A Deep Learning Approach to Classify Surgical Skill in Microsurgery Using Force Data from a Novel Sensorised Surgical Glove
Authors:
- Jialang XuJXJialang Xu
- Dimitrios AnastasiouDADimitrios Anastasiou
- James BookerJBJames Booker
- Oliver E. BurtonOBOliver E. Burton
- Hugo Layard HorsfallHHHugo Layard Horsfall
- Carmen Salvadores FernandezCFCarmen Salvadores Fernandez
- Yang XueYXYang Xue
- Danail StoyanovDSDanail Stoyanov
- Manish K. TiwariMTManish K. Tiwari
- Hani J. MarcusHMHani J. Marcus
- Evangelos B. MazomenosEMEvangelos B. Mazomenos
Open Access
Abstract
Microsurgery serves as the foundation for numerous operative procedures. Given its highly technical nature, the assessment of surgical skill becomes an essential component of clinical practice and microsurgery education. The interaction forces between surgical tools and tissues play a pivotal role in surgical success, making them a valuable indicator of surgical skill. In this study, we employ six distinct deep learning architectures (LSTM, GRU, Bi-LSTM, CLDNN, TCN, Transformer) specifically designed for the classification of surgical skill levels. We use force data obtained from a novel sensorized surgical glove utilized during a microsurgical task. To enhance the performance of our models, we propose six data augmentation techniques. The proposed frameworks are accompanied by a comprehensive analysis, both quantitative and qualitative, including experiments conducted with two cross-validation schemes and interpretable visualizations of the network’s decision-making process. Our experimental results show that CLDNN and TCN are the top-performing models, achieving impressive accuracy rates of 96.16% and 97.45%, respectively. This not only underscores the effectiveness of our proposed architectures, but also serves as compelling evidence that the force data obtained through the sensorized surgical glove contains valuable information regarding surgical skill.Keywords
Funding Information
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- UCLH/UCL Biomedical Research Centre (BRC) Neuroscience (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- UCL Graduate Research Scholarship (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- EPSRC DTP Grant (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- ISAD Award (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- RAE Chair in Emerging Technologies (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- EPSRC Early Career Research Fellowship (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- fellowship from la Caixa foundation and UCL Mechanical Engineering (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
- Royal Society Wolfson fellowship (203145Z/16/Z, NS/A000050/1, P/S021930/1, EP/R513143/1, EP/T517793/1, CiET1819/2/36, EP/P012841/1, LCF/BQ/EU19/11710055, EP/X023974/1)
This publication has 48 references indexed in Scilit:
- Synthesis and Thermal Degradation Studies of Melamine Formaldehyde ResinsThe Scientific World Journal, 2014
- Development of force-based metrics for skills assessment in minimally invasive surgerySurgical Endoscopy, 2014
- Surgical Skill and Complication Rates after Bariatric SurgeryNew England Journal of Medicine, 2013
- The use of neural network and discrete Fourier transform for real-time evaluation of friction stir weldingApplied Soft Computing, 2011
- Optimal Acquisition and Assessment of Proficiency on Simulators in SurgerySurgical Clinics of North America, 2010
- History of MicrosurgeryPlastic and Reconstructive Surgery, 2009
- Training program and learning curve in experimental microsurgery during the residency in plastic surgeryMicrosurgery, 2007
- Analysis of errors enacted by surgical trainees during skills training coursesSurgery, 2005
- Real-valued fast Fourier transform algorithmsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Use of dynamic influence coefficients in forced vibration problems with the aid of fast fourier transformComputers & Structures, 1978