Applying patient characteristics, stent-graft selection, and pre-operative computed tomographic angiography data to a machine learning algorithm: Is endoleak prediction possible?

INTRODUCTION: This study aims to predict endoleak after endovascular aneurysm repair (EVAR) using machine learning (ML) integration of patient characteristics, stent-graft configuration, and a selection of vessel lengths, diameters and angles measured using pre-operative computed tomography angiography (CTA). METHODS: We evaluated 1-year follow-up CT scans (arterial and delayed phases) in patients who underwent EVAR for the presence or absence of an endoleak. We also obtained data on the patient characteristics, stent-graft selection, and preoperative CT vessel morphology (diameter, length, and angle). The extreme gradient boosting (XGBoost) for the ML system was trained on 30 patients with endoleaks and 81 patients without. We evaluated 5217 items in 111 patients with abdominal aortic aneurysms, including the patient characteristics, stent-graft configuration and vascular morphology acquired using pre-EVAR abdominal CTA. We calculated the area under the curve (AUC) of our receiver operating characteristic analysis using the ML method. RESULTS: The AUC, accuracy, 95% confidence interval (CI), sensitivity, and specificity were 0.88, 0.88, 0.79-0.97, 0.85, and 0.91 for ML applying XGBoost, respectively. CONCLUSIONS: The diagnostic performance of the ML method was useful when factors such as the patient characteristics, stent-graft configuration and vessel length, diameter and angle of the vessels were considered from pre-EVAR CTA. IMPLICATIONS FOR PRACTICE: Based on our findings, we suggest that this is a potential application of ML for the interpretation of abdominal CTA scans in patients with abdominal aortic aneurysms scheduled for EVAR.

Radiation dose reduction method combining the ECG-Edit function and high helical pitch in retrospectively-gated CT angiography.

INTRODUCTION: The purpose of this study was to demonstrate that dose reduction does not compromise image quality when combining high helical pitch (HP) and the ECG-Edit function during low HP retrospectively gated computed tomography angiography (CTA). METHODS: This study made use of a pulsating cardiac phantom (ALPHA 1 VTPC). The heart rate (HR) of the cardiac phantom was changed in five intervals, every 5 beats per minute (bpm), from 40 to 60 bpm. Evaluation of a range of HR was important because data loss might occur when combining a low HR and high HP. We performed retrospectively gated CTA scans five times using a low HP (0.16) and high HP (0.24), for each of the five HR intervals, using a 64-detector row CT scanner. The CT volume dose index (CTDIvol) was recorded from the CT console of each scan. For the images with data loss, data were repaired using the ECG-Edit function. We compared the CTDIvol, estimated cardiac phantom volume, and the visualization of the coronary ladder phantom between HP 0.16, with or without repaired HP 0.24, using the ECG-Edit function. RESULTS: Data loss occurred with a HR of 40 bpm and 45 bpm when using HP 0.24. The CTDIvol was reduced by approximately 33% with HP 0.24 when compared with HP 0.16. There were no significant differences in the mean cardiac motion phantom volume and visualization scores between HP 0.16 and with and without repaired HP 0.24 using the ECG-Edit function (p < 0.05). CONCLUSION: The ECG-Edit function is potential useful for repairing the lost data in patients with a low HR, and when combined with a high HP, it is possible to reduce the radiation dose by approximately 33%. IMPLICATIONS FOR PRACTICE: The ECG-Edit function and high HP may be a viable option in pediatric CTA studies.

Effect of injection duration on contrast enhancement during cardiac computed tomography angiography in newborns and infants.

INTRODUCTION: To investigate how changing the injection duration at cardiac computed tomography angiography (CCTA) affects contrast enhancement in newborns and infants. METHODS: Included were 142 newborns and infants with confirmed congenital heart disease who underwent CCTA between January 2015 and December 2018. In group 1 (n = 71 patients), the injection duration was 8 s; in group 2 (n = 71) it was 16 s. Our findings were assessed by one-to-one matching analysis to estimate the propensity score of each patient. We compare the CT number for the pulmonary artery (PA), ascending aorta (AAO), left superior vena cava (SVC), AAO and PA enhancement ratio, and the scores for visualization between the two groups. RESULTS: In group 1, median CT number and ranges was 345 (211-591) HU in the AAO, 324 (213-567) HU in the PA, and 62 (1-70) HU in the SVC. These values were 465 (308-669) HU, 467 (295-638) HU, and 234 (67-443) HU, respectively, in group 2 (p < 0.05). The median score for volume-rendering visualization on 3D images of the CCTA was 2 in group 1 and 3 in group 2; the score for visualization of the left SVC of the maximum intensity projection images was 2 in group 1 and 3 in group 2 (p < 0.05). The CT number for the AAO and PA enhancement ratio was 15.2 in group 1 and 9.2 in group 2 (p < 0.05). CONCLUSION: The 16-sec injection protocol yielded significantly higher CT numbers for the AAO, PA, and the SVC than the 8-sec injection protocol; the visualization scores were also significantly higher in group 2. IMPLICATIONS FOR PRACTICE: In newborns and infants, the longer injection time for CCTA yields stable and higher contrast enhancement at identical CM concentrations.

Efficacy of the spiral flow generating extended tube during paediatric CCTA.

INTRODUCTION: To compare the computed tomography (CT) number for paediatric cardiac computed tomography angiography (CCTA) and visualisation score of the three-dimensional (3D) images using the conventional T-shaped extended tube (T-tube) and spiral flow-generating extended tube (spiral-tube) connected between the contrast injector and cannula. METHODS: In total, 108 patients suspected to have congenital heart disease (CHD) were considered for inclusion. We utilised the T-tube for intravenous contrast and spiral-tube in 54 patients each. Observers individually inspected randomized volume rendering images of the internal thoracic artery, each acquired from the with or without spiral-tube groups, using a four-point scale. We compared the mean CT number of the ascending aorta (AAO) and pulmonary artery (PA), contrast noise ratio (CNR), CT number for the AAO and PA enhancement ratio, and the visualisation scores between the groups. RESULTS: There were no significant differences in patient characteristics between the with or without spiral-tube groups (p > 0.05). The mean CT number ±standard deviation for the AAO and PA, and the CNR without or with spiral-tube groups were 441.2 ± 89.2 and 489.8 ± 86.1 HU for the AAO, 436.3 ± 100.6 and 475.3 ± 85.2 HU for the PA, and 9.5 ± 2.2 and 10.8 ± 2.4 for the CNR, respectively (p < 0.05). In the spiral-tube group, the CT number, CNR, and visualisations score of the 3D images were significantly higher for the AAO and PA than those in the T-tube group (p < 0.05). CONCLUSION: The spiral-tube proved to be beneficial in improving the CT number for the AAO and PA, CNR, and visualisation score compared with the conventional T-tube during paediatric CCTA. IMPLICATIONS FOR PRACTICE: The spiral-tube may allow the visualisation of smaller blood vessels than those visualised by the conventional T-tube for paediatric patients in CCTA.

Enhancement rate of venous phase to portal venous phase computed tomography and its correlation with ultrasound elastography determination of liver fibrosis.

INTRODUCTION: This study aimed to compare the correlation between the computed tomography (CT) enhancement rate of the venous to portal venous phase (VP-ER) and the extracellular volume (ECV) fraction with shear-wave ultrasound elastography (USE) findings in patients with liver fibrosis. METHODS: We included 450 patients with clinically suspected liver cirrhosis who underwent triphasic dynamic CT studies and USE. We compared the USE results with the unenhanced CT phase, with enhancement in the hepatic artery phase (HAP), portal venous phase (PVP), and venous phase (VP), and with the ECV fraction and the VP-ER. We also compared the area under the curve (AUC) of the receiver operating characteristic (ROC) curve of the ECV fraction and VP-ER with that of the values obtained with USE. RESULTS: The VP-ER was the most highly correlated with the liver stiffness value determined with USE (Pearson's correlation coefficient: r = 0.37), followed by enhancement in the PVP (r = -0.25), CT number on unenhanced CT scans (r = -0.22), the ECV fraction (r = 0.19), enhancement in the VP (r = 0.059), and enhancement in the HAP (r = -0.023) (all p < 0.01). The VP-ER showed a significantly higher AUC than the ECV fraction (0.75 vs 0.62) when the liver stiffness was >15 kPa in USE studies (p = 0.04). CONCLUSION: Compared to the ECV fraction, the VP-ER is more useful for predicting all degrees of liver fibrosis on routine triphasic dynamic CT images. IMPLICATIONS FOR PRACTICE: Although improvement is needed, the VP-ER has a higher diagnostic ability for liver fibrosis than the ECV fraction in clinical practice.

Evaluation of effective energy using radiochromic film and a step-shaped aluminum filter.

Although the half-value layer (HVL) is one of the important parameters for quality assurance (QA) and quality control (QC), constant monitoring has not been performed because measurements using an ionization chamber (IC) are time-consuming and complicated. To solve these problems, a method using radiochromic film and step-shaped aluminum (Al) filters has been developed. To this end, GAFCHROMIC EBT2 dosimetry film (GAF-EBT2), which shows only slight energy dependency errors in comparison with GAFCHROMIC XR TYPE-R (GAF-R) and other radiochromic films, has been used. The measurement X-ray tube voltages were 120, 100, and 80 kV. GAF-EBT2 was scanned using a flat-bed scanner before and after exposure. To remove the non-uniformity error caused by image acquisition of the flat-bed scanner, the scanning image of the GAF-EBT2 before exposure was subtracted after exposure. HVL was evaluated using the density attenuation ratio. The effective energies obtained using HVLs of GAF-EBT2, GAF-R, and an IC dosimeter were compared. Effective energies with X-ray tube voltages of 120, 100, and 80 kV using GAF-EBT2 were 40.6, 36.0, and 32.9 keV, respectively. The difference ratios of the effective energies using GAF-EBT2 and the IC were 5.0%, 0.9%, and 2.7%, respectively. GAF-EBT2 and GAF-R proved to be capable of measuring effective energy with comparable precision. However, in HVL measurements of devices operating in the high-energy range (X-ray CT, radiotherapy machines, and so on), GAF-EBT2 was found to offer higher measurement precision than GAF-R, because it shows only a slight energy dependency.

Half-value layer measurement: simple process method using radiochromic film.

Although the half-value layer (HVL) is one of the important parameters for QA and QC, constant monitoring has not been performed because the measurements using an ionization chamber (IC) are time-consuming and complicated. To solve these problems, the use of radiochromic film (GAFCHROMIC XR TYPE R: GAF-R) with step-shaped aluminum (Al) filters, referred to herein as the simple process method, has been developed. The measurement X-ray tube voltages were 120 kV, 100 kV, and 80 kV. The Al filter area, the full exposure area, and the unexposed area were set on the GAF-R so as to obtain correct data. The HVL was evaluated using the density attenuation ratio. The HVLs obtained using the GAF-R and an 1C dosimeter were compared. HVLs with X-ray tube voltages of 120 kV, 100 kV, and 80 kV using the GAF-R were 4.10 mm, 3.55 mm and 2.97 mm, respectively. The difference ratios of the HVLs using the GAF-R and the IC were 1.2%, 7.6%, and 10.0%, respectively. The HVL at 120 kV can be routinely and quickly measured using the simple process method. Therefore, an IC dosimeter is not needed for HVL measurements for QA and QC. However, the HVL measurements of low energy (100 kV and 80 kV) need attention.

Evaluation of effective energy for QA and QC: measurement of half-value layer using radiochromic film density.

The effective energy of diagnostic X-rays is important for quality assurance (QA) and quality control (QC). However, the half-value layer (HVL), which is necessary to evaluate the effective energy, is not ubiquitously monitored because ionization-chamber dosimetry is time-consuming and complicated. To verify the applicability of GAFCHROMIC XR type R (GAF-R) film for HVL measurement as an alternative to monitoring with an ionization chamber, a single-strip method for measuring the HVL has been evaluated. Calibration curves of absorbed dose versus film density were generated using this single-strip method with GAF-R film, and the coefficient of determination (r2) of the straight-line approximation was evaluated. The HVLs (effective energies) estimated using the GAF-R film and an ionization chamber were compared. The coefficient of determination (r2) of the straight-line approximation obtained with the GAF-R film was more than 0.99. The effective energies (HVLs) evaluated using the GAF-R film and the ionization chamber were 43.25 keV (5.10 mm) and 39.86 keV (4.45 mm), respectively. The difference in the effective energies determined by the two methods was thus 8.5%. These results suggest that GAF-R might be used to evaluate the effective energy from the film-density growth without the need for ionization-chamber measurements.

[Subtraction image for dynamic liver MRI using free breath-hold at functional residual capacity: a clinical trial].

PURPOSE: Dynamic liver MRI images have been obtained under expiration breath holding (BH). However, problems with obtaining reproducible liver positions often observed. This study investigated ways to improve the reproducibility of liver position on dynamic liver MRI. MATERIALS AND METHODS: After giving informed consent, 60 patients (32 males and 28 females, ages 33-85, median age 69) were examined by liver dynamic MRI under two types of BH. The BH phases were voluntary expiration (VE) phase without any explanations and functional residual capacity (FRC) phase after careful explanation was provided. Plain images, arterial phase images, portal phase images and parenchymal phase images were obtained. For statistical evaluation of reproducibility, the area of the 2nd or 3rd images from top of the liver was measured in each phase using a threshold value of half maximum. Misregistration areas were calculated by finding the remainder of the liver area in the plain-arterial (Pl-A) phase, arterial-portal (A-Po) phase, plain-parenchymal (Pl-Pa) phase. Contingency table analysis was done due to the misregistration was occurred or not. RESULTS: Misregistration of liver image on the VE and the FRC of three phase types were statistical significant on the Pl-A (p < 0.01), on the A-Po (p < 0.01) and on the Pl-Pa (p < 0.05), respectively. CONCLUSION: The FRC phase following careful explanation of the BH provided significantly improved reproducibility of liver position on dynamic liver MRI. Therefore, precise subtraction images could be obtained for routine clinical examinations without slice matching.

Dose distribution in pediatric CT head examination using a new phantom with radiochromic film.

Performing a detailed dose measurement is important to keep radiation doses during computed tomography (CT) examinations as low as reasonably achievable. To estimate in detail the dose distribution during pediatric CT examination of the head, a sheet roll CT dosimetry phantom (SRCT-P) with radiochromic film (RF) was developed. The dose distributions in the SRCT-P (diameters of 6 [premature baby], 10 [neonate], and 14 [infant] cm) were evaluated. The SRCT-Ps were made by rolling up flexible acrylic sheets (1.1 g/cm3). RFs were positioned every 5 mm along the radius at each SRCT-P, starting at 10 mm (center) and ending on the surface. The dose distribution along the z-axis at the center or on the surface showed a flat or wave pattern, respectively. When the mean surface dose at 10 cm diameter was taken as 100%, the mean surface doses at 6 or 14 cm diameters were 105 or 96%, respectively, and the mean center doses at 6, 10, and 14 cm were 109, 99, and 74%, respectively. The maximum-minimum doses and dose distribution of a CT examination can be measured separately by using the SRCT-P with RF.

Computed tomography phantom for radiochromic film dosimetry.

To evaluate in detail the dose distribution during computed tomography (CT), a sheet roll CT dosimetry phantom (SRCT-P) with a radiochromic film (RF) was experimentally developed. The SRCT-P was made by rolling up a vinyl chloride sheet in a cylindrical shape to arbitrarily select the SRCT-P diameter, dose measurement position, and depth. The SRCT-P centre core consisted of a plastic hose in which a 10 mm acrylic bar with a RF was inserted. To determine the availability of the SRCT-P, the surface and centre doses (at a 5 mm radius) at each SRCT-P diameter (6-16 cm; every 2 cm) were measured. The ratios of the centre-to-surface doses (D(centre)/D(surface)) systematically increased, from 80 to 111%, for decreasing SRCT-P diameters, between 16 and 6 cm, respectively. The centre dose approached the surface dose as the SRCT-P diameter decreased. To use a RF for a CT dose measurement, further detailed research and analysis is necessary. However, this study has shown that a SRCT-P is useful and beneficial for the measurement of the dose distribution during a CT examination.