Radiologists using an automated lung nodule matching program significantly improved diagnostic efficiency.
Radiologists using an automated lung nodule matching program significantly improved diagnostic efficiency, according to results of a study published in the July issue of American Journal of Roentgenology.
“Pulmonary nodules may be benign or malignant, so we follow these nodules over time with repeated CT scans to watch for changes in each nodule,” said Chi Wan Koo, MD, lead author of the study. “When many nodules are present, it can be difficult to match nodules up for comparison purposes.”
Researchers from New York University Langone Medical Center in New York timed how long it took for four radiologists to assess each of 325 pulmonary modules, identified by CT, found in 57 patients. The radiologists identified and manually matched the pulmonary nodules on CT.
The same radiologists were evaluated again six weeks later, using the same CT images, but this time they were using the automated nodule matching software.
The researchers found that the nodule matching was significantly faster with the automated program, regardless of the interpreting physician. The maximal time saved with the automatic matching was 11.4 minutes. The software was particularly helpful when there were more nodules to be matched, as was matching nodules that were 6 mm or smaller, the researchers noted. The automated program achieved 90 percent, 90 percent, 79 percent, and 92 percent accuracy for the four readers.
As the radiologists became quicker at identifying the nodules, accuracy remained consistent with the automated program, from 79 percent to 92 percent of the time.
“Prior studies have evaluated automated nodule matching accuracy, however no study to our knowledge has assessed the impact of a nodule matching program use on CT interpretation efficiency, where efficiency entails both accuracy and speed,” said Koo.
What is the Best Use of AI in CT Lung Cancer Screening?
April 18th 2025In comparison to radiologist assessment, the use of AI to pre-screen patients with low-dose CT lung cancer screening provided a 12 percent reduction in mean interpretation time with a slight increase in specificity and a slight decrease in the recall rate, according to new research.
The Reading Room: Racial and Ethnic Minorities, Cancer Screenings, and COVID-19
November 3rd 2020In this podcast episode, Dr. Shalom Kalnicki, from Montefiore and Albert Einstein College of Medicine, discusses the disparities minority patients face with cancer screenings and what can be done to increase access during the pandemic.
Can CT-Based AI Radiomics Enhance Prediction of Recurrence-Free Survival for Non-Metastatic ccRCC?
April 14th 2025In comparison to a model based on clinicopathological risk factors, a CT radiomics-based machine learning model offered greater than a 10 percent higher AUC for predicting five-year recurrence-free survival in patients with non-metastatic clear cell renal cell carcinoma (ccRCC).
Could Lymph Node Distribution Patterns on CT Improve Staging for Colon Cancer?
April 11th 2025For patients with microsatellite instability-high colon cancer, distribution-based clinical lymph node staging (dCN) with computed tomography (CT) offered nearly double the accuracy rate of clinical lymph node staging in a recent study.