Bonn 2025 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
QI: Fachverband Quanteninformation
QI 36: Poster – Quantum Information (joint session QI/Q)
QI 36.7: Poster
Thursday, March 13, 2025, 17:00–19:00, Tent
Surgical Procedure Recognition Using Quantum Machine Learning — •Abdul Razak Nuhu1,2, Peter Nimbe1, Mohammed Mustapha Adamu1, and Eliezer Ofori Odei-Lartey2 — 1Department of Computer Science and Informatics, UENR, P. O. Box 214, Sunyani, Ghana — 2Kintampo Health Research Centre, Kintampo, Ghana
Surgical procedure recognition is a critical field in robotic-assisted surgery that focuses on identifying complex surgical tasks like suturing, needle passing, and knot tying. This research explores Quantum Machine Learning (QML) algorithms, specifically the Quantum Support Vector Classifier (QSVC), to analyze surgical gestures more effectively than traditional methods. Using the JIGSAWS dataset with 76 motion characteristics, the study compared QSVC performance against a conventional Support Vector Classifier (SVC) using metrics like accuracy, precision, recall, and F1-score. The results demonstrated that QML-derived models significantly outperform classical machine learning techniques in processing surgical kinematic data. The research suggests that QML has transformative potential in surgical robotics and gesture recognition, particularly as quantum computing advances. By providing more sophisticated analysis of surgical procedures, this approach promises to enhance real-time surgical support, improve medical education, and ultimately develop more context-aware surgical systems that could improve patient care.
Keywords: Quantum Machine Learning; Surgical Procedure Recognition; JIGSAWS Dataset; Quantum Support Vector Classifier; Surgical Gesture Identification