{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T23:11:10Z","timestamp":1794438670391,"version":"4.9.1"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T00:00:00Z","timestamp":1657238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T00:00:00Z","timestamp":1657238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001407","name":"Department of Biotechnology, Ministry of Science and Technology, India","doi-asserted-by":"publisher","award":["BT\/PR33193\/AI\/133\/5\/2019"],"award-info":[{"award-number":["BT\/PR33193\/AI\/133\/5\/2019"]}],"id":[{"id":"10.13039\/501100001407","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001407","name":"Department of Biotechnology, Ministry of Science and Technology, India","doi-asserted-by":"publisher","award":["27\/02\/2020"],"award-info":[{"award-number":["27\/02\/2020"]}],"id":[{"id":"10.13039\/501100001407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>While detection of malignancies on mammography has received a boost with the use of Convolutional Neural Networks (CNN), detection of cancers of very small size remains challenging. This is however clinically significant as the purpose of mammography is early detection of cancer, making it imperative to pick them up when they are still very small. Mammography has the highest spatial resolution (image sizes as high as 3328\u00a0\u00d7\u00a04096 pixels) out of all imaging modalities, a requirement that stems from the need to detect fine features of the smallest cancers on screening. However due to computational constraints, most state of the art CNNs work on reduced resolution images. Those that work on higher resolutions, compromise on global context and work at single scale. In this work, we show that resolution, scale and image-context are all important independent factors in detection of small masses. We thereby use a fully convolutional network, with the ability to take any input size. In addition, we incorporate a systematic multi-scale, multi-resolution approach, and encode image context, which we show are critical factors to detection of small masses. We show that this approach improves the detection of cancer, particularly for small masses in comparison to the baseline model. We perform a single institution multicentre study, and show the performance of the model on a diagnostic mammography dataset, a screening mammography dataset, as well as a curated dataset of small cancers\u2009&lt;\u20091\u00a0cm in size. We show that our approach improves the sensitivity from 61.53 to 87.18% at 0.3 False Positives per Image (FPI) on this small cancer dataset. Model and code are available from\u00a0<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/amangupt01\/Small_Cancer_Detection\">https:\/\/github.com\/amangupt01\/Small_Cancer_Detection<\/jats:ext-link><\/jats:p>","DOI":"10.1038\/s41598-022-15259-7","type":"journal-article","created":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T11:03:10Z","timestamp":1657278190000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Ultra-high resolution, multi-scale, context-aware approach for detection of\u00a0small cancers on mammography"],"prefix":"10.1038","volume":"12","author":[{"given":"Krithika","family":"Rangarajan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aman","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saptarshi","family":"Dasgupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uday","family":"Marri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arun Kumar","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Smriti","family":"Hari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhashis","family":"Banerjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chetan","family":"Arora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,8]]},"reference":[{"key":"15259_CR1","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","volume":"68","author":"F Bray","year":"2018","unstructured":"Bray, F. et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA. Cancer J. Clin. 68, 394\u2013424 (2018).","journal-title":"CA. Cancer J. Clin."},{"key":"15259_CR2","unstructured":"Cancer Facts and Statistics 2015 | Research | American Cancer Society. https:\/\/www.cancer.org\/research\/cancer-facts-statistics\/all-cancer-facts-figures\/cancer-facts-figures-2015.html."},{"key":"15259_CR3","doi-asserted-by":"publisher","first-page":"S115","DOI":"10.3747\/co.25.3770","volume":"25","author":"JM Seely","year":"2018","unstructured":"Seely, J. M. & Alhassan, T. Screening for breast cancer in 2018-what should we be doing today?. Curr. Oncol. Tor. Ont 25, S115\u2013S124 (2018).","journal-title":"Curr. Oncol. Tor. Ont"},{"key":"15259_CR4","doi-asserted-by":"publisher","first-page":"22985","DOI":"10.18632\/oncotarget.3945","volume":"6","author":"Y-Z Zheng","year":"2015","unstructured":"Zheng, Y.-Z., Wang, L., Hu, X. & Shao, Z.-M. Effect of tumor size on breast cancer-specific survival stratified by joint hormone receptor status in a SEER population-based study. Oncotarget 6, 22985\u201322995 (2015).","journal-title":"Oncotarget"},{"key":"15259_CR5","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1016\/j.patcog.2005.07.006","volume":"39","author":"HD Cheng","year":"2006","unstructured":"Cheng, H. D. et al. Approaches for automated detection and classification of masses in mammograms. Pattern Recognit. 39, 646\u2013668 (2006).","journal-title":"Pattern Recognit."},{"key":"15259_CR6","doi-asserted-by":"publisher","first-page":"208","DOI":"10.2214\/AJR.15.15987","volume":"208","author":"P Grabler","year":"2017","unstructured":"Grabler, P., Sighoko, D., Wang, L., Allgood, K. & Ansell, D. Recall and cancer detection rates for screening mammography: Finding the sweet spot. AJR Am. J. Roentgenol. 208, 208\u2013213 (2017).","journal-title":"AJR Am. J. Roentgenol."},{"key":"15259_CR7","doi-asserted-by":"publisher","unstructured":"Hepsa\u011f, P. U., \u00d6zel, S. A. & Yaz\u0131c\u0131, A. Using deep learning for mammography classification. In 2017 International Conference on Computer Science and Engineering (UBMK) 418\u2013423. https:\/\/doi.org\/10.1109\/UBMK.2017.8093429 (2017).","DOI":"10.1109\/UBMK.2017.8093429"},{"key":"15259_CR8","doi-asserted-by":"crossref","unstructured":"Zhu, W., Lou, Q., Vang, Y. S. & Xie, X. Deep multi-instance networks with sparse label assignment for whole mammogram classification. ArXiv170508550 Cs (2017).","DOI":"10.1101\/095794"},{"key":"15259_CR9","doi-asserted-by":"publisher","first-page":"4165","DOI":"10.1038\/s41598-018-22437-z","volume":"8","author":"D Ribli","year":"2018","unstructured":"Ribli, D., Horv\u00e1th, A., Unger, Z., Pollner, P. & Csabai, I. Detecting and classifying lesions in mammograms with Deep Learning. Sci. Rep. 8, 4165 (2018).","journal-title":"Sci. Rep."},{"key":"15259_CR10","doi-asserted-by":"publisher","unstructured":"Detection of Masses in Mammograms Using a One-Stage Object Detector Based on a Deep Convolutional Neural Network. https:\/\/journals.plos.org\/plosone\/article?id=https:\/\/doi.org\/10.1371\/journal.pone.0203355.","DOI":"10.1371\/journal.pone.0203355"},{"key":"15259_CR11","doi-asserted-by":"publisher","first-page":"12495","DOI":"10.1038\/s41598-019-48995-4","volume":"9","author":"L Shen","year":"2019","unstructured":"Shen, L. et al. Deep Learning to Improve Breast Cancer Detection on Screening Mammography. Sci. Rep. 9, 12495 (2019).","journal-title":"Sci. Rep."},{"key":"15259_CR12","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n1872","volume":"374","author":"K Freeman","year":"2021","unstructured":"Freeman, K. et al. Use of artificial intelligence for image analysis in breast cancer screening programmes: Systematic review of test accuracy. BMJ 374, n1872 (2021).","journal-title":"BMJ"},{"key":"15259_CR13","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.6.3.031409","volume":"6","author":"R Agarwal","year":"2019","unstructured":"Agarwal, R., Diaz, O., Llad\u00f3, X., Yap, M. H. & Mart\u00ed, R. Automatic mass detection in mammograms using deep convolutional neural networks. J. Med. Imaging 6, 031409 (2019).","journal-title":"J. Med. Imaging"},{"key":"15259_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.101749","volume":"103","author":"B Savelli","year":"2020","unstructured":"Savelli, B., Bria, A., Molinara, M., Marrocco, C. & Tortorella, F. A multi-context CNN ensemble for small lesion detection. Artif. Intell. Med. 103, 101749 (2020).","journal-title":"Artif. Intell. Med."},{"key":"15259_CR15","doi-asserted-by":"crossref","unstructured":"Lotter, W., Sorensen, G. & Cox, D. A multi-scale cnn and curriculum learning strategy for mammogram classification. ArXiv170706978 Cs (2017).","DOI":"10.1007\/978-3-319-67558-9_20"},{"key":"15259_CR16","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.1148\/rg.226025128","volume":"22","author":"MF McNitt-Gray","year":"2002","unstructured":"McNitt-Gray, M. F. AAPM\/RSNA physics tutorial for residents: Topics in CT. Radiation dose in CT. Radiographics 22, 1541\u20131553 (2002).","journal-title":"Radiographics"},{"key":"15259_CR17","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/S0037-198X(03)00048-8","volume":"38","author":"ADA Maidment","year":"2003","unstructured":"Maidment, A. D. A. Digital mammography. Semin. Roentgenol. 38, 216\u2013230 (2003).","journal-title":"Semin. Roentgenol."},{"key":"15259_CR18","doi-asserted-by":"publisher","unstructured":"Hu, P. & Ramanan, D. Finding tiny faces. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1522\u20131530. https:\/\/doi.org\/10.1109\/CVPR.2017.166 (2017).","DOI":"10.1109\/CVPR.2017.166"},{"key":"15259_CR19","unstructured":"YOLOv5 Documentation. https:\/\/docs.ultralytics.com\/."},{"key":"15259_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117","volume":"107","author":"R Solovyev","year":"2021","unstructured":"Solovyev, R., Wang, W. & Gabruseva, T. Weighted boxes fusion: Ensembling boxes from different object detection models. Image Vis. Comput. 107, 104117 (2021).","journal-title":"Image Vis. Comput."},{"key":"15259_CR21","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1117\/12.955926","volume-title":"Application of Optical Instrumentation in Medicine VI","author":"PC Bunch","year":"1977","unstructured":"Bunch, P. C., Hamilton, J. F., Sanderson, G. K. & Simmons, A. H. A free response approach to the measurement and characterization of radiographic observer performance. In Application of Optical Instrumentation in Medicine VI Vol. 0127 124\u2013135 (International Society for Optics and Photonics, 1977)."},{"key":"15259_CR22","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1148\/radiol.2451060760","volume":"245","author":"RL Ellis","year":"2007","unstructured":"Ellis, R. L., Meade, A. A., Mathiason, M. A., Willison, K. M. & Logan-Young, W. Evaluation of computer-aided detection systems in the detection of small invasive breast carcinoma. Radiology 245, 88\u201394 (2007).","journal-title":"Radiology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-15259-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-15259-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-15259-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T07:01:18Z","timestamp":1669359678000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-15259-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,8]]},"references-count":22,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["15259"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-15259-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,8]]},"assertion":[{"value":"31 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"11622"}}