In a new podcast episode, Joseph Cavallo, MD, MBA, offered his perspective on AI integration, potential efficiency gains, navigating post-deployment monitoring and how to incorporate AI literacy into radiology resident training.
|Slideshows|November 20, 2015
11 Radiology Speech Recognition Bloopers
Author(s)Liza Haar
If only speech recognition understood what radiologists were saying.
Advertisement
Radiologists don’t need a reminder that there are a lot of things wrong with radiology reports.Curtis Langlotz, MD, Ph.D., professor of radiology and medicine at Stanford University Medical Center wrote a book on how to improve the radiology report.The Radiology Report: A Guide to Thoughtful Communication for Radiologists and Other Medical Professionals touches on many of the challenges radiology reports present, including the general disagreement of what actually constitutes a good radiology report. The book offers helpful, actionable advice on creating radiology reports.But it also mentions one of the greatest frustrations of the radiology report: technology. Here, we’ve assembled 11 speech recognition bloopers Langlotz describes in his book. Because if we don’t laugh, we’ll cry.Â
Advertisement
Related to this article
The FFR-IQ software recently demonstrated a 92.2 percent sensitivity for non-invasive estimation of fractional flow reserve (FFRC) based on coronary CT angiography (CCTA) scans.
A Kaiser score > 5 with breast MRI demonstrated a 97 percent sensitivity and 87.9 percent specificity for predicting malignancy in patients with BI-RADS 0 or 4 presentations on mammography and breast ultrasound, according to a new study.
In a recent interview, Francesco Giganti, MD, PhD, discussed findings from a recent multicenter study demonstrating the ability of an AI software to provide significant clarity to initial PI-RADS 3 assessments on MRI and facilitate a nearly 19 percent reduction in unnecessary prostate biopsies.
The NEXT-Cue AI software, which incorporates analysis of brain MRI scans, reportedly facilitates prognostic assessments of potential progression from mild cognitive impairment (MCI) to Alzheimer’s disease within five years.
In a new podcast episode, Amir Iravani, MD, FRACP, discusses emerging dosimetry data from the COMPETE trial for 177Lu-edotreotide and how it may help facilitate more personalized treatment for patients with gastroenteropancreatic neuroendocrine tumors (GEP-NETs).
In a recent interview, Phillip Koo, MD, discussed emerging trends with AI, theranostics and empowered patients, and how these developments may lead to challenges and potential opportunities for radiologists and nuclear medicine physicians.
AI has to do more than show potential. It has to deliver measurable results.The Rad AI Outcomes and Market Impact Compendium brings together real-world clinical, operational and financial evidence from health systems, academic medical centers and radiology practices using Rad AI Reporting, Impressions and Continuity.Explore results including 60+ minutes saved per radiologist shift, a 47% reduction in report error rates, 70%+ patient follow-up adherence and >7x ROI — plus, case studies showing how organizations are translating AI into greater capacity, quality and financial performance.See what AI built specifically for radiology can deliver in practice.
Advertisement
Advertisement
Trending on Diagnostic Imaging
1
FDA Clears MRI-Based AI Software for Prognostic Evaluation of Patients with Mild Cognitive Impairment
2
Can MRI-Based AI Have an Impact in Reducing Unnecessary Prostate Biopsies?
3
FDA Clears AI-Enabled FFR-IQ Software for Estimating Fractional Flow Reserve from CCTA
4
Can the Kaiser Score with Breast MRI Improve Clarity for BI-RADS 0 and 4 Assessments on Mammography and Ultrasound?
5