Related Experiment Video
Updated: May 23, 2025
07:27
Robotics in Surgery: A Modular Robotic Platform Driven Gastric Wedge Resection
Published on: February 7, 2025
401
Development of a deep learning-based model for guiding a dissection during robotic breast surgery
Jeea Lee1,2, Sungwon Ham3, Namkug Kim4,5
1Department of Surgery, Uijeongbu Eulji Medical Center, Eulji University, Uijeongbu-si, Gyeonggi-do, South Korea.
Breast Cancer Research : BCR
|March 11, 2025
Summary
This study developed a deep learning (DL) model to guide robotic mastectomy dissection planes. The DL surgical guide shows potential for training new surgeons and improving robotic breast surgery skills.
Area of Science:
- Medical Artificial Intelligence
- Surgical Robotics
- Computer-Assisted Surgery
Background:
- Traditional surgical education relies on observation and assistance.
- Deep learning (DL) advances enable surgical view recognition and landmark identification.
- No prior studies developed surgical guides for robotic breast surgery.
Purpose of the Study:
- To develop a DL model for guiding dissection planes in robotic mastectomy.
- To create a training tool for beginners and trainees in robotic breast surgery.
Main Methods:
- Ten robotic mastectomy videos were analyzed, extracting 8,834 frames.
- Ground truth delineations were performed by two experienced surgeons.
- The DL model was evaluated using Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD).
Main Results:
- The DL model achieved a DSC of 0.828 and HD of 9.80 for skin flap dissection.
- A total of 428 images were used for training, validation, and testing.
- The model demonstrated effectiveness in identifying surgical landmarks during robotic mastectomy.
Conclusions:
- Deep learning can function as an effective surgical guide for robotic mastectomy.
- The developed DL model can enhance surgical skills for trainees.
- DL-based surgical guidance holds promise for improving robotic breast surgery education.
