(HealthDay News) — A deep learning (DL)-based tool may help detect pancreatic cancer on CT scans, according to a study published in Radiology.

Po-Ting Chen, MD, from the National Taiwan University College of Medicine in Taipei, and colleagues developed and validated a DL-based tool for detecting pancreatic cancer on CT.

Contrast-enhanced CT studies 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 a normal pancreas obtained between January 2004 and December 2019. The patients were divided into training, test, and validation sets.

Continue Reading

A segmentation convolutional neural network (CNN) and a classifier ensembling 5 CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The McNemar test was used to compare the sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation.

The DL tool achieved 89.9% and 95.9% 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 with the original radiologist report (96.1%).

In a set of 1473 real-world CT studies (669 malignant and 804 control), the DL tool distinguished between the malignant and control studies with 89.7% sensitivity and 92.8% specificity  (AUC, 0.95). For malignancies smaller than 2 cm, the sensitivity was 74.7%.

“The CAD tool may be a useful supplement for radiologists to enhance detection of pancreatic cancer,” the authors wrote.

One author disclosed financial ties to NVIDIA.

Abstract/Full Text

Editorial (subscription or payment may be required)