{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T07:54:21Z","timestamp":1777794861518,"version":"3.51.4"},"reference-count":53,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T00:00:00Z","timestamp":1608595200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>In this work, a novel proliferation index (PI) calculator for Ki67 images called piNET is proposed. It is successfully tested on four datasets, from three scanners comprised of patches, tissue microarrays (TMAs) and whole slide images (WSI), representing a diverse multi-centre dataset for evaluating Ki67 quantification. Compared to state-of-the-art methods, piNET consistently performs the best over all datasets with an average PI difference of 5.603%, PI accuracy rate of 86% and correlation coefficient R = 0.927. The success of the system can be attributed to several innovations. Firstly, this tool is built based on deep learning, which can adapt to wide variability of medical images\u2014and it was posed as a detection problem to mimic pathologists\u2019 workflow which improves accuracy and efficiency. Secondly, the system is trained purely on tumor cells, which reduces false positives from non-tumor cells without needing the usual pre-requisite tumor segmentation step for Ki67 quantification. Thirdly, the concept of learning background regions through weak supervision is introduced, by providing the system with ideal and non-ideal (artifact) patches that further reduces false positives. Lastly, a novel hotspot analysis is proposed to allow automated methods to score patches from WSI that contain \u201csignificant\u201d activity.<\/jats:p>","DOI":"10.3390\/cancers13010011","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T12:42:28Z","timestamp":1608640948000},"page":"11","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["piNET\u2013An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8583-5829","authenticated-orcid":false,"given":"Rokshana Stephny","family":"Geread","sequence":"first","affiliation":[{"name":"Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7896-2547","authenticated-orcid":false,"given":"Abishika","family":"Sivanandarajah","sequence":"additional","affiliation":[{"name":"Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily Rita","family":"Brouwer","sequence":"additional","affiliation":[{"name":"Department of Pathobiology, Ontario Veterinarian College, University of Guelph, Guelph, ON NIG 2W1, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1756-8607","authenticated-orcid":false,"given":"Geoffrey A.","family":"Wood","sequence":"additional","affiliation":[{"name":"Department of Pathobiology, Ontario Veterinarian College, University of Guelph, Guelph, ON NIG 2W1, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitrios","family":"Androutsos","sequence":"additional","affiliation":[{"name":"Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hala","family":"Faragalla","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine &amp; Pathobiology, St. Michael\u2019s Hospital, Unity Health Network, Toronto, ON M5B 1W8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"April","family":"Khademi","sequence":"additional","affiliation":[{"name":"Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada"},{"name":"Keenan Research Center for Biomedical Science, St. Michael\u2019s Hospital, Unity Health Network, Toronto, ON M5B 1W8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global Cancer Statistics 2018: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"68","author":"Bray","year":"2018","journal-title":"Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mohan, H. (2010). Textbook of Pathology, Jaypee Brothers Medical Publishers. [6th ed.].","DOI":"10.5005\/jp\/books\/11091"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1038\/bjc.2013.6","article-title":"Breast cancer survival and stage at diagnosis in Australia, Canada, Denmark, Norway, Sweden and the UK, 2000\u20132007: A population-based study","volume":"108","author":"Walters","year":"2013","journal-title":"Br. J. Cancer"},{"key":"ref_4","unstructured":"Hortobagyi, G., Connolly, J., D\u2019Orsi, C., Edge, S., Mittendorf, E., Rugo, H., Solin, L., Weaver, D., Winchester, D., and Giuliano, A. (2018). Breast. AJCC Breast Cancer Staging System, The American College of Surgeons."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1111\/j.1365-2559.1991.tb00229.x","article-title":"Pathological Prognostic Factors in Breast Cancer. I. The Value of Histological Grade in Breast Cancer: Experience from a Large Study with Long-Term Follow-Up","volume":"19","author":"Elston","year":"1991","journal-title":"Histopathology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3926","DOI":"10.1002\/1097-0142(19930615)71:12<3926::AID-CNCR2820711221>3.0.CO;2-2","article-title":"Proliferation Index as a Prognostic Marker in Breast Cancer","volume":"71","author":"Veronese","year":"1993","journal-title":"Cancer"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/BF00285178","article-title":"Assignment of the gene(s) involved in the expression of the proliferation-related Ki-67 antigen to human chromosome 10","volume":"83","author":"Schonk","year":"1989","journal-title":"Hum. Genet."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1111\/j.1365-2559.2006.02402.x","article-title":"Ki67 immunohistochemistry: A valuable marker in prognostication but with a risk of misclassification: Proliferation subgroups formed based on Ki67 immunoreactivity and standardized mitotic index","volume":"48","author":"Jalava","year":"2006","journal-title":"Histopathology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1093\/jnci\/djr393","article-title":"Assessment of Ki67 in breast cancer: Recommendations from the International Ki67 in Breast Cancer working group","volume":"103","author":"Dowsett","year":"2011","journal-title":"J. Natl. Cancer Inst."},{"key":"ref_10","first-page":"51","article-title":"Image Analysis Solutions for Automatic Scoring and Grading of Digital Pathology Images","volume":"5","author":"Khademi","year":"2013","journal-title":"Can. J. Pathol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"v8","DOI":"10.1093\/annonc\/mdv298","article-title":"Primary breast cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up","volume":"26","author":"Senkus","year":"2015","journal-title":"Ann. Oncol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e194337","DOI":"10.1001\/jamanetworkopen.2019.4337","article-title":"Trends in the US and Canadian pathologist workforces from 2007 to 2017","volume":"2","author":"Metter","year":"2019","journal-title":"JAMA Netw. Open"},{"key":"ref_13","unstructured":"Royal College of Pathologists (2018). Meeting Pathology Demand: Histopathology Workforce Census, Royal College of Pathologists."},{"key":"ref_14","first-page":"8","article-title":"Hidden Danger in Pathology","volume":"7","author":"Maung","year":"2014","journal-title":"Can. J. Pathol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1002\/jso.20125","article-title":"Errors in pathology and laboratory medicine: Consequences and prevention","volume":"88","author":"Hollensead","year":"2004","journal-title":"J. Surg. Oncol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.jasc.2019.03.003","article-title":"Artificial intelligence in cytopathology: A review of the literature and overview of commercial landscape","volume":"8","author":"Landau","year":"2019","journal-title":"J. Am. Soc. Cytopathol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1093\/jnci\/djt306","article-title":"An International Ki67 Reproducibility Study","volume":"105","author":"Polley","year":"2013","journal-title":"J. Natl. Cancer Inst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"226","DOI":"10.3389\/fbioe.2019.00226","article-title":"IHC Colour Histograms for Unsupervised Ki67 Proliferation Index Calculation","volume":"7","author":"Geread","year":"2019","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10549-018-4669-2","article-title":"Digital image analysis of Ki67 proliferation index in breast cancer using virtual dual staining on whole tissue sections: Clinical validation and inter-platform agreement","volume":"169","author":"Koopman","year":"2018","journal-title":"Breast Cancer Res. Treat."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-49139-4","article-title":"Proliferation Tumor Marker Network (PTM-NET) for the identification of tumor region in Ki67 stained breast cancer whole slide images","volume":"9","author":"Joseph","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Swiderska-Chadaj, Z., Markiewicz, T., Gallego, J., Bueno, G., Grala, B., and Lorent, M. (2018). Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model. Bull. Polish Acad. Sci. Tech. Sci., 66.","DOI":"10.24425\/bpas.2018.125932"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3088","DOI":"10.1109\/TBME.2019.2900378","article-title":"Pixel-to-Pixel Learning With Weak Supervision for Single-Stage Nucleus Recognition in Ki67 Images","volume":"66","author":"Xing","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3213","DOI":"10.1038\/s41598-017-03405-5","article-title":"An Advanced Deep Learning Approach for Ki-67 Stained Hotspot Detection and Proliferation Rate Scoring for Prognostic Evaluation of Breast Cancer","volume":"7","author":"Saha","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_24","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":"Srinidhi","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_26","unstructured":"Senaras, C. (2018). DeepSlides Dataset, Zenodo, CERN."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"eaan2507","DOI":"10.1126\/science.aan2507","article-title":"A pathology atlas of the human cancer transcriptome","volume":"357","author":"Zhang","year":"2017","journal-title":"Science"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e83","DOI":"10.1158\/0008-5472.CAN-17-0323","article-title":"An Image Analysis Resource for Cancer Research: PIIP-Pathology Image Informatics Platform for Visualization, Analysis, and Management","volume":"77","author":"Martel","year":"2017","journal-title":"Cancer Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1038\/nmeth.2089","article-title":"NIH Image to ImageJ: 25 years of image analysis","volume":"9","author":"Schneider","year":"2012","journal-title":"Nat. Methods"},{"key":"ref_30","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","article-title":"A Threshold Selection Method from Gray-Level Histograms","volume":"9","author":"Otsu","year":"1978","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2015\/498746","article-title":"Comparison of the Manual, Semiautomatic, and Automatic Selection and Leveling of Hot Spots in Whole Slide Images for Ki-67 Quantification in Meningiomas","volume":"2015","author":"Swiderska","year":"2015","journal-title":"Anal. Cell. Pathol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Su, H., Xing, F., Kong, X., Xie, Y., Zhang, S., and Yang, L. (2015). Robust cell detection and segmentation in histopathological images using sparse reconstruction and stacked denoising autoencoders. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-319-24574-4_46"},{"key":"ref_34","first-page":"436","article-title":"An Integrated Framework for Automatic Ki-67 Scoring in Pancreatic Neuroendocrine Tumor","volume":"16","author":"Xing","year":"2013","journal-title":"Med. Image Comput. Comput. Assist. Interv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1002\/cyto.a.22085","article-title":"Clustering methods applied in the detection of Ki67 hot-spots in whole tumor slide images: An efficient way to characterize heterogeneous tissue-based biomarkers","volume":"81","author":"Lopez","year":"2012","journal-title":"Cytom. Part A"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1109\/TBME.2013.2291703","article-title":"Automatic Ki-67 Counting Using Robust Cell Detection and Online Dictionary Learning","volume":"61","author":"Xing","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.media.2017.07.003","article-title":"Efficient and robust cell detection: A structured regression approach","volume":"44","author":"Xie","year":"2018","journal-title":"Med. Image Anal."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"Gu","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_39","unstructured":"Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11\u201313). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale, FL, USA."},{"key":"ref_40","unstructured":"Atienza, R. (2018). Advanced Deep Learning with Keras: Apply Deep Learning Techniques, Autoencoders, GANs, Variational Autoencoders, Deep Reinforcement Learning, Policy Gradients, and More, Packt Publishing Ltd."},{"key":"ref_41","unstructured":"Chollet, F. (2017). Deep Learning with Python, Apress."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Meyer, G.P. (2020). An Alternative Probabilistic Interpretation of the Huber Loss. arXiv.","DOI":"10.1109\/CVPR46437.2021.00522"},{"key":"ref_43","unstructured":"Gulli, A., and Pal, S. (2017). Deep Learning with Keras, Packt Publishing Ltd."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Ketkar, N. (2017). Introduction to keras. Deep Learning with Python, Apress.","DOI":"10.1007\/978-1-4842-2766-4"},{"key":"ref_45","unstructured":"(2020, October 16). Tf.Keras.Losses.Log_cosh|TensorFlow Core v2.3.0. Available online: https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/keras\/losses\/log_cosh."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1007\/s00335-008-9128-7","article-title":"MicroRNA expression in canine mammary cancer","volume":"19","author":"Boggs","year":"2008","journal-title":"Mamm. Genome"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 1\u201326). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1109\/TBME.2011.2179298","article-title":"Robust Segmentation of Overlapping Cells in Histopathology Specimens Using Parallel Seed Detection and Repulsive Level Set","volume":"59","author":"Qi","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"83190J","DOI":"10.1117\/12.912388","article-title":"Managing and Querying Whole Slide Images","volume":"8319","author":"Wang","year":"2012","journal-title":"Proc. SPIE"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5114\/pjp.2013.34596","article-title":"Prognostic comparison of the proliferation markers mitotic activity index, phosphohistone H3, Ki67, steroid receptors, HER2, high molecular weight cytokeratins and classical prognostic factors in T 1-2 N 0 M 0 breast cancer","volume":"1","author":"Gudlaugsson","year":"2013","journal-title":"Pol. J. Pathol."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1097\/PAI.0000000000000555","article-title":"Comparison of Proliferation Markers Ki67 and Phosphohistone-H3 (pHH3) in Breast Ductal Carcinoma In Situ","volume":"25","author":"Bosch","year":"2017","journal-title":"Appl. Immunohistochem. Mol. Morphol."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/13\/1\/11\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:48:22Z","timestamp":1760179702000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/13\/1\/11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,22]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["cancers13010011"],"URL":"https:\/\/doi.org\/10.3390\/cancers13010011","relation":{"has-preprint":[{"id-type":"doi","id":"10.32920\/21287940.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1101\/2020.11.19.390401","asserted-by":"object"},{"id-type":"doi","id":"10.32920\/21287940","asserted-by":"object"}]},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,22]]}}}