Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery
Abstract Background A persistent problem with robot-assisted minimally invasive surgery is soft tissue damage caused by the exertion of excessive force due to the surgeon’s lack of direct access to the surgical site. A solution to predict clamp force accurately is needed to enhance surgical safety a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Surgery |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12893-025-03121-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238183236075520 |
|---|---|
| author | Yong-Li Yan Teng Ren Li Ding Tiansheng Sun Shandeng Huang |
| author_facet | Yong-Li Yan Teng Ren Li Ding Tiansheng Sun Shandeng Huang |
| author_sort | Yong-Li Yan |
| collection | DOAJ |
| description | Abstract Background A persistent problem with robot-assisted minimally invasive surgery is soft tissue damage caused by the exertion of excessive force due to the surgeon’s lack of direct access to the surgical site. A solution to predict clamp force accurately is needed to enhance surgical safety and efficiency. Methods The current proposal concerns a deep learning-based solution utilizing a backpropagation neural network (BPNN) optimized by improved sparrow search algorithm (ISSA) to predict clamp force on soft tissue. This method optimizes the BPNN using ISSA and combines dynamic parameters and geometric characteristics, such as contact area of the clamp blade, loading speed, displacement and time, during clamping to predict clamping force on soft tissue. Circular chaotic mapping, golden sine and crisscross strategies were introduced to increase sparrow search algorithm performance, enabling ISSA-optimized BP to achieve substantial improvements in precision and prediction speed for estimating soft tissue clamping force. Results The ISSA-BP clamping force prediction model outperforms the BP, ALO-BP, GA-BP, GWO-BP, WOA-BP and SSA-BP models for model evaluation indicators such as RMSE, MSE, MAE, SSE and R². The R² of ISSA-BPNN is 99.24%. Conclusions The enhanced ISSA-BPNN model demonstrates superior performance in predicting clamp force on soft tissues during robot-assisted surgeries. The novel method has the potential to increase surgical safety, accuracy and efficiency, representing an advance in the field of surgical robotics. |
| format | Article |
| id | doaj-art-e77a4ec184bc4e29b32a5fad11bb08cc |
| institution | Kabale University |
| issn | 1471-2482 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Surgery |
| spelling | doaj-art-e77a4ec184bc4e29b32a5fad11bb08cc2025-08-20T04:01:42ZengBMCBMC Surgery1471-24822025-08-0125111410.1186/s12893-025-03121-2Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgeryYong-Li Yan0Teng Ren1Li Ding2Tiansheng Sun3Shandeng Huang4Beijing Advanced Innovation Center for Biomedical Engineering, Beihang UniversitySchool of Mechanical Engineering, Shenyang University of TechnologyBeijing Advanced Innovation Center for Biomedical Engineering, Beihang UniversityThe Fourth Medical Center of China General Hospital of People’s Liberation ArmyNovaTimes Intelligent Technology (Chengdu) Co., LtdAbstract Background A persistent problem with robot-assisted minimally invasive surgery is soft tissue damage caused by the exertion of excessive force due to the surgeon’s lack of direct access to the surgical site. A solution to predict clamp force accurately is needed to enhance surgical safety and efficiency. Methods The current proposal concerns a deep learning-based solution utilizing a backpropagation neural network (BPNN) optimized by improved sparrow search algorithm (ISSA) to predict clamp force on soft tissue. This method optimizes the BPNN using ISSA and combines dynamic parameters and geometric characteristics, such as contact area of the clamp blade, loading speed, displacement and time, during clamping to predict clamping force on soft tissue. Circular chaotic mapping, golden sine and crisscross strategies were introduced to increase sparrow search algorithm performance, enabling ISSA-optimized BP to achieve substantial improvements in precision and prediction speed for estimating soft tissue clamping force. Results The ISSA-BP clamping force prediction model outperforms the BP, ALO-BP, GA-BP, GWO-BP, WOA-BP and SSA-BP models for model evaluation indicators such as RMSE, MSE, MAE, SSE and R². The R² of ISSA-BPNN is 99.24%. Conclusions The enhanced ISSA-BPNN model demonstrates superior performance in predicting clamp force on soft tissues during robot-assisted surgeries. The novel method has the potential to increase surgical safety, accuracy and efficiency, representing an advance in the field of surgical robotics.https://doi.org/10.1186/s12893-025-03121-2Surgical interaction force estimationBP neural networkSparrow search algorithmCircle chaotic mappingGolden sine strategyRobot-assisted surgery |
| spellingShingle | Yong-Li Yan Teng Ren Li Ding Tiansheng Sun Shandeng Huang Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery BMC Surgery Surgical interaction force estimation BP neural network Sparrow search algorithm Circle chaotic mapping Golden sine strategy Robot-assisted surgery |
| title | Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery |
| title_full | Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery |
| title_fullStr | Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery |
| title_full_unstemmed | Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery |
| title_short | Robust prediction of tool-tissue interaction force using ISSA-optimized BP neural networks in robotic surgery |
| title_sort | robust prediction of tool tissue interaction force using issa optimized bp neural networks in robotic surgery |
| topic | Surgical interaction force estimation BP neural network Sparrow search algorithm Circle chaotic mapping Golden sine strategy Robot-assisted surgery |
| url | https://doi.org/10.1186/s12893-025-03121-2 |
| work_keys_str_mv | AT yongliyan robustpredictionoftooltissueinteractionforceusingissaoptimizedbpneuralnetworksinroboticsurgery AT tengren robustpredictionoftooltissueinteractionforceusingissaoptimizedbpneuralnetworksinroboticsurgery AT liding robustpredictionoftooltissueinteractionforceusingissaoptimizedbpneuralnetworksinroboticsurgery AT tianshengsun robustpredictionoftooltissueinteractionforceusingissaoptimizedbpneuralnetworksinroboticsurgery AT shandenghuang robustpredictionoftooltissueinteractionforceusingissaoptimizedbpneuralnetworksinroboticsurgery |