Objective: To investigate the consistency among different experienced physicians in the measurement of morphological parameters of intracranial aneurysms. Methods: From April 1,2017 to April 30,2017, DSA data of 27 aneurysms from 24 consecutive patients in Department of Neurosurgery, Xuanwu Hospital, Capital Medical University were retrospectively collected. Morphological measurement of these aneurysms was performed after three-dimensional reconstruction (morphological parameters:diameter, height,width,neck widui and aneurysm inflow-angle).The measurement physicians were three interventional neuroradiologists who were engaged in cerebrovascular diseases for less than 5 years (3 years),5 to 10 years (9 years) and more than 10 years (13 years),and they were blinded to each other. The intraclass correlation coefficient (ICC) was used to compare the consistency of measurements among the three physicians,and the Kruskal-Wallis rank sum test was used to compare the statistical differences. Results: The ICC values were consistent in morphological parameters of aneurysm diameter,width,height and neck width among the three different experienced physicians (ICC = 0. 936 -0. 995). However, in terms of the inflowangle measurement, there was moderately consistent (ICC = 0. 561) between the physician within 5 years and the one experienced 5 to 10 years, and both of them were poorly consistent with the physician over 10years (ICC =0.465 and ICC = 0. 284, respectively). There were no statistically significant differences among the three different experienced physicians in measuring morphological parameters of length (diameter, height,width and neck width;H values were 0.881,0.743,1.651 and 0. 160;all P value >0.05),but the difference in inflow-angle was statistically significant (H = 1.391, P =0.006). Conclusion Length parameters have good consistency among different experienced physicians in clinical measurement, but the measurement of angle parameters has poor consistency and is not reliable enough.

Objective To evaluate the correlation between 3D morphological parameters of aneurysms based on the computer-assisted semi-automated measurement and the risk of aneurysm rupture.Methods From October 2019 to October 2022,patients with ruptured multiple aneurysms admitted to the Department of Neurosurgery of Xuanwu Hospital,Capital Medical University were retrospectively included.Aneurysmal morphological parameters(including aneurysmal diameter,maximum diameter,width,neck width,volume,flow angle,parental artery diameter,surface area,wave index and non-spherical index)were measured by computer-assisted semi-automated measurement methods.The length-to-width ratio,wide-to-neck ratio,aspect ratio and size ratio were calculated,and the aneurysm location information was recorded.The ruptured aneurysms in multiple aneurysms were included in the ruptured group,and the remaining aneurysms were included in the unruptured group.Uni variable analysis and binary Logistic analysis were used to evaluate the differences in morphological parameters and location information between the ruptured and unruptured groups.Results All 56 patients with multiple ruptured aneurysms and a total of 126aneurysms were included in the group for analysis.Concerning morphology,including diameter＞5 mm(51.8％[29/56]vs.15.7％[11/70],P＜0.01),maximum diameter＞6mm(57.1％[32/56]vs.25.7％[18/70],P＜0.01),flow angle＞107°(57.1％[32/56]vs.35.7％[25/70],P=0.016),wide-to-neck ratio＞1.1(50.0％[28/56]vs.30.0％[21/70],P=0.022),aspect ratio＞1.1(46.4％[26/56]vs.25.7％[18/70],P=0.015)and size ratio＞1.9(57.1％[32/56]vs.10.0％[7/70],P＜0.01),there was significant difference between the ruptured and unruptured group;Concerning locations,aneurysms are mainly located in the posterior communicating segment of the internal carotid artery(39.3％[22/56])and the middle cerebral artery(23.2％[13/56])in ruptured group,while in the middle cerebral artery(28.6％[20/70])and the non-posterior communicating segment of internal carotid artery(27.1％[19/70])in unruptured group,and there was significant difference in distribution of aneurysm locations(P=0.003).Multivariate Logistic regression analysis showed that size ratio＞1.9 was an independent risk factor for aneurysm rupture(OR,11.62,95％CI 2.40-56.15;P=0.002).Concerning locations,posterior communicating artery aneurysms had a significantly higher risk of rupture compared with the non-posterior communicating segment of internal carotid artery(OR,19.25,95％CI 2.19-169.51;P=0.008).Conclusion For multiple intracranial aneurysms,the size ratio of the three-dimensional morphological parameters of aneurysms＞1.9 is an independent risk factor for aneurysm rupture,and the rupture risk of posterior communicating artery aneurysms is significantly higher than that of non-posterior communicating segment of internal carotid artery.

Objective To create a semi-automatic technology based on convolutional neural networks for saccular aneurysm segmentation.Methods The single-center data of Xuanwu Hospital of Capital Medical University in the database of"China Intracranial Aneurysm Program"from July 2017 to July 2020 were retrospectively included,and all data were anonymized before analysis.Baseline data were collected from all patients,including sex,age(≥60 years and＜60 years),DSA model,number of DSA sequences,and aneurysm information,including the number of aneurysms,diameter(≥5 mm and＜5 mm),neck width(wide neck,narrow neck),and location(bifurcation,sidewall).According to the ratio of 8∶1∶1,the data were randomly divided into training set,test set and validation set by random number table method.The DSA 3D tomography data of all patients were completed in the contrast machine using the 3D rotary DSA mode,and the aneurysms shown in the DSA 3D tomography data were annotated by 3 experienced neurosurgeons,and the standard label of the aneurysm was finally generated.The proposed aneurysm segmentation method consisted of a training stage and a segmentation stage.In the training stage,the model was trained end-to-end by using the DSA 3D tomography image data of the training set,the segmentation label of the aneurysm and the vascular edge information extracted by the Marching Cubes algorithm,and the segmentation index of the model was monitored on the test set to retain the model with the highest segmentation index.In the segmentation stage,the physician selects a point inside the aneurysm on the DSA 3D tomography image of the aneurysm in the validation set,intercepts the volume of interest(VOI),inputs the trained optimal model of vascular and aneurysm segmentation,obtains the segmentation result of the aneurysm,and locates the segmented VOI back to the original DSA 3D tomography image to obtain the final aneurysm outline.The segmentation results of the segmentation network model were compared with standard labels to calculate the Dice similarity coefficient(DSC).The validation set data was stratified by aneurysm diameter,neck width,and location to compare the segmentation results in different datasets.We calculated the bounding boxes for the length,width,and height of the aneurysm segmentation mask,and used the maximum of these as the longest diameter of the aneurysm compared to the maximum diameter in the standard label.In the validation set,the standard label manual acquisition time was counted and compared with the segmentation network model acquisition time(from the time of locating the aneurysm to obtaining a satisfactory aneurysm neck segmentation).Results Finally,969 DSA sequences from 756 patients were included to show 3D tomographic data for 1 094 aneurysms.Among them,604 patients with 877 aneurysms with a total of 783 DSA sequences were included in the training set,117 aneurysms with a total of 100 DSA sequences in 77 patients were included in the test set,and 100 aneurysms with a total of 86 DSA sequences were included in 75 patients in the validation set.(1)The baseline comparison results of each dataset showed that there were statistically significant differences between the datasets of aneurysm diameter(P=0.003)and aneurysm location(P=0.003).There was no significant difference between the remaining baseline data sets(all P＞0.05).(2)The mean DSC of centralized aneurysm segmentation was 0.868±0.078.The mean DSC of aneurysm segmentation≥5 mm diameter was higher than that of aneurysms with＜5 mm diameter(0.891±0.041 vs.0.855±0.088,P=0.038).The DSC values of narrow-necked,wide-necked,bifurcated and lateral wall aneurysms were 0.882±0.065,0.859±0.085,0.876±0.072 and 0.863±0.080,respectively,and there was no significant difference between the groups(all P＞0.05).(3)The maximum diameter of the mask obtained by the aneurysm segmentation model in the validation set was in good agreement with the maximum diameter of the standard label obtained by manual segmentation([5.78±3.18]mm vs.[5.37±2.92]mm,r=0.97).In the validation set,the average time of manual segmentation and neural network segmentation of aneurysms was 2.5 min and 34 s,respectively.Conclusion In this study,a semi-automatic saccular aneurysm segmentation technique based on convolutional neural network can accurately segment aneurysms and is helpful to improve aneurysm morphology analysis.