ISSN (Online): 2456-0448 info@ijirmet.com
Home / Archives / Volume 10 (2025), Issue 12 / Article Details
Volume 10, Issue 12 (2025) Open Access Peer Reviewed

Dual-Modality Transfer Learning For Breast Cancer Detection In Ultrasound And Histopathological Images

Syambabu Badugu 1 V.D.Ambeth Kumar 2

Author Affiliations

[1] [2] Department of Computer Engineering, Mizoram University, Aizawl-796 004, India
Corresponding author: ambeth@mzu.edu.in

Abstract

Histology and breast ultrasonography reveal the same illness at various scales, but automated analysis is modality-specific. In this dual-modality transfer-learning breast cancer diagnosis system, public ultrasound and histopathology imaging datasets are used. A modality-specific preprocessing, ImageNet-initialized EfficientNetB0 for three-class ultrasound classification, and DenseNet121 for benign-versus-malignant histopathology classification are used Grad-CAM inspection, patient-aware partitioning, class-sensitive optimisation, probability calibration, and leakage reduction increase interpretability. BUSI and BreaKHis constitute ethical public standards since they give de-identified labelled photos and research access. Not clinical research, the outcomes section includes literature-anchored benchmark synthesis and reproducible evaluation. Certain datasets and split methods can provide modern transfer-learning algorithms 96% accuracy in breast ultrasonography and 98% in histopathology. The paradigm prioritises modality-aware validation above headline accuracy.

Keywords: Breast cancer, ultrasound imaging, histology, transfer learning, deep learning, EfficientNet, DenseNet, explainable AI.

References

  1. Arora, L., Yadav, K. K., Malik, A., Kumar, N., Mamodiya, U., & Jain, R. (2026). Cross-Modality Transfer Learning for Breast Cancer Detection Using Ultrasound-Pretrained Deep Network on Histopathology Images. IEEE Access.
  2. Iniyan, S., Raja, M. S., Poonguzhali, R., Vikram, A., Ramesh, J. V. N., Mohanty, S. N., & Dudekula, K. V. (2024). Enhanced breast cancer diagnosis through integration of computer vision with fusion based joint transfer learning using multi modality medical images. Scientific reports, 14(1), 28376.
  3. Kaur, S., Kaur, M., & Khanna, A. (2025). Integrating multi-modal insights with transfer learning for detecting metastatic breast cancer (MBC-stage IV) prognostics. International Journal of Information Technology, 17(1), 637-643.
  4. Madani, M., Behzadi, M. M., & Nabavi, S. (2022). The role of deep learning in advancing breast cancer detection using different imaging modalities: A systematic review. Cancers, 14(21), 5334.
  5. Misra, S., Jeon, S., Managuli, R., Lee, S., Kim, G., Yoon, C., ... & Kim, C. (2021). Bi-modal transfer learning for classifying breast cancers via combined B-mode and ultrasound strain imaging. IEEE Transactions on ultrasonics, ferroelectrics, and frequency control, 69(1), 222-232.
  6. Sushanki, S., Bhandari, A. K., & Singh, A. K. (2024). A review on computational methods for breast cancer detection in ultrasound images using multi-image modalities. Archives of Computational Methods in Engineering, 31(3), 1277-1296.
  7. Shen, J., Chen, G., Lun, H., Huang, H., Zhang, L., Li, L., ... & Hu, Q. (2025). Dual-modal ultrasound-based deep learning radiomics for differentiation of benign and malignant breast lesions. Gland Surgery, 14(10), 2035.
  8. Ravikumar, A., Sriraman, H., Saleena, B., & Prakash, B. (2023). Selecting the optimal transfer learning model for precise breast cancer diagnosis utilizing pre-trained deep learning models and histopathology images. Health and Technology, 13(5), 721-745.
  9. Ayana, G., Dese, K., & Choe, S. W. (2021). Transfer learning in breast cancer diagnoses via ultrasound imaging. Cancers, 13(4), 738.
  10. Atrey, K., Singh, B. K., Roy, A., & Bodhey, N. K. (2023). A dual-modality evaluation of computer-aided breast lesion segmentation in mammogram and ultrasound using customized transfer learning approach. Signal, Image and Video Processing, 17(5), 1955-1963.
  11. Han, X., Wang, J., Zhou, W., Chang, C., Ying, S., & Shi, J. (2020, September). Deep doubly supervised transfer network for diagnosis of breast cancer with imbalanced ultrasound imaging modalities. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 141-149). Cham: Springer International Publishing.
  12. Atrey, K., Singh, B. K., Bodhey, N. K., & Pachori, R. B. (2023). Mammography and ultrasound based dual modality classification of breast cancer using a hybrid deep learning approach. Biomedical Signal Processing and Control, 86, 104919.
  13. Parwekar, P., Agrawal, K. K., Ali, J., Gundagatti, S., Rajpoot, D. S., Ahmed, T., & Vidyarthi, A. (2026). Dual-parallel artificial intelligence framework for breast cancer grading via high-intensity ultrasound and biomarkers. Cancer Biotherapy and Radiopharmaceuticals, 41(6), 544-552.
  14. Atrey, K., Singh, B. K., & Bodhey, N. K. (2024). Integration of ultrasound and mammogram for multimodal classification of breast cancer using hybrid residual neural network and machine learning. Image and Vision Computing, 145, 104987.
  15. Gupta, M., Verma, N., Sharma, N., Singh, S. N., Brojen Singh, R. K., & Sharma, S. K. (2025). Deep transfer learning hybrid techniques for precision in breast cancer tumor histopathology classification. Health Information Science and Systems, 13(1), 20.
  16. Kormpos, C., Zantalis, F., Katsoulis, S., & Koulouras, G. (2025). Evaluating deep learning architectures for breast tumor classification and ultrasound image detection using transfer learning. Big Data and Cognitive Computing, 9(5), 111.
  17. Ranjan, R. K., Kolte, R., & Khare, P. (2025, September). Dual-Modality Breast Cancer Detection Using Machine Learning and Deep Learning on Structured and Unstructured Data. In International Conference on Next-Generation Networks and Deployable Artificial Intelligence (pp. 277-293). Cham: Springer Nature Switzerland.
  18. Fu, Y., Chen, H. J., Zhang, H., Liu, D. J., Chen, X., Qiu, C. Y., ... & Ni, X. J. (2025). Integrating multimodal ultrasound imaging and machine learning for predicting luminal and non-luminal breast cancer subtypes. Frontiers in Oncology, 15, 1558880.
  19. Wang, Y. M., Wang, C. Y., Liu, K. Y., Huang, Y. H., Chen, T. B., Chiu, K. N., ... & Lu, N. H. (2024). CNN-based cross-modality fusion for enhanced breast cancer detection using mammography and ultrasound. Tomography, 10(12), 2038-2057.

How to Cite This Article

Syambabu Badugu, V.D.Ambeth Kumar (2025). Dual-Modality Transfer Learning For Breast Cancer Detection In Ultrasound And Histopathological Images. International Journal of Innovative Research in Multidisciplinary Education & Technology (IJIRMET), 10(12).

Full Text Article PDF

Journal Metadata
ISSN2456-0448
VolumeVolume 10
IssueIssue 12
Year2025
DOI10.37841/ijirmet.2025.v10.i12.002
AccessOpen Access
ReviewDouble Blind
Full Text PDF

Download the complete publication PDF for off-line reading and citation.

Download Article PDF