Query-by-example surgical activity detection
- 681 Downloads
Easy acquisition of surgical data opens many opportunities to automate skill evaluation and teaching. Current technology to search tool motion data for surgical activity segments of interest is limited by the need for manual pre-processing, which can be prohibitive at scale. We developed a content-based information retrieval method, query-by-example (QBE), to automatically detect activity segments within surgical data recordings of long duration that match a query.
The example segment of interest (query) and the surgical data recording (target trial) are time series of kinematics. Our approach includes an unsupervised feature learning module using a stacked denoising autoencoder (SDAE), two scoring modules based on asymmetric subsequence dynamic time warping (AS-DTW) and template matching, respectively, and a detection module. A distance matrix of the query against the trial is computed using the SDAE features, followed by AS-DTW combined with template scoring, to generate a ranked list of candidate subsequences (substrings). To evaluate the quality of the ranked list against the ground-truth, thresholding conventional DTW distances and bipartite matching are applied. We computed the recall, precision, F1-score, and a Jaccard index-based score on three experimental setups. We evaluated our QBE method using a suture throw maneuver as the query, on two tool motion datasets (JIGSAWS and MISTIC-SL) captured in a training laboratory.
We observed a recall of 93, 90 and 87 % and a precision of 93, 91, and 88 % with same surgeon same trial (SSST), same surgeon different trial (SSDT) and different surgeon (DS) experiment setups on JIGSAWS, and a recall of 87, 81 and 75 % and a precision of 72, 61, and 53 % with SSST, SSDT and DS experiment setups on MISTIC-SL, respectively.
We developed a novel, content-based information retrieval method to automatically detect multiple instances of an activity within long surgical recordings. Our method demonstrated adequate recall across different complexity datasets and experimental conditions.
KeywordsQuery-by-example Stacked denoising autoencoder Asymmetric subsequence dynamic time warping Surgical data indexing Surgical activity detection
We acknowledge Intuitive Surgical Inc., Sunnyvale, CA for facilitating capture of data from the da Vinci Surgical Systems for the JIGSAWS and MISTIC-SL datasets. We would also like to thank Anand Malpani and Madeleine Waldram for the MISTIC-SL dataset collection and processing.
Compliance with ethical standards
Conflicts of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
The Johns Hopkins Science of Learning Institute provided a research grant to conduct the study that yielded the MISTIC-SL dataset. Y. Gao was supported by Department of Computer Science, The Johns Hopkins University.
Informed consent was obtained from all individual participants included in the MISTIC-SL study. The JIGSAWS dataset is publicly accessible.
- 1.Ahmidi N, Gao Y, Béjar B, Vedula SS, Khudanpur S, Vidal R, Hager GD (2013) String motif-based description of tool motion for detecting skill and gestures in robotic surgery. In: Medical image computing and computer-assisted intervention–MICCAI 2013. Springer, Nagoya, JapanGoogle Scholar
- 2.Béjar B, Zappella L, Vidal R (2012) Surgical gesture classification from video data. In: Medical image computing and computer-assisted intervention—MICCAI 2012. Springer, Nice, France, pp 34–41Google Scholar
- 3.Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 19:153–160Google Scholar
- 4.Carlin M, Thomas S, Jansen A, Hermansky H (2011) Rapid evaluation of speech representations for spoken term discovery. In: Proceedings of the annual conference of the international speech communication association, INTERSPEECH, pp 821–824Google Scholar
- 5.Gao Y, Vedula SS, Reiley CE, Ahmidi N, Varadarajan B, Lin HC, Tao L, Zappella L, Bejar B, Yuh DD, Chen CCG, Vidal R, Khudanpur S, Hager GD (2014) The JHU-ISI gesture and skill assessment dataset (JIGSAWS): a surgical activity working set for human motion modeling. In: Medical image computing and computer-assisted intervention M2CAI—MICCAI workshopGoogle Scholar
- 6.Gao Y, Vedula SS, Lee GI, Lee MR, Khudanpur S, Hager GD (2016) Unsupervised surgical data alignment with application to automatic activity annotation. In: Proceedings of the IEEE international conference on robotics and automation—ICRA 2016 (Accepted)Google Scholar
- 7.Hazen T, Shen W, White C (2009) Query-by-example spoken term detection using phonetic posteriorgram templates. In: IEEE workshop on automatic speech recognition understanding, 2009. ASRU 2009, pp 421–426Google Scholar
- 8.Lea C, Hager GD, Vidal R (2015) An improved model for segmentation and recognition of fine-grained activities with application to surgical training tasks. In: 2015 IEEE Winter Conference on applications of computer vision (WACV), pp 1123–1129Google Scholar
- 9.Lea C, Vidal R, Hager GD (2016) Learning convolutional action primitives from multimodal timeseries data. In: Proceedings of the IEEE international conference on robotics and automation—ICRA 2016 (Accepted)Google Scholar
- 11.Muller M (2007) Dynamic time warping. In: Information retrieval for music and motion. Springer, New YorkGoogle Scholar
- 12.Palm RB (2012) Prediction as a candidate for learning deep hierarchical models of data. Master’s thesisGoogle Scholar
- 14.Sefati S, Cowan NJ, Vidal R (2015) Learning shared, discriminative dictionaries for surgical gesture segmentation and classification. In: Modeling and monitoring of computer assisted interventions (M2CAI)—MICCAI workshopGoogle Scholar
- 15.Tao L, Elhamifar E, Khudanpur S, Hager GD, Vidal R (2012) Sparsehidden markov models for surgical gesture classification and skill evaluation. In: Information processing in computer-assisted interventions. Springer, Berlin, vol 7330, pp 167–177Google Scholar
- 16.Tao L, Zappella L, Hager GD, Vidal R (2013) Surgical gesture segmentation and recognition. In: Medical image computing and computer-assisted intervention—MICCAI 2013, Nagoya, JapanGoogle Scholar
- 17.Twinanda AP, de Mathelin M, Padoy N (2014) Fisher kernel based task boundary retrieval in laparoscopic database with single video query. In: Medical image computing and computer-assisted intervention—MICCAI 2014, Boston, MAGoogle Scholar
- 18.Varadarajan B, Reiley CE, Lin HC, Khudanpur S, Hager GD (2009) Data-derived models for segmentation with application to surgical assessment and training. In: Medical image computing and computer-assisted intervention—MICCAI 2009, Springer, pp 426–434Google Scholar
- 19.Vedula SS, Malpani A, Ahmidi N, Khudanpur S, Hager G, Chen CCG (2016) Task-level vs. segment-level quantitative metrics for surgical skill assessment. J Surg Educ 73(2). doi: 10.1016/j.jsurg.2015.11.009
- 20.Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning—ICML ’08, pp 1096–1103Google Scholar