No gold standard needed: Method ranks the precision of medical imaging measurements
Advances in medical imaging and artificial intelligence (AI) have revolutionized many aspects of medical practice in recent years. Quantitative measurements derived from medical images are increasingly being used to support diagnosis and clinical decision-making. Consequently, many new quantitative imaging tools, including those based on AI, are being developed.
Advances in medical imaging and artificial intelligence have transformed medical practice, with quantitative measurements from images aiding diagnosis and clinical decisions. However, assessing the reliability of these tools can be difficult, especially when true values are unknown. A research team at Washington University in St. Louis has developed a technique called NGSE-Corr to objectively evaluate the precision of medical imaging methods, even without a gold standard or true value.
This method accounts for correlated noise in measurement, which can be an issue when using multiple tools to measure the same clinical property. In virtual trials involving three SPECT methods for measuring tumor activity in patients with prostate cancer, NGSE-Corr accurately ranked the methods in 91% of trials with 50 virtual patients and identified the most precise method in 95% of cases.
The technique has potential applications for researchers developing new imaging methods, physicians using different tools for decision-making, and regulators evaluating new technologies.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
