coefficient and the intraclass correlation coefficient ( ICC) with a two-way mixed model for absolute agreement. In addition, the total time and total mouse movement distance required for manual assessment versus the DL model on the validation datasets were recorded and compared. Results:The algorithm demonstrated excellent segmentation performance on aortic root anatomical targets, achieving outstanding consistency within both internal and external validation datasets (0.955

Objective To evaluate the constancy of CT numbers of SIEMENS Sensation Open CT-simulator by analyzing the CT numbers of seven materials obtained from quality assurance(QA)tests. Methods QA tests for SIEMENS Sensation Open CT-simulator were performed with the Catphan504 phantom monthly. The CT images were obtained using three scan protocols(HeadSeq,RT_Head,and RT_Abdomen)for the CTP404 module in the phantom. The DoseLab software was used to analyze the 72 CT images acquired from January 2014 to December 2015,and the CT numbers(Y)of seven materials were obtained. Statistical analysis was performed on the Y data. The mean,standard deviation,maximum, minimum,and range values of Y for seven materials were calculated in three scan protocols. Results The standard deviation values of air,polymethylpentene,low-density polyethylene,polystyrene,acrylic acid, polyoxymethylene resin(Delrin),and polytetrafluoroethylene(Teflon)were as follows:(1)HeadSeq:0.54, 0.60,0.82,0.58,0.75,0.66,and 1.83 HU;(2)RT_Head:0.08,0.69,0.86,0.66,0.80,0.89,and 2.49 HU;(3)RT_Abdomen:0.11,0.61,0.76,0.72,0.78,0.96,and 2.56 HU.According to the statistical data, the constancy of CT numbers of the SIEMENS Sensation Open CT-simulator was in good condition in two years. Conclusions The variation of CT numbers of Teflon is the biggest among the seven materials. The relative values of CT numbers between different scan protocols vary with the relative electron density of materials.

Objective To compare various CT signs of pancreatic carcinoma (PC) and inflammatory pancreatic mass (IPM), and to study the diagnostic value of these signs for distinguishing two diseases. Methods Eigty-five patients with PC and IPM were proved by surgery, fine needle aspiration or other comprehensive methods. These patients underwent non-enhanced and enhanced CT scans. CT findings were analyzed retrospectively. The occurrance rates of various CT signs in these two diseases were analyzed with Fisher test and were compared with the corresponding clinical and operational results as welL Results Among the 85 patients, 66 patients were proved to have PC, and 19 were proved to have IPM. In PC group,58 were corerectly diagnosed with CT, 3 (4. 5% ) were misdiagnosed, and 5 (7.6%) were omitted. In IPM group, 9 were correctly diagnosed with CT and 10 (52. 6% ) were misdiagnosed. The CT findings were as follows: (1) Pancreatic mass with liver metastases, lymph node metastases, encased celiac arteries, and cancer emboli in portal veins just occurred in PC group. (2) The occurrence rates of mass over 3 cm in diameter, clear boundary, low-density area within the mass, pseudocysts, peripancreatie infiltration, ascites, and slight and moderate pancreatic-bile duct dilation in PC group were 90. 91% (60/66), 15.15% ( 10/66), 54. 55% ( 36/66 ), 10. 61% ( 7/66 ), 4. 55% ( 3/66 ), 22. 73% ( 15/66 ), 24. 24% ( 16/66 ), 45.45% (30/66), and 27. 27% (18/66) respectively, the occurrence rates in IPM group were 94. 74% ( 18/19), 15.79% ( 3/19 ), 52. 63% ( 10/19 ), 15.79% ( 3/19 ), 15. 79% ( 3/19 ), 21.05% (4/19), 31.58% (6/19) ,21.05% (4/19), and 5.26% (1/19) respectively. There was no statistical difference for these CT findings between two groups(P >0. 05). (3) Pancreatic head mass with atrophy of pancreatic body and tail, mass calcification, pancreatic duct-penetrating sign, pancreatic head mass with hypertrophy of pancreatic body and tail, biliary stones with inflammation , and thickening of pre-kidney fascia in PC group were 48.48% ( 32/66 ), 3.03% ( 2/66 ), 1.52% ( 1/66 ), 10. 61% ( 7/66 ), 6. 06% ( 4/66 ) and 3.03% (2/66) respectively, the occurrence rates of those in IPM group were 5. 26% (1/19),47.37% (9/19), 15.79% ( 3/19 ), 84. 21% ( 16/19 ), 36. 84% ( 7/19 ) and 21.05% ( 4/19 ) respectively. There was statistical difference for these CT findings between two groups ( P < 0. 05 ) . Conclusion Accurate evaluation of various CT signs in PC and IPM is of great importance in the diagnosis of the two diseases.

Cystic pancreatic lesions include many pancreatic diseases.Imaging examinations,such as computerized tomography,magnetic resonance imaging,ultrasonography,endoscopic ultrasonography,endoscopic retrograde cholangiopancreatography,magnetic retrograde cholangiopancreatography,positron emission tomography-CT,and so on,have great significance in the diagnosis and differention of cystic pancreatic lesions.This article reviews the imaging manifestations of various cystic pancreatic lesions in order to gain deeper insights into them.