Prediction of endovascular leaks after thoracic endovascular aneurysm repair though machine learning applied to pre-procedural computed tomography angiographs.

To predict endoleaks after thoracic endovascular aneurysm repair (TEVAR) we submitted patient characteristics and vessel features observed on pre- operative computed tomography angiography (CTA) to machine-learning. We evaluated 1-year follow-up CT scans (arterial and delayed phases) in patients who underwent TEVAR for the presence or absence of an endoleak. We evaluated the effect of machine learning of the patient age, sex, weight, and height, plus 22 vascular features on the ability to predict post-TEVAR endoleaks. The extreme Gradient Boosting (XGBoost) for ML system was trained on 14 patients with- and 131 without endoleaks. We calculated their importance by applying XGBoost to machine learning and compared our findings between with those of conventional vessel measurement-based methods such as the 22 vascular features by using the Pearson correlation coefficients. Pearson correlation coefficient and 95% confidence interval (CI) were r = 0.86 and 0.75 to 0.92 for the machine learning, r = - 0.44 and - 0.56 to - 0.29 for the vascular angle, and r = - 0.19 and - 0.34 to - 0.02 for the diameter between the subclavian artery and the aneurysm (Fig. 3a-c, all: p < 0.05). With machine-learning, the univariate analysis was significant higher compared with the vascular angle and in the diameter between the subclavian artery and the aneurysm such as the conventional methods (p < 0.05). To predict the risk for post-TEVAR endoleaks, machine learning was superior to the conventional vessel measurement method when factors such as patient characteristics, and vascular features (vessel length, diameter, and angle) were evaluated on pre-TEVAR thoracic CTA images.

Using Patient-Specific Contrast Enhancement Optimizer Simulation Software During the Transcatheter Aortic Valve Implantation-Computed Tomography Angiography in Patients With Aortic Stenosis.

OBJECTIVES: This study assessed whether patient-specific contrast enhancement optimizer simulation software (p-COP) can reduce the contrast material (CM) dose compared with the conventional body weight (BW)-tailored scan protocol during transcatheter aortic valve implantation-computed tomography angiography (TAVI-CTA) in patients with aortic stenosis. METHODS: We used the CM injection protocol selected by the p-COP in group A (n = 30). p-COP uses an algorithm that concerns data on an individual patient's cardiac output. Group B (n = 30) was assigned to the conventional BW-tailored CM injection protocol group. We compared the CM dose, CM amount, injection rate, and computed tomography (CT) values in the abdominal aorta between the 2 groups and classified them as acceptable (>280 Hounsfield units (HU)) or unacceptable (<279 HU) based on the optimal CT value and visualization scores for TAVI-CTA. We used the Mann-Whitney U test to compare patient characteristics and assess the interpatient variability of subjects in both groups. RESULTS: Group A received 56.2 mL CM and 2.6 mL/s of injection, whereas group B received 76.9 mL CM and 3.4 mL/s of injection (P < 0.01). The CT value for the abdominal aorta at the celiac level was 287.0 HU in group A and 301.7HU in group B (P = 0.46). The acceptable (>280 HU) and unacceptable (<280 HU) CT value rates were 22 and 8 patients in group A and 24 and 6 patients in group B, respectively (P = 0.76). We observed no significant differences in the visualization scores between groups A and B (visualization score = 3, P = 0.71). CONCLUSION: The utilization of p-COP may decrease the CM dosage and injection rate by approximately 30% in individuals with aortic stenosis compared with the body-weight-tailored scan protocol during TAVI-CTA.

Utility of lower tube voltage scans in reducing exposure of healthcare workers within computed tomography room to scattered radiation.

The aim of this study was to estimate the effect of tube voltage on the scattered dose in a computed tomography (CT) room. To this end, we conducted experiments using anthropomorphic phantoms and a CT scanner at different tube voltages during CT. The scattered dose was measured using an electronic pocket dosemeter at 50-cm intervals from the centre of the gantry. The structure of the CT room was measured at 57 points (28 points in the front of the gantry (on the bed side), 6 points on the side of the gantry and 23 points behind the gantry) to be up to 200 cm. We compared the scattered dose distributions between 80 and 120 kVp at heights of 50, 100 and 150 cm above the floor surface. The scattered dose was reduced by ~30% when the tube voltage was reduced from 120 to 80 kVp.

Can Machine Learning Identify the Intravenous Contrast Dose and Injection Rate Needed for Optimal Enhancement on Dynamic Liver Computed Tomography?

OBJECTIVES: This study aimed to investigate whether machine learning (ML) is useful for predicting the contrast material (CM) dose required to obtain a clinically optimal contrast enhancement in hepatic dynamic computed tomography (CT). METHODS: We trained and evaluated ensemble ML regressors to predict the CM doses needed for optimal enhancement in hepatic dynamic CT using 236 patients for a training data set and 94 patients for a test data set. After the ML training, we randomly divided using the ML-based (n = 100) and the body weight (BW)-based protocols (n = 100) by the prospective trial. The BW protocol was performed using routine protocol (600 mg/kg of iodine) by the prospective trial. The CT numbers of the abdominal aorta and hepatic parenchyma, CM dose, and injection rate were compared between each protocol using the paired t test. Equivalence tests were performed with equivalent margins of 100 and 20 Hounsfield units for the aorta and liver, respectively. RESULTS: The CM dose and injection rate for the ML and BW protocols were 112.3 mL and 3.7 mL/s, and 118.0 mL and 3.9 mL/s ( P < 0.05). There were no significant differences in the CT numbers of the abdominal aorta and hepatic parenchyma between the 2 protocols ( P = 0.20 and 0.45). The 95% confidence interval for the difference in the CT number of the abdominal aorta and hepatic parenchyma between 2 protocols was within the range of predetermined equivalence margins. CONCLUSIONS: Machine learning is useful for predicting the CM dose and injection rate required to obtain the optimal clinical contrast enhancement for hepatic dynamic CT without reducing the CT number of the abdominal aorta and hepatic parenchyma.

Usefulness of electrocardiogram mA modulation during the electrocardiogram-gated CT scan in paediatrics with high heart rate for different helical pitch: a phantom-based assessment study.

We investigated the effect of electrocardiographic (ECG) mA-modulation of ECG-gated scans of computed tomography (CTA) on radiation dose and image noise at high heart rates (HR) above 100 bpm between helical pitches (HP) 0.16 and 0.24. ECG mA-modulation range during ECG-gated CTA is 50-100 mA, the phase setting is 40-60% and the scan range is 90 mm for clinical data during HR for 90, 120 and 150 bpm. Radiation dose and image noise in Housfield units are measured for CT equipment during HR for 90, 120 and 150 bpm between HP 0.16 and 0.24. ECG mA-modulation, dose reduction ratio for HR 90, 120 and 150 bpm are 19.1, 13.4 and 8.7% at HP 0.16 and 17.1, 13.3 and 7.7% at HP 0.24, respectively. No significant differences were observed in image noise between both HP. Dose reductions of 8-24% are achieved with ECG mA-modulation during ECG-gated CCTA scan, which is beneficial even in high HR more than 100 bpm.

RADIATION DOSE REDUCTION AT LOW TUBE VOLTAGE WITH CORONARY ARTERY BYPASS GRAFT COMPUTED TOMOGRAPHY ANGIOGRAPHY BASED ON THE CONTRAST NOISE RATIO INDEX.

To compare the radiation dose and diagnostic ability of the 100-kVp protocol, based on the contrast noise ratio (CNR) index, during coronary artery bypass graft (CABG) vessels with those of the 120-kVp protocol. For the 120-kVp scans (150 patients), the targeted image level was set at 25 Hounsfield units (HU) (CNR120 = iodine contrast/25 HU). For the 100-kVp scans (150 patients), the targeted noise level was set at 30 HU to obtain the same CNR as in the 120-kVp scans (i.e. using 1.2-fold higher iodine contrast, CNR100 = 1.2 × iodine contrast/(1.2 × 25 HU) = CNR120). We compared the CNRs, radiation doses, detection of CABG vessels and visualisation scores of the scans acquired at 120 and 100 kVp, respectively. At the same CNR, the 100-kVp protocol may help reduce the radiation dose by ⁓30% compared with the 120-kVp protocol, without degradation of diagnostic ability during CABG.

Effect of patient characteristics on vessel enhancement on arterio-venous fistula CT angiography in a retrospective cohort study.

To evaluate the effects of various patient characteristics on vessel enhancement on arterio-venous fistula (AVF) computed tomography (CT) angiography (AVF-CT angiography). A total of 127 patients with suspected or confirmed shunt stenosis and internal AVF complications were considered for inclusion in a retrospective cohort study. The tube voltage was 120 kVp, and the tube current was changed from 300 to 770 mA to maintain the image quality (noise index: 14) using automatic tube current modulation. To evaluate the effects of age, sex, body size, and scan delay on the CT number of the brachial artery or vein, we used correlation coefficients and multivariate regression analyses. There was a significant positive correlation between the CT number of the brachial artery or vein and age (R = 0.21 or 0.23, P < .01). The correlations were inverse with the height (r = -0.45 or -0.42), total body weight (r = -0.52 or -0.50), body mass index (r = -0.21 or -0.23), body surface area (body surface area [BSA]; r = -0.56 or -0.54), and lean body weight (r = -0.55 or -0.53) in linear regression analysis (P < .01 for all). There was a significant correlation between the CT number of the brachial artery or vein and scan delay (R = 0.19 or 01.9, P < .01). Only the BSA had significant effects on the CT number in multivariate regression analysis (P < .01). The BSA was significantly correlated with the CT number of the brachial artery or vein on AVF-CT angiography.

Usefulness of large beam-shaping filters at different tube voltages of newborn chest CT.

BACKGROUND: To investigate optimizing the use of different beam shaping filters (viz. small, medium and large) when using different tube voltages during the newborn chest computed tomography (CT) on a GE Lightspeed VCT scanner. METHODS: We used pediatric anthropomorphic phantoms with a 64 detector-row CT scanner while scanning the chest. A real-time skin dosimeter (RD - 1000; Trek Corporation, Kanagawa, Japan) was positioned into the phantom center of the body, the surface of the body back, and the right and left mammary glands. We performed and compared six scan protocols using small, medium, and large beam shaping filters at 80 and 120 kVp protocols. RESULT: There were no significant differences in the image noise for the chest scan among the different beam shaping filters. By using the large beam shaping filter at 80 kVp, it was possible to reduce the exposure dose by 5% in comparison with the small beam shaping filter, and by 10% in comparison with the medium beam shaping filter. By using the large beam shaping filter at 120 kVp, it was possible to reduce the exposure dose by 15% in comparison with the small beam shaping filter and by 20% in comparison with the medium beam shaping filter (p < 0.01). CONCLUSION: The large beam shaping filter had the most dose reduction effect during newborn chest CT on a GE Lightspeed VCT scanner. The additional copper filtration being present in the large bowtie filter of the GE Lightspeed CT scanner when using different tube voltages is more effective in reducing radiation exposure in children.

COMPARISON OF PEDIATRIC LENS DOSE MEASUREMENTS BETWEEN AXIAL SCAN MODE WITHOUT ACTIVE COLLIMATOR AND HELICAL SCAN MODE WITH ACTIVE COLLIMATOR BY USING A 64 DETECTOR-ROW COMPUTED TOMOGRAPHY SCANNER.

To investigate the pediatric eye lens entrance surface dose for both axial scan modes without an active collimator and helical scan modes with an active collimator on 64 detector-row computed tomography (CT) scanner. We used three pediatric anthropomorphic phantoms with axial and helical scan modes from the superior orbitomeatal line to the crown of the head. We compared the measured dose values of the real-time skin dosemeter at the surfaces of the lens and the image noise at different scan modes. The median measured dose values for the lens of newborn, 1-year-old and the 5-year-old phantom were 31.3, 0.97 and 0.65 mGy, respectively, in the axial scan mode and 0.89, 1.21 and 0.71 mGy, respectively, in the helical scan mode. Compared with helical scans with an active collimators, axial scans can reduce the lens dose by ∼10% during head CT on 64 detector-row CT scanner without deterioration of image noise.

Prediction of Aortic Contrast Enhancement on Dynamic Hepatic Computed Tomography-Performance Comparison of Machine Learning Methods and Simulation Software.

OBJECTIVES: The aim of this study was to compare prediction ability between ensemble machine learning (ML) methods and simulation software for aortic contrast enhancement on dynamic hepatic computed tomography. METHODS: We divided 339 human hepatic dynamic computed tomography scans into 2 groups. One group consisted of 279 scans used to create cross-validation data sets, the other group of 60 scans were used as test data sets. To evaluate the effect of the patient characteristics on enhancement, we calculated changes in the contrast medium dose per enhancement of the abdominal aorta in the hepatic arterial phase. The parameters for ML were the patient sex, age, height, body weight, body mass index, and cardiac output. We trained 9 ML regressors by applying 5-fold cross-validation, integrated the predictions of all ML regressors for ensemble learning and the simulations, and used the training and test data to compare their Pearson correlation coefficients. RESULTS: Comparison of different ML methods showed that the Pearson correlation coefficient for the real and predicted contrast medium dose per enhancement of the abdominal aorta was highest with ensemble ML (r = 0.786). It was higher than that obtained with the simulation software (r = 0.350). With ensemble ML, the Bland-Altman limit of agreement [mean difference, 5.26 Hounsfield units (HU); 95% limit of agreement, -112.88 to 123.40 HU] was narrower than that obtained with the simulation software (mean difference, 11.70 HU; 95% limit of agreement, -164.71 to 188.11 HU). CONCLUSION: The performance for predicting contrast enhancement of the abdominal aorta in the hepatic arterial phase was higher with ensemble ML than with the simulation software.

Usefulness of the patient-specific contrast enhancement optimizer simulation software during the whole-body computed tomography angiography.

To evaluate whether the patient-specific contrast enhancement optimizer simulation software (p-COP) is useful for predicting contrast enhancement during whole-body computed tomography angiography (WBCTA). We randomly divided the patients into two groups using a random number table. We used the contrast material (CM) injection protocol selected by p-COP in group A (n = 52). The p-COP used an algorithm including data on the individual patient's cardiac output. Group B (n = 50) was assigned to the conventional CM injection protocol based on body weight. We compared the CT number in the abdominal aorta at the celiac artery level between the two groups and classified them as acceptable (> 280 HU) and unacceptable (< 279 HU) based on the optimal CT number for the WBCTA scans. To evaluate the difference in both injection protocols, we compared the visual inspection of the images of the artery of Adamkiewicz in both protocols. The CM dosage and injection rate in group A were significantly lower than those in group B (480.8 vs. 501.1 mg I/kg and 3.1 vs. 3.3 ml/s, p < 0.05). The CT number of the abdominal aorta at the celiac level was 382.4 ± 62.3 HU in group A and 363.8 ± 71.3 HU in group B (p = 0.23). CM dosage and injection rate were positively correlated to cardiac output for group A (r = 0.80, p < 0.05) and group B (r = 0.16, p < 0.05). The number of patients with an acceptable CT number was higher in group A [46/6 (86.7%)] than in group B [43/7 (71.4%)], but not significant (p = 0.71). The visualization rate for the Adamkiewicz artery was not significantly different between groups A and B (p = 0.89). The p-COP was useful for predicting contrast enhancement during WBCTA with a lower CM dosage and a lower contrast injection rate than that based on the body weight protocol. In patients with lower cardiac output a reduction in contrast injection rate and CM dosage did not lead to a reduced imaging quality, thus particularly in this group CM dosage can be reduced by p-COP.

[Study of the additional filter in transcatheter hepatic arterial embolization].

It is well known that Interventional Radiology (IVR) is useful. However, the patient dose in IVR is increasing because of the prolongation of fluoroscopic time and the increase in the number of radiographies in recent years. We studied the adequacy of the additional filter for the decrease of the skin surface dose in patients with hepatocellular carcinoma of transcatheter arterial embolization (TAE). In 20 patients (15 men and 5 women, average age: 66.9 and 72.0 years old) who had undergone TAE, we estimated the skin surface dose from the records of their exposure condition (tube voltage, tube current, time, and field size of image intensifier) and the results of the phantom experiment with 2 kinds of additional filter. The estimated skin surface dose of the patient was 1.75 ± 0.84 with the additional filter of 1.5 mm thickness of aluminum (1.5 mmAl), 1.46 ± 0.67 Gy with 0.03 mm thickness tantalum (0.03 mmTa) and 1.17 ± 0.55 Gy with 0.06 mm thickness of tantalum (0.06 mmTa). Against a skin surface dose of 1.5 mmAl, the dose reduction of 16.7% was shown in 0.03 mmTa and 33.2% in 0.06 mmTa. With a DSA phantom of iodine density 0.5 and 1.0 and 2.0 mgI/ml, DSA images were acquisitioned at tube voltage 70, 80 and 90 kV to compare the detectability of contrast media in 0.06 mmTa with 1.5 mmAl. To evaluate the detectability of contrast media in 0.06 mmTa in 1.5 mmAl, receiver operating characteristic (ROC) analysis was performed with the pixel value of the phantom image. The area under the ROC curve in a 1.5 mmAl filter and the 0.06 mmTa filter provided with each contrast media density and each tube voltage was approximately a constant value. It was suggested that there was no differences in the detectability of contrast media in both additional filters. In conclusion, the skin surface dose of the patient was able to be reduced 33.2% without decreasing contrast media detectability by changing the additional filter from 1.5 mmAl to 0.06 mmTa. It was most suitable in TAE in our hospital to choose 0.06 mmTa as an additional filter.