AI Article Synopsis

  • Dual-energy CT (DECT) is used to non-invasively detect monosodium urate crystals in gout, and an automated deep-learning (DL) tool was developed to improve detection efficiency.
  • A study comparing readings with and without the DL tool showed that it significantly reduced reading time for trainee radiologists but not for experienced ones, while confidence levels remained the same for both groups.
  • The DL tool also helped identify small MSU deposits and changed diagnoses positively in a few cases, ultimately suggesting it can enhance diagnostic accuracy for less experienced readers.

Article Abstract

Introduction: Dual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Manually identifying these foci (most commonly labeled green) is tedious, and an automated detection system could streamline the process. This study aims to evaluate the impact of a deep-learning (DL) algorithm developed for detecting green pixelations on DECT on reader time, accuracy, and confidence.

Methods: We collected a sample of positive and negative DECTs, reviewed twice-once with and once without the DL tool-with a 2-week washout period. An attending musculoskeletal radiologist and a fellow separately reviewed the cases, simulating clinical workflow. Metrics such as time taken, confidence in diagnosis, and the tool's helpfulness were recorded and statistically analyzed.

Results: We included thirty DECTs from different patients. The DL tool significantly reduced the reading time for the trainee radiologist ( = 0.02), but not for the attending radiologist ( = 0.15). Diagnostic confidence remained unchanged for both ( = 0.45). However, the DL model identified tiny MSU deposits that led to a change in diagnosis in two cases for the in-training radiologist and one case for the attending radiologist. In 3/3 of these cases, the diagnosis was correct when using DL.

Conclusions: The implementation of the developed DL model slightly reduced reading time for our less experienced reader and led to improved diagnostic accuracy. There was no statistically significant difference in diagnostic confidence when studies were interpreted without and with the DL model.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10909828PMC
http://dx.doi.org/10.3389/fradi.2024.1330399DOI Listing

Publication Analysis

Top Keywords

automated detection
8
msu deposits
8
reduced reading
8
reading time
8
attending radiologist
8
diagnostic confidence
8
radiologist
5
deep-learning automated
4
msu
4
detection msu
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!