Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery
Abstract Laparoscopic pancreatic surgery remains highly challenging due to the complexity of the pancreas and surrounding vascular structures, with risk of injuring critical blood vessels such as the Superior Mesenteric Vein (SMV)-Portal Vein (PV) axis and splenic vein. Here, we evaluated the High R...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01663-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849314872462934016 |
|---|---|
| author | Jile Shi Ruohan Cui Zhihong Wang Qi Yan Lu Ping Hu Zhou Junyi Gao Chihua Fang Xianlin Han Surong Hua Wenming Wu |
| author_facet | Jile Shi Ruohan Cui Zhihong Wang Qi Yan Lu Ping Hu Zhou Junyi Gao Chihua Fang Xianlin Han Surong Hua Wenming Wu |
| author_sort | Jile Shi |
| collection | DOAJ |
| description | Abstract Laparoscopic pancreatic surgery remains highly challenging due to the complexity of the pancreas and surrounding vascular structures, with risk of injuring critical blood vessels such as the Superior Mesenteric Vein (SMV)-Portal Vein (PV) axis and splenic vein. Here, we evaluated the High Resolution Network (HRNet)-Full Convolutional Network (FCN) model for its ability to accurately identify vascular contours and improve surgical safety. Using 12,694 images from 126 laparoscopic distal pancreatectomy (LDP) videos and 35,986 images from 138 Whipple procedure videos, the model demonstrated robust performance, achieving a mean Dice coefficient of 0.754, a recall of 85.00%, and a precision of 91.10%. By combining datasets from LDP and Whipple procedures, the model showed strong generalization across different surgical contexts and achieved real-time processing speeds of 11 frames per second during surgery process. These findings highlight HRNet-FCN’s potential to recognize anatomical landmarks, enhance surgical precision, reduce complications, and improve laparoscopic pancreatic outcomes. |
| format | Article |
| id | doaj-art-5892a8b9ec2b40b28402aa0344e3c7dd |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-5892a8b9ec2b40b28402aa0344e3c7dd2025-08-20T03:52:19ZengNature Portfolionpj Digital Medicine2398-63522025-05-01811810.1038/s41746-025-01663-6Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgeryJile Shi0Ruohan Cui1Zhihong Wang2Qi Yan3Lu Ping4Hu Zhou5Junyi Gao6Chihua Fang7Xianlin Han8Surong Hua9Wenming Wu10Peking Union Medical College, Chinese Academy of Medical SciencesPeking Union Medical College, Chinese Academy of Medical SciencesPeking Union Medical College, Chinese Academy of Medical SciencesSchool of Life Sciences, Tsinghua UniversityPeking Union Medical College, Chinese Academy of Medical SciencesPeking Union Medical College, Chinese Academy of Medical SciencesPeking Union Medical College, Chinese Academy of Medical SciencesDepartment of Hepatobiliary Surgery I, Zhujiang Hospital Southern Medical UniversityPeking Union Medical College, Chinese Academy of Medical SciencesPeking Union Medical College, Chinese Academy of Medical SciencesPeking Union Medical College, Chinese Academy of Medical SciencesAbstract Laparoscopic pancreatic surgery remains highly challenging due to the complexity of the pancreas and surrounding vascular structures, with risk of injuring critical blood vessels such as the Superior Mesenteric Vein (SMV)-Portal Vein (PV) axis and splenic vein. Here, we evaluated the High Resolution Network (HRNet)-Full Convolutional Network (FCN) model for its ability to accurately identify vascular contours and improve surgical safety. Using 12,694 images from 126 laparoscopic distal pancreatectomy (LDP) videos and 35,986 images from 138 Whipple procedure videos, the model demonstrated robust performance, achieving a mean Dice coefficient of 0.754, a recall of 85.00%, and a precision of 91.10%. By combining datasets from LDP and Whipple procedures, the model showed strong generalization across different surgical contexts and achieved real-time processing speeds of 11 frames per second during surgery process. These findings highlight HRNet-FCN’s potential to recognize anatomical landmarks, enhance surgical precision, reduce complications, and improve laparoscopic pancreatic outcomes.https://doi.org/10.1038/s41746-025-01663-6 |
| spellingShingle | Jile Shi Ruohan Cui Zhihong Wang Qi Yan Lu Ping Hu Zhou Junyi Gao Chihua Fang Xianlin Han Surong Hua Wenming Wu Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery npj Digital Medicine |
| title | Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery |
| title_full | Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery |
| title_fullStr | Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery |
| title_full_unstemmed | Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery |
| title_short | Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery |
| title_sort | deep learning hrnet fcn for blood vessel identification in laparoscopic pancreatic surgery |
| url | https://doi.org/10.1038/s41746-025-01663-6 |
| work_keys_str_mv | AT jileshi deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT ruohancui deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT zhihongwang deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT qiyan deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT luping deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT huzhou deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT junyigao deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT chihuafang deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT xianlinhan deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT suronghua deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery AT wenmingwu deeplearninghrnetfcnforbloodvesselidentificationinlaparoscopicpancreaticsurgery |