What AI Can See in Medical Scans That Doctors Can't
Thursday, September 3, 2026
Transcript intelligence
What OpenRounds heard
Source-grounded signals extracted from the episode transcript. Timestamps and supporting excerpts appear when available.
The speaker reports that a neural network trained on endomyocardial biopsies achieved 98% accuracy in predicting heart failure, while three pathologists reviewing the same biopsies averaged 73% accuracy.
“we trained a neural network to predict heart failure from endomyocardial biopsies and we got some ridiculous accuracy like that ninety eight percent in identifying heart failure and then we had three pathologists do a review of these endomyocardial biopsies and found that um you know they had a seventy three percent average accuracy right”
The speaker expresses a desire for access to large-scale EHR data from systems like Epic to train AI models for global health applications in low-resource settings such as Angola or Indonesia.
The speaker argues that the AI machine learning community must prioritize explainable and biologically interpretable approaches to gain clinician confidence for treatment decisions.
What if medical scans we already collect contain signals that could predict cancer treatment response, reveal disease risk years earlier, or identify biological patterns the human eye cannot see? In this episode of AI & Healthcare, oncologists Dr. Sanjay Juneja and Dr. Doug Flora, speak with AI and biomedical imaging researcher Anant Madabhushi, PhD about the hidden information inside routine CT scans, retinal images, and pathology slides. They explore how AI could help predict treatment response, detect warning signs of disease, uncover meaningful signals in tumor vessels and surrounding tissue, and expand access in regions facing shortages of radiologists and pathologists. The conversation also examines explainability, automation bias, clinical validation, health equity, and the consequences of waiting too long to use potentially valuable technology. Anant Madabhushi, PhD is the Robert W. Woodruff Professor of Biomedical Engineering at Emory University and Georgia Tech and Executive Director of the Emory Empathetic AI for Health Institute. His work focuses on AI, radiomics, computational pathology, and predicting treatment response from routinely collected medical images. Subscribe for conversations about artificial intelligence, oncology, clinical medicine, and the future of healthcare. What if medical scans we already collect contain signals that could predict cancer treatment response, reveal disease risk years earlier, or identify biological patterns the human eye cannot see? In this episode of AI & Healthcare, oncologists Dr. Sanjay Juneja and Dr. Doug Flora, speak with AI and biomedical imaging researcher Anant Madabhushi, PhD about the hidden information inside routine CT scans, retinal images, and pathology slides. They explore how AI could help predict treatment response, detect warning signs of disease, uncover meaningful signals in tumor vessels and surrounding tissue, and expand access in regions facing shortages of radiologists and pathologists. T
Show transcript excerpt
What if medical scans we already collect contain signals that could predict cancer treatment response, reveal disease risk years earlier, or identify biological patterns the human eye cannot see? In this episode of AI & Healthcare, oncologists Dr. Sanjay Juneja and Dr. Doug Flora, speak with AI and biomedical imaging researcher Anant Madabhushi, PhD about the hidden information inside routine CT scans, retinal images, and pathology slides. They explore how AI could help predict treatment response, detect warning signs of disease, uncover meaningful signals in tumor vessels and surrounding tissue, and expand access in regions facing shortages of radiologists and pathologists. The conversation also examines explainability, automation bias, clinical validation, health equity, and the consequences of waiting too long to use potentially valuable technology. Anant Madabhushi, PhD is the Robert W. Woodruff Professor of Biomedical Engineering at Emory University and Georgia Tech and Executive Director of the Emory Empathetic AI for Health Institute. His work focuses on AI, radiomics, computational pathology, and predicting treatment response from routinely collected medical images. Subscribe for conversations about artificial intelligence, oncology, clinical medicine, and the future of healthcare.
Daily healthcare AI brief
Get the free healthcare AI briefing
One concise briefing built from reporting, research, policy, blogs, videos, and full podcast transcripts.
Free. No account needed. Unsubscribe anytime. Already subscribed? Sign in to save and personalize.