Abstract
An early and accurate breast cancer diagnosis will reduce the death rate and improve survival chances. Thermography is a promising non-invasive early detection modality for breast cancer. Artificial intelligence-based classification systems are being used to classify thermographic infrared images. The success of these classification systems also depends on the quality of infrared images. However, the thermographic images acquired using digital infrared cameras are inevitably degraded by noise. In this paper, we propose novel denoising auto-encoders using image pyramids. The denoising auto-encoders are forced to learn the non-local noises by corrupting the input images in the image pyramid domain. We also propose a method to estimate the noise probability distribution in infrared images using statistical methods. The proposed denoising auto-encoder framework will learn better data representations from the corrupted images generated using image pyramids and estimated noise probability distribution. The Experimentation with four different infrared breast image data sets demonstrates robust representation learning by the agent showing promising improvements in the peak signal-to-noise ratio.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mehrotra, R., Yadav, K.: Breast cancer in India: present scenario and the challenges ahead. World J. Clin. Oncol. 13(3), 209–218 (2022)
Sarigoz, T., Ertan, T.: Role of dynamic thermography in diagnosis of nodal involvement in patients with breast cancer: a pilot study. Infrared Phys. Technol. 108, 103336 (2020)
Budzan, S., Wyżgolik, R.: Remarks on noise removal in infrared images. Meas. Autom. Monit. 61(6), 187–190 (2015)
Prabha, S., Sujatha, C. M., Ramakrishnan, S.: Asymmetry analysis of breast thermograms using BM3D technique and statistical texture features. In: 2014 International Conference on Informatics, Electronics & Vision (ICIEV), pp. 1–4 (2014). https://doi.org/10.1109/ICIEV.2014.6850730
Kafieh, R., Rabbani, H.: Wavelet-based medical infrared image noise reduction using local model for signal and noise. In: 2011 IEEE Statistical Signal Processing Workshop (SSP), pp. 549–552 (2011)
Moraes, M.S., Borchartt, T.B., Conci, A., MacHenry, T.: Using wavelets on denoising infrared medical images. In: 2015 IEEE International Conference on Industrial Technology (ICIT), pp. 1791–1798 (2015)
Wippig, D., Klauer, B., Zeidler, H.C.: Denoising of infrared images by wavelet thresholding. In: Elleithy, K., Sobh, T., Mahmood, A., Iskander, M., Karim, M. (eds.) Advances in Computer, Information, and Systems Sciences, and Engineering, pp. 103–108. Springer, Dordrecht (2007). https://doi.org/10.1007/1-4020-5261-8_18
Indumathi, T.V., Sannihith, K., Krishna, S., Remya Ajai, A.S.: Effect of co-occurrence filtering for recognizing abnormality from breast thermograms. In: 2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 1170–1175 (2021)
Li, Q., Li, W., Zhang, J., Xu, Z.: An improved k-nearest neighbour method to diagnose breast cancer. Analyst. 143(12), 2807–2811 (2018)
Lai, F., Kandukuri, J., Yuan, B., Zhang, Z., Jin, M.: Thermal image enhancement through the deconvolution methods for low-cost infrared cameras. Quant. Infrared Thermogr. J. 15(2), 223–239 (2018)
Zhang, Z., Zheng, W., Ma, Z., Yin, L., Xie, M., Wu, Y.: Infrared star image denoising using regions with deep reinforcement learning. Infrared Phys. Technol. 117, 103819 (2021)
Pérez-García, F., Sparks, R., Ourselin, S.: TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput. Methods Programs Biomed. 208, 106236 (2021)
Silva, L.F., Saade, D.C.M., Sequeiros, G.O., Silva, A.C., Paiva, A.C., Bravo, R.S., et al.: A new database for breast research with infrared image. J. Med. Imaging Health Inform. 4(1), 92–100 (2014)
Bhowmik, M.K., Gogoi, U.R., Majumdar, G., Bhattacharjee, D., Datta, D., Ghosh, A.K.: Designing of ground-truth-annotated DBT-TU-JU breast thermogram database toward early abnormality prediction. IEEE J. Biomed. Health Inform. 22(4), 1238–1249 (2017)
Gomez, L., Ospina, R., Frery, A.C.: Unassisted quantitative evaluation of despeckling filters. Remote Sens. 9(4), 389 (2017)
Sun, Q., Liu, X., Bourennane, S., Liu, B.: Multiscale denoising autoencoder for improvement of target detection. Int. J. Remote Sens. 42(8), 3002–3016 (2021)
Yan, L., et al.: Infrared and visible image fusion via octave Gaussian pyramid framework. Sci. Rep. 11(1), 1–12 (2021)
Wang, Z., Cui, Z., Zhu, Y.: Multi-modal medical image fusion by Laplacian pyramid and adaptive sparse representation. Comput. Biol. Med. 123, 103823 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Raghavan, K., Sivaselavan, B., Kamakoti, V. (2023). iPyrDAE: Image Pyramid-Based Denoising Autoencoder for Infrared Breast Images. In: Maji, P., Huang, T., Pal, N.R., Chaudhury, S., De, R.K. (eds) Pattern Recognition and Machine Intelligence. PReMI 2023. Lecture Notes in Computer Science, vol 14301. Springer, Cham. https://doi.org/10.1007/978-3-031-45170-6_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-45170-6_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45169-0
Online ISBN: 978-3-031-45170-6
eBook Packages: Computer ScienceComputer Science (R0)