International Journal of Electronics and Computer Applications

Volume: 1 Issue: 2

  • Open Access
  • Original Article

Deep Learning for Improved Breast Cancer Detection: ResNet-50 vs VGG16

Rupali A Patil1∗, V V Dixit2

1 Ph.D. Research Scholar, G H Raisoni College of Engineering and Management, Pune, Maharashtra, India
2 Principal/Director, RMDSTIC Warje, Pune, Maharashtra, India

 

*Corresponding author email: [email protected]

 

Year: 2024, Page: 26-31, Doi: https://doi.org/10.54839/ijeaca.v1i2.1

Received: June 11, 2024 Accepted: Oct. 20, 2024 Published: Dec. 4, 2024

Abstract

Breast cancer continues to pose a major global health challenge, underscoring the need for advanced detection and classification methods for mammograms. This study examines the effectiveness of ResNet-50 and VGG16 models in detecting and classifying multiview mammograms. Early and accurate detection of breast cancer is essential for improving patient outcomes and reducing mortality rates. Our approach began with the preparation of mammography images using various image processing techniques, including transfer learning and median filtering. The processed images were then used to train ResNet-50 and VGG16 models for detection and classification tasks. Our experiments demonstrated impressive performance, achieving an accuracy of 96% and an F1 score of 94.66% on the Digital Database for Screening Mammography (DDSM) datasets. These results underscore the potential of deep learning models, particularly ResNet-50, in effectively detecting and classifying multiview mammograms.

Keywords: Deep Learning for Improved Breast Cancer Detection: ResNet-50 vs VGG16

References

  1. Khan HN, Shahid AR, Raza B, Dar AH, Alquhayz H. Multi-View Feature Fusion Based Four Views Model for Mammogram Classification Using Convolutional Neural NetworkIEEE Access . 2019 ;7:165724 –165733. Available from: https://doi.org/10.1109/ACCESS.2019.2953318

  2. Wang Z, Li M, Wang H, Jiang H, Yao Y, Zhang H. Breast Cancer Detection Using Extreme Learning Machine Based on Feature Fusion with CNN Deep FeaturesIEEE Access . 2019;7:105146 –105158. Available from: https://doi.org/10.1109/ACCESS.2019.2892795

  3. Carneiro G, Nascimento J, Bradley AP. Automated Analysis of Unregistered Multi-View Mammograms With Deep LearningIEEE Transactions on Medical Imaging. 2017;36(11):2355 –2365. Available from: https://doi.org/10.1109/TMI.2017.2751523

  4. Wang H, Feng J, Zhang Z, Su H, Cui L, He H, et al. Breast Mass Classification Via Deeply Integrating the Contextual Information from Multi-view DataPattern Recognition. 2018;80:42–52. Available from: https://doi.org/10.1016/j.patcog.2018.02.026

  5. Bardou D, Zhang K, Ahmad SM. Classification of Breast Cancer Based on Histology Images Using Convolutional Neural NetworksIEEE Access. 2018;6:24680 –24693. Available from: https://doi.org/10.1109/ACCESS.2018.2831280

  6. Liu K, Kang G, Zhang N, Hou B. Breast Cancer Classification Based on Fully-Connected Layer First Convolutional Neural NetworksIEEE Access. 2018;6:23722 –23732. Available from: https://doi.org/10.1109/ACCESS.2018.2817593

  7. Cruz TN, Cruz TM, Santos WP. Detection and Classification of Lesions in Mammographies Using Neural Networks and Morphological WaveletsIEEE Latin America Transactions . 2018;16(3):926 –932. Available from: https://doi.org/10.1109/TLA.2018.8358675

  8. Samala RK, Chan HP, Hadjiiski L, Helvie MA, Richter CD, Cha KH. Breast Cancer Diagnosis in Digital Breast Tomosynthesis: Effects of Training Sample Size on Multi-Stage Transfer Learning using Deep Neural etsIEEE Transactions on Medical Imaging. 2019;38(3):686–696. Available from: https://doi.org/10.1109/tmi.2018.2870343

  9. Shams S, Platania R, Zhang J, Kim J, Lee K, Park SJ. Deep Generative Breast Cancer Screening and Diagnosis. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, Lecture Notes in Computer Science. 11071:859–867.

  10. Gastounioti A, Oustimov A, Hsieh MK, Pantalone L, EFC, Kontos D. Using Convolutional Neural Networks for Enhanced Capture of Breast Parenchymal Complexity Patterns Associated with Breast Cancer RiskAcademic Radiology. 2018;25(8):977–984. Available from: https://doi.org/10.1016/j.acra.2017.12.025

  11. Aboutalib SS, Mohamed AA, Berg WA, Zuley ML, Sumkin JH, Wu S. Deep Learning to Distinguish Recalled but Benign Mammography Images in Breast Cancer ScreeningClinical Cancer Research. 2018;23:5902–5909. Available from: https://doi.org/10.1158/1078-0432.ccr-18-1115

  12. Zhang X, Zhang Y, Han EY, Jacobs N, Han Q, Wang X, et al. Classification of Whole Mammogram and Tomosynthesis Images Using Deep Convolutional Neural NetworksIEEE Transactions on NanoBioscience. 2018;17(3):237–242. Available from: https://doi.org/10.1109/tnb.2018.2845103

  13. Berbar MA. Hybrid methods for feature extraction for breast masses classificationEgyptian Informatics Journal. 2018;19(1):63–73. Available from: http://dx.doi.org/10.1016/j.eij.2017.08.0011110-8665/2017

  14. Kanadam KP, Chereddy SR. Mammogram classification using sparse-ROI: A novel representation to arbitrary shaped massesExpert Systems with Applications. 2016;57:204–213. Available from: https://doi.org/10.1016/j.eswa.2016.03.037

  15. Kaura P, Singh G, Kaur P. Intellectual detection and validation of automated mammogram breast cancer images by multi-class SVM using deep learning classificationInformatics in Medicine Unlocked. 2019;16:1–35. Available from: https://doi.org/10.1016/j.imu.2019.01.001

  16. Li H, Zhuang S, Li Da, Zhao J, Ma Y. Benign and malignant classification of mammogram images based on deep learningBiomedical Signal Processing and Control. 2019;51:347–354. Available from: https://doi.org/10.1016/j.bspc.2019.02.017

  17. Ngadi M, Amine A, Nassih B, Hachimi H. A highly efficient system for Mammographic Image Classification Using NSVC AlgorithmProcedia Computer Science. 2019;148:135–144. Available from: https://doi.org/10.1016/j.procs.2019.01.017

  18. Shastri AA, Tamrakar D, Ahuja K. Density-wise two stage mammogram classification using texture exploiting descriptorsExpert Systems with Applications. 2018;99:71–82. Available from: https://doi.org/10.1016/j.eswa.2018.01.024

  19. Vijayarajeswari R, Parthasarathy P, Vivekanandan S, Basha AA. Classification of mammogram for early detection of breast cancer using SVM classifier and Hough transformMeasurement. 2019;146:800–805. Available from: https://doi.org/10.1016/j.measurement.2019.05.083

  20. Xie W, Li Y, Ma Y. Breast mass classification in digital mammography based on extreme learning machineNeurocomputing. 2016;173(Part 3):930–941. Available from: https://doi.org/10.1016/j.neucom.2015.08.048

  21. Thawkar S, Ingolikar R. Classification of masses in digital mammograms using Biogeography-based optimization techniqueJournal of King Saud University - Computer and Information Sciences. 2020;32(10):1140–1148. Available from: https://doi.org/10.1016/j.jksuci.2018.01.004

  22. Wu E, Wu K, Cox D, WL. Conditional Infilling GANs for Data Augmentation in Mammogram Classification. In: Image Analysis for Moving Organ, Breast, and Thoracic Images , Lecture Notes in Computer Science. (Vol. 11040, pp. 98-106) Springer, Cham. 2018.

  23. MSM, Afify HM, Marzouk SY. Fully automated computer-aided diagnosis system for microcalcifications cancer based on improved mammographic image techniquesAin Shams Engineering Journal. 2019;10(3):517–527. Available from: https://doi.org/10.1016/j.asej.2019.01.009

  24. Lévy D, Jain A. Breast Mass Classification from Mammograms using Deep Convolutional Neural NetworksarXiv. 2016;p. 1–6. Available from: https://doi.org/10.48550/arXiv.1612.00542

  25. Shen L, Margolies LR, Rothstein JH, Fluder E, Mcbride R, Sieh W. Deep Learning to Improve Breast Cancer Detection on Screening MammographyScientific Reports. 2019;9(1):1–12. Available from: https://doi.org/10.1038/s41598-019-48995-4

Cite this article

Patil RA, Dixit VV. (2024). Deep Learning for Improved Breast Cancer Detection: ResNet-50 vs VGG16. International Journal of Electronics and Computer Applications. 1(2): 26-31. https://doi.org/10.54839/ijeaca.v1i2.1
 

Views
41
Downloads
15
Citations