Benign and malignant breast masses classification based on AdaBoosting fine-tuned AlexNet

Authors

  • Komeil Simaei Department of Electrical Engineering, Ra.C., Islamic Azad University, Rasht, Iran.
  • Azadeh Kiani-Sarkaleh * Department of Electrical Engineering, Ra.C., Islamic Azad University, Rasht, Iran. https://orcid.org/0000-0003-0143-1892
  • Ali Esmaeeli Department of Physics and Medical Engineering, Ra.C., Islamic Azad University, Rasht, Iran.

https://doi.org/10.22105/thi.v3i2.55

Abstract

Early and precise differentiation between benign and malignant breast masses in mammographic imaging is critical for improving patient prognosis and minimizing unnecessary invasive biopsies. Despite recent advances in Computer-Aided Diagnosis (CAD) systems, deep convolutional models frequently suffer from misclassification near subtle lesion boundaries and class imbalance challenges. In this paper, we propose a robust ensemble deep learning framework termed Adaptive Boosting with Fine-Tuned AlexNet (Ada-FTAN) tailored for automated breast mass classification. The proposed pipeline incorporates an initial pre-processing stage involving Contrast-Limited Adaptive Histogram Equalization (CLAHE) and extensive geometric-intensity data augmentation to mitigate contrast variations and overfitting. The core architecture integrates an iterative AdaBoost ensemble with transfer-learned AlexNet backbones, which dynamically updates sample distribution weights across consecutive boosting iterations to penalize misclassified hard samples. The proposed method was comprehensively evaluated on two benchmark mammography repositories: The Mammographic Image Analysis Society (MIAS) and the Digital Database for Screening Mammography (DDSM). Quantitative assessments reveal that the baseline AlexNet achieves classification accuracies of 94.52% on MIAS and 94.21% on DDSM. In contrast, our proposed Ada-FTAN model demonstrates superior diagnostic performance, boosting the overall classification accuracy to 98.54% on MIAS and 98.01% on DDSM, while substantially decreasing both false negative and false positive rates. The empirical results confirm that the synergy between boosting mechanisms and fine-tuned deep representations provides a reliable, high-precision CAD solution for clinical breast cancer screening.

Keywords:

Breast cancer diagnosis, Mammography, Convolutional neural network, AlexNet, AdaBoost, Ada-FTAN, Transfer learning

References

  1. [1] Lee, R. S., Dunnmon, J. A., He, A., Tang, S., Re, C., & Rubin, D. L. (2021). Comparison of segmentation-free and segmentation-dependent computer-aided diagnosis of breast masses on a public mammography dataset. Journal of Biomedical Informatics, 113, 103656. https://doi.org/10.1016/j.jbi.2020.103656
  2. [2] Pérez-Benito, F. J., Signol, F., Perez-Cortes, J. C., Fuster-Baggetto, A., Pollan, M., Pérez-Gómez, B., … & LLobet, R. (2020). A deep learning system to obtain the optimal parameters for a threshold-based breast and dense tissue segmentation. Computer Methods and Programs in Biomedicine, 195, 105668. https://doi.org/10.1016/j.cmpb.2020.105668
  3. [3] Doi, K. (2007). Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Computerized Medical Imaging and Graphics, 31(4–5), 198–211. https://doi.org/10.1016/j.compmedimag.2007.02.002
  4. [4] Jiang, Y., Nishikawa, R. M., Schmidt, R. A., Metz, C. E., Giger, M. L., & Doi, K. (1999). Improving breast cancer diagnosis with computer-aided diagnosis. Academic Radiology, 6(1), 22–33. https://doi.org/10.1016/S1076-6332(99)80058-0
  5. [5] Chan, H. P., Vybrony, C. J., Schmidt, R. A., Metz, C. E., Lam, K. L., Ogura, T., ... & Macmahon, H. (1990). Improvement in radiologists’ detection of clustered microcalcifications on mammograms: The potential of computer-aided diagnosis. Investigative Radiology, 25(10), 1102–1110. https://www.ovid.com/jnls/investigativeradiology/toc/1990/10000
  6. [6] Patel, B. C., & Sinha, G. R. (2014). Abnormality detection and classification in computer-aided diagnosis (CAD) of breast cancer images. Journal of Medical Imaging and Health Informatics, 4(6), 881–885. https://doi.org/10.1166/jmihi.2014.1349
  7. [7] Jiao, Z., Gao, X., Wang, Y., & Li, J. (2016). A deep feature based framework for breast masses classification. Neurocomputing, 197, 221–231. https://doi.org/10.1016/j.neucom.2016.02.060
  8. [8] Arevalo, J., González, F. A., Ramos-Pollán, R., Oliveira, J. L., & Lopez, M. A. G. (2016). Representation learning for mammography mass lesion classification with convolutional neural networks. Computer Methods and Programs in Biomedicine, 127, 248–257. https://doi.org/10.1016/j.cmpb.2015.12.014
  9. [9] Li, Y., Zhang, L., Chen, H., & Cheng, L. (2020). Mass detection in mammograms by bilateral analysis using convolution neural network. Computer Methods and Programs in Biomedicine, 195, 105518. https://doi.org/10.1016/j.cmpb.2020.105518
  10. [10] Guan, Y., Wang, X., Li, H., Zhang, Z., Chen, X., Siddiqui, O., … & Huang, X. (2020). Detecting asymmetric patterns and localizing cancers on mammograms. Patterns, 1(7). https://doi.org/10.1016/j.patter.2020.100106
  11. [11] Dhungel, N., Carneiro, G., & Bradley, A. P. (2015). Automated mass detection in mammograms using cascaded deep learning and random forests. 2015 international conference on digital image computing: techniques and applications (DICTA) (pp. 1–8). IEEE. https://doi.org/10.1109/DICTA.2015.7371234
  12. [12] Shen, L., He, M., Shen, N., Yousefi, N., Wang, C., & Liu, G. (2020). Optimal breast tumor diagnosis using discrete wavelet transform and deep belief network based on improved sunflower optimization method. Biomedical Signal Processing and Control, 60, 101953. https://doi.org/10.1016/j.bspc.2020.101953
  13. [13] S Singh, V. K., Rashwan, H. A., Romani, S., Akram, F., Pandey, N., Sarker, M. M. K., ... & Torrents-Barrena, J. (2020). Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network. Expert Systems with Applications, 139, 112855. https://doi.org/10.1016/j.eswa.2019.112855
  14. [14] Salama, W. M., Elbagoury, A. M., & Aly, M. H. (2020). Novel breast cancer classification framework based on deep learning. IET Image Processing, 14(13), 3254–3259. https://doi.org/10.1049/iet-ipr.2020.0122
  15. [15] Al-Antari, M. A., Al-Masni, M. A., Choi, M. T., Han, S. M., & Kim, T. S. (2018). A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification. International Journal of Medical Informatics, 117, 44–54. https://doi.org/10.1016/j.ijmedinf.2018.06.003
  16. [16] Dhungel, N., Carneiro, G., & Bradley, A. P. (2017). A deep learning approach for the analysis of masses in mammograms with minimal user intervention. Medical Image Analysis, 37, 114–128. https://doi.org/10.1016/j.media.2017.01.009
  17. [17] Geras, K. J., Wolfson, S., Shen, Y., Wu, N., Kim, S., Kim, E., … & Cho, K. (2017). High-resolution breast cancer screening with multi-view deep convolutional neural networks. https://arxiv.org/abs/1703.07047
  18. [18] Carneiro, G., Nascimento, J., & Bradley, A. P. (2017). Automated analysis of unregistered multi-view mammograms with deep learning. IEEE Transactions on Medical Imaging, 36(11), 2355–2365. https://doi.org/10.1109/TMI.2017.2751523
  19. [19] Rodríguez-Ruiz, A., Krupinski, E., Mordang, J. J., Schilling, K., Heywang-Köbrunner, S. H., Sechopoulos, I., & Mann, R. M. (2019). Detection of breast cancer with mammography: effect of an artificial intelligence support system. Radiology, 290(2), 305–314. https://doi.org/10.1148/radiol.2018181371
  20. [20] McKinney, S. M., Sieniek, M., Godbole, V., Godwin, J., Antropova, N., Ashrafian, H., ... & Shetty, S. (2020). International evaluation of an AI system for breast cancer screening. Nature, 577(7788), 89–94. https://doi.org/10.1038/s41586-019-1799-6
  21. [21] Taherkhani, A., Cosma, G., & McGinnity, T. M. (2020). AdaBoost-CNN: An adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning. Neurocomputing, 404, 351–366. https://doi.org/10.1016/j.neucom.2020.03.064
  22. [22] Zuiderveld, K. (1994). Contrast limited adaptive histogram equalization. In Graphics gems iv (pp. 474–485). https://doi.org/10.1016/B978-0-12-336156-1.50061-6
  23. [23] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems (Vol. 25, pp. 1097–1105). NeurIPS Foundation. https://proceedings.neurips.cc/paper_files/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
  24. [24] Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd international conference on machine learning (pp. 448–456). PMLR. https://proceedings.mlr.press/v37/ioffe15.html?utm_source=chatgpt.com
  25. [25] Hastie, T., Rosset, S., Zhu, J., & Zou, H. (2009). Multi-class adaboost. Statistics and Its Interface, 2(3), 349–360. https://doi.org/10.4310/SII.2009.v2.n3.a8
  26. [26] Suckling, J., Parker, J., Dance, D., Astley, S., Hutt, I., Boggis, C., ... & Savage, J. (2015). Mammographic Image Analysis Society (MIAS) database v1.21. Apollo-University of Cambridge Repository. https://doi.org/10.17863/CAM.105113
  27. [27] Sawyer-Lee, R., Gimenez, F., Hoogi, A., & Rubin, D. (2016). Curated breast imaging subset of digital database for screening mammography (CBIS-DDSM). https://doi.org/10.7937/K9/TCIA.2016.7O02S9CY
  28. [28] Metz, C. E. (1978). Basic principles of ROC analysis. Seminars in Nuclear Medicine, 8(4), 283–298. https://doi.org/10.1016/S0001-2998(78)80014-2
  29. [29] Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006). Beyond accuracy, f-score and roc: a family of discriminant measures for performance evaluation. Australasian joint conference on artificial intelligence (pp. 1015–1021). Springer, Berlin, Heidelberg. https://doi.org/10.1007/11941439_114

Published

2026-06-10

Issue

Vol. 3 No. 2 (2026): Trends in Health Informatics

Section

Articles

License

Copyright (c) 2026 Trends in Health Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Simaei, K. ., Kiani-Sarkaleh, A., & Esmaeeli, A. . (2026). Benign and malignant breast masses classification based on AdaBoosting fine-tuned AlexNet. Trends in Health Informatics, 3(2), 98-112. https://doi.org/10.22105/thi.v3i2.55

Similar Articles

1-10 of 18

You may also start an advanced similarity search for this article.