Prediction of puncturing events through LSTM for multilayer tissue

Area of Science:

• Biomedical Engineering
• Machine Learning
• Robotics

Background:

• Accurate detection of penetration events in multilayer tissue is crucial for surgical procedures and medical diagnostics.
• Traditional methods may lack the precision and real-time feedback required for complex tissue interactions.

Purpose of the Study:

• To develop and validate a novel method for detecting penetration events in multilayer tissue using Long Short-Term Memory (LSTM) networks.
• To enhance the precision and safety of medical procedures involving multilayer tissue interaction.

Main Methods:

• Collected time-series insertion force data using sensors integrated with a 1-DOF prismatic robot during tissue penetration.
• Processed the sensor data with a trained LSTM network to recognize patterns indicative of penetration events across tissue layers.

Main Results:

• The LSTM network demonstrated high accuracy and reliability in detecting penetration events in multilayer tissue.
• Experimental validation confirmed the effectiveness of the proposed method.

Conclusions:

• The developed LSTM-based technique offers a significant advancement over traditional methods for penetration event detection.
• This non-invasive, real-time solution improves the precision and safety of medical procedures involving multilayer tissue interaction.