AI-powered radiology workflow software
Autoradiology builds software that analyzes diagnostic images, applies machine learning, and delivers structured preliminary report drafts for physician review — starting with targeted musculoskeletal X-ray use cases, then expanding as capability is validated and proven.
Transforms imaging analysis into structured draft reports that give radiologists a clear starting point to review with confidence and finalize on their own clinical judgment.
Draft reports delivered as structured starting points augment radiologist performance — reducing repetitive effort while keeping the physician fully in control of every finding.
Starts with simple MSK X-rays, expanding into additional pathologies and study types as capability is proven.
Designed with healthcare data security, validation discipline, and operational adoption in mind.
Platform direction
Begin with defined radiology inputs and constrained imaging categories, initially emphasizing simple musculoskeletal X-ray workflows.
Evaluate relevant image regions, identify scoped criteria, and support draft report generation using best-fit techniques.
Produce a structured draft report that a radiologist can evaluate against the study, apply their clinical judgment, and finalize with confidence.
Increase coverage after demonstrating reliability, repeatability, validation confidence, and clinical utility.
Technical posture
Autoradiology's technical story combines machine learning, report-generation workflow, secure infrastructure thinking, and an explicit appreciation for compliance and adoption. That balance matters in a clinical domain where performance, traceability, and usability all shape whether software is trusted and utilized.
Our approach
Autoradiology is a technical AI company focused on practical radiology workflow improvement — narrowly scoped, clinically useful software that helps convert routine imaging into draft diagnostic reports for physician review.
Software that evaluates diagnostic imaging, applies machine learning and AI, and generates structured preliminary radiology reports. The current direction emphasizes simple, high-volume studies where focused automation improves efficiency without overextending scope.
An engineering-led path: start with constrained use cases, validate rigorously, improve reliability and repeatability, then expand capability. That approach reflects both software discipline and clinical practicality.
Radiology demand continues to rise while specialist time remains constrained. Autoradiology reduces the effort spent on routine studies, improves turnaround, and lets radiologists concentrate where expert judgment matters most.
Leadership
Executive systems leadership, modern software and platform engineering, and practicing radiology expertise — together shaping both capability and product direction.
John brings systems-engineering and program-management discipline to turn complex ideas into structured execution. His background includes large-scale engineering analysis, safety-critical aerospace programs, validation-oriented work, and patented innovation — shaping the company's operating model around thoughtful scope selection, disciplined progress, and partner-facing strategy.
Micheal is the technical engine behind Autoradiology's software direction. His experience spans platform engineering, DevSecOps, secure cloud environments, healthcare-adjacent infrastructure, and AI development. With a biomedical engineering background and hands-on experience leading modern engineering organizations, he architects AI products that work reliably in demanding, security-conscious environments.
Dr. Jaclyn Taylor provides the clinical authority that grounds product decisions in real radiology practice. A board-certified radiologist with VA experience, fellowship training in body imaging and nuclear medicine, and strong academic distinction — her guidance ensures technical ambitions remain anchored to diagnostic relevance and the standards expected in medical imaging.
About
Autoradiology is the radiology-focused AI subsidiary of JM Research, combining software engineering, machine learning, systems thinking, and practicing radiology expertise to build clinically useful tools — focused on implementation, verification, infrastructure, and practical physician workflow fit.
Reduce friction in routine radiology by delivering high-quality draft interpretations for physician review. Better leverage of radiologist time, more consistent routine output, and a product philosophy centered on real clinical utility.