ABSTRACT
Objective:To explore the application value of artificial intelligence (AI) in image post-processing of reconstructed CTA based on CT cerebral perfusion (CTP).Methods:Clinical and radiological data of 100 patients suspected of cerebrovascular diseases in Hebei General Hospital from January to July 2020 were retrospectively selected. All patients were divided into A and B group on average according to the different examination schemes. Cerebral CTP examination was performed in group A (the temporal maximum intensity projective data set generated by the first 5 time phases in the maximum period of the difference between arteriovenous CT values selected as subgroup A1, and the corresponding original thin-layer images selected as subgroup A2), single phase CTA examination was performed in group B, manual and AI image post-processing were performed respectively. Subjective scoring of the image data was performed, and the objective bid evaluation indexes such as CT value, noise (SD), signal-to-noise ratio (SNR), contrast to noise ratio (CNR) were measured, the qualified rate of artificial and AI vascular segmentation was counted, and post-processing time were recorded. The objective evaluation indexes were compared between three groups using one-way ANOVA, and the Kruskal-Wallis H test was used to compare the difference of subjective scores.Results:Statistically significant differences were observed in subjective score and objective evaluation index of original images among group A1, group A2 and group B (all P<0.05). Among them, arterial enhancement, arteriolar detail display score, cerebral artery CT value, SNR and CNR in group A1 were higher than those in group A2 and group B (all P<0.05). In a total of 100 patients with 1 100 blood vessels, the qualified rates of AI vascular segmentation in group A1 [98.4% (541/550)] and group B [98.7% (543/550)] were higher than those of manual [82.9% (456/550), 87.1% (479/550), χ2=77.392, 56.521, P<0.001], but the qualified rate of AI vascular segmentation of group A2 [78.4% (431/550)] was lower than that of manual [85.6% (471/550), χ2=9.855, P=0.002]. The completion time of AI post-processing were reduced by 56.30%, 49.63%, 50.81%, respectively than those with manual. Conclusion:Compared with manual image post-processing, AI has certain advantages in image quality and work efficiency of reconstructed CTA post-processing based on CTP de-noising dataset, and it is worth popularizing and applying in the image post-processing of cerebrovascular disease, combined with artificial quality control.
ABSTRACT
Objective:To investigate the feasibility of one-step coronary and carotid-cerebrovascular computed tomography angiography (CTA) using high-pitch Double Turbo Flash mode and to analyze the image quality and radiation dose in patients with heart rate variability using multi-slice detector dual-source CT.Methods:A total of 79 patients with heart rate variability higher than 3 beat/min (bpm) were retrospectively analyzed. They were grouped by the scanning methods. Group A ( n=40) were performed double turbo flash mode for one-step coronary and carotid-cerebrovascular arteriesinjected with one injection of contrast agent.further divided into Single A (only the phase 1 image)and Double A(combined images of phases 1 and 2). Group B ( n=39) were performed separately with twice injection of contrast agent. Subjective scoring was performed on the image quality of the group Single A, Double A and B using a 4-point. Then the objective parameters of image quality, CT attenuations, image noise, signal-to-noise (SNR), and contrast-to-noise (CNR), were evaluated. Then subjective scores, objective evaluation indicators, and radiation dose were compared with one-way ANOVA analysis among the three groups.Contrast agent were compared by using t test in group A and B. Results:No significant difference was found ( F=2.093, P=0.128) for the subjective scores of the head and neck CTA among the three groups with (3.47±0.51), (3.53±0.51), (3.69±0.47). Significant difference was found ( F=50.955, P<0.01) for the subjective scores of coronary CTA among the three groups with (2.70±0.76), (3.35±0.66), (3.58±0.50), and there was no statistically significant difference between Double A and B groups ( P=0.104), met the requirements for diagnosis. The objective evaluation of the three groups compared the head and neck CTA images were statistically significant ( P<0.05), of which the difference between the Single A and the Double A was not statistically significant ( P>0.05), met the requirements for diagnosis; the differences in SNR and CNR of coronary CTA images are statistically significant ( F=12.991, 12.236, P<0.01), and there was no statistically significant difference between Double A and B ( P>0.05), met the requirements for diagnosis. Radiation dose in the group Double A was lower than group B (decreased by 46.15%, P<0.01).The amount of the contrast agent in the group Double A was lower than group B (decreased by 44.13%, t=-45.455; P<0.01). Conclusion:The double turbo flash mode is feasibility for one-step coronary and carotid-cerebrovascular CTA in patients with the heart rate variability using multi-slice dual-source CT.This scan mode can maintain the diagnostic image quality with low contrast agent and radiation dose.
ABSTRACT
Objective@#To investigate the feasibility of one-step coronary and carotid-cerebrovascular computed tomography angiography (CTA) using high-pitch Double Turbo Flash mode and to analyze the image quality and radiation dose in patients with heart rate variability using multi-slice detector dual-source CT.@*Methods@#A total of 79 patients with heart rate variability higher than 3 beat/min (bpm) were retrospectively analyzed. They were grouped by the scanning methods. Group A (n=40) were performed double turbo flash mode for one-step coronary and carotid-cerebrovascular arteriesinjected with one injection of contrast agent.further divided into Single A (only the phase 1 image)and Double A(combined images of phases 1 and 2). Group B (n=39) were performed separately with twice injection of contrast agent. Subjective scoring was performed on the image quality of the group Single A, Double A and B using a 4-point. Then the objective parameters of image quality, CT attenuations, image noise, signal-to-noise (SNR), and contrast-to-noise (CNR), were evaluated. Then subjective scores, objective evaluation indicators, and radiation dose were compared with one-way ANOVA analysis among the three groups.Contrast agent were compared by using t test in group A and B.@*Results@#No significant difference was found (F=2.093, P=0.128) for the subjective scores of the head and neck CTA among the three groups with (3.47±0.51), (3.53±0.51), (3.69±0.47). Significant difference was found (F=50.955, P<0.01) for the subjective scores of coronary CTA among the three groups with (2.70±0.76), (3.35±0.66), (3.58±0.50), and there was no statistically significant difference between Double A and B groups (P=0.104), met the requirements for diagnosis. The objective evaluation of the three groups compared the head and neck CTA images were statistically significant (P<0.05), of which the difference between the Single A and the Double A was not statistically significant (P>0.05), met the requirements for diagnosis; the differences in SNR and CNR of coronary CTA images are statistically significant (F=12.991, 12.236, P<0.01), and there was no statistically significant difference between Double A and B (P>0.05), met the requirements for diagnosis. Radiation dose in the group Double A was lower than group B (decreased by 46.15%,P<0.01).The amount of the contrast agent in the group Double A was lower than group B (decreased by 44.13%, t=-45.455;P<0.01).@*Conclusion@#The double turbo flash mode is feasibility for one-step coronary and carotid-cerebrovascular CTA in patients with the heart rate variability using multi-slice dual-source CT.This scan mode can maintain the diagnostic image quality with low contrast agent and radiation dose.
ABSTRACT
Objective To assess the diagnostic value of magnetic source imaging(MSI) in the preoperative localization of focal cortical dysplasia(FCD). Methods Eighty-two patients with intractable epilepsy resulting from FCD undergone preoperative assessment including MSI, video electroencephalography(VEEG) and electrocorticography(ECoG)from February 2006 to June 2012.The consistency between pre- and intra-surgical assessment was evaluated. For patients who had consistent results,postoperative curative effect was also recorded. The accuracy and predictive values of noninvasive preoperative tests were compared by χ2 test. Results For MSI and ECoG, their results were consistent in 57 cases, partially consistent in 14 cases, and inconsistent in 11 cases. In the postoperative follow-up of 57 patients with consistent results, there were 46 cases with Engel class Ⅰ, 3 cases with Engel class Ⅱ, 4 cases with Engel class Ⅲ, and 4 cases with Engel class IV. For VEEG and ECoG, the results were consistent in 43 cases, partially consistent in 33 cases, inconsistent in 6 cases.The postoperative follow-up showed that 27 cases were graded as Engel classⅠ, 5 cases as Engel classⅡ,7 cases as Engel classⅢ, and 4 cases as Engel class IV. There were statistically significant differences(χ2=5.023,P=0.025)of the concordance rate with ECoG between MSI(69.51%,57/82)and VEEG(52.44%,43/82). In the postoperative follow-up of patients with consistent results, the curative effect was better in group MSI than in group VEEG (χ2=3.989,P=0.046). Conclusions Preoperativelocalization by MSI shows advantage over VEEG, which meanswhen it achieves an agreement with ECoG, patients with FCD may get better prognosis from the surgical process.