Purpose: The AAST Organ Injury Scale is widely adopted for splenic injury severity but suffers from only moderate inter-rater agreement. This work assesses SpleenPro, a prototype interactive explainable artificial intelligence/machine learning (AI/ML) diagnostic aid to support AAST grading, for effects on radiologist dwell time, agreement, clinical utility, and user acceptance.
Methods: Two trauma radiology ad hoc expert panelists independently performed timed AAST grading on 76 admission CT studies with blunt splenic injury, first without AI/ML assistance, and after a 2-month washout period and randomization, with AI/ML assistance.
Background: AI/ML CAD tools can potentially improve outcomes in the high-stakes, high-volume model of trauma radiology. No prior scoping review has been undertaken to comprehensively assess tools in this subspecialty.
Purpose: To map the evolution and current state of trauma radiology CAD tools along key dimensions of technology readiness.
Purpose: To evaluate the capability of a dual-cooling technique in suppressing motion artifact and to evaluate the feasibility of the noninvasive muscle fibers tracking using DTI during chick embryonic development.
Materials And Methods: Fifteen eggs were divided into three groups of 5 eggs each (one group for each imaging sequence), and eggs were imaged every 48 h from incubation day 4; embryos were imaged in ovo using three sequences of varying duration (T1, T2, and DTI). For each sequence, three preprocessing methods were used: no-cooling (NC), single-cooling (SC), and dual-cooling (DC).
Background: ZD6126 is a novel vascular-targeting agent that disrupts the endothelial tubulin cytoskeleton causing selective occlusion of tumor vasculature and extensive tumor necrosis. This Phase I clinical study was conducted to evaluate the dose and administration schedule of ZD6126.
Methods: Adult patients with solid tumors refractory to existing treatments received a 10-min, single-dose intravenous infusion of ZD6126 every 14 or 21 days.