{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T21:36:18Z","timestamp":1790717778388,"version":"4.1.0"},"reference-count":49,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"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":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Automatic detection of very small and nonmass abnormalities from mammogram images has remained challenging. In clinical practice for each patient, radiologists commonly not only screen the mammogram images obtained during the examination, but also compare them with previous mammogram images to make a clinical decision. To design an artificial intelligence (AI) system to mimic radiologists for better cancer detection, in this work we proposed an end\u2010to\u2010end enhanced Siamese convolutional neural network to detect breast cancer using previous year and current year mammogram\u00a0images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed Siamese\u2010based network uses high\u2010resolution mammogram images and fuses features of pairs of previous year and current year mammogram images to predict cancer probabilities. The proposed approach is developed based on the concept of one\u2010shot learning that learns the abnormal differences between current and prior images instead of abnormal objects, and as a result can perform better with small sample size data sets. We developed two variants of the proposed network. In the first model, to fuse the features of current and previous images, we designed an enhanced distance learning network that considers not only the overall distance, but also the pixel\u2010wise distances between the features. In the other model, we concatenated the features of current and previous images to fuse\u00a0them.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We compared the performance of the proposed models with those of some baseline models that use current images only (ResNet and VGG) and also use current and prior images (long short\u2010term memory [LSTM] and vanilla Siamese) in terms of accuracy, sensitivity, precision, F1 score, and area under the curve (AUC). Results show that the proposed models outperform the baseline models and the proposed model with the distance learning network performs the best (accuracy: 0.92, sensitivity: 0.93, precision: 0.91, specificity: 0.91, F1: 0.92 and AUC: 0.95).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Integrating prior mammogram images improves automatic cancer classification, specially for very small and nonmass abnormalities. For classification models that integrate current and prior mammogram images, using an enhanced and effective distance learning network can advance the performance of the\u00a0models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.15598","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T16:33:01Z","timestamp":1646929981000},"page":"3654-3669","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Feature fusion Siamese network for breast cancer detection comparing current and prior mammograms"],"prefix":"10.1002","volume":"49","author":[{"given":"Jun","family":"Bai","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering University of Connecticut  Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annie","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Connecticut School of Medicine  Farmington Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering University of Connecticut  Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clifford","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Connecticut School of Medicine  Farmington Connecticut USA"},{"name":"Department of Radiology UConn Health  Farmington Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheida","family":"Nabavi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering University of Connecticut  Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,4,22]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21590"},{"key":"e_1_2_11_3_1","unstructured":"American Cancer Society.How Common is Breast Cancer?2020.https:\/\/www.cancer.org\/cancer\/breast\u2010cancer\/about\/how\u2010common\u2010is\u2010breast\u2010cancer.html"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.soncn.2017.02.009"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(20010501)91:9<1724::AID-CNCR1190>3.0.CO;2-V"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0959-8049(03)00259-4"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.3322\/canjclin.53.3.141"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/jso.20801"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiographics.18.5.9747612"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2014.1087"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.7326\/M15-0970"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-017-9993-2"},{"key":"e_1_2_11_13_1","unstructured":"HangW LiuZ&HannunA.GlimpseNet: Attentional Methods for Full\u2010Image Mammogram Diagnosis.2017:9.http:\/\/cs231n.stanford.edu\/reports\/2017\/pdfs\/517.pdf"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_20"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-22437-z"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.538937"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.993133"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41546-8_7"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12110"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"AbbasQ.DeepCAD: a computer\u2010aided diagnosis system for mammographic masses using deep invariant features.Multidisciplinary Digital Publishing Institute;2016;5:28.","DOI":"10.3390\/computers5040028"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.3.3.034501"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2945514"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","unstructured":"HaywardJH RayKM WisnerDJ et\u00a0al.Improving screening mammography outcomes through comparison with multiple prior mammograms.Public Access;2016;207:918.","DOI":"10.2214\/AJR.15.15917"},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"PerekS NessL AmitM BarkanE&AmitG.Learning from longitudinal mammography studies. International Conference on Medical Image Computing and Computer\u2010Assisted Intervention. Springer 2019:712\u2010720.","DOI":"10.1007\/978-3-030-32226-7_79"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.4.4.044501"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3054390"},{"key":"e_1_2_11_27_1","doi-asserted-by":"crossref","unstructured":"HeidariM Fouladi\u2010GhalehK.Using siamese networks with transfer learning for face recognition on small\u2010samples datasets.2020 International Conference on Machine Vision and Image Processing (MVIP).IEEE;2020:1\u20104.","DOI":"10.1109\/MVIP49855.2020.9116915"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101631"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200079"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107700"},{"key":"e_1_2_11_31_1","first-page":"1571","article-title":"Classification of neurofibromatosis\u2010related dystrophic or nondystrophic scoliosis based on image features using bilateral","volume":"48","author":"He Z","year":"2021","journal-title":"CNN"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102697"},{"key":"e_1_2_11_33_1","unstructured":"ChungY\u2010A&WengW\u2010H.Learning deep representations of medical images using siamese CNNs with application to content\u2010based image retrieval. arXiv preprint arXiv:1711.08490.2017."},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14397"},{"key":"e_1_2_11_35_1","volume-title":"Medical Imaging 2020: Computer\u2010Aided Diagnosis","author":"Mahajan A"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0255-1"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102083"},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"LiuY ZhangF ZhangQ WangS WangY YuY.Cross\u2010view correspondence reasoning based on bipartite graph convolutional network for mammogram mass detection.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2020:3812\u20103822.","DOI":"10.1109\/CVPR42600.2020.00387"},{"key":"e_1_2_11_39_1","unstructured":"KochG et\u00a0al.Siamese neural networks for one\u2010shot image recognition.ICML Deep Learning Workshop. vol2.Lille;2015."},{"key":"e_1_2_11_40_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Delving deep into rectifiers: surpassing human\u2010level performance on imagenet classification.Proceedings of the IEEE International Conference on Computer Vision.2015:1026\u20101034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_11_41_1","unstructured":"SimonyanK&ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. arXiv preprint arXiv:1409.1556.2014."},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_11_43_1","doi-asserted-by":"crossref","unstructured":"ClarkK VendtB SmithK et\u00a0al.The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository.26:1045\u20101057.","DOI":"10.1007\/s10278-013-9622-7"},{"key":"e_1_2_11_44_1","unstructured":"Sawyer\u2010LeeR GimenezF HoogiA&RubinD.Curated breast imaging subset of DDSM.2016."},{"key":"e_1_2_11_45_1","unstructured":"CuiC LiL&CaiH et\u00a0al.The Chinese Mammography Database (CMMD): an online mammography database with biopsy confirmed types for machine diagnosis of breast.2021."},{"key":"e_1_2_11_46_1","unstructured":"BudaM SahaA&WalshR et\u00a0al.Breast cancer screening \u2010 digital breast tomosynthesis (BCS\u2010DBT).2020"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aafcda"},{"key":"e_1_2_11_48_1","volume-title":"Synthesized 2D Mammographic Imaging","author":"Smith A","year":"2016"},{"key":"e_1_2_11_49_1","doi-asserted-by":"crossref","unstructured":"PizerSM AmburnEP&AustinJD et\u00a0al.Adaptive histogram equalization and its variations.Computer vision graphics and image processing.1987;39(3):355\u2010368.","DOI":"10.1016\/S0734-189X(87)80186-X"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15598","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15598","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T03:51:34Z","timestamp":1692849094000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,22]]},"references-count":49,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10.1002\/mp.15598"],"URL":"https:\/\/doi.org\/10.1002\/mp.15598","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,22]]},"assertion":[{"value":"2021-12-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}