The week's pick
Reseach Article
Breast Cancer Multi-Class Classification using ViT Model
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 13 |
| Year of Publication: 2024 |
| Authors: Esam Mohammed Othman |
10.5120/ijca2024923504
|
Esam Mohammed Othman . Breast Cancer Multi-Class Classification using ViT Model. International Journal of Computer Applications. 186, 13 ( Mar 2024), 13-18. DOI=10.5120/ijca2024923504
Abstract
Breast cancer ranks as the most prevalent form of cancer among women worldwide, underscoring the importance of early detection for enhancing treatment success rates. The ability to accurately differentiate between malignant (aggressive) and benign breast tumors is crucial for determining appropriate treatment strategies. This research introduces a novel methodology leveraging Transformer models for the task of breast cancer image classification. Utilizing a Vision Transformer (ViT) pre-trained across a broad array of domains, this approach incorporates an ensemble of densely connected network layers specifically refined for a dataset dedicated to breast cancer imagery. The performance of this innovative model was rigorously evaluated against a benchmark dataset, demonstrating superior classification capabilities with remarkable accuracy levels—97.5% in binary categorizations and 94% in multi-class scenarios. The findings from this study underscore the potential of employing advanced Transformer models in the precise classification of breast tumors, thereby contributing to the advancement of diagnostic techniques in oncology.
References
- Md. Mahbubur Rahman, Md. Saikat Islam Khan, Hafiz Md. Hasan Babu, "BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer," Array, vol. 16, pp. 100256, 2022.
- B. Xu et al., "Attention by Selection: A Deep Selective Attention Approach to Breast Cancer Classification," in IEEE Transactions on Medical Imaging, vol. 39, no. 6, pp. 1930-1941, June 2020, doi: 10.1109/TMI.2019.2962013.
- X. Yu, C. Kang, D. S. Guttery, S. Kadry, Y. Chen and Y. -D. Zhang, "ResNet-SCDA-50 for Breast Abnormality Classification," in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 18, no. 1, pp. 94-102, 1 Jan.-Feb. 2021, doi: 10.1109/TCBB.2020.2986544.
- M. Huang, S. Liu, and K. Q. Weinberger, "Densely connected convolutional networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700-4708. doi: 10.1109/CVPR.2017.243.
- K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in Proceedings of the International Conference on Learning Representations, 2015. arXiv: 1409.1556.
- A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "MobileNets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017.
- K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778. doi: 10.1109/CVPR.2016.90.
- Zhang, H., Lu, S., Ren, J., and Liu, J., "A hybrid CNN-RNN model for breast cancer classification," Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 3, pp. 2817-2828, 2021.
- Wang, X., Sun, Y., and Li, B., "Multi-scale convolutional neural network for breast cancer classification in mammography images," Journal of Healthcare Engineering, vol. 11, no. 3, pp. 401-409, 2020.
- Liu, X., Huang, Y., Wang, C., and Zeng, X., "A random forest-based breast cancer classification model using gene expression profiles," Journal of Healthcare Engineering, vol. 11, no. 2, pp. 235-244, 2020.
- Chen, X., Li, Y., and Li, J., "A Support Vector Machine-Based Model for Breast Cancer Classification Using Diffusion-Weighted Magnetic Resonance Imaging," Journal of Healthcare Engineering, vol. 12, no. 3, pp. 2817-2828, 2021.
- J. Xie, et al., "Breast cancer diagnosis based on vision transformer," International Journal of Advanced Science and Technology, vol. 30, no. 5, pp. 2826-2836, 2021.
- Z. Li, et al., "Integrating Vision Transformer with clinical data for breast cancer classification," Frontiers in Medicine, vol. 9, p. 841457, 2022.
- Y. Zhang, et al., "Transformer-based breast tumor segmentation in MRI scans," Medical Image Analysis, vol. 78, p. 102183, 2023.
- Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ..., and Hinton, G., "An image is worth 16x16 words: Transformers for image recognition at scale," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3156-3164, 2021.
- F. A. Spanhol, L. S. Oliveira, C. Petitjean, and L. Heutte, “A Dataset for Breast Cancer Histopathological Image Classification,” IEEE Trans. Biomed. Eng., vol. 63, no. 7, pp. 1455–1462, Jul. 2016.
- F.A. Spanhol, L.S. Oliveira, C. Petitjean, and L. Heutte, "Breast cancer histopathological image classification using convolutional neural networks," in International Joint Conference on Neural Networks, 2016, pp. 2560-2567.
- Z. Han, B. Wei, and Y. Zheng, "Breast cancer multi-classification from histopathological images with structured deep learning model," Scientific Reports, vol. 7, no. 1, p. 4172, 2017.
Index Terms
Keywords