Deep learning based ResNet integrated U-Net approach for segmentation and classification of breast cancer images

Abstract

Deep learning models, particularly Convolutional Neural Networks and U-Net architectures, are successfully utilized for segmenting breast cancer histology images, enabling precise identification of anatomical structures and pathological lesions. This study highlights the effectiveness of the U-Net architecture in histology imaging and segmentation, demonstrating its potential to enhance the diagnosis process in medical imaging. Such advancements are crucial for improving the speed and accuracy of breast cancer diagnosis, potentially benefiting thousands of patients annually, primarily women, and advancing the development of deep learning models. Specifically, this model integrating ResNet+U-Net have been applied to early breast cancer detection, achieving an accuracy of 96.3%, a MeanIoU of 98.0%, and a specificity of 98.1%. These results underscore the significant impact of deep learning methods in diagnosing breast cancer, increasing patient life expectancy by facilitating early detection. Moreover, the study aims to refine the sensitivity and accuracy of these algorithms, thereby reducing false positives and negatives to render the treatment process more effective.

Keywords

• Breast cancer
• Deep learning
• Histology
• ResNet
• U-Net

References

1. [1] Wang L. Early diagnosis of breast cancer. Sensors (Basel). 2017;17(7):1572. doi:10.3390/s17071572
2. [2] McLellan GL. Screening and early diagnosis of breast cancer. J Fam Pract. 1988;26(5):561-8. Available from: https://pubmed.ncbi.nlm.nih.gov/3284964/
3. [3] Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68(6):394-424. doi:10.3322/caac.21492
4. [4] Dyba T, Randi G, Bray F, Martos C, Giusti F, Nicholson N, et al. The European cancer burden in 2020: Incidence and mortality estimates for 40 countries and 25 major cancers. Eur J Cancer. 2021;157:308-47. doi:10.1016/j.ejca.2021.07.039
5. [5] Kosch T, Welsch R, Chuang L, Schmidt A. The placebo effect of artificial intelligence in human–computer interaction. ACM Trans Comput Hum Interact. 2023;29(6):1-32. doi:10.1145/3529225
6. [6] Jadoon MM, Zhang Q, Haq IU, Butt S, Jadoon A. Three-class mammogram classification based on descriptive CNN features. Biomed Res Int. 2017;2017:3640901. doi:10.1155/2017/3640901
7. [7] Yousif M, van Diest PJ, Laurinavicius A, Rimm D, van der Laak J, Madabhushi A, et al. Artificial intelligence applied to breast pathology. Virchows Arch. 2022;480(2):1-19. doi:10.1007/s00428-021-03213-3
8. [8] Özgür SN, Keser SB. Classification of Breast Cancer Tumors with Deep Learning Algorithms. Turkish Journal of Nature and Science. 2021;10(2):212-22. Doi: 10.46810/tdfd.957618

9. [9] Canatalay PJ, Uçan ON, Zontul M. Diagnosis of breast cancer from X-ray images using deep learning methods. PONTE Int J Sci Res. 2021;77(6):1-9. doi:10.21506/j.ponte.2021.6.1
10. [10] Hepsağ PU, Özel SA, Yazıcı A, editors. Using deep learning for mammography classification. In: 2017 Int Conf Comput Sci Eng (UBMK); 2017 Oct 5–8; Antalya, Türkiye. IEEE; 2017. doi:10.1109/UBMK.2017.8093429
11. [11] Nahid AA, Mehrabi MA, Kong Y. Histopathological breast cancer image classification by deep neural network techniques guided by local clustering. Biomed Res Int. 2018;2018:2362108. doi:10.1155/2018/2362108
12. [12] Chen Y. Application of Resnet18-Unet in separating tumors from brain MRI images. J Phys Conf Ser. 2023;2580:012057. doi:10.1088/1742-6596/2580/1/012057
13. [13] Sivasakthiselvan S, Sahoo S, Panda A, Mishra R. Image classification toward breast cancer. Int J Res Eng Sci. 2018;6(8):129-39.
14. [14] Ragab DA, Sharkas M, Marshall S, Ren J. Breast cancer detection using deep convolutional neural networks and support vector machines. PeerJ. 2019;7:e6201. doi:10.7717/peerj.6201
15. [15] Xie J, Liu R, Luttrell J, Zhang C. Deep learning-based analysis of histopathological images of breast cancer. Front Genet. 2019;10:426. doi:10.3389/fgene.2019.00426
16. [16] Li H, Zhuang S, Li D, Zhao J, Ma Y. Benign and malignant classification of mammogram images based on deep learning. Biomed Signal Process Control. 2019;51:347-54. doi:10.1016/j.bspc.2019.03.019
17. [17] Jiménez G, Racoceanu D. Deep learning for semantic segmentation vs. classification in computational pathology: application to mitosis analysis in breast cancer grading. Front Bioeng Biotechnol. 2019;7:145. doi:10.3389/fbioe.2019.00145
18. [18] Saha M, Chakraborty C. Her2Net: A deep framework for semantic segmentation and classification of cell membranes and nuclei in breast cancer evaluation. IEEE Trans Image Process. 2018;27(5):2189-200. doi:10.1109/TIP.2018.2806441
19. [19] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Med Image Comput Comput Assist Interv – MICCAI 2015. Springer; 2015. p. 234-41. doi:10.1007/978-3-319-24574-4_28
20. [20] Abderrahim NYQ, Abderrahim S, Rida A, editors. Road segmentation using U-Net architecture. In: 2020 IEEE Int Conf Moroccan Geomatics (Morgeo); 2020 May 11–13. doi:10.1109/Morgeo49228.2020.9121882
21. [21] Targ S, Almeida D, Lyman K. Resnet in resnet: Generalizing residual architectures. arXiv. 2016. Available from: https://arxiv.org/abs/1603.08029
22. [22] Xu W, Fu YL, Zhu D. ResNet and its application to medical image processing: Research progress and challenges. Comput Methods Programs Biomed. 2023;240:107660. doi:10.1016/j.cmpb.2023.107660
23. [23] Liang J. Image classification based on RESNET. J Phys Conf Ser. 2020;1648(3):032106. doi:10.1088/1742-6596/1648/3/032106
24. [24] Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297-302. doi:10.2307/1932409
25. [25] Zhang YD, Pan C, Chen X, Wang F. Abnormal breast identification by nine-layer convolutional neural network with parametric rectified linear unit and rank-based stochastic pooling. J Comput Sci. 2018;27:57-68. doi:10.1016/j.jocs.2018.04.006
26. [26] Bukhori S, Bariiqy MA, Eka YRW, Adi Putra J. Segmentation of breast cancer using convolutional neural network and U-Net architecture. J AI Data Min. 2023;11(3):477-85. doi:10.1007/978-981-97-6992-6_5
27. [27] Öter A. Automatic detection of epileptic seizures from EEG signals using artificial intelligence methods. Gazi Univ J Sci Part C Des Technol. 2024. doi:10.29109/gujsc.1416435
28. [28] Sezer S, Öter A, Ersoz B, Topcuoglu C, Bulbul HI, Sagiroglu S, et al. Explainable artificial intelligence for LDL cholesterol prediction and classification. Clin Biochem. 2024:110791. doi:10.1016/j.clinbiochem.2024.110791
29. [29] Öter A, Aydoğan O, Tuncel D. Automatic sleep stage classification using artificial neural networks with wavelet transform. Niğde Ömer Halisdemir Univ J Eng Sci. 2019;8(1):59-68. doi:10.28948/ngumuh.516809
30. [30] Ortega-Ruiz MA, Roman-Rangel E, Reyes-Aldasoro CC. Multiclass semantic segmentation of immunostained breast cancer tissue with a deep-learning approach. medRxiv. 2022. doi:10.1101/2022.08.17.22278889
31. [31] Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell. 2017;40(4):834-48. doi:10.1109/TPAMI.2017.2699184