{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T15:07:43Z","timestamp":1775920063005,"version":"3.50.1"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100020194","name":"Wellcome\/EPSRC Centre for Interventional and Surgical Sciences","doi-asserted-by":"crossref","award":["203145\/Z\/16\/Z"],"award-info":[{"award-number":["203145\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/501100020194","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/P027938\/1"],"award-info":[{"award-number":["EP\/P027938\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R004080\/1"],"award-info":[{"award-number":["EP\/R004080\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/P012841\/1"],"award-info":[{"award-number":["EP\/P012841\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Royal Academy of Engineering Chair in Emerging Technologies Scheme"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"published-print":{"date-parts":[[2022,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose:<\/jats:title>\n                <jats:p>Workflow recognition can aid surgeons before an operation when used as a training tool, during an operation by increasing operating room efficiency, and after an operation in the completion of operation notes. Although several methods have been applied to this task, they have been tested on few surgical datasets. Therefore, their generalisability is not well tested, particularly for surgical approaches utilising smaller working spaces which are susceptible to occlusion and necessitate frequent withdrawal of the endoscope. This leads to rapidly changing predictions, which reduces the clinical confidence of the methods, and hence limits their suitability for clinical translation.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods:<\/jats:title>\n                <jats:p>Firstly, the optimal neural network is found using established methods, using endoscopic pituitary surgery as an exemplar. Then, prediction volatility is formally defined as a new evaluation metric as a proxy for uncertainty, and two temporal smoothing functions are created. The first (modal, <jats:inline-formula><jats:alternatives><jats:tex-math>$$M_n$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:msub>\n                      <mml:mi>M<\/mml:mi>\n                      <mml:mi>n<\/mml:mi>\n                    <\/mml:msub>\n                  <\/mml:math><\/jats:alternatives><\/jats:inline-formula>) mode-averages over the previous <jats:italic>n<\/jats:italic> predictions, and the second (threshold, <jats:inline-formula><jats:alternatives><jats:tex-math>$$T_n$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:msub>\n                      <mml:mi>T<\/mml:mi>\n                      <mml:mi>n<\/mml:mi>\n                    <\/mml:msub>\n                  <\/mml:math><\/jats:alternatives><\/jats:inline-formula>) ensures a class is only changed after being continuously predicted for <jats:italic>n<\/jats:italic> predictions. Both functions are independently applied to the predictions of the optimal network.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results:<\/jats:title>\n                <jats:p>The methods are evaluated on a 50-video dataset using fivefold cross-validation, and the optimised evaluation metric is weighted-<jats:inline-formula><jats:alternatives><jats:tex-math>$$F_1$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:msub>\n                      <mml:mi>F<\/mml:mi>\n                      <mml:mn>1<\/mml:mn>\n                    <\/mml:msub>\n                  <\/mml:math><\/jats:alternatives><\/jats:inline-formula> score. The optimal model is ResNet-50+LSTM achieving 0.84 in 3-phase classification and 0.74 in 7-step classification. Applying threshold smoothing further improves these results, achieving 0.86 in 3-phase classification, and 0.75 in 7-step classification, while also drastically reducing the prediction volatility.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion:<\/jats:title>\n                <jats:p>The results confirm the established methods generalise to endoscopic pituitary surgery, and show simple temporal smoothing not only reduces prediction volatility, but actively improves performance.\n<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-022-02599-y","type":"journal-article","created":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T10:44:40Z","timestamp":1648809880000},"page":"1445-1452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Reducing prediction volatility in the surgical workflow recognition of endoscopic pituitary surgery"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5682-9545","authenticated-orcid":false,"given":"Adrito","family":"Das","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophia","family":"Bano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco","family":"Vasconcelos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danyal Z.","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hani J","family":"Marcus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,1]]},"reference":[{"issue":"6","key":"2599_CR1","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1007\/s11102-021-01162-3","volume":"24","author":"HJ Marcus","year":"2021","unstructured":"Marcus HJ, Khan DZ, Borg A, Buchfelder M, Cetas JS, Collins JW, Dorward NL, Fleseriu M, Gurnell M, Javadpour M, Jones PS, Koh CH, Horsfall HL, Mamelak AN, Mortini P, Muirhead W, Oyesiku NM, Schwartz TH, Sinha S, Stoyanov D, Syro LV, Tsermoulas G, Williams A, Winder MJ, Zada G, Laws ER (2021) Pituitary society expert delphi consensus: operative workflow in endoscopic transsphenoidal pituitary adenoma resection. Pituitary 24(6):839\u2013853. https:\/\/doi.org\/10.1007\/s11102-021-01162-3","journal-title":"Pituitary"},{"issue":"3","key":"2599_CR2","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s11548-013-0940-5","volume":"9","author":"F Lalys","year":"2014","unstructured":"Lalys F, Jannin P (2014) Surgical process modelling: a review. IJCARS 9(3):495\u2013511. https:\/\/doi.org\/10.1007\/s11548-013-0940-5","journal-title":"Surgical process modelling: a review. IJCARS"},{"issue":"4","key":"2599_CR3","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1097\/sla.0000000000004425","volume":"273","author":"CR Garrow","year":"2021","unstructured":"Garrow CR, Kowalewski K-F, Li L, Wagner M, Schmidt MW, Engelhardt S, Hashimoto DA, Kenngott HG, Bodenstedt S, Speidel S, Muller-Stich BP, Nickel F (2021) Machine learning for surgical phase recognition: a systematic review. Ann Surg 273(4):684\u2013693. https:\/\/doi.org\/10.1097\/sla.0000000000004425","journal-title":"Ann Surg"},{"issue":"6","key":"2599_CR4","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1109\/TBME.2021.3054828","volume":"68","author":"B van Amsterdam","year":"2021","unstructured":"van Amsterdam B, Clarkson MJ, Stoyanov D (2021) Gesture recognition in robotic surgery: a review. IEEE Trans Biomed Engi 68(6):2021\u20132035. https:\/\/doi.org\/10.1109\/TBME.2021.3054828","journal-title":"IEEE Trans Biomed Engi"},{"key":"2599_CR5","doi-asserted-by":"publisher","first-page":"101572","DOI":"10.1016\/j.media.2019.101572","volume":"59","author":"Y Jin","year":"2020","unstructured":"Jin Y, Li H, Dou Q, Chen H, Qin J, Fu C-W, Heng P-A (2020) Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med Image Analysis 59:101572. https:\/\/doi.org\/10.1016\/j.media.2019.101572","journal-title":"Med Image Analysis"},{"issue":"11263","key":"2599_CR6","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-030-59716-0_33","volume":"2020","author":"T Czempiel","year":"2020","unstructured":"Czempiel T, Paschali M, Keicher M, Simson W, Feussner H, Kim ST, Navab N (2020) TeCNO: Surgical phase recognition with multi-stage temporal convolutional networks. LNCS - MICCAI 2020(11263):343\u2013352. https:\/\/doi.org\/10.1007\/978-3-030-59716-0_33","journal-title":"LNCS - MICCAI"},{"issue":"7","key":"2599_CR7","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1007\/s11548-021-02388-z","volume":"16","author":"S Ramesh","year":"2021","unstructured":"Ramesh S, DallAlba D, Gonzalez C, Yu T, Mascagni P, Mutter D, Marescaux J, Fiorini P, Padoy N (2021) Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures. Int J Comp Ass Radiol Surg 16(7):1111\u20131119. https:\/\/doi.org\/10.1007\/s11548-021-02388-z","journal-title":"Int J Comp Ass Radiol Surg"},{"issue":"1","key":"2599_CR8","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/tmi.2016.2593957","volume":"36","author":"AP Twinanda","year":"2017","unstructured":"Twinanda AP, Shehata S, Mutter D, Marescaux J, de Mathelin M, Padoy N (2017) EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imag 36(1):86\u201397. https:\/\/doi.org\/10.1109\/tmi.2016.2593957","journal-title":"IEEE Trans Med Imag"},{"issue":"5","key":"2599_CR9","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/tmi.2017.2787657","volume":"37","author":"Y Jin","year":"2018","unstructured":"Jin Y, Dou Q, Chen H, Yu L, Qin J, Fu C-W, Heng P-A (2018) SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans Med Imag 37(5):1114\u20131126. https:\/\/doi.org\/10.1109\/tmi.2017.2787657","journal-title":"IEEE Trans Med Imag"},{"key":"2599_CR10","unstructured":"Jin Y, Dou Q, Chen H, Yu L, Heng P-A (2021) EndoRCN: Recurrent convolutional networks for recognition of surgical workflow in cholecystectomy procedure video (2016, Accessed 31 Dec). http:\/\/camma.u-strasbg.fr\/m2cai2016\/reports\/Jin-Workflow.pdf"},{"key":"2599_CR11","unstructured":"Cadene R, Robert T, Thome N, Cord, M (2021) M2CAI workflow challenge: Convolutional neural networks with time smoothing and hidden markov model for video frames classification (2016, Accessed 31 Dec). http:\/\/camma.u-strasbg.fr\/m2cai2016\/reports\/Cadene-Workflow.pdf"},{"key":"2599_CR12","doi-asserted-by":"publisher","unstructured":"Maier-Hein L, Eisenmann M, Sarikaya D, Marz K, Collins T, Malpani A, Fallert J, Feussner H, Giannarou S, Mascagni P, Nakawala H, Park A, Pugh C, Stoyanov D, Vedula SS, Cleary K, Fichtinger G, Forestier G, Gibaud B, Grantcharov T, Hashizume M, Heckmann-Notzel D, Kenngott HG, Kikinis R, Mundermann L, Navab N, Onogur S, Ross T, Sznitman R, Taylor RH, Tizabi MD, Wagner M, Hager GD, Neumuth T, Padoy N, Collins J, Gockel I, Goedeke J, Hashimoto DA, Joyeux L, Lam K, Leff DR, Madani A, Marcus HJ, Meireles O, Seitel A, Teber D, Uckert F, Muller-Stich BP, Jannin P, Speidel S (2022) Surgical data science - from concepts toward clinical translation. Medical Image Analysis 76:102306. https:\/\/doi.org\/10.1016\/j.media.2021.102306","DOI":"10.1016\/j.media.2021.102306"},{"key":"2599_CR13","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/978-3-030-00937-3_31","volume":"2018","author":"O Zisimopoulos","year":"2018","unstructured":"Zisimopoulos O, Flouty E, Luengo I, Giataganas P, Nehme J, Chow A, Stoyanov D (2018) DeepPhase: Surgical phase recognition in CATARACTS videos. Med Image Comput Comp Ass Interv - MICCAI 2018:265\u2013272. https:\/\/doi.org\/10.1007\/978-3-030-00937-3_31","journal-title":"Med Image Comput Comp Ass Interv - MICCAI"},{"key":"2599_CR14","doi-asserted-by":"publisher","unstructured":"Khan DZ, Luengo I, Barbarisi S, Addis C, Culshaw L, Dorward NL, Haikka P, Jain A, Kerr K, Koh CH, Horsfall HL, Muirhead W, Palmisciano P, Vasey B, Stoyanov D, Marcus HJ (2021) Automated operative workflow analysis of endoscopic pituitary surgery using machine learning: development and preclinical evaluation (IDEAL stage 0). JNSPG, 1\u20138. https:\/\/doi.org\/10.3171\/2021.6.jns21923","DOI":"10.3171\/2021.6.jns21923"},{"key":"2599_CR15","doi-asserted-by":"publisher","unstructured":"Williams S, Layard\u00a0Horsfall H, Funnell JP, Hanrahan JG, Khan DZ, Muirhead W, Stoyanov D, Marcus HJ (2021) Artificial intelligence in brain tumour surgery-an emerging paradigm. Cancers 13(19). https:\/\/doi.org\/10.3390\/cancers13195010","DOI":"10.3390\/cancers13195010"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02599-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-022-02599-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02599-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,23]],"date-time":"2022-07-23T03:40:40Z","timestamp":1658547640000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-022-02599-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,1]]},"references-count":15,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["2599"],"URL":"https:\/\/doi.org\/10.1007\/s11548-022-02599-y","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,1]]},"assertion":[{"value":"3 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2022","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Tables 1 and 2 layout corrections and article title correction have been updated.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The study was registered with the National Hospital for Neurology and Neurosurgery local audit committee and data sharing was approved by the information governance lead. All patients provided written informed consent for their images to be collected for research.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}