Abstract
Photoacoustic imaging can potentially be used for early detection of prostate cancer. Photoacoustic imaging, which is a hybrid of pure optical and ultrasound imaging technique can potentially detect malignant lesions at early stage. In this study, unsupervised classification was performed with photoacoustic data, generated by freshly excised prostate specimens from actual human patients. An auto-encoder network, specifically tuned for clustering, was employed for unsupervised classification of malignant and nonmalignant prostate tissue. The performance of the auto-encoder algorithm was compared with that of K-means with original as well as compressed photoacoustic data. The preliminary results show that it is possible to perform unsupervised classification with moderate accuracy for prostate cancer detection using photoacoustic imaging. The performance of this network was compared with various implementations of K-means algorithm. While the specifically tuned auto-encoder provided the maximum accuracy and sensitivity, K-means with auto-encoder code space representation of photoacoustic data provided the maximum specificity.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ferlay, J., et al.: GLOBOCAN 2012 v1.0, Cancer Incidence and Mortality Worldwide: IARC CancerBase No. 11 [Internet]. International Agency for Research on Cancer, Lyon (2013)
Anon.: Three year report of population based cancer registries 2009–2011. National Cancer Registry Programme, Indian Council of Medical Research, Bangalore, India (2013)
American Cancer Society. https://www.cancer.org/cancer/prostate-cancer/about/key-statistics.html
American Cancer Society. https://www.cancer.org/acs/groups/cid/documents/webcontent
Presti Jr., J.C.: Prostate biopsy: current status and limitations. Reviews in Urology 9(3), 93 (2007)
Beard, P.: Biomedical photoacoustic imaging. Interface Focus 1(4), 602–631 (2011)
Valluru, K.S., Chinni, B.K., Rao, N.A., Bhatt, S., Dogra, V.S.: Basics and clinical applications of photoacoustic imaging. Ultrasound Clin. 4, 403–429 (2009)
Shen, D., Guorong, W., Suk, H.-I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)
Shin, H.-C., Orton, M.R., Collins, D.J., Doran, S.J., Leach, M.O.: Stacked auto-encoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1930–1943 (2013)
Suk, H.-I., Lee, S.-W., Shen, D.: Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. Brain Struct. Func. 220, 841–859 (2015)
Cheng, J.-Z., et al.: Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Sci. Rep. 6, 24454 (2016)
Wang, J., Yang, X., Cai, H., Tan, W., Jin, C., Li, L.: Discrimination of breast cancer with microcalcifications on mammography by deep learning. Sci. Rep. 6, 27327 (2016)
Jha, D., Kwon, G.-R.: Alzheimer’s disease detection using sparse auto-encoder, scale conjugate gradient and softmax output layer with fine tuning. Int. J. Mach. Learn. Comput. 7(1), 13–17 (2017)
Kim, B.-C., Sung, Y.S., Suk, H.-I.: Deep feature learning for pulmonary nodule classification in a lung CT. In: 4th International Winter Conference on Brain-Computer Interface (2016)
Sevakula, R.K., Singh, V., Verma, N.K., Kumar, C., Cui, Y.: Transfer learning for molecular cancer classification using deep neural networks. IEEE Trans. Comput. Biol. Bioinform. 16, 2089–2100 (2018)
Qiu, Y., Zhou, W., Nana, Yu., Peidong, D.: Denoising sparse autoencoder-based ictal EEG classification. IEEE Trans. Neural Syst. Rehabil. Eng. 26(9), 1717–1726 (2018)
Wen, T., Zhang, Z.: Deep convolution neural network and auto-encoders based unsupervised feature learning of EEG signals. IEEE Access 6, 25399–25410 (2018)
Song, C., Liu, F., Huang, Y., Wang, L., Tan, T.: Auto-encoder based data clustering. In: CIARP 2013, pp. 117–124 (2013)
Saugata, S., Rao, N.A., Chinni, B.K., Dogra, V.S.: Evaluation of frequency domain analysis of a multiwavelength photoacoustic signal for differentiating malignant from benign and normal prostates. J. Ultrasound Med. 35(10), 2165–2177 (2016)
Sinha, S., Rao, N., Chinni, B., Moalem, J., Giampolli, E.J., Dogra, V.: Differentiation between malignant and normal human thyroid tissue using frequency analysis of multispectral photoacoustic images. In: IEEE Western New York Image Processing Workshop (WNYIPW 2013), pp. 5–8. IEEE (2013)
Saugata, S., Rao, N.A., Valluru, K.S., Chinni, B.K., Dogra, V.S., Helguera, M.: Frequency analysis of multispectral photoacoustic images for differentiating malignant region from normal region in excised human prostate. In: SPIE Medical Imaging, pp. 90400P–90400P. International Society for Optics and Photonics (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Patil, M., Sinha, S., Dhengre, N., Chinni, B., Dogra, V., Rao, N. (2021). Evaluation of Auto-encoder Network with Photoacoustic Signal for Unsupervised Classification of Prostate Cancer. In: Singh, S.K., Roy, P., Raman, B., Nagabhushan, P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1376. Springer, Singapore. https://doi.org/10.1007/978-981-16-1086-8_37
Download citation
DOI: https://doi.org/10.1007/978-981-16-1086-8_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1085-1
Online ISBN: 978-981-16-1086-8
eBook Packages: Computer ScienceComputer Science (R0)