Abstract
Labeled medical datasets may include a limited number of observations for each class, while unlabeled datasets may include observations from patients with pathologies other than those observed in the labeled dataset. This negatively influences the performance of the prediction algorithms. Including out-of-distribution data in the unlabeled dataset can lead to varying degrees of performance degradation, or even improvement, by using a distance to measure how out-of-distribution a piece of data is. This work aims to propose an approach that allows estimating the predictive uncertainty of supervised algorithms, improving the behaviour when atypical samples are presented to the distribution of the dataset. In particular, we have used this approach to mammograms X-ray images applied to binary classification tasks. The proposal makes use of Feature Density, which consists of estimating the density of features from the calculation of a histogram. The obtained results report slight differences when different neural network architectures and uncertainty estimators are used.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Calderon-Ramirez, S., et al.: Improving uncertainty estimation with semi-supervised deep learning for Covid-19 detection using chest x-ray images. IEEE Access 9, 85, 442–485 (2021)
Calderon-Ramirez, S., et al.: Dealing with scarce labelled data: semi-supervised deep learning with mix match for Covid-19 detection using chest x-ray images. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5294–5301. IEEE (2021)
Wild, C., Weiderpass, E., Stewart, B.: World cancer report: cancer research for cancer prevention. International Agency for Research on Cancer, Lyon, France (2020)
A. C. Society: Breast Cancer Facts & Figures 2019–2020. American Cancer Society, Atlanta (2019)
Molina-Cabello, M.A., Accino, C., López-Rubio, E., Thurnhofer-Hemsi, K.: Optimization of convolutional neural network ensemble classifiers by genetic algorithms. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2019. LNCS, vol. 11507, pp. 163–173. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20518-8_14
Molina-Cabello, M.A., Rodríguez-Rodríguez, J.A., Thurnhofer-Hemsi, K., López-Rubio, E.: Histopathological image analysis for breast cancer diagnosis by ensembles of convolutional neural networks and genetic algorithms. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Calderon-Ramirez, S., et al.: Correcting data imbalance for semi-supervised Covid-19 detection using x-ray chest images. Appl. Soft Comput. 111, 107692 (2021)
Ramírez, S.C., Murillo-Hernández, D., Rojas-Salazar, K., Elizondo, D., Moemeni, A., Molina-Cabello, M.A.: A real use case of semi-supervised learning for mammogram classification in a local clinic of Costa Rica. Med. Biol. Eng. Comput. (2022)
Calderon-Ramirez, S., et al.: Mixmood: a systematic approach to class distribution mismatch in semi-supervised learning using deep dataset dissimilarity measures. arXiv preprint arXiv:2006.07767 (2020)
Calderon-Ramirez, S., Yang, S., Elizondo, D., Moemeni, A.: Dealing with distribution mismatch in semi-supervised deep learning for Covid-19 detection using chest x-ray images: a novel approach using feature densities. arXiv preprint arXiv:2109.00889 (2021)
Sun, W., Tseng, B., Zhang, J., Qian, W.: Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data. Comput. Med. Imaging Graph. (2016)
Tardy, M., Scheffer, B., Mateus, D.: Uncertainty Measurements for the Reliable Classification of Mammograms. In: Shen, D., Liu, T., Peters, T.M., Staib, L.H., Essert, C., Zhou, S., Yap, P.-T., Khan, A. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 495–503. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_55
Jøsang, A.: Subjective Logic: A Formalism for Reasoning Under Uncertainty. International Series of Monographs on Physics. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42337-1
Denouden, T., Salay, R., Czarnecki, K., Abdelzad, V., Phan, B., Vernekar, S.: Improving reconstruction autoencoder out-of-distribution detection with Mahalanobis distance. CoRR, vol. abs/1812.02765 (2018). http://arxiv.org/abs/1812.02765
Calderón-Ramírez, S., et al: Improving uncertainty estimations for mammogram classification using semi-supervised learning. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning (2016)
Moreira, I.C., Amaral, I., Domingues, I., Cardoso, A., Cardoso, M.J., Cardoso, J.S.: INbreast: toward a full-field digital mammographic database. Acad. Radiol. 19(2), 236–248 (2012)
Lee, R.S., Gimenez, F., Hoogi, A., Miyake, K.K., Gorovoy, M., Rubin, D.: A curated mammography data set for use in computer-aided detection and diagnosis research. Sci. Data 4 (2017)
Beeravolu, A.R., Azam, S., Jonkman, M., Shanmugam, B., Kannoorpatti, K., Anwar, A.: Preprocessing of breast cancer images to create datasets for deep-CNN. IEEE Access 9, 438–463 (2021)
Acknowledgments
This work is partially supported by the following Spanish grants RTI2018-094645-B-I00 and UMA18-FEDERJA-084. All of them include funds from the European Regional Development Fund (ERDF). The authors acknowledge the computer resources, technical expertise and assistance provided by the SCBI (Supercomputing and Bioinformatics) center of the University of Malaga. The authors acknowledge the funding from the Instituto de Investigación Biomédica de Málaga - IBIMA and the Universidad de Málaga.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Fuentes-Fino, R.J., Calderón-Ramírez, S., Domínguez, E., López-Rubio, E., Hernandez-Vasquez, M.A., Molina-Cabello, M.A. (2022). Feature Density as an Uncertainty Estimator Method in the Binary Classification Mammography Images Task for a Supervised Deep Learning Model. In: Rojas, I., Valenzuela, O., Rojas, F., Herrera, L.J., Ortuño, F. (eds) Bioinformatics and Biomedical Engineering. IWBBIO 2022. Lecture Notes in Computer Science(), vol 13347. Springer, Cham. https://doi.org/10.1007/978-3-031-07802-6_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-07802-6_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-07801-9
Online ISBN: 978-3-031-07802-6
eBook Packages: Computer ScienceComputer Science (R0)