{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T09:21:05Z","timestamp":1722936065003},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,6,13]],"date-time":"2021-06-13T00:00:00Z","timestamp":1623542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,13]],"date-time":"2021-06-13T00:00:00Z","timestamp":1623542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["218380\/Z\/19\/Z\/","218380\/Z\/19\/Z\/"],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["218380\/Z\/19\/Z\/","203145Z\/16\/Z"],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["203148\/Z\/16\/Z"],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["NS\/A000049\/1"],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"publisher","award":["RCSRF1819\/7\/34"],"id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"published-print":{"date-parts":[[2021,10]]},"abstract":"Abstract<\/jats:title>\n Purpose<\/jats:title>\n Accurate segmentation of brain resection cavities (RCs) aids in postoperative analysis and determining follow-up treatment. Convolutional neural networks (CNNs) are the state-of-the-art image segmentation technique, but require large annotated datasets for training. Annotation of 3D medical images is time-consuming, requires highly trained raters and may suffer from high inter-rater variability. Self-supervised learning strategies can leverage unlabeled data for training.<\/jats:p>\n <\/jats:sec>\n Methods<\/jats:title>\n We developed an algorithm to simulate resections from preoperative magnetic resonance images (MRIs). We performed self-supervised training of a 3D CNN for RC segmentation using our simulation method. We curated EPISURG, a dataset comprising 430 postoperative and 268 preoperative MRIs from 430 refractory epilepsy patients who underwent resective neurosurgery. We fine-tuned our model on three small annotated datasets from different institutions and on the annotated images in EPISURG, comprising 20, 33, 19 and 133 subjects.<\/jats:p>\n <\/jats:sec>\n Results<\/jats:title>\n The model trained on data with simulated resections obtained median (interquartile range) Dice score coefficients (DSCs) of 81.7 (16.4), 82.4 (36.4), 74.9 (24.2) and 80.5 (18.7) for each of the four datasets. After fine-tuning, DSCs were 89.2 (13.3), 84.1 (19.8), 80.2 (20.1) and 85.2 (10.8). For comparison, inter-rater agreement between human annotators from our previous study was 84.0 (9.9).<\/jats:p>\n <\/jats:sec>\n Conclusion<\/jats:title>\n We present a self-supervised learning strategy for 3D CNNs using simulated RCs to accurately segment real RCs on postoperative MRI. Our method generalizes well to data from different institutions, pathologies and modalities. Source code, segmentation models and the EPISURG dataset are available at https:\/\/github.com\/fepegar\/resseg-ijcars<\/jats:ext-link>.<\/jats:p>\n <\/jats:sec>","DOI":"10.1007\/s11548-021-02420-2","type":"journal-article","created":{"date-parts":[[2021,6,13]],"date-time":"2021-06-13T12:02:32Z","timestamp":1623585752000},"page":"1653-1661","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9090-3024","authenticated-orcid":false,"given":"Fernando","family":"P\u00e9rez-Garc\u00eda","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7530-0644","authenticated-orcid":false,"given":"Reuben","family":"Dorent","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7936-6536","authenticated-orcid":false,"given":"Michele","family":"Rizzi","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5141-9202","authenticated-orcid":false,"given":"Francesco","family":"Cardinale","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1187-3352","authenticated-orcid":false,"given":"Valerio","family":"Frazzini","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0077-8114","authenticated-orcid":false,"given":"Vincent","family":"Navarro","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2572-9730","authenticated-orcid":false,"given":"Caroline","family":"Essert","sequence":"additional","affiliation":[]},{"given":"Ir\u00e8ne","family":"Ollivier","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1794-0456","authenticated-orcid":false,"given":"Tom","family":"Vercauteren","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1553-7903","authenticated-orcid":false,"given":"Rachel","family":"Sparks","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1373-0681","authenticated-orcid":false,"given":"John S.","family":"Duncan","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5694-5340","authenticated-orcid":false,"given":"S\u00e9bastien","family":"Ourselin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,13]]},"reference":[{"key":"2420_CR1","unstructured":"Billot B, Greve DN, Leemput KV, Fischl B, Iglesias JE, Dalca A (2020) A learning strategy for contrast-agnostic MRI segmentation. In: Medical imaging with deep learning. PMLR, pp 75\u201393. ISSN: 2640-3498"},{"issue":"2","key":"2420_CR2","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1006\/nimg.2001.0845","volume":"14","author":"M Brett","year":"2001","unstructured":"Brett M, Leff AP, Rorden C, Ashburner J (2001) Spatial normalization of brain images with focal lesions using cost function masking. Neuroimage 14(2):486\u2013500. https:\/\/doi.org\/10.1006\/nimg.2001.0845","journal-title":"Neuroimage"},{"issue":"9","key":"2420_CR3","doi-asserted-by":"publisher","first-page":"1976","DOI":"10.1109\/TMI.2015.2418298","volume":"34","author":"MJ Cardoso","year":"2015","unstructured":"Cardoso MJ, Modat M, Wolz R, Melbourne A, Cash D, Rueckert D, Ourselin S (2015) Geodesic information flows: spatially-variant graphs and their application to segmentation and fusion. IEEE Trans Med Imaging 34(9):1976\u20131988. https:\/\/doi.org\/10.1109\/TMI.2015.2418298","journal-title":"IEEE Trans Med Imaging"},{"key":"2420_CR4","series-title":"Lecture notes in computer science","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1007\/978-3-319-18461-6_29","volume-title":"Scale space and variational methods in computer vision","author":"K Chen","year":"2015","unstructured":"Chen K, Derksen A, Heldmann S, Hallmann M, Berkels B (2015) Deformable image registration with automatic non-correspondence detection. In: Aujol JF, Nikolova M, Papadakis N (eds) Scale space and variational methods in computer vision. Lecture notes in computer science. Springer, Cham, pp 360\u2013371. https:\/\/doi.org\/10.1007\/978-3-319-18461-6_29"},{"key":"2420_CR5","doi-asserted-by":"publisher","first-page":"101539","DOI":"10.1016\/j.media.2019.101539","volume":"58","author":"L Chen","year":"2019","unstructured":"Chen L, Bentley P, Mori K, Misawa K, Fujiwara M, Rueckert D (2019) Self-supervised learning for medical image analysis using image context restoration. Med Image Anal 58:101539. https:\/\/doi.org\/10.1016\/j.media.2019.101539","journal-title":"Med Image Anal"},{"key":"2420_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/978-3-642-15705-9_45","volume-title":"MICCAI 2010","author":"N Chitphakdithai","year":"2010","unstructured":"Chitphakdithai N, Duncan JS (2010) Non-rigid registration with missing correspondences in preoperative and postresection brain images. In: Jiang T, Navab N, Pluim JPW, Viergever MA (eds) MICCAI 2010. Lecture Notes in Computer Science. Springer, Berlin, pp 367\u2013374. https:\/\/doi.org\/10.1007\/978-3-642-15705-9_45"},{"key":"2420_CR7","series-title":"Lecture notes in computer science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","volume-title":"Medical image computing and computer-assisted intervention\u2014MICCAI 2016","author":"O \u00c7i\u00e7ek","year":"2016","unstructured":"\u00c7i\u00e7ek O, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W (eds) Medical image computing and computer-assisted intervention\u2014MICCAI 2016. Lecture notes in computer science. Springer, Cham, pp 424\u2013432. https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49"},{"issue":"3","key":"2420_CR8","doi-asserted-by":"publisher","first-page":"302","DOI":"10.5853\/jos.2017.02922","volume":"20","author":"E Cuadrado-Godia","year":"2018","unstructured":"Cuadrado-Godia E, Dwivedi P, Sharma S, Ois Santiago A, Roquer Gonzalez J, Balcells M, Laird J, Turk M, Suri HS, Nicolaides A, Saba L, Khanna NN, Suri JS (2018) Cerebral small vessel disease: a review focusing on pathophysiology, biomarkers, and machine learning strategies. J Stroke 20(3):302\u2013320. https:\/\/doi.org\/10.5853\/jos.2017.02922","journal-title":"J Stroke"},{"key":"2420_CR9","doi-asserted-by":"publisher","first-page":"101862","DOI":"10.1016\/j.media.2020.101862","volume":"67","author":"R Dorent","year":"2021","unstructured":"Dorent R, Booth T, Li W, Sudre CH, Kafiabadi S, Cardoso J, Ourselin S, Vercauteren T (2021) Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets. Med Image Anal 67:101862. https:\/\/doi.org\/10.1016\/j.media.2020.101862","journal-title":"Med Image Anal"},{"issue":"1","key":"2420_CR10","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1186\/s13014-020-01553-z","volume":"15","author":"E Ermi\u015f","year":"2020","unstructured":"Ermi\u015f E, Jungo A, Poel R, Blatti-Moreno M, Meier R, Knecht U, Aebersold DM, Fix MK, Manser P, Reyes M, Herrmann E (2020) Fully automated brain resection cavity delineation for radiation target volume definition in glioblastoma patients using deep learning. Radiat Oncol 15(1):100. https:\/\/doi.org\/10.1186\/s13014-020-01553-z","journal-title":"Radiat Oncol"},{"issue":"9","key":"2420_CR11","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","volume":"30","author":"A Fedorov","year":"2012","unstructured":"Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin JC, Pujol S, Bauer C, Jennings D, Fennessy F, Sonka M, Buatti J, Aylward S, Miller JV, Pieper S, Kikinis R (2012) 3D Slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging 30(9):1323\u20131341. https:\/\/doi.org\/10.1016\/j.mri.2012.05.001","journal-title":"Magn Reson Imaging"},{"key":"2420_CR12","doi-asserted-by":"publisher","unstructured":"Granados A, P\u00e9rez-Garc\u00eda F, Schweiger M, Vakharia V, Vos SB, Miserocchi A, McEvoy AW, Duncan JS, Sparks R, Ourselin S (2021) A generative model of hyperelastic strain energy density functions for multiple tissue brain deformation. Int J Comput Assist Radiol Surg 16(1):141\u2013150. https:\/\/doi.org\/10.1007\/s11548-020-02284-y","DOI":"10.1007\/s11548-020-02284-y"},{"key":"2420_CR13","doi-asserted-by":"publisher","unstructured":"Greff K, Klein A, Chovanec M, Hutter F, Schmidhuber J (2017) The sacred infrastructure for computational research. In: Proceedings of the 16th python in science conference, pp 49\u201356. https:\/\/doi.org\/10.25080\/shinma-7f4c6e7-008","DOI":"10.25080\/shinma-7f4c6e7-008"},{"issue":"6","key":"2420_CR14","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1002\/mrm.1910340618","volume":"34","author":"H Gudbjartsson","year":"1995","unstructured":"Gudbjartsson H, Patz S (1995) The Rician distribution of noisy MRI data. Magn Reson Med 34(6):910\u2013914","journal-title":"Magn Reson Med"},{"issue":"9","key":"2420_CR15","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TMI.2011.2138152","volume":"30","author":"JE Iglesias","year":"2011","unstructured":"Iglesias JE, Liu CY, Thompson PM, Tu Z (2011) Robust brain extraction across datasets and comparison with publicly available methods. IEEE Trans Med Imaging 30(9):1617\u20131634. https:\/\/doi.org\/10.1109\/TMI.2011.2138152","journal-title":"IEEE Trans Med Imaging"},{"issue":"3","key":"2420_CR16","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1001\/jama.2014.17426","volume":"313","author":"BC Jobst","year":"2015","unstructured":"Jobst BC, Cascino GD (2015) Resective epilepsy surgery for drug-resistant focal epilepsy: a review. JAMA 313(3):285\u2013293. https:\/\/doi.org\/10.1001\/jama.2014.17426","journal-title":"JAMA"},{"key":"2420_CR17","doi-asserted-by":"publisher","unstructured":"Matzkin F, Newcombe V, Stevenson S, Khetani A, Newman T, Digby R, Stevens A, Glocker B, Ferrante E (2020) Self-supervised skull reconstruction in brain CT images with decompressive craniectomy. In: Martel AL, Abolmaesumi P, Stoyanov D, Mateus D, Zuluaga MA, Zhou SK, Racoceanu D, Joskowicz L (eds) MICCAI 2020. Lecture notes in computer science. Springer, Cham, pp 390\u2013399. https:\/\/doi.org\/10.1007\/978-3-030-59713-9_38","DOI":"10.1007\/978-3-030-59713-9_38"},{"issue":"4","key":"2420_CR18","doi-asserted-by":"publisher","first-page":"798","DOI":"10.3171\/2016.9.JNS16146","volume":"127","author":"R Meier","year":"2017","unstructured":"Meier R, Porz N, Knecht U, Loosli T, Schucht P, Beck J, Slotboom J, Wiest R, Reyes M (2017) Automatic estimation of extent of resection and residual tumor volume of patients with glioblastoma. J Neurosurg 127(4):798\u2013806. https:\/\/doi.org\/10.3171\/2016.9.JNS16146","journal-title":"J Neurosurg"},{"issue":"6","key":"2420_CR19","doi-asserted-by":"publisher","first-page":"3253","DOI":"10.1118\/1.4709600","volume":"39","author":"L Mercier","year":"2012","unstructured":"Mercier L, Del Maestro RF, Petrecca K, Araujo D, Haegelen C, Collins DL (2012) Online database of clinical MR and ultrasound images of brain tumors. Med Phys 39(6):3253\u20133261. https:\/\/doi.org\/10.1118\/1.4709600","journal-title":"Med Phys"},{"key":"2420_CR20","doi-asserted-by":"publisher","unstructured":"Mohamed AR, Freeman JL, Maixner W, Bailey CA, Wrennall JA, Harvey AS (2011) Temporoparietooccipital disconnection in children with intractable epilepsy: clinical article. J Neurosurg Pediatr 7(6):660\u2013670. https:\/\/doi.org\/10.3171\/2011.4.PEDS10454","DOI":"10.3171\/2011.4.PEDS10454"},{"key":"2420_CR21","doi-asserted-by":"publisher","unstructured":"P\u00e9rez-Garc\u00eda F, Rodionov R, Alim-Marvasti A, Sparks R, Duncan J, Ourselin S (2020) EPISURG: a dataset of postoperative magnetic resonance images (MRI) for quantitative analysis of resection neurosurgery for refractory epilepsy. University College London. https:\/\/doi.org\/10.5522\/04\/9996158.v1","DOI":"10.5522\/04\/9996158.v1"},{"key":"2420_CR22","series-title":"Lecture notes in computer science","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-030-59716-0_12","volume-title":"MICCAI 2020","author":"F P\u00e9rez-Garc\u00eda","year":"2020","unstructured":"P\u00e9rez-Garc\u00eda F, Rodionov R, Alim-Marvasti A, Sparks R, Duncan JS, Ourselin S (2020) Simulation of brain resection for cavity segmentation using self-supervised and semi-supervised learning. MICCAI 2020. Lecture notes in computer science. Springer, Cham, pp 115\u2013125. https:\/\/doi.org\/10.1007\/978-3-030-59716-0_12"},{"key":"2420_CR23","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Garc\u00eda F, Sparks R, Ourselin S (2020) TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. arXiv:2003.04696 [cs, eess, stat]","DOI":"10.1016\/j.cmpb.2021.106236"},{"issue":"3","key":"2420_CR24","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1145\/566654.566636","volume":"21","author":"K Perlin","year":"2002","unstructured":"Perlin K (2002) Improving noise. ACM Trans Graph (TOG) 21(3):681\u2013682. https:\/\/doi.org\/10.1145\/566654.566636","journal-title":"ACM Trans Graph (TOG)"},{"issue":"4","key":"2420_CR25","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1109\/TMI.2016.2640180","volume":"36","author":"A Pezeshk","year":"2017","unstructured":"Pezeshk A, Petrick N, Chen W, Sahiner B (2017) Seamless lesion insertion for data augmentation in CAD training. IEEE Trans Med Imaging 36(4):1005\u20131015. https:\/\/doi.org\/10.1109\/TMI.2016.2640180","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"2420_CR26","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1093\/brain\/124.9.1683","volume":"124","author":"F Rosenow","year":"2001","unstructured":"Rosenow F, L\u00fcders H (2001) Presurgical evaluation of epilepsy. Brain 124(9):1683\u20131700. https:\/\/doi.org\/10.1093\/brain\/124.9.1683","journal-title":"Brain"},{"issue":"3","key":"2420_CR27","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1002\/ana.22619","volume":"71","author":"GP Winston","year":"2012","unstructured":"Winston GP, Daga P, Stretton J, Modat M, Symms MR, McEvoy AW, Ourselin S, Duncan JS (2012) Optic radiation tractography and vision in anterior temporal lobe resection. Ann Neurol 71(3):334\u2013341. https:\/\/doi.org\/10.1002\/ana.22619","journal-title":"Ann Neurol"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-021-02420-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-021-02420-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-021-02420-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,11]],"date-time":"2021-11-11T03:16:56Z","timestamp":1636600616000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-021-02420-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,13]]},"references-count":27,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["2420"],"URL":"https:\/\/doi.org\/10.1007\/s11548-021-02420-2","relation":{},"ISSN":["1861-6410","1861-6429"],"issn-type":[{"value":"1861-6410","type":"print"},{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,13]]},"assertion":[{"value":"1 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2021","order":3,"name":"first_online","label":"First Online","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":"Conflicts of interest"}},{"value":"The code for resection simulation, training and inference is available at ExternalRef removed. A tool to segment RCs using our best model (section \u201cSelf-supervised learning: training with simulated resections only\u201d) can be installed from the Python Package Index (PyPI): pip install resseg<\/tt>.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"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.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research involving human participants"}},{"value":"For this type of study, formal consent was not required.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}]}}