WEDNESDAY, Sept. 21, 2022 (HealthDay News) — According to a study published online Sept. 13 in Radiology.

Po-Ting Chen, MD, of the National Taiwan University College of Medicine in Taipei, and colleagues developed and validated a DL-based tool for detecting pancreatic cancer on CT. CT studies with contrast medium in 546 patients diagnosed with pancreatic cancer between January 2006 and July 2018 were retrospectively collected and compared to CT studies of 733 controls with normal pancreas obtained between January 2004 and December 2019. segmentation convolutional neural (CNN) classifier and a clustered five-CNN classifier was developed and validated in the internal test set and a nationwide real-world validation set. McNemar’s test was used to compare the sensitivities of the computer-aided detection (CAD) tool and the radiologist’s interpretation.

The researchers found that the DL tool achieved 89.9 and 95.9 percent sensitivity and specificity, respectively, in the internal test set, with an area under the receiver operating characteristic curve (AUC) of 0, 96 and with no significant difference in sensitivity compared to the original radiologist. ratio (96.1%). The DL tool distinguished between malignant and control CT studies with a sensitivity of 89.7% and a specificity of 92.8% in a test set of 1,473 real-world CT studies (AUC, 0 .95); for malignant tumors smaller than 2 cm, the sensitivity was 74.7%.

“The CAD tool may be a useful adjunct for radiologists to improve pancreatic cancer detection,” the authors write.

An author disclosed financial ties to NVIDIA.

Editorial (subscription or payment may be required)