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.

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.

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.

USE OF VACUUM MATTRESSES CAN REDUCE THE ABSORBED DOSE DURING PEDIATRIC CT.

To evaluate and compare the absorbed dose and image quality when applying a commercially produced fixation device (group A) and a vaccum mattress fixation device to pediatric patients (group B). We compared the absorbed dose and image noise between the groups at the phantom and clinical study. For phantom study, the measurement absorbed dose for a real time skin dosimeter was 3.0 mGy at the group A and 1.9 mGy at the group B (p < 0.05). For clinical study, computed tomography dose index product, dose-length and effective radiation dose were significantly lower with the group B compared to the group A, (3.4 mGy, 27.0 mGy-cm, and 2.2 mSv vs 4.4 mGy, and 36.7 mGy-cm, and 3.0 mSv), p < 0.05 for all comparisons. Compared to the commercially produced fixation device, the vaccum mattress fixation device composed of a less absorptive material enabled a reduction in the absorbed dose while maintaining the image quality during pediatric CT examinations.