Adaptive-Preprocessing-Enhanced YOLOX-L For Breast Cancer Mass Detection in Contrast-Enhanced Spectral Mammography

Ahmed Alaa Hani Alkurdi; Amira B. Sallow

doi:10.65542/djei.v2i3.92

Authors

Ahmed Alaa Hani Alkurdi Department of Information Technology, Technical College of Duhok, Duhok Polytechnic University, Duhok 42001, Iraq
Amira B. Sallow Department of Information Technology, Technical College of Duhok, Duhok Polytechnic University, Duhok 42001, Iraq https://orcid.org/0000-0002-5102-6193

DOI:

https://doi.org/10.65542/djei.v2i3.92

Keywords:

Breast cancer detection, Contrast-enhanced spectral mammography, YOLOX, Image preprocessing, Deep learning

Abstract

Breast cancer detection using contrast-enhanced spectral mammography (CESM) is still a challenging task, especially when lesions are subtle, low in contrast, or located within dense breast tissue. In this paper, an automated breast mass localization pipeline was developed using the YOLOX-L object detection framework. The proposed pipeline applies a piecewise adaptive contrast enhancement method before the detection stage. This method depends on dynamic thresholding to improve the visibility of lesion regions while preserving the surrounding anatomical structures. The proposed method was evaluated using the public CDD-CESM dataset. The enhanced YOLOX-L model achieved a [email protected]:0.95 of 0.703, while the unenhanced baseline achieved 0.186 under the same evaluation setting. Furthermore, additional experiments showed that the proposed enhancement method performed better than histogram equalization and CLAHE when using the same patient-level split, training configuration, and evaluation protocol. The pipeline also achieved near-real-time inference under the tested computational environment. Hence, the proposed system may be useful as an assistive tool for CESM breast mass detection. However, further external and prospective validation is still required before clinical use.

References

1. World Health Organization. Breast Cancer. Available online:https://www.who.int/news-room/fact-sheets/detail/breast-cancer (accessed on 10 August 2026).

2. Hassan, N.M.; Hamad, S.; Mahar, K. YOLO-based CAD framework with ViT transformer for breast mass detection and classification in CESM and FFDM images. Neural Comput. Appl. 2024, 36, 6467–6496. https://doi.org/10.1007/s00521-023-09364-5. DOI: https://doi.org/10.1007/s00521-023-09364-5

3. Kinkar, K.; Cen, S.Y.; Gujar, S.A.; Jannat, R.; Lei, X.; Fields, J.; Chang, M.; Thomas, M.; Yamashita, M.; Varghese, B.A. Automated Detection and Segmentation of Breast Lesions in Contrast-Enhanced Mammograms. In Proceedings of the 20th International Symposium on Medical Information Processing and Analysis (SIPAIM), Antigua, Guatemala, 2024; pp. 1–5. https://doi.org/10.1109/SIPAIM62974.2024.10783555. DOI: https://doi.org/10.1109/SIPAIM62974.2024.10783555

4. Huynh, H.N.; Tran, A.T.; Tran, T.N. Region-of-Interest Optimization for Deep-Learning-Based Breast Cancer Detection in Mammograms. Appl. Sci. 2023, 13, 6894. https://doi.org/10.3390/app13126894 DOI: https://doi.org/10.3390/app13126894

5. Achak, A.; Hedyehzadeh, M. Determining the Differentiation of Benign and Malignant NME Lesions in Contrast-Enhanced Spectral Mammography Images Based on Convolutional Neural Networks. J. Med. Biol. Eng. 2023, 43, 585–595. https://doi.org/10.1007/s40846-023-00814-y. DOI: https://doi.org/10.1007/s40846-023-00814-y

6. Venkatakrishnan, R.; Annamalai, R.; Navaneethakrishnan, R. Enhancing Breast Cancer Detection in Mammography Images: A Comprehensive Analysis. In Proceedings of International Conference on Recent Innovations in Computing: ICRIC 2023; Singh, Y.; Gonçalves, P.J.S.; Singh, P.K.; Kolekar, M.H., Eds.; Lecture Notes in Electrical Engineering; Springer: Singapore, 2024; Volume 1196, pp. 569–581. https://doi.org/10.1007/978-981-97-7862-1_39. DOI: https://doi.org/10.1007/978-981-97-7862-1_39

7. Titisari, D.; Yuniarno, E.M.; Purnama, I.K.E.; Purnomo, M.H. Enhancing Breast Cancer Detection: Optimizing YOLOv8's Performance Through Hyperparameter Tuning. In Proceedings of the 2023 8th International Conference on Information Technology and Digital Applications (ICITDA), Yogyakarta, Indonesia, 2023; pp. 1–6. https://doi.org/10.1109/ICITDA60835.2023.10427255. DOI: https://doi.org/10.1109/ICITDA60835.2023.10427255

8. Araújo, T.; Aresta, G.; Castro, E.; Rouco, J.; Aguiar, P.; Eloy, C.; Polónia, A.; Campilho, A. Classification of Breast Cancer Histology Images Using Convolutional Neural Networks. PLoS ONE 2017, 12, e0177544. https://doi.org/10.1371/journal.pone.0177544. DOI: https://doi.org/10.1371/journal.pone.0177544

9. Amin, M.N.; Kamal, R.; Farouk, A.; Gomaa, M.; Rushdi, M.A.; Mahmoud, A.M. An Efficient Hybrid Computer-Aided Breast Cancer Diagnosis System with Wavelet Packet Transform and Synthetically-Generated Contrast-Enhanced Spectral Mammography Images. Biomed. Signal Process. Control 2023, 85, 104808. https://doi.org/10.1016/j.bspc.2023.104808 DOI: https://doi.org/10.1016/j.bspc.2023.104808

10. Dhungel, N.; Carneiro, G.; Bradley, A.P. Automated Mass Detection in Mammograms Using Cascaded Deep Learning and Random Forests. In Proceedings of the 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Adelaide, Australia, 23–25 November 2015; pp. 1–8. https://doi.org/10.1109/DICTA.2015.7371234. DOI: https://doi.org/10.1109/DICTA.2015.7371234

11. Priya, L.C.V.; V.G., B.; V.R., V.; Ramachandran, S. Deep Learning Approaches for Breast Cancer Detection in Histopathology Images: A Review. Cancer Biomark. 2024, 40, 1–25. https://doi.org/10.3233/CBM-230251. DOI: https://doi.org/10.3233/CBM-230251

12. Kebede, S.R.; et al. Dual View Deep Learning for Enhanced Breast Cancer Screening Using Mammography. Sci. Rep. 2024, 14, 3839. https://doi.org/10.1038/s41598-023-50797-8. DOI: https://doi.org/10.1038/s41598-023-50797-8

13. Ragab, D.A.; Sharkas, M.; Marshall, S.; Ren, J. Breast Cancer Detection Using Deep Convolutional Neural Networks and Support Vector Machines. PeerJ 2019, 7, e6201. https://doi.org/10.7717/peerj.6201. DOI: https://doi.org/10.7717/peerj.6201