Journal Press India^®

Author Details ( * ) denotes Corresponding author

Breast cancer constitutes a significant public health challenge, demanding effective diagnostic Approaches. While ultrasound, mammography, and MRI remain pivotal, their practicality for regular, short-interval mass screenings is limited. Thermography, as a non-invasive and cost effective option, holds potential for routine self-screening. Leveraging the self-attention based Vision Transformer designs in lieu of traditional CNNs, this study explores various SWIN transformer variations and augmentation strategies for breast cancer detection. DMR-IR benchmark dataset was used, which was partitioned into training, testing, and validation subsets with the ratio of 70:15:15%, the obtained results exhibit significant promise. The SWIN-L architecture exhibited exceptional performance, achieving 96.55% accuracy, 95.50% precision, 95.76% recall, 95.43% F1 score, 97.34% specificity, and 96.21% AUC, thus demonstrating its remarkable capability in breast cancer detection. Based on the observed results, it is evident that the proposed system holds promise and can be considered for breast cancer detection.

Keywords

Breast Cancer; Thermography Image; Vision Transformer; Self Attention; SWIN

1. S. Francis, M. Sasikala, S. J.-A. of I. to, and undefined 2017, “Detection of breast abnormality using rotational thermography,” SpringerSV Francis, M Sasikala, SD JaipurkarApplication of Infrared to Biomedical Sciences, 2017•Springer, Accessed: Sep. 03, 2023. [Online].Available: https://link.springer.com/chapter/10.1007/978-981-10-3147-2_9


2. D. Singh and A. K. Singh, “Role of image thermography in early breast cancer detection-Past, present and future,” Comput Methods Programs Biomed, vol. 183, Jan. 2020, doi: 10.1016/J.CMPB.2019.105074.


3. S. G. Kandlikar et al., “Infrared imaging technology for breast cancer detection – Current status, protocols and new directions,” Int J Heat Mass Transf, vol. 108, pp. 2303–2320, 2017, doi: 10.1016/J.IJHEATMASSTRANSFER.2017.01.086.


4. E. Mahoro and M. A. Akhloufi, “Breast cancer classification on thermograms using deep CNN and transformers,” Quant Infrared Thermogr J, 2022, doi: 10.1080/17686733.2022.2129135.


5. R. Kamal, S. Mansour, A. Farouk, M. Hanafy, A. Elhatw, and M. M. Goma, “Contrastenhanced mammography in comparison with dynamic contrast-enhanced MRI: which modality is appropriate for whom?,” Egyptian Journal of Radiology and Nuclear Medicine, vol. 52, no. 1, Dec. 2021, doi: 10.1186/S43055-021-00586-Y.


6. M. Yap, G. Pons, J. Marti, … S. G.-I. journal of, and undefined 2017, “Automated breast ultrasound lesions detection using convolutional neural networks,” ieeexplore.ieee.orgMH Yap, G Pons, J Marti, S Ganau, M Sentis, R Zwiggelaar, AK Davison, R Mar6IEEE journal of biomedical and health informatics, 2017•ieeexplore.ieee.org, Accessed: Sep. 03, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8003418/


7. L. Li et al., “Cross-AEention Based Multi-Scale Feature Fusion Vision Transformer For Breast Ultrasound Image Classification,” ieeexplore.ieee.org L Li, Z Wu, J Liu, L Wang, Y Jin, P Jiang, J Feng, M Wu2022 IEEE International Conference on Bioinformatics and, 2022•ieeexplore.ieee.org, Accessed: Sep. 03, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9994966/?casa_token=-_SHyAm_CegAAAAA:u5Hsh8LWB1-S_IDeoK6T5EVE_fPTYJsN4O5zDMi9gimpQFayADhGupCYUvYbIxyjmB1nXqkFg


8. A. Hayat, A. Singh, V. Shahare, and N. Arora, “An efficient system for early diagnosis of breast cancer using support vector machine,” International Journal of Engineering and Advanced Technology (IJEAT), doi: 10.35940/ijeat.A1626.109119.


9. T. BorcharE, A. Conci, R. Lima, R. R.-S. processing, and undefined 2013, “Breast thermography from an image processing viewpoint: A survey,” Elsevier, Accessed: Sep. 03, 2023. [Online]. Available: https://www.sciencedirect.com/science/ar0cle/pii/S0165168412002794?casa_token=RJNgGGb3ri8AAAAA:G1rUVvnCmHaGn-gZgHb7-qGh`xcJFsSux94b-vd7FS3_aTQA85L11m-U3rhJpJfSXJTz1q4_g


10. S. Mishra, A. Prakash, … S. R.-2020 7th I., and undefined 2020, “Breast cancer detection using thermal images and deep learning,” ieeexplore.ieee.org S Mishra, A Prakash, SK Roy, P Sharan, N Mathur2020 7th International Conference on Computing for Sustainable, 2020•ieeexplore.ieee.org, Accessed: Sep. 03, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9083722/


11. I. Rojas, O. Valenzuela, F. Rojas, and F. Ortuño, Eds., “Bioinformatics and Biomedical Engineering,” vol. 11466, 2019, doi: 10.1007/978-3-030-17935-9.


12. A. Vaswani et al., “AEention Is All You Need,” Adv Neural Inf Process Syst, vol. 2017-December, pp. 5999–6009, Jun. 2017, Accessed: Sep. 03, 2023. [Online]. Available: https://arxiv.org/abs/1706.03762v7


13. A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arxiv.org, Accessed: Sep. 03, 2023. [Online]. Available: https://arxiv.org/abs/2010.11929


14. M. Gheini, X. Ren, and J. May, “Cross-AEention is All You Need: Adapting Pretrained Transformers for Machine Translation,” EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings, pp. 1754–1765, 2021, doi: 10.18653/v1/2021.emnlp-main.132.


15. Y. Dai, Y. Gao, F. Liu, Y. ; Dai, Y. ; Gao, and F. Liu, “Transmed: Transformers advance multi-modal medical image classification,” mdpi.comY Dai, Y Gao, F LiuDiagnostics, 2021•mdpi.com, 2021, doi: 10.3390/diagnos0cs11081384.


16. Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shi`ed Windows,” Proceedings of the IEEE Interna6onal Conference on Computer Vision, pp. 9992–10002, 2021, doi: 10.1109/ICCV48922.2021.00986.


17. N. Köşüş, A. Köşüş, M. Duran, S. Simavli, and N. Turhan, “Comparison of standard mammography with digital mammography and digital infrared thermal imaging for breast cancer screening,” Journal of the Turkish German Gynecology Associa6on, vol. 11, no. 3, pp. 152–157, 2010, doi: 10.5152/JTGGA.2010.24.


18. S. Ekici and H. Jawzal, “Breast cancer diagnosis using thermography and convolutional neural networks,” Med Hypotheses, vol. 137, Apr. 2020, doi: 10.1016/J.MEHY.2019.109542.


19. M. A. S. Al Husaini, M. H. Habaebi, M. R. Islam, and T. S. Gunawan, “Self-detection of early breast cancer application with infrared camera and deep learning,” Electronics (Switzerland), vol. 10, no. 20, Oct. 2021, doi: 10.3390/ELECTRONICS10202538.


20. S. T. Kakile0, A. Dalmia, and G. Manjunath, “Exploring deep learning networks for tumour segmentation in infrared images,” Quant Infrared Thermogr J, vol. 17, no. 3, pp. 153–168, Jul. 2020, doi: 10.1080/17686733.2019.1619355.


21. B. Krawczyk and G. Schaefer, “Breast thermogram analysis using classifier ensembles and image symmetry features,” IEEE Syst J, vol. 8, no. 3, pp. 921–928, 2014, doi: 10.1109/JSYST.2013.2283135.


22. L. S. Garia and M. Hariharan, “Vision Transformers for Breast Cancer Classification from Thermal Images,” pp. 177–185, 2023, doi: 10.1007/978-981-99-0236-1_13.


23. A. Alshehri and D. AlSaeed, “Breast Cancer Detection in Thermography Using Convolutional Neural Networks (CNNs) with Deep Attention Mechanisms,” Applied Sciences (Switzerland), vol. 12, no. 24, Dec. 2022, doi: 10.3390/APP122412922.


24. E. Rashed and M. Samir Abou El Seoud, “Deep learning approach for breast cancer diagnosis,” ACM International Conference Proceeding Series, pp. 243–247, Apr. 2019, doi: 10.1145/3328833.3328867.


25. J. Deng, Y. Ma, D. ao Li, J. Zhao, Y. Liu, and H. Zhang, “Classification of breast density categories based on SE-AEention neural networks,” Comput Methods Programs Biomed, vol. 193, Sep. 2020, doi: 10.1016/J.CMPB.2020.105489.


26. A. K. Arslan, S. Yasar, and C. Colak, “Breast cancer classification using a constructed convolutional neural network on the basis of the histopathological images by an interactiveweb-based interface,” 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2019 - Proceedings, Oct. 2019, doi: 10.1109/ISMSIT.2019.8932942.


27. L. Silva, D. Saade, … G. S.-J. of M., and undefined 2014, “A new database for breast research with infrared image,” ingentaconnect.com LF Silva, DCM Saade, GO Sequeiros, AC Silva, AC Paiva, RS Bravo, A Conci Journal of Medical Imaging and Health Informatics, 2014•ingentaconnect.com, Accessed: Sep. 03, 2023. [Online]. Available: https://www.ingentaconnect.com/contentone/asp/jmihi/2014/00000004/00000001/art00015







 
28.  
29.  
30.  
31.  
32.