Experts from Stanford and Mayo Clinic Arizona tested few-shot prompting effectiveness with GPT-4 and Mistral-7B.
We scan the top radiology sources so you don’t have to.
From AI breakthroughs to imaging trends, we serve up real-time radiology insights.
-
Experts propose generalist radiology AI framework
A team of researchers outlined five key features of diagnostic generalist radiology AI (GRAI).
-
Bayer pivots away from AI platform business
Bayer is discontinuing its Calantic Digital Solutions platform as well as products and services from its Blackford Analysis subsidiary…
-
Agentic AI as the new infrastructure for interoperability
Agentic AI can improve interoperability in imaging, according to a column by PocketHealth Co-founder and CEO Rishi Nayyar.
-
AI interpretation leads to high NPV, recall rates in breast imaging
In a new study, an AI system reached near-perfect negative predictive value (NPV) in breast imaging but almost doubled the recall…
-
Patient-facing AI shifts focus from reports to relationships
AI’s patient-facing side has not been adequately explored, according to this column from Intelerad CEO Jordan Bazinsky.
-
Should hospitals pursue local domain LLM adaptation for radiology reports?
Specialized large language model (LLM) fine-tuned for summarizing free-text radiology findings performed better than GPT-4o.
-
AI model shows promise in diagnosing prostate cancer
The sensitivity of the model was comparable to that of nuclear medicine physicians.
-
'Habitat' AI model shows promise for stratifying lung nodule disease risk on LDCT
This type of model has an edge on its 2D and radiomics counterparts, researchers reported.
-
'Habitat' AI model helps stratify lung nodule disease risk on LDCT
This type of model has an edge on its 2D and radiomics counterparts, researchers reported.