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.
CT Study: AI Algorithm Comparable to Radiologists in Differentiating Small Renal Masses
May 14th 2024An emerging deep learning algorithm had a lower AUC and sensitivity than urological radiologists for differentiating between small renal masses on computed tomography (CT) scans but had a 21 percent higher sensitivity rate than non-urological radiologists, 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.
Study Finds High Concordance Between AI and Radiologists for Cervical Spine Fractures on CT
May 6th 2024Researchers found a 98.3 percent concordance between attending radiology reports and AI assessments for possible cervical spine fractures on CT, according to new research presented at the 2024 ARRS Annual Meeting.