HeyJaredThe Vasty Deep | Radiology: AI
The Vasty Deep is the official blog of the journal Radiology: Artificial Intelligence featuring regular posts from Dr. Charles Kahn, Editor, and deputy editors. Subscribe to receive email alerts and never miss what's new in radiology AI!
- Indexed issues, last 90 days
- 10
- Latest publication
- Sep 30, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 8, 2026
Latest issues
AI and Sustainability: Greener Scanners, Hotter Servers? (opens the original)
Read excerpt
At several US graduation ceremonies in the spring of 2026, artificial intelligence (AI) received an unusual welcome: boos.At Middle Tennessee State University, graduates jeered when music executive Scott Borchetta described AI as a force already transforming their industry and told them to “deal with it.” Similar reactions followed at the University of Central Florida and the University of Arizona, where speakers compared the rise of AI with the Industrial Revolution or other major technological
Training Radiologists in the Age of AI (opens the original)
Read excerpt
Artificial intelligence is already changing how doctors read medical images. The radiologist of 10 years ago wrote their report based solely on a patient’s X-ray, CT, MRI, or ultrasound images. Increasingly, however, today’s radiologist may not be looking at those images alone. AI systems can now help detect abnormalities, measure tumors, prioritize urgent scans, and flag findings that might otherwise be missed. Some can generate preliminary interpretations or suggest diagnoses. As these tools b
What a Denoiser Borrows From Other Patients (opens the original)
Read excerpt
Most scanners process an image before anyone looks at it. Denoising takes an already acquired image and returns a cleaner-looking version. Deep-learning reconstruction and image enhancement do the same job by other means. Scanners ship with the processing steps switched on by default, and all built-in steps have run by the time I open the study.According to information theory, none of that processing should help me much. The chain runs one way: lesion (any abnormality of interest), then image, t
Venture Capital in Radiology AI: Fueling the Fire of Innovation (opens the original)
Read excerpt
You have an idea and an early prototype. When is the right time to seek Venture Capital funding? Since transitioning from my role as a physician leader (former Chief of Pediatric Radiology at UCSF-San Francisco) and launching my own venture fund, Radiologue Ventures, I’ve gotten this question from many aspiring founders. This is a nuanced question and, excitingly, one often asked by academic radiologists who are new to the world of business. In this post, I will speak from my perspective as an i
The Art of Designing Intelligence (opens the original)
Read excerpt
Artificial intelligence has transformed the way we approach medical imaging. Every year, new architectures emerge, each promising greater accuracy, faster convergence, and better generalization. As researchers, we ask which model performs best, whether a transformer can outperform a convolutional network, or whether the latest foundation model can solve problems that previously seemed out of reach.Despite the growth of AI research in medical imaging, few models have made the transition from prom
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.