Abstract
Breast cancer, the most commonly diagnosed cancer in women worldwide. In areas with limited budgets, training qualified medical professionals to accurately diagnose breast cancer remains a challenge, particularly in the interpretation of mammogram images due to the subtle distinctions between benign and malignant lesions. While breast cancer patients need to be diagnosed as early as possible to increase the chance of cure. All these reasons raises a significant need for a more economical, timely and accurate solution. We introduce a novel combination of image enhancement techniques, including Gamma Correction, Contrast Limited Adaptive Histogram Equalization (CLAHE), Retinex, and Image Super-Resolution (ISR) - tailored to overcome these interpretive challenges by significantly improving image quality and detail visibility. Furthermore, we leverage progressive image resizing, an innovative technique that systematically increases the resolution of images during the model training process, to effectively capture detailed patterns in mammogram evaluation. Additionally, we present a fine-tuning strategy for pre-trained models such as ResNet-50, EfficientNet-B5, and Xception, combining multiple preprocessing methods and extracting inherent features through transfer learning to improve model reliability and classification accuracy. Finally, we systematically compare three ensemble methods: averaging, voting, and weighted averaging, with the latter showing superior accuracy for breast cancer detection classification results. This approach synergizes each model’s distinct feature extraction strengths, culminating in a high predictive performance. Progressive image resizing from 150\(\times \)150 to 240\(\times \)240 improves model generalization. Ensemble modeling by averaging, voting, and weighted averaging predictions achieves up to 91.36% accuracy for mass/calcification classification and 76.79% for benign/malignant classification. This study develops an accurate deep learning framework for breast cancer prediction that holds promise to assist radiologists and improve patient care, utilizing the publicly accessible Curated Breast Imaging Subset of the Digital Database for Screening Mammography dataset (CBIS-DDSM).
Similar content being viewed by others
Availability of Data, Code, and Material
Data for this study are published on repository link at. https://doi.org/10.1038/sdata.2017.177
References
National Cancer Institute (2023) What is cancer? https://www.cancer.gov/about-cancer/understanding/what-is-cancer#definition. Accessed 05 Nov 2023
World Health Organization (2023) Cancer fact sheet. https://www.who.int/news-room/fact-sheets/detail/cancer. Accessed: 05 Nov 2023
Deshpande TM, Pandey A, Shyama S (2023) OAText Issue number if available, Page range if available. https://doi.org/10.15761/TiM.1000110. https://www.oatext.com/review-breast-cancer-and-etiology.php. Accessed 05 Nov 2023
Menon JU (2021) Pharmaceutics 13(5):723. https://doi.org/10.3390/pharmaceutics13050723. https://www.mdpi.com/1999-4923/13/5/723. Accessed 05 Nov 2023
Wang J, Khan MA, Wang S, Zhang Y (2023) Computers, Materials & Continua 76(2): 2201. https://doi.org/10.32604/cmc.2023.041191. http://www.techscience.com/cmc/v76n2/54027
Rehman SU, Khan MA, Masood A, Almujally NA, Baili J, Alhaisoni M, Tariq U, Zhang YD (2023) Diagnostics 13(9). https://doi.org/10.3390/diagnostics13091618. https://www.mdpi.com/2075-4418/13/9/1618
Fatima M, Khan MA, Shaheen S, Almujally NA, Wang SH (2023) CAAI Trans Intell Technol 8(4):1374. https://doi.org/10.1049/cit2.12219. https://ietresearch.onlinelibrary.wiley.com/doi/abs/10.1049/cit2.12219
Chaudhury S, Sau K, Khan MA, Shabaz M (2023) Math Biosci Eng 20(6):10404. https://doi.org/10.3934/mbe.2023457
Abunasser BS, AL-Hiealy MRJ, Zaqout IS, Abu-Naser SS (2023) Asian Pac J Cancer Prev 24(2):531. https://doi.org/10.31557/APJCP.2023.24.2.531
Alkhaleefah M, Tan TH, Chang CH, Wang TC, Ma SC, Chang L, Chang YL (2022) Cancers 14(16). https://doi.org/10.3390/cancers14164030. https://www.mdpi.com/2072-6694/14/16/4030
Jabeen K, Khan MA, Balili J, Alhaisoni M, Almujally NA, Alrashidi H, Tariq U, Cha JH(2023) Diagnostics 13(7). https://doi.org/10.3390/diagnostics13071238. https://www.mdpi.com/2075-4418/13/7/1238
Aamir S, Rahim A, Aamir Z, Abbasi SF, Khan MS, Alhaisoni M, Khan MA, Khan K, Ahmad J (2022) Comput Math Methods Med 2022:5869529. https://doi.org/10.1155/2022/5869529
Safdar Gardezi SJ, Adjed F, Faye I, Kamel N, Eltoukhy MM (2018) Multimed Tools Appl 77(3):3919. https://doi.org/10.1007/s11042-016-4283-4
Kharel N, Alsadoon A, Prasad PWC, Elchouemi A (2017) In: 2017 8th International conference on information and communication systems (ICICS), pp 120–124. https://doi.org/10.1109/IACS.2017.7921957
Al-Juboori RAL (2022) Iraqi J Sci 58(1B):327. https://ijs.uobaghdad.edu.iq/index.php/eijs/article/view/6166
Juhong A, Li B, Yao CY, Yang CW, Agnew DW, Lei YL, Huang X, Piyawattanametha W, Qiu Z (2023) Biomed Opt Express 14(1):18. https://doi.org/10.1364/BOE.463839
Sarosa S, Utaminingrum F, Bachtiar F (2018) Mammogram breast cancer classification using gray-level co-occurrence matrix and support vector machine. In: 2018 international conference on sustainable information engineering and technology (SIET). IEEE, pp 54–59. https://doi.org/10.1109/SIET.2018.8693146
Ansar W, Shahid A, Raza B, Dar A (2020) breast cancer detection and localization using MobileNet based transfer learning for mammograms, pp 11–21. https://doi.org/10.1007/978-3-030-43364-2_2
Tsochatzidis L, Costaridou L, Pratikakis I (2019) J Imaging 5:37. https://doi.org/10.3390/jimaging5030037
Almeida R, Chen D, Filho A, Brandão W (2021) Proceedings of the 23rd international conference on enterprise information systems pp 660–667. DOIurlhttps://doi.org/10.5220/0010440906600667. https://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0010440906600667
Amini M, Salimi Y, Mansouri Z, Arabi H, Shiri I, Zaidi H (2022) 2022 IEEE Nuclear science symposium and medical imaging conference (NSS/MIC) pp 1–3. https://doi.org/10.1109/NSS/MIC44845.2022.10398928
Gengtian S, Bing B, Guoyou Z (2023) 2023 8th International conference on computer and communication systems (ICCCS) pp 972–977. https://doi.org/10.1109/ICCCS57501.2023.10151156
Gujar SA, Lei X, Cen SY, Hwang DH, Varghese B (2023) 2023 19th International symposium on medical information processing and analysis (SIPAIM) pp 1–5. https://doi.org/10.1109/SIPAIM56729.2023.10373475
Myles C, atel A, Chen S-J, McMillan L, Harris-Birtill D (2023) A divide and conquer approach to maximise deep learning mammography classification accuracies. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0280841
Karuppanagounder S, Palanisamy K (2011) Int J Knowl Manag E-Learning 3:15
Rakibul A, Rafid ARH, Azam S, Montaha S, Karim A, Fahim K, Hasan M (2022) Biology 11. https://doi.org/10.3390/biology11111654
Weizhen S, Fei L, Qinzhen Z (2012) The applications of improved retinex algorithm for X-ray medical image enhancement. In: 2012 International conference on computer science and service system. IEEE, pp 1655–1658. https://doi.org/10.1109/CSSS.2012.414
Wang X, Xie L, Dong C, Shan Y (2021) In: 2021 IEEE/CVF International conference on computer vision workshops (ICCVW), pp 1905–1914. https://doi.org/10.1109/ICCVW54120.2021.00217
Song R, Li T, Wang Y (2020) IEEE Access PP, 1. https://doi.org/10.1109/ACCESS.2020.2986546
Oza P, Sharma P, Patel S, Adedoyin F, Bruno A (2022) J Imaging 8(5). https://doi.org/10.3390/jimaging8050141. Place: Switzerland
Oza P, Sharma P, Patel S, Adedoyin F, Bruno A (2022) J Imaging 8(5). https://doi.org/10.3390/jimaging8050141. https://www.mdpi.com/2313-433X/8/5/141
Kumari V, Ghosh R (2023) Healthcare Anal 3:100207. https://doi.org/10.1016/j.health.2023.100207. https://www.sciencedirect.com/science/article/pii/S2772442523000746
Li J, Shi J, Su H, Gao L (2022) Electronics 11:2322. https://doi.org/10.3390/electronics11152322
Cossio M (2023) Augmenting medical imaging: a comprehensive catalogue of 65 techniques for enhanced data analysis . http://arxiv.org/abs/2303.01178. ArXiv:2303.01178 [cs, eess]
Baghdadi NA, Malki A, Magdy Balaha H, AbdulAzeem Y, Badawy M, Elhosseini M (2022) PeerJ Comput Sci 8:1054. https://doi.org/10.7717/peerj-cs.1054
Zhu M, Xia J, Jin X, Yan M, Cai G, Yan J, Ning G (2018) IEEE Access 6:4641. https://doi.org/10.1109/ACCESS.2018.2789428
Zhang S, Han F, Liang Z, Tan J, Cao W, Gao Y, Pomeroy M, Ng K, Hou W (2019) Computerized medical imaging and graphics: the official journal of the computerized medical imaging society 77:101645. https://doi.org/10.1016/j.compmedimag.2019.101645. Place: United States
Albadr MAA, Ayob M, Tiun S, Al-Dhief FT, Arram A, Khalaf S (2023) Front Oncol 13:1150840. https://doi.org/10.3389/fonc.2023.1150840
Liu H, Vohra N, Bailey K, El-Shenawee M, Nelson AH (2022) Journal of infrared, millimeter and terahertz waves. 43(1-2):48. https://doi.org/10.1007/s10762-021-00839-x. Place: United States
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
AR, Al-Dujaili A, Hadi Z, Humaidi A (2023) International Journal of Electrical and Computer Engineering (IJECE) 13:6240. https://doi.org/10.11591/ijece.v13i6.pp6240-6248
Showkat S, Qureshi S (2022) Chemometr Intell Lab Syst 224:104534. https://doi.org/10.1016/j.chemolab.2022.104534. https://www.sciencedirect.com/science/article/pii/S0169743922000454
Deng Y, Yin J, Wang Y, Chen J, Sun L, Li Q (2021) J Phys Conf Ser 1880:012019. https://doi.org/10.1088/1742-6596/1880/1/012019
Sakli N, Ghabri H, Soufiene BO, Almalki FA, Sakli H, Ali O, Najjari M, Maleh Y (2022) Intell Neurosci 2022. https://doi.org/10.1155/2022/7617551
Tan M, Le QV (2020) EfficientNet: Rethinking model scaling for convolutional neural networks. http://arxiv.org/abs/1905.11946ArXiv:1905.11946 [cs.LG]
Lu S, Zhang X, Zhang Y (2021) A new pulmonary disease diagnosis system based on EfficientNet and transfer learning: pulmonary disease diagnosis based on EfficientNet and TL. In: Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion pp 1–4. https://doi.org/10.1145/3492323.3495568
Sharma G, Anand V, Gupta S (2023) Generous approach for diagnosis and detection of gastrointestinal tract disease with application of deep neural network. In: 2023 International conference on research methodologies in knowledge management, artificial intelligence and telecommunication engineering (RMKMATE) pp 1–6. https://doi.org/10.1109/RMKMATE59243.2023.10369883. IEEE
Babu Vimala B, Srinivasan S, Mathivanan SK, Mahalakshmi, Jayagopal P, Dalu GT (2023) Sci Rep 13(1):23029. https://doi.org/10.1038/s41598-023-50505-6
Chollet F (2017) Xception: Deep Learning with Depthwise Separable Convolutions. pp 1800–1807. https://doi.org/10.1109/CVPR.2017.195
Hashmi MF, Katiyar S, Keskar A, Bokde ND, Geem ZW (2020) Efficient pneumonia detection in chest xray images using deep transfer learning. Diagnostics 10(6):417. https://doi.org/10.3390/diagnostics10060417
Cobilla R, Carlo Dichoso J, Miñon AB, Kate Pascual A, Abisado M, Huyo-a SL, Avelino Sampedro G (2023) In: 2023 International conference on electronics, information, and communication (ICEIC) , pp. 1–4. https://doi.org/10.1109/ICEIC57457.2023.10049979
Madhu G, Kautish S, Gupta Y, Nagachandrika G, Biju SM, Kumar M (2023) Multimed Tools Appl 83:1. https://doi.org/10.1007/s11042-023-16944-z
Lee S, Amgad M, Masoud M, Subramanian R, Gutman D, Cooper L (2019) In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) , pp 2549–2553. https://doi.org/10.1109/BIBM47256.2019.8983317
Khuriwal N, Mishra N (2018) In: 2018 IEEMA Engineer infinite conference (eTechNxT), pp 1–5. https://doi.org/10.1109/ETECHNXT.2018.8385355
Farea M, Chen Z (2023) Breast Cancer classification by adaptive weighted average ensemble of previously trained models. https://doi.org/10.13140/RG.2.2.24587.05924
Lee R, Gimenez F, Hoogi A, Miyake K, Gorovoy M, Rubin D (2017) Sci Data 4:170177. https://doi.org/10.1038/sdata.2017.177
Wiki (2016) Curated breast imaging subset of digital database for screening mammography (cbis-ddsm). https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=22516629
Kaggle (2018) Ddsm mammography. https://www.kaggle.com/datasets/skooch/ddsm-mammography
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 618–626. https://doi.org/10.1109/ICCV.2017.74
Acknowledgements
Luong Hoang Huong was funded by the Master, PhD Scholarship Programme of Vingroup Innovation Foundation (VINIF), code VINIF.2023.TS.049
Author information
Authors and Affiliations
Contributions
Huong Hoang Luong conceived the study conception and design, designed the experiments, performed the experiments, analyzed the data, performed the computation work, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Dat Vo Minh performed the experiments, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Phuc Phan Hong performed the experiments, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Anh Dinh The performed the experiments, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Thinh Nguyen Le Quang performed the experiments, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Thai Tran Quoc performed the experiments, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Nguyen Thai-Nghe performed the experiments, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft. Hai Thanh Nguyen conceived the study conception and design, designed the experiments, analyzed the data, prepared figures and tables, authored or reviewed drafts of the paper, and approved the final draft.
Corresponding author
Ethics declarations
Competing Interests
All authors declare that they have no competing interests.
Ethical and informed consent for data used
The dataset used has no ethical risk and is public dataset.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Luong, H.H., Vo, M.D., Phan, H.P. et al. Improving breast cancer prediction via progressive ensemble and image enhancement. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-19299-1
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-024-19299-1