Summary of Machine Learning-based Automated Assessment Of Intracorporeal Suturing in Laparoscopic Fundoplication, by Shekhar Madhav Khairnar et al.
Machine Learning-Based Automated Assessment of Intracorporeal Suturing in Laparoscopic Fundoplication
by Shekhar Madhav Khairnar, Huu Phong Nguyen, Alexis Desir, Carla Holcomb, Daniel J. Scott, Ganesh Sankaranarayanan
First submitted to arxiv on: 16 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed AI-based tool tracking model utilizes the Segment Anything Model (SAM) to automatically assess surgical skills in laparoscopic tasks. The study evaluates the usefulness of this model during a laparoscopic suturing task in the fundoplication procedure. Surgeons were grouped as novices and experts, and their tool motions were extracted using a low-pass filter with a 24 Hz cut-off frequency. Kinematic features such as RMS velocity, RMS acceleration, RMS jerk, total path length, and Bimanual Dexterity were analyzed using various machine learning models, including Logistic Regression, Random Forest, Support Vector Classifier, and XGBoost. The study achieved an accuracy of 0.795 and an F1 score of 0.778 with supervised learning and PCA, while the unsupervised 1-D CNN achieved superior results with an accuracy of 0.817 and an F1 score of 0.806. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses AI to help doctors learn new surgical skills. It develops a special model that can track tool movements in real-time without needing human help. The model is tested on videos of surgeons performing a specific type of surgery, and it’s able to accurately assess their performance. This could be very helpful for training surgeons and making sure they’re good enough to operate safely. |
Keywords
» Artificial intelligence » Cnn » F1 score » Logistic regression » Machine learning » Pca » Random forest » Sam » Supervised » Tracking » Unsupervised » Xgboost
