Abstract Breast cancer is the main health burden worldwide. Cancer is located in the breast, starts when the cell grows under control and begins as in-situ carcinoma and when spread into other parts known as invasive carcinoma. Breast cancer mass can early be found by image modality when discovering mass early can easily diagnose and treated. Multimodalities used for the classification of breast cancer Such as mammography, ultrasound, and Magnetic resonance imaging. Two types of fusion are used earlier fusion and later fusion. Early fusion it’s a simple relation between modalities while later fusion gives more interest to fusion strategy to learn the complex relationship between various modalities as a result, can get highly accurate results when using the later fusion. When combining two image modalities (mammography, ultrasound) and using an excel sheet containing the age, view, side, and status attribute associated with each mammographic image using DenseNet 201 with Layer level fusion strategy as later fusion by making connections between the various paths and same path by using Concatenated layer. Fusing at the feature level achieves the best performance in terms of several evaluation metrics (accuracy, recall, precision area under the curve, and F1 score) and performance.

References

[1] Al-Dhabyani W., Gomaa M., Khaled H., and Fahmya A., “Deep Learning Approaches for Data Augmentation and Classification of Breast Masses Using Ultrasound Images,” Journal of Advanced Computer Science and Applications, vol. 10, no. 5, pp. 1-11, 2019.

[2] Dolz J., Gopinath K., Yuan J., Lombaert H., Desrosiers C., and Ben Ayed I., “HyperDense- Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation,” IEEE Transactions on Medical Imaging, vol. 38, no. 5, pp. 1116-1126, 2019.

[3] Fujioka T., Kubota K., Mori M., Kikuchi Y., Katsuta L., Kasahara M., Oda G., Ishiba T., Nakagawa T., and Tateishi U., “Distinction Between Benign and Malignant Breast Masses at Breast Ultrasound Using Deep Learning Method With A Convolutional Neural Network,” Japanese journal of radiology, vol. 37, no. 6, pp. 466-472 2019.

[4] Garg S. and Jindal B., “Skin Lesion Segmentation in Dermoscopy Imagery,” The International Arab Journal of Information Technology, vol. 19, no. 1, pp. 29-37, 2022.

[5] Guo Z., Li X, Huang H., Guo N., and Li Q., “Medical Image Segmentation Based on Multi- Modal Convolutional Neural Network: Study on Image Fusion Schemes,” in Proceeding of the IEEE 15th International Symposium on Biomedical Imaging, USA, pp. 903-907, 2018.

[6] Hamdy E., Zaghloul M., and Badawy O., “Deep Learning Supported Breast Cancer Classification with Multi-Modal Image Fusion,” in Proceeding of the 2021 22nd International Arab Conference on Information Technology, Oman, pp. 1-7, Densely Convolutional Networks For Breast Cancer Classification With Multi-Modal Image Fusion 469 2021.

[7] Huang G., Liu Z., Maaten L., and Weinberger K., “Densely Connected Convolutional Networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA, pp. 4700-4708 2017.

[8] Kaggle.https://www.kaggle.com/cheddad/minidd s2, Last Visited, 2021.

[9] Shen L., Margolies L., Rothstein J. Fludere., McBride R., and Sieh W., Reports S., “Deep Learning to Improve Breast Cancer Detection on Screening Mammography,” Scientific Reports, vol. 9, no. 1, pp. 1-12, 2019.

[10] Singh A., Demedicalizing Women’s Health, New Delhi, Gyan Publishing House, 2010.

[11] Zhou T., Ruan S. and Canu S., “A review: Deep Learning for Medical Image Segmentation Using Multi-Modality Fusion,” Array vol. 3, pp. 100004, 2019. Eman Hamdy was born in 1997 in Alexandria, Egypt. She received her B.Sc. in College of Computing and Information Technology and M.Sc. in Deep learning supported breast cancer classification with multi- modal image fusion from the Faculty of Computing and Information Technology, Alex., Egypt, Arab Academy for Science Technology and Maritime Transport (AASTMT) at Alexandria, Egypt. She is currently an Assistant Lecturer College of Computing and Information Technology, Arab Academy for Science and Technology and Maritime Transport, Alexandria, Egypt. Osama Badawy was born in 1949 in Al Minya, Egypt. He received his B.Sc. in Electrical Engineering and M.Sc. in the Optimum Smoothing of Data Using Digital Filter from the Faculty of Military-Technical Engineering, Cairo, Egypt, and a Ph.D. in Expert Systems for Image Processing from the Faculty of Engineering, Ein Shams University at Cairo, Egypt. He is currently a Full Professor at the College of Computing and Information Technology, Arab Academy for Science and Technology and Maritime Transport, Alexandria, Egypt. Mohamed Zaghloul Asst. prof. 2009 Ph.D. degree in Electrical Engineering 2002 from Menofia Faculty of Engineering. M.SC degree in Electrical Engineering from Faculty of Engineering, Alexandria University, 1991. Diploma in Electrical Engineering from Faculty of Engineering, Alexandria University, 1984. B.SC in Electrical Engineering from M T C, July 1977, Cairo. Expert for supervision on research projects with EU and master’s thesis for students. Lecturer in artificial intelligent Faculty of Engineering/ Arab Academy for Science and Technology (AAST) & Maritime Transport. Alex. Egypt. Member of Egyptian industry comity and scientific research. Lecturer, in Electronic and Communications Department Tanta University and Kafr El Shek University. Lecturer, in Electronic and Communications Department Naval College.