{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:45:45Z","timestamp":1775274345954,"version":"3.50.1"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Purpose<\/jats:title>\n            <jats:p>Breast cancer remains one of the most prevalent cancers globally, necessitating effective early screening and diagnosis. This study investigates the effectiveness and generalizability of our recently proposed data augmentation technique, attention-guided erasing (AGE), across various transfer learning classification tasks for breast abnormality classification in mammography.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>AGE utilizes attention head visualizations from DINO self-supervised pretraining to weakly localize regions of interest (ROI) in images. These localizations are then used to stochastically erase non-essential background information from training images during transfer learning. Our research evaluates AGE across two image-level and three patch-level classification tasks. The image-level tasks involve breast density categorization in digital mammography (DM) and malignancy classification in contrast-enhanced mammography (CEM). Patch-level tasks include classifying calcifications and masses in scanned film mammography (SFM), as well as malignancy classification of ROIs in CEM.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>AGE significantly boosts classification performance with statistically significant improvements in mean F1-scores across four tasks compared to baselines. Specifically, for image-level classification of breast density in DM and malignancy in CEM, we achieve gains of 2% and 1.5%, respectively. Additionally, for patch-level classification of calcifications in SFM and CEM ROIs, gains of 0.4% and 0.6% are observed, respectively. However, marginal improvement is noted in the mass classification task, indicating the necessity for further optimization in tasks where critical features may be obscured by erasing techniques.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>Our findings underscore the potential of AGE, a dataset- and task-specific augmentation strategy powered by self-supervised learning, to enhance the downstream classification performance of DL models, particularly involving ViTs, in medical imaging.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-024-03317-6","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T11:46:27Z","timestamp":1736941587000},"page":"433-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Attention-guided erasing for enhanced transfer learning in breast abnormality classification"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8067-1150","authenticated-orcid":false,"given":"Adarsh Bhandary","family":"Panambur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheethal","family":"Bhat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prathmesh","family":"Madhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siming","family":"Bayer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"issue":"3","key":"3317_CR1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","volume":"71","author":"H Sung","year":"2021","unstructured":"Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, Bray F (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71(3):209\u2013249","journal-title":"CA Cancer J Clin"},{"key":"3317_CR2","unstructured":"Sickles EA, D\u2019Orsi CJ, Bassett LW, Appleton CM, Berg WA, Burnside ES et al (2013) ACR BI-RADS\u00ae mammography. ACR BI-RADS\u00ae Atlas, Breast Imaging Reporting and Data System 5"},{"issue":"4","key":"3317_CR3","doi-asserted-by":"publisher","first-page":"990","DOI":"10.4143\/crt.2016.488","volume":"49","author":"PDY Trieu","year":"2017","unstructured":"Trieu PDY, Mello-Thoms C, Peat JK, Do TD, Brennan PC (2017) Risk factors of female breast cancer in vietnam: a case-control study. Cancer Res Treatment Off J Korean Cancer Associat 49(4):990\u20131000","journal-title":"Cancer Res Treatment Off J Korean Cancer Associat"},{"key":"3317_CR4","doi-asserted-by":"publisher","unstructured":"Nguyen HTX, Tran SB, Nguyen DB, Pham HH, Nguyen HQ (2022) A novel multi-view deep learning approach for BI-RADS and density assessment of mammograms. In: 2022 44th Annual International Conference of the IEEE EMBC, pp. 2144\u20132148. https:\/\/doi.org\/10.1109\/EMBC48229.2022.9871564","DOI":"10.1109\/EMBC48229.2022.9871564"},{"issue":"5","key":"3317_CR5","doi-asserted-by":"publisher","first-page":"267","DOI":"10.2214\/AJR.17.19355","volume":"211","author":"V Sorin","year":"2018","unstructured":"Sorin V, Yagil Y, Yosepovich A, Shalmon A, Gotlieb M, Neiman OH, Sklair-Levy M (2018) CESM in women with intermediate breast cancer risk and dense breasts. AJR Am J Roentgenol 211(5):267\u2013274","journal-title":"AJR Am J Roentgenol"},{"key":"3317_CR6","doi-asserted-by":"publisher","first-page":"111457","DOI":"10.1016\/j.ejrad.2024.111457","volume":"16","author":"O D\u00edaz","year":"2024","unstructured":"D\u00edaz O, Rodr\u00edguez A, Sechopoulos I (2024) Artificial intelligence for breast cancer detection: Technology, challenges, and prospects. Eur. J. Radiol. 16:111457","journal-title":"Eur. J. Radiol."},{"issue":"11","key":"3317_CR7","doi-asserted-by":"publisher","first-page":"988","DOI":"10.3390\/diagnostics10110988","volume":"10","author":"N Saffari","year":"2020","unstructured":"Saffari N, Rashwan HA, Abdel-Nasser M, Kumar Singh V, Arenas M, Mangina E, Herrera B, Puig D (2020) Fully automated breast density segmentation and classification using deep learning. Diagnostics 10(11):988","journal-title":"Diagnostics"},{"issue":"2","key":"3317_CR8","doi-asserted-by":"publisher","first-page":"531","DOI":"10.31557\/APJCP.2023.24.2.531","volume":"24","author":"BS Abunasser","year":"2023","unstructured":"Abunasser BS, Al-Hiealy MRJ, Zaqout IS, Abu-Naser SS (2023) Convolution neural network for breast cancer detection and classification using deep learning. Asian Pacific J Cancer Prev: APJCP 24(2):531","journal-title":"Asian Pacific J Cancer Prev: APJCP"},{"issue":"1","key":"3317_CR9","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1038\/s41598-023-29875-4","volume":"13","author":"AS Elkorany","year":"2023","unstructured":"Elkorany AS, Elsharkawy ZF (2023) Efficient breast cancer mammograms diagnosis using three deep neural networks and term variance. Sci Rep 13(1):2663","journal-title":"Sci Rep"},{"key":"3317_CR10","first-page":"249","volume":"14","author":"S Perek","year":"2019","unstructured":"Perek S, Kiryati N, Zimmerman-Moreno G, Sklair-Levy M, Konen E, Mayer A (2019) Classification of contrast-enhanced spectral mammography (cesm) images. Int J Comput Ass Rad 14:249\u2013257","journal-title":"Int J Comput Ass Rad"},{"key":"3317_CR11","doi-asserted-by":"crossref","unstructured":"Caron M, Touvron H, Misra I, J\u00e9gou H, Mairal J, Bojanowski P, Joulin A (2021) Emerging properties in self-supervised vision transformers. In: Proc. ICCV. https:\/\/github.com\/facebookresearch\/dino","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"3317_CR12","unstructured":"Fu S, Hamilton M, Brandt LE, Feldmann A, Zhang Z, Freeman WT (2024) Featup: A model-agnostic framework for features at any resolution. In: The Twelfth ICLR. https:\/\/openreview.net\/forum?id=GkJiNn2QDF"},{"key":"3317_CR13","doi-asserted-by":"crossref","unstructured":"Panambur AB, Yu H, Bhat S, Madhu P, Bayer S, Maier A (2024) Attention-guided erasing: Novel augmentation method for enhancing downstream breast density classification. In: BVM Workshop, pp. 13\u201318. Springer","DOI":"10.1007\/978-3-658-44037-4_8"},{"issue":"1","key":"3317_CR14","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1038\/s41597-023-02100-7","volume":"10","author":"HT Nguyen","year":"2023","unstructured":"Nguyen HT, Nguyen HQ, Pham HH, Lam K, Le LT, Dao M, Vu V (2023) VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography. Sci Data 10(1):277","journal-title":"Sci Data"},{"key":"3317_CR15","doi-asserted-by":"crossref","unstructured":"Khaled R, Helal M, Alfarghaly O, Mokhtar O, Elkorany A, El Kassas H, Fahmy A (2022) Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research. Sci Data 9(1):122","DOI":"10.1038\/s41597-022-01238-0"},{"key":"3317_CR16","doi-asserted-by":"crossref","unstructured":"Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M et al (2013) The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imag 26(6):1045\u20131057","DOI":"10.1007\/s10278-013-9622-7"},{"issue":"1","key":"3317_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2017.177","volume":"4","author":"RS Lee","year":"2017","unstructured":"Lee RS, Gimenez F, Hoogi A, Miyake KK, Gorovoy M, Rubin DL (2017) A curated mammography data set for use in computer-aided detection and diagnosis research. Sci data 4(1):1\u20139","journal-title":"Sci data"},{"key":"3317_CR18","first-page":"13001","volume":"34","author":"Z Zhong","year":"2020","unstructured":"Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. Proc of the AAAI Conf Artif Intell 34:13001\u201313008","journal-title":"Proc of the AAAI Conf Artif Intell"},{"key":"3317_CR19","doi-asserted-by":"crossref","unstructured":"Panambur AB, Madhu P, Maier A (2022) Effect of RHE on breast calcification analysis using deep learning. In: BVM 2022: Proceedings, German Workshop on Medical Image Computing, Heidelberg, June 2022, pp. 173\u2013178. Springer","DOI":"10.1007\/978-3-658-36932-3_38"},{"issue":"5","key":"3317_CR20","doi-asserted-by":"publisher","first-page":"141","DOI":"10.3390\/jimaging8050141","volume":"8","author":"P Oza","year":"2022","unstructured":"Oza P, Sharma P, Patel S, Adedoyin F, Bruno A (2022) Image augmentation techniques for mammogram analysis. J Imag 8(5):141","journal-title":"J Imag"},{"key":"3317_CR21","first-page":"129270","volume":"12927","author":"AB Panambur","year":"2024","unstructured":"Panambur AB, Madhu P, Bayer S, Maier A (2024) Enhancing downstream classification of breast abnormalities in CESM using a neighborhood representation loss. Int Soc Opt Photon 12927:129270","journal-title":"Int Soc Opt Photon"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03317-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-024-03317-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03317-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T09:14:21Z","timestamp":1742721261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-024-03317-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":21,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["3317"],"URL":"https:\/\/doi.org\/10.1007\/s11548-024-03317-6","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"assertion":[{"value":"10 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare no affiliations or involvement with any entity having financial or non-financial interests in the subject of this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The methods in this paper are not available for commercial use, with no guarantee of future availability. Intended for research use only.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclaimer."}}]}}