Background: Contrast-enhanced endoscopic ultrasound (CE-EUS) is useful for the differentiation of pancreatic tumors. Using deep learning for the segmentation and classification of pancreatic tumors might further improve the diagnostic capability of CE-EUS.
Aims: The aim of this study was to evaluate the capability of deep learning for the automatic segmentation of pancreatic tumors on CE-EUS video images and possible factors affecting the automatic segmentation.
Methods: This retrospective study included 100 patients who underwent CE-EUS for pancreatic tumors. The CE-EUS video images were converted from the originals to 90-s segments with six frames per second. Manual segmentation of pancreatic tumors from B-mode images was performed as ground truth. Automatic segmentation was performed using U-Net with 100 epochs and was evaluated with 4-fold cross-validation. The degree of respiratory movement (RM) and tumor boundary (TB) were divided into 3-degree intervals in each patient and evaluated as possible factors affecting the segmentation. The concordance rate was calculated using the intersection over union (IoU).
Results: The median IoU of all cases was 0.77. The median IoUs in TB-1 (clear around), TB-2, and TB-3 (unclear more than half) were 0.80, 0.76, and 0.69, respectively. The IoU for TB-1 was significantly higher than that of TB-3 (p < 0.01). However, there was no significant difference between the degrees of RM.
Conclusions: Automatic segmentation of pancreatic tumors using U-Net on CE-EUS video images showed a decent concordance rate. The concordance rate was lowered by an unclear TB but was not affected by RM.
Keywords: artificial intelligence; contrast enhanced; endoscopic ultrasound; microbubble; pancreatic cancer.