{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T19:01:01Z","timestamp":1793473261904,"version":"4.5.0"},"reference-count":55,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:00:00Z","timestamp":1738195200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:00:00Z","timestamp":1738195200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100007710","name":"University of Connecticut","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Breast cancer screening via mammography plays a crucial role in early detection, significantly impacting women's health outcomes worldwide. However, the manual analysis of mammographic images is time\u2010consuming and requires specialized expertise, presenting substantial challenges in medical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To address these challenges, we introduce a CNN\u2010Transformer based model tailored for breast cancer classification through mammographic analysis. This model leverages both prior and current images to monitor temporal changes, aiming to enhance the efficiency and accuracy (ACC) of computer\u2010aided diagnosis systems by mimicking the detailed examination process of radiologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, our proposed model incorporates a novel integration of a position\u2010wise feedforward network and multi\u2010head self\u2010attention, enabling it to detect abnormal or cancerous changes in mammograms over time. Additionally, the model employs positional encoding and channel attention methods to accurately highlight critical spatial features, thus precisely differentiating between normal and cancerous tissues. Our methodology utilizes focal loss (FL) to precisely address challenging instances that are difficult to classify, reducing false negatives and false positives to improve diagnostic ACC.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      We compared our model with eight baseline models; specifically, we utilized only current images for the single model ResNet50 while employing both prior and current images for the remaining models in terms of accuracy (ACC), sensitivity (SEN), precision (PRE), specificity (SPE), F1 score, and area under the curve (AUC). The results demonstrate that the proposed model outperforms the baseline models, achieving an ACC of 90.80%, SEN of 90.80%, PRE of 90.80%, SPE of 90.88%, an F1 score of 90.95%, and an AUC of 92.58%. The codes and related information are available at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/NabaviLab\/PCTM\">https:\/\/github.com\/NabaviLab\/PCTM<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our proposed CNN\u2010Transformer model integrates both prior and current images, removes long\u2010range dependencies, and enhances its capability for nuanced classification. The application of FL reduces false positive rate (FPR) and false negative rates (FNR), improving both SEN and SPE. Furthermore, the model achieves the lowest false discovery rate and FNR across various abnormalities, including masses, calcification, and architectural distortions (ADs). These low error rates highlight the model's reliability and underscore its potential to improve early breast cancer detection in clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17650","type":"journal-article","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T00:30:46Z","timestamp":1738283446000},"page":"2999-3014","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Hybrid transformer\u2010based model for mammogram classification by integrating prior and current images"],"prefix":"10.1002","volume":"52","author":[{"given":"Afsana Ahsan","family":"Jeny","sequence":"first","affiliation":[{"name":"School of Computing University of Connecticut Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahand","family":"Hamzehei","sequence":"additional","affiliation":[{"name":"School of Computing University of Connecticut Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annie","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Radiology UConn Health Farmington Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen Andrew","family":"Baker","sequence":"additional","affiliation":[{"name":"Department of Radiology UConn Health Farmington Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tucker","family":"Van Rathe","sequence":"additional","affiliation":[{"name":"Department of Radiology UConn Health Farmington Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computing University of Connecticut Storrs Connecticut USA"},{"name":"Department of Computer Science University of Cincinnati Cincinnati Ohio USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clifford","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiology UConn Health Farmington Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheida","family":"Nabavi","sequence":"additional","affiliation":[{"name":"School of Computing University of Connecticut Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21708"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-18-0098"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2017.04.024"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(20)30215-1"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-12-0468"},{"key":"e_1_2_10_7_1","article-title":"Frequently asked questions about mammography and the USPSTF recommendations: a guide for practitioners","author":"Berg W","year":"2009","journal-title":"Reston: Society of Breast Imaging"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000166"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.17.18730"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.147.6.1149"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2421050684"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.j4683"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.18.20392"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2013.2286539"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.07.046"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.10.040"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3002559"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3054248"},{"key":"e_1_2_10_19_1","unstructured":"LotterW SorensenG CoxD.A multi\u2010scale CNN and curriculum learning strategy for mammogram classification. In:Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop DLMIA 2017 and 7th International Workshop ML\u2010CDS 2017 Held in Conjunction with MICCAI 2017 Qu\u00e9bec City QC Canada September 14 Proceedings 3.Springer;2017:163\u2010177."},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-22437-z"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2945514"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-019-1494-z"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/biology11010015"},{"key":"e_1_2_10_24_1","first-page":"346","volume-title":"International Workshop on Machine Learning in Medical Imaging","author":"Junayed MS","year":"2023"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-810408-8.00019-5"},{"key":"e_1_2_10_26_1","first-page":"310","volume-title":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","author":"Carneiro G","year":"2017"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2953318"},{"key":"e_1_2_10_28_1","article-title":"Screening mammogram classification with prior exams","author":"Park J","year":"2019","journal-title":"arXiv preprint arXiv:1907.13057"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0237674"},{"key":"e_1_2_10_30_1","first-page":"133","volume-title":"2021 International Symposium on Electrical and Electronics Engineering (ISEE)","author":"Quy HD","year":"2021"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.028"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3077484"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"HamzeheiS JenyAA JinA YangC NabaviS.Benchmarking distance functions in Siamese networks for current and prior mammogram image analysis. In:2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).IEEE;2024:1996\u20102003.","DOI":"10.1109\/BIBM62325.2024.10822291"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.4.4.044501"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15598"},{"key":"e_1_2_10_36_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et\u00a0al.An image is worth 16x16 words: transformers for image recognition at scale.arXiv preprint arXiv:2010.11929.2020;abs\/2010.11929."},{"key":"e_1_2_10_37_1","doi-asserted-by":"crossref","unstructured":"KamranSA HossainKF TavakkoliA ZuckerbrodSL BakerSA.VTGAN: semi\u2010supervised retinal image synthesis and disease prediction using vision transformers. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2021:3235\u20103245.","DOI":"10.1109\/ICCVW54120.2021.00362"},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"GheflatiB RivazH.Vision transformers for classification of breast ultrasound images. In:2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).IEEE;2022:480\u2010483.","DOI":"10.1109\/EMBC48229.2022.9871809"},{"key":"e_1_2_10_39_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA TangY NathV et\u00a0al.UNETR: transformers for 3d medical image segmentation. In:Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision.IEEE;2022:574\u2010584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aba4373"},{"key":"e_1_2_10_41_1","first-page":"389","article-title":"Enhancing breast cancer risk prediction by incorporating prior images","volume":"14224","author":"Lee H","year":"2023","journal-title":"arXiv preprint arXiv:2303.15699"},{"key":"e_1_2_10_42_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Delving deep into rectifiers: surpassing human\u2010level performance on imagenet classification. In:Proceedings of the IEEE International Conference on Computer Vision.IEEE;2015:1026\u20101034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_10_43_1","article-title":"A data\u2010scalable transformer for medical image segmentation: architecture, model efficiency, and benchmark","author":"Gao Y","year":"2022","journal-title":"arXiv preprint arXiv:2203.00131"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2021.102026"},{"key":"e_1_2_10_45_1","volume-title":"ICML Deep Learning Workshop","author":"Koch G","year":"2015"},{"key":"e_1_2_10_46_1","first-page":"1","article-title":"MV\u2010Swin\u2010T: mammogram classification with multi\u2010view Swin transformer","author":"Sarker S","year":"2024","journal-title":"arXiv preprint arXiv:2402.16298"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.177"},{"key":"e_1_2_10_48_1","first-page":"123","article-title":"The Chinese Mammography Database (CMMD): an online mammography database with biopsy confirmed types for machine diagnosis of breast","author":"Cui C","year":"2021","journal-title":"Cancer Imaging Archive"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.19100"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02100-7"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106465"},{"key":"e_1_2_10_52_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR LiL\u2010J LiK Fei\u2010FeiL.Imagenet: a large\u2010scale hierarchical image database. In:2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2009:248\u2010255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-10834-0"},{"key":"e_1_2_10_54_1","doi-asserted-by":"crossref","unstructured":"SelvarajuRR CogswellM DasA VedantamR ParikhD BatraD.Grad\u2010CAM: visual explanations from deep networks via gradient\u2010based localization. In:Proceedings of the IEEE International Conference on Computer Vision.IEEE;2017:618\u2010626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-18-1115"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3233535"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17650","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.17650","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T10:01:04Z","timestamp":1777716064000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,30]]},"references-count":55,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1002\/mp.17650"],"URL":"https:\/\/doi.org\/10.1002\/mp.17650","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,30]]},"assertion":[{"value":"2024-05-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}