Imaging Informatics

Mammography acquisition parameters affect both AI, radiologist reads
By Kate Madden Yee
The findings could help clinicians better develop "effective strategies for the clinical integration of AI," researchers noted.
September 18, 2025
Ai Hand
AI model detects achalasia on chest x-rays
By Will Morton
Currently, few noninvasive tests are available for diagnosing the swallowing condition.
September 18, 2025
Saliency maps using Grad-CAM++ (E and H) show the model’s point of interest in chest radiographs (C and F) of patients with achalasia. The model’s point of interest is highlighted with red, yellow, and green. In both the upper and lower panels (E and H), the point of interest is located in a region around the upper esophagus that corresponds to an air esophagogram and/or air-fluid level in the esophagus in the barium esophagogram (D and G).
AI model uses mammograms to predict cardiovascular risk
By Amerigo Allegretto
The researchers report that the algorithm is on par with traditional cardiovascular risk equations.
September 17, 2025
Heart Artificial Intelligence Ai 400
Cardiac MRI measures aid in predicting future MACE after heart attack
By Liz Carey
Left atrial minimum volume index can help predict future major adverse cardiovascular events (MACE) after acute myocardial infarction.
September 16, 2025
2025 09 16 Ami Mace Study Radiology Thumbnail
DL algorithm estimates lung nodule cancer risk, reduces false positives
By Kate Madden Yee
The deep-learning (DL) tool reduced false-positive results by almost 40% and showed high cancer detection rates.
September 16, 2025
2025 09 16 Radiology Antonissen Fig4 Thumbnail
LLMs perform well on Japanese radiology board exam
By Will Morton
So far, LLMs have passed text-based radiology exams but their image interpretation capabilities have not been impressive.
September 15, 2025
Question 4 from the Japan Diagnostic Radiology Board Examination 2024, representing a clinical scenario of a man in his 30s presented with transient dysphasia. The question asks to identify the most probable diagnosis from the following options: (a) glioblastoma, (b) hemangioblastoma, (c) metastatic brain tumor, (d) oligodendroglioma, and (e) primary central nervous system lymphoma (PCNSL). The correct answer is (d) oligodendroglioma. The figure also includes a summary of responses from four large language models, along with their legitimacy scores rated by diagnostic radiologists.
Medicare pays about one-third of radiology SaaS AI claims
By Will Morton
Between 2018 and 2023, radiologists received $8 million in payments but were denied a potential $16.4 million.
September 11, 2025
Ai Money
4 ways AI is modernizing MRI to solve radiology’s toughest problems
By Roland Rott
AI can play a key role in MRI in several ways, including helping to reduce wait times and addressing radiologist burnout.
September 11, 2025
Roland Rott.
General-purpose LLMs can be used to track true critical findings
By Liz Carey
Experts from Stanford and Mayo Clinic Arizona tested few-shot prompting effectiveness with GPT-4 and Mistral-7B.
September 10, 2025
Chatgpt Artificial Intelligence Ai Head n9f Ar0 G2 Ll
Experts propose generalist radiology AI framework
By Liz Carey
A team of researchers outlined five key features of diagnostic generalist radiology AI (GRAI).
September 9, 2025
2025 09 09 Generalist Radiology Ai Six Diagnoses Thumbnail
Bayer pivots away from AI platform business
By Erik L. Ridley
Bayer is discontinuing its Calantic Digital Solutions platform as well as products and services from its Blackford Analysis subsidiary.
September 8, 2025
Bayer Thumbnail
Agentic AI as the new infrastructure for interoperability
By Rishi Nayyar
Agentic AI can improve interoperability in imaging, according to a column by PocketHealth Co-founder and CEO Rishi Nayyar.
September 3, 2025
Nayyar Rishi Thumbnail
Page 1 of 1844
Next Page