{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:36:06Z","timestamp":1773200166990,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009912","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000}}],"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T00:00:00Z","timestamp":1646006400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UNIPRS and UNRSC","award":["2016 University of Newcastle Australia Scholarship"],"award-info":[{"award-number":["2016 University of Newcastle Australia Scholarship"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Accurate quantification of nerves in cancer specimens is important to understand cancer behaviour. Typically, nerves are manually detected and counted in digitised images of thin tissue sections from excised tumours using immunohistochemistry. However the images are of a large size with nerves having substantial variation in morphology that renders accurate and objective quantification difficult using existing manual and automated counting techniques. Manual counting is precise, but time-consuming, susceptible to inconsistency and has a high rate of false negatives. Existing automated techniques using digitised tissue sections and colour filters are sensitive, however, have a high rate of false positives. In this paper we develop a new automated nerve detection approach, based on a deep learning model with an augmented classification structure. This approach involves pre-processing to extract the image patches for the deep learning model, followed by pixel-level nerve detection utilising the proposed deep learning model. Outcomes assessed were a) sensitivity of the model in detecting manually identified nerves (expert annotations), and b) the precision of additional model-detected nerves. The proposed deep learning model based approach results in a sensitivity of 89% and a precision of 75%. The code and pre-trained model are publicly available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/IA92\/Automated_Nerves_Quantification\" xlink:type=\"simple\">https:\/\/github.com\/IA92\/Automated_Nerves_Quantification<\/jats:ext-link>.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1009912","type":"journal-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T18:35:20Z","timestamp":1646073320000},"page":"e1009912","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Objective quantification of nerves in immunohistochemistry specimens of thyroid cancer utilising deep learning"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9873-8318","authenticated-orcid":true,"given":"Indriani P.","family":"Astono","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8313-1361","authenticated-orcid":true,"given":"James S.","family":"Welsh","sequence":"additional","affiliation":[]},{"given":"Christopher W.","family":"Rowe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2892-1843","authenticated-orcid":true,"given":"Phillip","family":"Jobling","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2022,2,28]]},"reference":[{"issue":"3","key":"pcbi.1009912.ref001","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.ccell.2017.02.005","article-title":"Nerve Dependence: From Regeneration to Cancer","volume":"31","author":"B Boilly","year":"2017","journal-title":"Cancer Cell"},{"issue":"6142","key":"pcbi.1009912.ref002","doi-asserted-by":"crossref","first-page":"1236361","DOI":"10.1126\/science.1236361","article-title":"Autonomic nerve development contributes to prostate cancer progression","volume":"341","author":"C Magnon","year":"2013","journal-title":"Science"},{"issue":"8","key":"pcbi.1009912.ref003","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1016\/j.molonc.2015.05.001","article-title":"Nerve fibers infiltrate the tumor microenvironment and are associated with nerve growth factor production and lymph node invasion in breast cancer","volume":"9","author":"J Pundavela","year":"2015","journal-title":"Mol Oncol"},{"issue":"4","key":"pcbi.1009912.ref004","doi-asserted-by":"crossref","first-page":"1491","DOI":"10.1111\/cas.13975","article-title":"Reduction of intrapancreatic neural density in cancer tissue predicts poorer outcome in pancreatic ductal carcinoma","volume":"110","author":"T Iwasaki","year":"2019","journal-title":"Cancer Sci"},{"issue":"1","key":"pcbi.1009912.ref005","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1038\/s41598-020-58425-5","article-title":"Innervation of papillary thyroid cancer and its association with extra-thyroidal invasion","volume":"10","author":"CW Rowe","year":"2020","journal-title":"Scientific Reports"},{"issue":"4","key":"pcbi.1009912.ref006","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.eururo.2013.04.043","article-title":"Computerized quantification and planimetry of prostatic capsular nerves in relation to adjacent prostate cancer foci","volume":"65","author":"J Br\u00fcndl","year":"2014","journal-title":"Eur Urol"},{"issue":"2","key":"pcbi.1009912.ref007","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.eururo.2008.04.018","article-title":"Topographical anatomy of periprostatic and capsular nerves: quantification and computerised planimetry","volume":"54","author":"R Ganzer","year":"2008","journal-title":"Eur Urol"},{"issue":"1","key":"pcbi.1009912.ref008","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1186\/1471-2105-15-169","article-title":"A semi-automated technique for labeling and counting of apoptosing retinal cells","volume":"15","author":"M Bizrah","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1009912.ref009","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition; 2014. p. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"pcbi.1009912.ref010","doi-asserted-by":"crossref","unstructured":"Girshick R. Fast R-CNN. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). ICCV\u201915. USA: IEEE Computer Society; 2015. p. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"pcbi.1009912.ref011","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"S Ren","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1009912.ref012","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/978-3-319-46723-8_48","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016","author":"PF Christ","year":"2016"},{"key":"pcbi.1009912.ref013","first-page":"110","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"H Jia"},{"key":"pcbi.1009912.ref014","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/978-3-642-40763-5_51","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2013","author":"DC Cire\u015fan","year":"2013"},{"issue":"3","key":"pcbi.1009912.ref015","doi-asserted-by":"crossref","first-page":"034003","DOI":"10.1117\/1.JMI.1.3.034003","article-title":"Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features","volume":"1","author":"H Wang","year":"2014","journal-title":"J Med Imaging (Bellingham)"},{"issue":"10","key":"pcbi.1009912.ref016","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1109\/TBME.2015.2430895","article-title":"Accurate Segmentation of Cervical Cytoplasm and Nuclei Based on Multiscale Convolutional Network and Graph Partitioning","volume":"62","author":"Y Song","year":"2015","journal-title":"IEEE Trans Biomed Eng"},{"key":"pcbi.1009912.ref017","article-title":"Comparing the Performance of L*A*B* and HSV Color Spaces with Respect to Color Image Segmentation","author":"DJ Bora","year":"2015","journal-title":"CoRR"},{"issue":"12","key":"pcbi.1009912.ref018","article-title":"Guided Filter for Grayscale, RGB and HSV color space","volume":"5","author":"Swati Shankar Shetkar","year":"2016","journal-title":"International Journal of Engineering and Computer Science"},{"issue":"7-8","key":"pcbi.1009912.ref019","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1002\/mrd.22489","article-title":"The ImageJ ecosystem: An open platform for biomedical image analysis","volume":"82","author":"J Schindelin","year":"2015","journal-title":"Mol Reprod Dev"},{"issue":"1","key":"pcbi.1009912.ref020","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s13007-020-00602-8","article-title":"DiSCount: computer vision for automated quantification of Striga seed germination","volume":"16","author":"R Masteling","year":"2020","journal-title":"Plant Methods"},{"issue":"3","key":"pcbi.1009912.ref021","doi-asserted-by":"crossref","DOI":"10.1093\/gigascience\/giaa012","article-title":"DeepPod: a convolutional neural network based quantification of fruit number in Arabidopsis","volume":"9","author":"A Hamidinekoo","year":"2020","journal-title":"GigaScience"},{"key":"pcbi.1009912.ref022","doi-asserted-by":"crossref","unstructured":"Harzallah H, Jurie F, Schmid C. Combining efficient object localization and image classification. In: 2009 IEEE 12th International Conference on Computer Vision; 2009. p. 237\u2013244.","DOI":"10.1109\/ICCV.2009.5459257"},{"issue":"9","key":"pcbi.1009912.ref023","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object Detection with Discriminatively Trained Part-Based Models","volume":"32","author":"PF Felzenszwalb","year":"2010","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1009912.ref024","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. Overfeat: Integrated recognition, localization and detection using convolutional networks; 2014."},{"issue":"2","key":"pcbi.1009912.ref025","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective Search for Object Recognition","volume":"104","author":"JR Uijlings","year":"2013","journal-title":"Int J Comput Vision"},{"issue":"9","key":"pcbi.1009912.ref026","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"K He","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1009912.ref027","doi-asserted-by":"crossref","first-page":"101813","DOI":"10.1016\/j.media.2020.101813","article-title":"Deep neural network models for computational histopathology: A survey","volume":"67","author":"CL Srinidhi","year":"2021","journal-title":"Med Image Anal"},{"key":"pcbi.1009912.ref028","doi-asserted-by":"crossref","first-page":"101547","DOI":"10.1016\/j.media.2019.101547","article-title":"Learning to detect lymphocytes in immunohistochemistry with deep learning","volume":"58","author":"Z Swiderska-Chadaj","year":"2019","journal-title":"Med Image Anal"},{"key":"pcbi.1009912.ref029","doi-asserted-by":"crossref","unstructured":"de Bel T, Hermsen M, Smeets B, Hilbrands L, van der Laak J, Litjens G. Automatic segmentation of histopathological slides of renal tissue using deep learning. In: Tomaszewski JE, Gurcan MN, editors. Medical Imaging 2018: Digital Pathology. vol. 10581. International Society for Optics and Photonics. SPIE; 2018. p. 285\u2013290.","DOI":"10.1117\/12.2293717"},{"issue":"1","key":"pcbi.1009912.ref030","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1093\/nsr\/nwx106","article-title":"A brief introduction to weakly supervised learning","volume":"5","author":"ZH Zhou","year":"2017","journal-title":"Natl Sci Rev"},{"issue":"1","key":"pcbi.1009912.ref031","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"JM Johnson","year":"2019","journal-title":"Journal of Big Data"},{"key":"pcbi.1009912.ref032","doi-asserted-by":"crossref","first-page":"101549","DOI":"10.1016\/j.media.2019.101549","article-title":"RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification","volume":"58","author":"S Wang","year":"2019","journal-title":"Med Image Anal"},{"key":"pcbi.1009912.ref033","unstructured":"Rowe CW, Dill T, Griffin N, Jobling P, Faulkner S, Paul JW, et al.. 4 micron sections of human thyroid cancer stained with PGP9.5 and counterstained with haematoxylin; 2021. Available from: https:\/\/doi.org\/10.5281\/zenodo.4459863."},{"issue":"1","key":"pcbi.1009912.ref034","doi-asserted-by":"crossref","first-page":"16878","DOI":"10.1038\/s41598-017-17204-5","article-title":"QuPath: Open source software for digital pathology image analysis","volume":"7","author":"P Bankhead","year":"2017","journal-title":"Scientific Reports"},{"key":"pcbi.1009912.ref035","volume-title":"Machine Vision: Automated Visual Inspection and Robot Vision","author":"D Vernon","year":"1991"},{"issue":"6","key":"pcbi.1009912.ref036","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1038\/modpathol.2012.235","article-title":"Interobserver variability and the effect of education in the histopathological diagnosis of differentiated vulvar intraepithelial neoplasia","volume":"26","author":"LCG van den Einden","year":"2013","journal-title":"Modern Pathology"},{"issue":"5","key":"pcbi.1009912.ref037","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1038\/eye.1997.178","article-title":"Inter-observer and intra-observer agreement in the interpretation of visual fields in glaucoma","volume":"11","author":"AJ King","year":"1997","journal-title":"Eye"},{"key":"pcbi.1009912.ref038","volume-title":"SpringerBriefs in Applied Sciences and Technology","author":"PV Krishna","year":"2018"},{"issue":"7","key":"pcbi.1009912.ref039","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.3390\/app10072601","article-title":"Optimisation of 2D U-Net Model Components for Automatic Prostate Segmentation on MRI","volume":"10","author":"IP Astono","year":"2020","journal-title":"Applied Sciences"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009912","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T19:04:54Z","timestamp":1646939094000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009912"}},"subtitle":[],"editor":[{"given":"Faisal","family":"Mahmood","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,2,28]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009912","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1009912","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,28]]}}}