Publications by authors named "J Hiratsuka"
Article Synopsis
- Researchers used machine learning techniques to predict the likelihood of endoleaks following thoracic endovascular aneurysm repair (TEVAR) by analyzing patient data and vessel features from pre-operative CT scans.
- The study trained an extreme Gradient Boosting (XGBoost) system on data from 145 patients—14 with endoleaks and 131 without—and compared its efficacy to traditional measurement methods.
- Results showed that machine learning significantly outperformed conventional methods in predicting post-TEVAR endoleaks, achieving a higher correlation with patient and vascular characteristics.
Article Synopsis
- This study evaluated the effectiveness of a patient-specific contrast enhancement optimizer simulation software (p-COP) in reducing contrast material (CM) dosage during TAVI-CTA in patients with aortic stenosis.
- Two groups were compared: one used p-COP with an individualized CM protocol, while the other followed a conventional body weight-tailored protocol, analyzing CM amounts, injection rates, and CT values.
- Results indicated a significant reduction in CM dose and injection rate in the p-COP group, although both groups achieved similar CT values and visualization scores, suggesting the potential of p-COP to optimize contrast use without compromising imagery quality.
Introduction: To compare CT (computed tomography) values for enhancement of the abdominal aorta and liver parenchyma during dynamic contrast enhancement (CE) CT in cirrhotic patients with and without splenomegaly (SM).
Methods: We considered 258 patients (83 males and 46 females for the splenomegaly group, and 83 males and 46 females for the control group) for this retrospective study. We measured CT values in the abdominal aorta and hepatic parenchyma during the hepatic arterial (HAP) and portal venous (PVP) phases.
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.
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.
View Article and Find Full Text PDF