Assessment of Automated Identification of Phases in Videos of Cataract Surgery Using Machine Learning and Deep Learning Techniques

Key Points Question Are deep learning techniques sufficiently accurate to classify presegmented phases in videos of cataract surgery for subsequent automated skill assessment and feedback? Findings In this cross-sectional study including videos from a convenience sample of 100 cataract procedures, modeling time series of labels of instruments in use appeared to yield greater accuracy in classifying phases of cataract operations than modeling cross-sectional data on instrument labels, spatial video image features, spatiotemporal video image features, or spatiotemporal video image features with appended instrument labels. Meaning Time series models of instruments in use may serve to automate the identification of phases in cataract surgery, helping to develop efficient and effective surgical skill training tools in ophthalmology.

[1]  E. Leifer,et al.  Multiple Outputation: Inference for Complex Clustered Data by Averaging Analyses from Independent Data , 2003, Biometrics.

[2]  Accreditation Council for Graduate Medical Education Mourns Marvin R. Dunn, Director of Residency Review Committee Activities , 2003, Journal of Investigative Medicine.

[3]  N. Congdon,et al.  Prevalence of cataract and pseudophakia/aphakia among adults in the United States. , 2004, Archives of ophthalmology.

[4]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[5]  G. Binenbaum,et al.  Ophthalmology resident surgical competency: a national survey. , 2006, Ophthalmology (Rochester, Minn.).

[6]  Maria A. Woodward,et al.  The resident surgeon phacoemulsification learning curve. , 2007, Archives of ophthalmology.

[7]  P. McDonnell,et al.  Perceptions of recent ophthalmology residency graduates regarding preparation for practice. , 2007, Ophthalmology.

[8]  Pierre Jannin,et al.  Surgical Tools Recognition and Pupil Segmentation for Cataract Surgical Process Modeling , 2012, MMVR.

[9]  Pierre Jannin,et al.  A Framework for the Recognition of High-Level Surgical Tasks From Video Images for Cataract Surgeries , 2012, IEEE Transactions on Biomedical Engineering.

[10]  Chong-Wah Ngo,et al.  Multimedia modeling , 2013, Multimedia Tools and Applications.

[11]  S. Sikder,et al.  Cataract surgical skill assessment tools. , 2014, Journal of cataract and refractive surgery.

[12]  Gwénolé Quellec,et al.  Real-time recognition of surgical tasks in eye surgery videos , 2014, Medical Image Anal..

[13]  Mathieu Lamard,et al.  Indexing of cataract surgery video by content based video retrieval , 2014 .

[14]  Gwénolé Quellec,et al.  Real-Time Task Recognition in Cataract Surgery Videos Using Adaptive Spatiotemporal Polynomials , 2015, IEEE Transactions on Medical Imaging.

[15]  Fang Zhou,et al.  A VidEo-Based Intelligent Recognition and Decision System for the Phacoemulsification Cataract Surgery , 2015, Comput. Math. Methods Medicine.

[16]  A. Coleman,et al.  Cataract Surgery and Mortality in the United States Medicare Population. , 2016, Ophthalmology.

[17]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[18]  Su-Lin Lee,et al.  Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis , 2017, Lecture Notes in Computer Science.

[19]  Gwénolé Quellec,et al.  Real-time analysis of cataract surgery videos using statistical models , 2017, Multimedia Tools and Applications.

[20]  M. J. Hall,et al.  Ambulatory Surgery Data From Hospitals and Ambulatory Surgery Centers: United States, 2010. , 2017, National health statistics reports.

[21]  Klaus Schöffmann,et al.  Cataract-101: video dataset of 101 cataract surgeries , 2018, MMSys.

[22]  Gregory D. Hager,et al.  Crowdsourcing Annotation of Surgical Instruments in Videos of Cataract Surgery , 2018, CVII-STENT/LABELS@MICCAI.

[23]  Gwénolé Quellec,et al.  Monitoring tool usage in surgery videos using boosted convolutional and recurrent neural networks , 2018, Medical Image Anal..

[24]  Oliver Kramer,et al.  Multi-label Classification of Surgical Tools with Convolutional Neural Networks , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[25]  Klaus Schöffmann,et al.  Frame-Based Classification of Operation Phases in Cataract Surgery Videos , 2018, MMM.

[26]  Danail Stoyanov,et al.  DeepPhase: Surgical Phase Recognition in CATARACTS Videos , 2018, MICCAI.