A deep learning approach for contrast-agent-free breast lesion detection and classification using adversarial synthesis of contrast-enhanced mammograms
Contrast-enhanced digital mammography (CEDM) has emerged as a promising complementary imaging modality for breast cancer diagnosis, offering enhanced lesion visualization and improved diagnostic accuracy, particularly for patients with dense breast tissues. However, the reliance of CEDM on contrast...
Saved in:
Published in | Image and vision computing Vol. 162; p. 105692 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.10.2025
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Contrast-enhanced digital mammography (CEDM) has emerged as a promising complementary imaging modality for breast cancer diagnosis, offering enhanced lesion visualization and improved diagnostic accuracy, particularly for patients with dense breast tissues. However, the reliance of CEDM on contrast agents poses challenges to patient safety and accessibility. To overcome those challenges, this paper introduces a deep learning methodology for improved breast lesion detection and classification. In particular, an image-to-image translation model based on cycle-consistent generative adversarial networks (CycleGAN) is utilized to generate synthetic CEDM (SynCEDM) images from full-field digital mammography in order to enhance visual contrast perception without the need for contrast agents. A new dataset of 3958 pairs of low-energy (LE) and CEDM images was collected from 2908 female subjects to train the CycleGAN model to generate SynCEDM images. Thus, we trained different You-Only-Look-Once (YOLO) architectures on CEDM and SynCEDM images for breast lesion detection and classification. SynCEDM images were generated with a structural similarity index (SSIM) of 0.94 ± 0.02. A YOLO lesion detector trained on original CEDM images led to a 91.34% accuracy, a 90.37% sensitivity, and a 92.06% specificity. In comparison, a detector trained on the SynCEDM images exhibited a comparable accuracy of 91.20%, a marginally higher sensitivity of 91.44%, and a slightly lower specificity of 91.30%. This approach not only aims to mitigate contrast agent risks but also to improve breast cancer detection and characterization using mammography.
•Synthetic CEDM images can be generated via image-to-image translation.•Synthesized CEDM images are safer to obtain than conventional CEDM.•CAD systems were developed for breast lesion detection and classification.•Remarkable performance was obtained with synthetic CEDM images. |
---|---|
AbstractList | Contrast-enhanced digital mammography (CEDM) has emerged as a promising complementary imaging modality for breast cancer diagnosis, offering enhanced lesion visualization and improved diagnostic accuracy, particularly for patients with dense breast tissues. However, the reliance of CEDM on contrast agents poses challenges to patient safety and accessibility. To overcome those challenges, this paper introduces a deep learning methodology for improved breast lesion detection and classification. In particular, an image-to-image translation model based on cycle-consistent generative adversarial networks (CycleGAN) is utilized to generate synthetic CEDM (SynCEDM) images from full-field digital mammography in order to enhance visual contrast perception without the need for contrast agents. A new dataset of 3958 pairs of low-energy (LE) and CEDM images was collected from 2908 female subjects to train the CycleGAN model to generate SynCEDM images. Thus, we trained different You-Only-Look-Once (YOLO) architectures on CEDM and SynCEDM images for breast lesion detection and classification. SynCEDM images were generated with a structural similarity index (SSIM) of 0.94 ± 0.02. A YOLO lesion detector trained on original CEDM images led to a 91.34% accuracy, a 90.37% sensitivity, and a 92.06% specificity. In comparison, a detector trained on the SynCEDM images exhibited a comparable accuracy of 91.20%, a marginally higher sensitivity of 91.44%, and a slightly lower specificity of 91.30%. This approach not only aims to mitigate contrast agent risks but also to improve breast cancer detection and characterization using mammography.
•Synthetic CEDM images can be generated via image-to-image translation.•Synthesized CEDM images are safer to obtain than conventional CEDM.•CAD systems were developed for breast lesion detection and classification.•Remarkable performance was obtained with synthetic CEDM images. |
ArticleNumber | 105692 |
Author | Mahmoud, Ahmed M. Gomaa, Mohamed Kamal, Rasha Rushdi, Muhammad A. Farouk, Amr Fouad, Noha M. Amin, Manar N. |
Author_xml | – sequence: 1 givenname: Manar N. surname: Amin fullname: Amin, Manar N. organization: Department of Biomedical Engineering and Systems, Cairo University, Giza 12613, Egypt – sequence: 2 givenname: Muhammad A. surname: Rushdi fullname: Rushdi, Muhammad A. organization: Department of Biomedical Engineering and Systems, Cairo University, Giza 12613, Egypt – sequence: 3 givenname: Rasha surname: Kamal fullname: Kamal, Rasha organization: Radiology Department, Faculty of Medicine - Kasr ElAiny Hospital (Women's Imaging Unit), Cairo University, Giza, Egypt – sequence: 4 givenname: Amr surname: Farouk fullname: Farouk, Amr organization: Department of Diagnostic Radiology, National Cancer Institute, Cairo, Egypt – sequence: 5 givenname: Mohamed surname: Gomaa fullname: Gomaa, Mohamed organization: Department of Diagnostic Radiology, National Cancer Institute, Cairo, Egypt – sequence: 6 givenname: Noha M. surname: Fouad fullname: Fouad, Noha M. organization: Department of Biomedical Engineering and Systems, Cairo University, Giza 12613, Egypt – sequence: 7 givenname: Ahmed M. surname: Mahmoud fullname: Mahmoud, Ahmed M. email: a.ehab.mahmoud@eng1.cu.edu.eg organization: Department of Biomedical Engineering and Systems, Cairo University, Giza 12613, Egypt |
BookMark | eNp9kM9qAjEQh3OwULV9gx7yAmuT6G52LwWR_oNCL-05jJNZjbiJJFvBJ-nrNquF3nqa4Qffj5lvwkY-eGLsToqZFLK6381cB0eXZkqoMkdl1agRGwtVqaKuy-qaTVLaCSG00M2YfS-5JTrwPUH0zm84HA4xAG55GyLH4PsIqS9gQ74v2kjE15FykoHkgs9wT9gPG3jLcQ8pudYhnKOvdG60R4oJooM9TyffbzOZeGj_2slvwSNZ3kHXhU2ELt2wqxb2iW5_55R9Pj1-rF6Kt_fn19XyrUCpVV-ssamlXpOQDc6taLCptC2xkaCppVqDklTpRqGVUMs5qIWWLUicI1otrZ1P2eLSizGkFKk1h5gFxpORwgxCzc5chJpBqLkIzdjDBaN829FRNAkdDT-4mH0YG9z_BT-r-Yof |
Cites_doi | 10.1016/j.bspc.2024.106255 10.1001/jamainternmed.2014.981 10.1021/cr100025t 10.1038/s41598-022-09929-9 10.1016/j.asoc.2023.110224 10.1016/j.radi.2023.02.025 10.1109/TPAMI.2020.2970919 10.3390/machines11070677 10.1016/j.ejrad.2014.05.015 10.1080/13696998.2023.2222035 10.1016/j.diii.2016.08.013 10.1109/TKDE.2021.3130191 10.1016/j.eswa.2023.120943 10.1016/j.bspc.2016.02.006 10.1186/1471-2288-13-91 10.1007/s10439-018-2044-4 10.1186/s13244-019-0756-0 10.1016/S0720-048X(99)00066-2 10.1117/1.JMI.4.3.035501 10.1016/j.engappai.2022.105151 10.1016/j.neunet.2023.05.028 10.1016/j.bspc.2023.104808 10.1016/j.acra.2019.10.034 10.1109/MSP.2017.2765202 10.1007/s11548-018-1876-6 10.1016/j.compmedimag.2024.102398 10.3390/technologies11020040 10.1007/s00330-015-3904-z 10.1016/j.jacr.2019.04.007 10.3390/jimaging9030069 |
ContentType | Journal Article |
Copyright | 2025 Elsevier B.V. |
Copyright_xml | – notice: 2025 Elsevier B.V. |
DBID | AAYXX CITATION |
DOI | 10.1016/j.imavis.2025.105692 |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Applied Sciences Engineering |
ExternalDocumentID | 10_1016_j_imavis_2025_105692 S026288562500280X |
GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABDPE ABFNM ABFRF ABJNI ABMAC ABOCM ABWVN ABXDB ACDAQ ACGFO ACGFS ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO ADTZH AEBSH AECPX AEFWE AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGCQF AGHFR AGQPQ AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RNS ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UHS UNMZH VOH WUQ XPP ZMT ZY4 ~G- AAYXX CITATION EFLBG |
ID | FETCH-LOGICAL-c172t-bc9817be019c3d09c967d5c91a7efe87a21e6792cd1a813a2471fa1c3ccd71dd3 |
IEDL.DBID | .~1 |
ISSN | 0262-8856 |
IngestDate | Wed Sep 03 16:41:34 EDT 2025 Sat Aug 30 17:13:31 EDT 2025 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Deep learning Image-to-image translation Breast cancer Generative adversarial network Contrast-enhanced digital mammography CycleGAN |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c172t-bc9817be019c3d09c967d5c91a7efe87a21e6792cd1a813a2471fa1c3ccd71dd3 |
ParticipantIDs | crossref_primary_10_1016_j_imavis_2025_105692 elsevier_sciencedirect_doi_10_1016_j_imavis_2025_105692 |
PublicationCentury | 2000 |
PublicationDate | October 2025 2025-10-00 |
PublicationDateYYYYMMDD | 2025-10-01 |
PublicationDate_xml | – month: 10 year: 2025 text: October 2025 |
PublicationDecade | 2020 |
PublicationTitle | Image and vision computing |
PublicationYear | 2025 |
Publisher | Elsevier B.V |
Publisher_xml | – name: Elsevier B.V |
References | Alukić, Homar, Pavić, Žibert, Mekiš (bb0025) May 2023; 29 Terreno, Castelli, Viale, Aime (bb0035) May 2010; 110 Karthi, Muthulakshmi, Priscilla, Praveen, Vanisri (bb0210) 2021 Sorin (bb0065) Sep. 2020; 27 Ndajah, Kikuchi, Watanabe, Muramatsu, Yukawa (bb0230) 2011; 4 National Cancer Institute (bb0015) 2025 Nori, Kaur (bb0175) 2018 Blankenburg (bb0075) Dec. 2023; 26 Zanardo (bb0070) Aug. 2019; 10 Kim, Cha, Kim, Lee, Kim (bb0140) 2017 Skandarani, Jodoin, Lalande (bb0100) Mar. 2023; 9 Shcherbakov, Brebels, Shcherbakova, Tyukov, Janovsky, Kamaev (bb0235) 2013; 24 Iman, Arabnia, Rasheed (bb0250) Mar. 2023; 11 Cheung, Tsai, Lo, Ueng, Huang, Chen (bb0060) Apr. 2016; 26 Goodfellow (bb0195) Jun. 2014; 3 The American Cancer Society medical and editorial content team (bb0010) 2025 Mi, Ma, Zheng, Zhang, Li, Wang (bb0205) Dec. 2023; 233 Ganaie, Hu, Malik, Tanveer, Suganthan (bb0255) Oct. 2022; 115 Abdelhafiz, Yang, Ammar, Nabavi (bb0080) Jun. 2019; 20 Al Jaberi, Patel, Al-Masri (bb0115) May 2023; 139 Mehmood, Bashir, Giri (bb0200) September-2022; 9 Isola, Zhu, Zhou, Efros (bb0120) Nov. 2017 Gwet (bb0260) 2019 Muller (bb0020) Jul. 1999; 31 Chow, Paramesran (bb0240) May 2016; 27 Perek, Kiryati, Zimmerman-Moreno, Sklair-Levy, Konen, Mayer (bb0085) Feb. 2019; 14 Danala (bb0045) Sep. 2018; 46 Radford, Metz, Chintala (bb0125) 2015 Francescone (bb0165) Aug. 2014; 83 Rofena (bb0160) Sep. 2024; 116 Weng (bb0150) 2019 Hussain (bb0190) Jul. 2023; 11 Serrano (bb0090) Aug. 2023; 165 Chaudhury, Sau (bb0095) May 2023; 3 Kim (bb0055) Oct. 2019; 16 Tosteson (bb0030) Jun. 2014; 174 Liu, Breuel, Kautz (bb0155) 2017 Oyelade, Ezugwu, Almutairi, Saha, Abualigah, Chiroma (bb0105) Apr. 2022; 12 Jiang, Zheng, Jia, Song, Ding (bb0265) 2021 World Health Organization (bb0005) 2025 Bochkovskiy, Wang, Liao (bb0220) Apr. 2020 Mao, Li, Xie, Lau, Wang, Smolley (bb0145) Dec. 2017 Karras, Laine, Aila (bb0135) Dec. 2018; 43 Chu, Zhmoginov, Sandler (bb0130) 2017 Wang, Mark Liao, Wu, Chen, Hsieh, Yeh (bb0215) Jun. 2020 Creswell, White, Dumoulin, Arulkumaran, Sengupta, Bharath (bb0180) Jan. 2018; 35 Runge (bb0040) 2001 Gui, Sun, Wen, Tao, Ye (bb0185) 2023; 35 Renieblas, Nogués, A. M. G. M.D, León, del Castillo (bb0225) Jul. 2017; 4 Fagerland, Lydersen, Laake (bb0245) Jul. 2013; 13 Li (bb0050) Feb. 2017; 98 Amin, Kamal, Farouk, Gomaa, Rushdi, Mahmoud (bb0170) Aug. 2023; 85 Jiménez-Gaona, Carrión-Figueroa, Lakshminarayanan, José Rodríguez-Álvarez (bb0110) Aug. 2024; 94 Radford (10.1016/j.imavis.2025.105692_bb0125) 2015 Fagerland (10.1016/j.imavis.2025.105692_bb0245) 2013; 13 World Health Organization (10.1016/j.imavis.2025.105692_bb0005) Ganaie (10.1016/j.imavis.2025.105692_bb0255) 2022; 115 Karthi (10.1016/j.imavis.2025.105692_bb0210) 2021 Gwet (10.1016/j.imavis.2025.105692_bb0260) 2019 Al Jaberi (10.1016/j.imavis.2025.105692_bb0115) 2023; 139 Gui (10.1016/j.imavis.2025.105692_bb0185) 2023; 35 Renieblas (10.1016/j.imavis.2025.105692_bb0225) 2017; 4 Amin (10.1016/j.imavis.2025.105692_bb0170) 2023; 85 Jiménez-Gaona (10.1016/j.imavis.2025.105692_bb0110) 2024; 94 Hussain (10.1016/j.imavis.2025.105692_bb0190) 2023; 11 Goodfellow (10.1016/j.imavis.2025.105692_bb0195) 2014; 3 Karras (10.1016/j.imavis.2025.105692_bb0135) 2018; 43 Tosteson (10.1016/j.imavis.2025.105692_bb0030) 2014; 174 Blankenburg (10.1016/j.imavis.2025.105692_bb0075) 2023; 26 Runge (10.1016/j.imavis.2025.105692_bb0040) Danala (10.1016/j.imavis.2025.105692_bb0045) 2018; 46 Bochkovskiy (10.1016/j.imavis.2025.105692_bb0220) Serrano (10.1016/j.imavis.2025.105692_bb0090) 2023; 165 Chow (10.1016/j.imavis.2025.105692_bb0240) 2016; 27 National Cancer Institute (10.1016/j.imavis.2025.105692_bb0015) 2025 Liu (10.1016/j.imavis.2025.105692_bb0155) 2017 Weng (10.1016/j.imavis.2025.105692_bb0150) 2019 Kim (10.1016/j.imavis.2025.105692_bb0140) 2017 Sorin (10.1016/j.imavis.2025.105692_bb0065) 2020; 27 Francescone (10.1016/j.imavis.2025.105692_bb0165) 2014; 83 Isola (10.1016/j.imavis.2025.105692_bb0120) 2017 Mao (10.1016/j.imavis.2025.105692_bb0145) 2017 Nori (10.1016/j.imavis.2025.105692_bb0175) 2018 The American Cancer Society medical and editorial content team (10.1016/j.imavis.2025.105692_bb0010) 2025 Rofena (10.1016/j.imavis.2025.105692_bb0160) 2024; 116 Ndajah (10.1016/j.imavis.2025.105692_bb0230) 2011; 4 Perek (10.1016/j.imavis.2025.105692_bb0085) 2019; 14 Cheung (10.1016/j.imavis.2025.105692_bb0060) 2016; 26 Abdelhafiz (10.1016/j.imavis.2025.105692_bb0080) 2019; 20 Oyelade (10.1016/j.imavis.2025.105692_bb0105) 2022; 12 Shcherbakov (10.1016/j.imavis.2025.105692_bb0235) 2013; 24 Alukić (10.1016/j.imavis.2025.105692_bb0025) 2023; 29 Iman (10.1016/j.imavis.2025.105692_bb0250) 2023; 11 Terreno (10.1016/j.imavis.2025.105692_bb0035) 2010; 110 Wang (10.1016/j.imavis.2025.105692_bb0215) 2020 Zanardo (10.1016/j.imavis.2025.105692_bb0070) 2019; 10 Creswell (10.1016/j.imavis.2025.105692_bb0180) 2018; 35 Mi (10.1016/j.imavis.2025.105692_bb0205) 2023; 233 Li (10.1016/j.imavis.2025.105692_bb0050) 2017; 98 Chaudhury (10.1016/j.imavis.2025.105692_bb0095) 2023; 3 Muller (10.1016/j.imavis.2025.105692_bb0020) 1999; 31 Skandarani (10.1016/j.imavis.2025.105692_bb0100) 2023; 9 Mehmood (10.1016/j.imavis.2025.105692_bb0200) 2022; 9 Chu (10.1016/j.imavis.2025.105692_bb0130) 2017 Kim (10.1016/j.imavis.2025.105692_bb0055) 2019; 16 Jiang (10.1016/j.imavis.2025.105692_bb0265) 2021 |
References_xml | – year: 2025 ident: bb0005 article-title: Breast Cancer – start-page: 68 year: 2021 end-page: 77 ident: bb0265 article-title: Synthesis of contrast-enhanced spectral mammograms from low-energy mammograms using cGAN-based synthesis network publication-title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 – year: 2018 ident: bb0175 article-title: Contrast-Enhanced Digital Mammography (CEDM) – year: Apr. 2020 ident: bb0220 article-title: YOLOv4: Optimal Speed and Accuracy of Object Detection – volume: 115 year: Oct. 2022 ident: bb0255 article-title: Ensemble deep learning: a review publication-title: Eng. Appl. Artif. Intell. – volume: 27 start-page: 145 year: May 2016 end-page: 154 ident: bb0240 article-title: Review of medical image quality assessment publication-title: Biomed. Signal Process. Control – volume: 31 start-page: 25 year: Jul. 1999 end-page: 34 ident: bb0020 article-title: Full-field digital mammography designed as a complete system publication-title: Eur. J. Radiol. – volume: 27 start-page: 1234 year: Sep. 2020 end-page: 1240 ident: bb0065 article-title: Background parenchymal enhancement at contrast-enhanced spectral mammography (CESM) as a breast cancer risk factor publication-title: Acad. Radiol. – volume: 10 start-page: 1 year: Aug. 2019 end-page: 15 ident: bb0070 article-title: Technique, protocols and adverse reactions for contrast-enhanced spectral mammography (CESM): a systematic review publication-title: Insights Imaging – start-page: 700 year: 2017 end-page: 708 ident: bb0155 article-title: Unsupervised image-to-image translation networks publication-title: NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems – volume: 20 start-page: 1 year: Jun. 2019 end-page: 20 ident: bb0080 article-title: Deep convolutional neural networks for mammography: advances, challenges and applications publication-title: BMC Bioinform. – volume: 12 start-page: 1 year: Apr. 2022 end-page: 30 ident: bb0105 article-title: A generative adversarial network for synthetization of regions of interest based on digital mammograms publication-title: Sci. Rep. – volume: 9 start-page: 2394 year: September-2022 end-page: 7454 ident: bb0200 article-title: Mathematical analysis of loss function of GAN and its loss function variants publication-title: Int. J. Adv. Technol. Eng. Explor. – year: 2021 ident: bb0210 article-title: Evolution of YOLO-V5 algorithm for object detection: automated detection of library books and performace validation of dataset publication-title: Proceedings of the 2021 IEEE International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2021 – year: 2017 ident: bb0140 article-title: Learning to Discover Cross-Domain Relations with Generative Adversarial Networks – volume: 3 start-page: 142 year: May 2023 end-page: 153 ident: bb0095 article-title: Classification of breast masses using ultrasound images by approaching GAN, transfer learning, and deep learning techniques publication-title: J. Artif. Intell. Technol. – volume: 43 start-page: 4217 year: Dec. 2018 end-page: 4228 ident: bb0135 article-title: A style-based generator architecture for generative adversarial networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2015 ident: bb0125 article-title: Unsupervised representation learning with deep convolutional generative adversarial networks publication-title: International Conference on Learning Representations – volume: 94 year: Aug. 2024 ident: bb0110 article-title: Gan-based data augmentation to improve breast ultrasound and mammography mass classification publication-title: Biomed. Signal Process. Control – volume: 11 year: Jul. 2023 ident: bb0190 article-title: YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection publication-title: Machines – volume: 83 start-page: 1350 year: Aug. 2014 end-page: 1355 ident: bb0165 article-title: Low energy mammogram obtained in contrast-enhanced digital mammography (CEDM) is comparable to routine full-field digital mammography (FFDM) publication-title: Eur. J. Radiol. – volume: 110 start-page: 3019 year: May 2010 end-page: 3042 ident: bb0035 article-title: Challenges for molecular magnetic resonance imaging publication-title: Chem. Rev. – volume: 98 start-page: 113 year: Feb. 2017 end-page: 123 ident: bb0050 article-title: Contrast-enhanced spectral mammography (CESM) versus breast magnetic resonance imaging (MRI): a retrospective comparison in 66 breast lesions publication-title: Diagn. Interv. Imaging – volume: 139 year: May 2023 ident: bb0115 article-title: Object tracking and detection techniques under GANN threats: a systemic review publication-title: Appl. Soft Comput. – volume: 26 start-page: 850 year: Dec. 2023 end-page: 861 ident: bb0075 article-title: Economic evaluation of supplemental breast cancer screening modalities to mammography or digital breast tomosynthesis in women with heterogeneously and extremely dense breasts and average or intermediate breast cancer risk in US healthcare publication-title: J. Med. Econ. – volume: 14 start-page: 249 year: Feb. 2019 end-page: 257 ident: bb0085 article-title: Classification of contrast-enhanced spectral mammography (CESM) images publication-title: Int. J. Comput. Assist. Radiol. Surg. – year: 2019 ident: bb0260 article-title: Handbook of Inter-Rater Reliability: The Definitive Guide to Measuring the Extent of Agreement among Raters – volume: 3 start-page: 2672 year: Jun. 2014 end-page: 2680 ident: bb0195 article-title: Generative adversarial networks publication-title: Sci. Robot. – volume: 11 start-page: 40 year: Mar. 2023 ident: bb0250 article-title: A review of deep transfer learning and recent advancements publication-title: Technologies – volume: 165 start-page: 420 year: Aug. 2023 end-page: 434 ident: bb0090 article-title: The deep learning generative adversarial random neural network in data marketplaces: the digital creative publication-title: Neural Netw. – volume: 116 year: Sep. 2024 ident: bb0160 article-title: A deep learning approach for virtual contrast enhancement in contrast enhanced spectral mammography publication-title: Comput. Med. Imaging Graph. – year: 2001 ident: bb0040 article-title: Safety of Magnetic Resonance Contrast Media – year: 2017 ident: bb0130 article-title: CycleGAN, A Master of Steganography – start-page: 1571 year: Jun. 2020 end-page: 1580 ident: bb0215 article-title: CSPNet: a new backbone that can enhance learning capability of CNN publication-title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Vol. 2020-June – volume: 13 start-page: 1 year: Jul. 2013 end-page: 8 ident: bb0245 article-title: The McNemar test for binary matched-pairs data: mid-p and asymptotic are better than exact conditional publication-title: BMC Med. Res. Methodol. – volume: 35 start-page: 3313 year: 2023 end-page: 3332 ident: bb0185 article-title: A review on generative adversarial networks: algorithms, theory, and applications publication-title: IEEE Trans. Knowl. Data Eng. – volume: 26 start-page: 1082 year: Apr. 2016 end-page: 1089 ident: bb0060 article-title: Clinical utility of dual-energy contrast-enhanced spectral mammography for breast microcalcifications without associated mass: a preliminary analysis publication-title: Eur. Radiol. – start-page: 2813 year: Dec. 2017 end-page: 2821 ident: bb0145 article-title: Least squares generative adversarial networks publication-title: Proceedings of the IEEE International Conference on Computer Vision, Vol. 2017-October – volume: 4 year: Jul. 2017 ident: bb0225 article-title: Structural similarity index family for image quality assessment in radiological images publication-title: J. Med. Imaging – volume: 4 year: 2011 ident: bb0230 article-title: An investigation on the quality of denoised images publication-title: Int. J. Circ. Syst. Signal Process. – volume: 24 start-page: 171 year: 2013 end-page: 176 ident: bb0235 article-title: A survey of forecast error measures publication-title: World Appl. Sci. J. – volume: 35 start-page: 53 year: Jan. 2018 end-page: 65 ident: bb0180 article-title: Generative adversarial networks: an overview publication-title: IEEE Signal Process. Mag. – volume: 85 year: Aug. 2023 ident: bb0170 article-title: An efficient hybrid computer-aided breast cancer diagnosis system with wavelet packet transform and synthetically-generated contrast-enhanced spectral mammography images publication-title: Biomed Signal Process Control – year: 2025 ident: bb0010 article-title: Breast Cancer Statistics | How Common Is Breast Cancer? – volume: 29 start-page: 526 year: May 2023 end-page: 532 ident: bb0025 article-title: The impact of subjective image quality evaluation in mammography publication-title: Radiography – year: 2025 ident: bb0015 article-title: Female breast cancer — cancer stat facts publication-title: Female Breast Cancer — Cancer Stat Facts – volume: 16 start-page: 1456 year: Oct. 2019 end-page: 1463 ident: bb0055 article-title: Comparison of contrast-enhanced mammography with conventional digital mammography in breast cancer screening: a pilot study publication-title: J. Am. Coll. Radiol. – volume: 233 year: Dec. 2023 ident: bb0205 article-title: WGAN-CL: a Wasserstein GAN with confidence loss for small-sample augmentation publication-title: Expert Syst. Appl. – volume: 9 year: Mar. 2023 ident: bb0100 article-title: GANs for medical image synthesis: an empirical study publication-title: J. Imaging – start-page: 5967 year: Nov. 2017 end-page: 5976 ident: bb0120 article-title: Image-to-image translation with conditional adversarial networks publication-title: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Vol. 2017-January – year: 2019 ident: bb0150 article-title: From GAN to WGAN – volume: 46 start-page: 1419 year: Sep. 2018 end-page: 1431 ident: bb0045 article-title: Classification of breast masses using a computer-aided diagnosis scheme of contrast enhanced digital mammograms publication-title: Ann. Biomed. Eng. – volume: 174 start-page: 954 year: Jun. 2014 end-page: 961 ident: bb0030 article-title: Consequences of false-positive screening mammograms publication-title: JAMA Intern. Med. – volume: 94 year: 2024 ident: 10.1016/j.imavis.2025.105692_bb0110 article-title: Gan-based data augmentation to improve breast ultrasound and mammography mass classification publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2024.106255 – year: 2025 ident: 10.1016/j.imavis.2025.105692_bb0010 – year: 2018 ident: 10.1016/j.imavis.2025.105692_bb0175 – volume: 3 start-page: 2672 issue: January year: 2014 ident: 10.1016/j.imavis.2025.105692_bb0195 article-title: Generative adversarial networks publication-title: Sci. Robot. – year: 2021 ident: 10.1016/j.imavis.2025.105692_bb0210 article-title: Evolution of YOLO-V5 algorithm for object detection: automated detection of library books and performace validation of dataset – ident: 10.1016/j.imavis.2025.105692_bb0005 – volume: 174 start-page: 954 issue: 6 year: 2014 ident: 10.1016/j.imavis.2025.105692_bb0030 article-title: Consequences of false-positive screening mammograms publication-title: JAMA Intern. Med. doi: 10.1001/jamainternmed.2014.981 – start-page: 1571 year: 2020 ident: 10.1016/j.imavis.2025.105692_bb0215 article-title: CSPNet: a new backbone that can enhance learning capability of CNN – volume: 110 start-page: 3019 issue: 5 year: 2010 ident: 10.1016/j.imavis.2025.105692_bb0035 article-title: Challenges for molecular magnetic resonance imaging publication-title: Chem. Rev. doi: 10.1021/cr100025t – volume: 12 start-page: 1 issue: 1 year: 2022 ident: 10.1016/j.imavis.2025.105692_bb0105 article-title: A generative adversarial network for synthetization of regions of interest based on digital mammograms publication-title: Sci. Rep. doi: 10.1038/s41598-022-09929-9 – year: 2015 ident: 10.1016/j.imavis.2025.105692_bb0125 article-title: Unsupervised representation learning with deep convolutional generative adversarial networks – volume: 139 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0115 article-title: Object tracking and detection techniques under GANN threats: a systemic review publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2023.110224 – year: 2019 ident: 10.1016/j.imavis.2025.105692_bb0150 – year: 2019 ident: 10.1016/j.imavis.2025.105692_bb0260 – volume: 29 start-page: 526 issue: 3 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0025 article-title: The impact of subjective image quality evaluation in mammography publication-title: Radiography doi: 10.1016/j.radi.2023.02.025 – volume: 43 start-page: 4217 issue: 12 year: 2018 ident: 10.1016/j.imavis.2025.105692_bb0135 article-title: A style-based generator architecture for generative adversarial networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.2970919 – volume: 11 issue: 7 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0190 article-title: YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection publication-title: Machines doi: 10.3390/machines11070677 – year: 2025 ident: 10.1016/j.imavis.2025.105692_bb0015 article-title: Female breast cancer — cancer stat facts – volume: 24 start-page: 171 issue: 24 year: 2013 ident: 10.1016/j.imavis.2025.105692_bb0235 article-title: A survey of forecast error measures publication-title: World Appl. Sci. J. – volume: 83 start-page: 1350 issue: 8 year: 2014 ident: 10.1016/j.imavis.2025.105692_bb0165 article-title: Low energy mammogram obtained in contrast-enhanced digital mammography (CEDM) is comparable to routine full-field digital mammography (FFDM) publication-title: Eur. J. Radiol. doi: 10.1016/j.ejrad.2014.05.015 – volume: 26 start-page: 850 issue: 1 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0075 article-title: Economic evaluation of supplemental breast cancer screening modalities to mammography or digital breast tomosynthesis in women with heterogeneously and extremely dense breasts and average or intermediate breast cancer risk in US healthcare publication-title: J. Med. Econ. doi: 10.1080/13696998.2023.2222035 – volume: 98 start-page: 113 issue: 2 year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0050 article-title: Contrast-enhanced spectral mammography (CESM) versus breast magnetic resonance imaging (MRI): a retrospective comparison in 66 breast lesions publication-title: Diagn. Interv. Imaging doi: 10.1016/j.diii.2016.08.013 – volume: 35 start-page: 3313 issue: 4 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0185 article-title: A review on generative adversarial networks: algorithms, theory, and applications publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2021.3130191 – start-page: 68 year: 2021 ident: 10.1016/j.imavis.2025.105692_bb0265 article-title: Synthesis of contrast-enhanced spectral mammograms from low-energy mammograms using cGAN-based synthesis network – volume: 233 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0205 article-title: WGAN-CL: a Wasserstein GAN with confidence loss for small-sample augmentation publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.120943 – ident: 10.1016/j.imavis.2025.105692_bb0040 – volume: 27 start-page: 145 year: 2016 ident: 10.1016/j.imavis.2025.105692_bb0240 article-title: Review of medical image quality assessment publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2016.02.006 – volume: 3 start-page: 142 issue: 4 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0095 article-title: Classification of breast masses using ultrasound images by approaching GAN, transfer learning, and deep learning techniques publication-title: J. Artif. Intell. Technol. – volume: 13 start-page: 1 issue: 1 year: 2013 ident: 10.1016/j.imavis.2025.105692_bb0245 article-title: The McNemar test for binary matched-pairs data: mid-p and asymptotic are better than exact conditional publication-title: BMC Med. Res. Methodol. doi: 10.1186/1471-2288-13-91 – volume: 46 start-page: 1419 issue: 9 year: 2018 ident: 10.1016/j.imavis.2025.105692_bb0045 article-title: Classification of breast masses using a computer-aided diagnosis scheme of contrast enhanced digital mammograms publication-title: Ann. Biomed. Eng. doi: 10.1007/s10439-018-2044-4 – volume: 10 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.imavis.2025.105692_bb0070 article-title: Technique, protocols and adverse reactions for contrast-enhanced spectral mammography (CESM): a systematic review publication-title: Insights Imaging doi: 10.1186/s13244-019-0756-0 – ident: 10.1016/j.imavis.2025.105692_bb0220 – volume: 31 start-page: 25 issue: 1 year: 1999 ident: 10.1016/j.imavis.2025.105692_bb0020 article-title: Full-field digital mammography designed as a complete system publication-title: Eur. J. Radiol. doi: 10.1016/S0720-048X(99)00066-2 – volume: 4 issue: 3 year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0225 article-title: Structural similarity index family for image quality assessment in radiological images publication-title: J. Med. Imaging doi: 10.1117/1.JMI.4.3.035501 – volume: 115 year: 2022 ident: 10.1016/j.imavis.2025.105692_bb0255 article-title: Ensemble deep learning: a review publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2022.105151 – volume: 165 start-page: 420 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0090 article-title: The deep learning generative adversarial random neural network in data marketplaces: the digital creative publication-title: Neural Netw. doi: 10.1016/j.neunet.2023.05.028 – year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0140 – volume: 20 start-page: 1 issue: 11 year: 2019 ident: 10.1016/j.imavis.2025.105692_bb0080 article-title: Deep convolutional neural networks for mammography: advances, challenges and applications publication-title: BMC Bioinform. – volume: 4 issue: 5 year: 2011 ident: 10.1016/j.imavis.2025.105692_bb0230 article-title: An investigation on the quality of denoised images publication-title: Int. J. Circ. Syst. Signal Process. – volume: 85 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0170 article-title: An efficient hybrid computer-aided breast cancer diagnosis system with wavelet packet transform and synthetically-generated contrast-enhanced spectral mammography images publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2023.104808 – volume: 27 start-page: 1234 issue: 9 year: 2020 ident: 10.1016/j.imavis.2025.105692_bb0065 article-title: Background parenchymal enhancement at contrast-enhanced spectral mammography (CESM) as a breast cancer risk factor publication-title: Acad. Radiol. doi: 10.1016/j.acra.2019.10.034 – volume: 35 start-page: 53 issue: 1 year: 2018 ident: 10.1016/j.imavis.2025.105692_bb0180 article-title: Generative adversarial networks: an overview publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2017.2765202 – start-page: 2813 year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0145 article-title: Least squares generative adversarial networks – volume: 14 start-page: 249 issue: 2 year: 2019 ident: 10.1016/j.imavis.2025.105692_bb0085 article-title: Classification of contrast-enhanced spectral mammography (CESM) images publication-title: Int. J. Comput. Assist. Radiol. Surg. doi: 10.1007/s11548-018-1876-6 – volume: 116 year: 2024 ident: 10.1016/j.imavis.2025.105692_bb0160 article-title: A deep learning approach for virtual contrast enhancement in contrast enhanced spectral mammography publication-title: Comput. Med. Imaging Graph. doi: 10.1016/j.compmedimag.2024.102398 – volume: 11 start-page: 40 issue: 2 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0250 article-title: A review of deep transfer learning and recent advancements publication-title: Technologies doi: 10.3390/technologies11020040 – start-page: 5967 year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0120 article-title: Image-to-image translation with conditional adversarial networks – volume: 26 start-page: 1082 issue: 4 year: 2016 ident: 10.1016/j.imavis.2025.105692_bb0060 article-title: Clinical utility of dual-energy contrast-enhanced spectral mammography for breast microcalcifications without associated mass: a preliminary analysis publication-title: Eur. Radiol. doi: 10.1007/s00330-015-3904-z – volume: 16 start-page: 1456 issue: 10 year: 2019 ident: 10.1016/j.imavis.2025.105692_bb0055 article-title: Comparison of contrast-enhanced mammography with conventional digital mammography in breast cancer screening: a pilot study publication-title: J. Am. Coll. Radiol. doi: 10.1016/j.jacr.2019.04.007 – start-page: 700 year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0155 article-title: Unsupervised image-to-image translation networks – volume: 9 start-page: 2394 issue: 94 year: 2022 ident: 10.1016/j.imavis.2025.105692_bb0200 article-title: Mathematical analysis of loss function of GAN and its loss function variants publication-title: Int. J. Adv. Technol. Eng. Explor. – volume: 9 issue: 3 year: 2023 ident: 10.1016/j.imavis.2025.105692_bb0100 article-title: GANs for medical image synthesis: an empirical study publication-title: J. Imaging doi: 10.3390/jimaging9030069 – year: 2017 ident: 10.1016/j.imavis.2025.105692_bb0130 |
SSID | ssj0007079 |
Score | 2.460549 |
Snippet | Contrast-enhanced digital mammography (CEDM) has emerged as a promising complementary imaging modality for breast cancer diagnosis, offering enhanced lesion... |
SourceID | crossref elsevier |
SourceType | Index Database Publisher |
StartPage | 105692 |
SubjectTerms | Breast cancer Contrast-enhanced digital mammography CycleGAN Deep learning Generative adversarial network Image-to-image translation |
Title | A deep learning approach for contrast-agent-free breast lesion detection and classification using adversarial synthesis of contrast-enhanced mammograms |
URI | https://dx.doi.org/10.1016/j.imavis.2025.105692 |
Volume | 162 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELZQWWDgUUA8Kw-spnWSxvFYIaoCogsgdYsc-wJFaqhIGFj4G_xd7pxEgIQYGBPlrMh3vvtsf3fH2GkMkdMYSUTujBKRAym0UUoMnBsmcaJz6avr30zjyX10NRvOVth5mwtDtMrG99c-3Xvr5k2_mc3-cj7v3-LuIUgSAvD-fnBGGeyRIis_e_-ieVAFuPqcBVc-ft2mz3mO13xBqfy4SwyGvgW9Dn4PT99CzniLbTRYkY_q39lmK1B02WaDG3mzKssuW_9WVHCHfYy4A1jyph_EA2_LhnPEp9xT001ZCUM5VSJ_AeAZEdMrFKCTMxSuPD2r4KZw3BK6JjqR1yAnmjyOSF2cS0O2y8u3AjFkOS_5c_41OhSPnlrAFwYNnRhg5S67H1_cnU9E035BWEQ1lcisTqTKAEGgDd1AWx0rN7RaGgU5JMoEEmKlA-ukSWRoAoxzuZE2tNYp6Vy4xzrFcwH7jMPA4MYuBPQWNgqczEJtJchMGaPyRAcHTLSzni7rKhtpSz97SmstpaSltNbSAVOtatIf1pJiIPhT8vDfkkdsjZ5qIt8x61Qvr3CCgKTKet7iemx1dHk9mX4C32bk6w |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT9wwEB3R3QPlUL6KgLbgA1dr18kmjo8rVLSU3b10kfYWOfaELhJhRcKBX8LfZew4lEqoB66Jxoo845k3zpsZgLMUR1ZRJOGl1ZKPLAqutJR8aG2SpZkqhe-uP5unk-vRr2Wy3IDzrhbG0SqD7299uvfW4ckg7OZgvVoNflP2EGWZA_D-_-DyE_Rdd6qkB_3x5dVk_uqQXRO49qqFDj8JdBV0nua1unPV_JQoRomfQq-i9yPUm6hzsQNfAlxk4_aLdmEDqz3YDtCRhYNZ78HWm76C-_A8ZhZxzcJIiBvWdQ5nBFGZZ6fruuHalVXx8gGRFY6b3pCAuzwj4cYztCqmK8uMA9iOUeSVyBxTnlZ0g5xr7cyX1U8Vwch6VbP78u_qWP3x7AJ2p8nWHQms_grXFz8X5xMeJjBwQ8Cm4YVRmZAFEg40sR0qo1JpE6OEllhiJnUkMJUqMlboTMQ6olBXamFiY6wU1sYH0KvuKzwEhkNNuV2M5DDMKLKiiJURKAqptSwzFR0B73Y9X7eNNvKOgXabt1rKnZbyVktHIDvV5P8YTE6x4L-Sxx-WPIXNyWI2zaeX86tv8Nm9aXl936HXPDziD8InTXES7O8Fs4fnnA |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+deep+learning+approach+for+contrast-agent-free+breast+lesion+detection+and+classification+using+adversarial+synthesis+of+contrast-enhanced+mammograms&rft.jtitle=Image+and+vision+computing&rft.au=Amin%2C+Manar+N.&rft.au=Rushdi%2C+Muhammad+A.&rft.au=Kamal%2C+Rasha&rft.au=Farouk%2C+Amr&rft.date=2025-10-01&rft.issn=0262-8856&rft.volume=162&rft.spage=105692&rft_id=info:doi/10.1016%2Fj.imavis.2025.105692&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_imavis_2025_105692 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0262-8856&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0262-8856&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0262-8856&client=summon |