activity
20242026
collaborators

11 papers

cs.CV2026

ReXInTheWild: A Unified Benchmark for Medical Photograph Understanding

Oishi Banerjee, Sung Eun Kim, Alexandra N. Willauer +9

Everyday photographs taken with ordinary cameras are already widely used in telemedicine and other online health conversations, yet no comprehensive benchmark evaluates whether vis…

cs.HC2025

Voice-guided Orchestrated Intelligence for Clinical Evaluation (VOICE): A Voice AI Agent System for Prehospital Stroke Assessment

Julian Acosta, Scott Adams, Julius Kernbach +7

We developed a voice-driven artificial intelligence (AI) system that guides anyone - from paramedics to family members - through expert-level stroke evaluations using natural conve…

cs.CV2025

MedVersa: A Generalist Foundation Model for Medical Image Interpretation

Hong-Yu Zhou, Julián Nicolás Acosta, Subathra Adithan +3

Current medical AI systems are often limited to narrow applications, hindering widespread adoption. We present MedVersa, a generalist foundation model trained on tens of millions o…

eess.IV2025

ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports

Xiaoman Zhang, Julián N. Acosta, Josh Miller +2

We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. This dataset contains 160,000 chest X-ray s…

eess.IV2024

a2z-1 for Multi-Disease Detection in Abdomen-Pelvis CT: External Validation and Performance Analysis Across 21 Conditions

Pranav Rajpurkar, Julian N. Acosta, Siddhant Dogra +4

We present a comprehensive evaluation of a2z-1, an artificial intelligence (AI) model designed to analyze abdomen-pelvis CT scans for 21 time-sensitive and actionable findings. Our…

cs.HC2024

The Impact of AI Assistance on Radiology Reporting: A Pilot Study Using Simulated AI Draft Reports

Julián N. Acosta, Siddhant Dogra, Subathra Adithan +4

Radiologists face increasing workload pressures amid growing imaging volumes, creating risks of burnout and delayed reporting times. While artificial intelligence (AI) based automa…