Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2024 Mar 1;14:5089. doi: 10.1038/s41598-024-51777-2

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2024

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Deep learning attention maps overlaid on computed tomography images of patients in the test dataset. (A) A preoperative axial computed tomography image of a 76-year-old man with a pancreatic cancer in the head of pancreas (not shown). In both attention maps of the deep learning models for predicting the occurrence of (B) in all postoperative pancreatic fistula and (C) clinically relevant postoperative pancreatic fistula, the activated gradient regions focused on the area in the head of pancreas and peripancreatic area around the potential pancreatic resection site. In this patient, the postoperative course was uneventful. (D) A preoperative axial computed tomography image of a 74-year-old man diagnosed with distal bile duct cancer (not shown) who experienced Grade B postoperative pancreatic fistula following pancreaticoduodenectomy. In the attention maps of the deep learning models for predicting the occurrence of (E) all postoperative pancreatic fistula and (F) clinically relevant postoperative pancreatic fistula, the attention of both models is found predominantly in the area around the expected pancreatic resection site. POPF postoperative pancreatic fistula, CR-POPF clinically relevant postoperative pancreatic fistula.