Abstract
Multiple retinal diseases co-occur more frequently. It is extremely challenging to effectively diagnose several diseases in an image and provide appropriate treatment for those diseases with high accuracy. The performance of such an imbalanced dataset, which has minority classes, can be enhanced. The Retinal Fundus Multi-Disease Image Dataset (RFMiD) is a collection of 3200 Multi-labeled Imbalanced Dataset (MLID) marked with 46 different disease labels. The suggested Logarithmic Progressive Synthetic Minority Oversampling Technique (LP-SMOTE) is intended to oversample the minority classes in imbalanced dataset. The Imbalance Ratio Per Label (IRPL) and Mean Imbalance Ratio (MeanIR) are used and assessed to distinguish the minority and majority classes. The logarithmic progressive sampling per label is applied to minority classes. The Oversampling is implemented to level up the samples in minority classes. The proposed technique improved the overall minority class samples by 5.4 times. After employing LP-SMOTE technique, the overall validation accuracy and test accuracy is improved by 2.81% and 4.53% respectively on VGG19 pre-trained model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
World Health Organization, 14 October 2021. https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment. Accessed 22 Mar 2022
Vision Loss Expert Group of the Global Burden of Disease Study: Causes of blindness and vision impairment in 2020 and trends over 30 years: evaluating the prevalence of avoidable blindness in relation to “VISION 2020: the Right to Sight”. Lancet Glob. Health (2020). https://doi.org/10.1016/S2214-109X(20)30489-7
WHO Publishes SEAsia-Specific DR Guidelines - The International Agency for the Prevention of Blindness. https://www.iapb.org/news/who-publishes-seasia-specific-dr-guidelines. Accessed 05 Mar 2022
World report on vision, World Health Organization (2019). https://cdn.who.int/media/docs/default-source/infographics-pdf/world-vision-infographic-final.pdf?sfvrsn=85b7bcde_2. Accessed 22 Mar 2022
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002). https://doi.org/10.1613/jair.953
Xu, Y., Noy, A., Lin, M., Qian, Q., Li, H., Jin, R.: WeMix: how to better utilize data augmentation. arXiv (2020). https://doi.org/10.48550/arxiv.2010.01267
Rodriguez, M.A., AlMarzouqi, H., Liatsis, P.: Multi-label retinal disease classification using transformers. arXiv (2022). https://doi.org/10.48550/arXiv.2207.02335
Rodriguez, M., AlMarzouqi, H., Liatsis, P.: Multi-label retinal disease (MuReD) dataset. IEEE DataPort (2022). https://doi.org/10.21227/7fx7-8q47
Pereira, R.M., Costa, Y.M.G., Silla, C.N., Jr.: MLTL: a multi-label approach for the Tomek Link undersampling algorithm. Neurocomputing 383, 95–105 (2020). https://doi.org/10.1016/j.neucom.2019.11.076
Charte, F., Rivera, A.J., del Jesus, M.J., Herrera, F.: MLSMOTE: approaching imbalanced multilabel learning through synthetic instance generation. Knowl.-Based Syst. 89, 385–397 (2015). https://doi.org/10.1016/j.knosys.2015.07.019
Dablain, D., Krawczyk, B., Chawla, N.V.: DeepSMOTE: fusing deep learning and SMOTE for imbalanced data. IEEE Trans. Neural Netw. Learn. Syst. 1–15 (2022). https://doi.org/10.1109/TNNLS.2021.3136503
Müller, D., Soto-Rey, I., Kramer, F.: Multi-disease detection in retinal imaging based on ensembling heterogeneous deep learning models, March 2021. arXiv:2103.14660. https://doi.org/10.48550/arXiv.2103.14660
Pachade, S., et al.: Retinal fundus multi-disease image dataset (RFMiD): a dataset for multi-disease detection research. Data 62 (2021). https://doi.org/10.3390/data6020014
Castellanos, F.J., Valero-Mas, J.J., Calvo-Zaragoza, J., Rico-Juan, J.R.: Oversampling imbalanced data in the string space. Pattern Recogn. Lett. (2018). https://doi.org/10.1016/j.patrec.2018.01.003
Liu, X.Y., Wu, J., Zhou, Z.H.: Exploratory undersampling for class-imbalance learning. IEEE Trans. Syst. Part B Cybern. (2009). https://doi.org/10.1109/TSMCB.2008.2007853
Charte, F., Rivera, A., del Jesus, M.J., Herrera, F.: A first approach to deal with imbalance in multi-label datasets. In: Pan, J.-S., Polycarpou, M.M., Woźniak, M., de Carvalho, A.C.P.L.F., Quintián, H., Corchado, E. (eds.) HAIS 2013. LNCS (LNAI), vol. 8073, pp. 150–160. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40846-5_16
Charte, F., Rivera, A.J., del Jesus, M.J., Herrera, F.: Addressing imbalance in multilabel classification: measures and random resampling algorithms. Neurocomputing 163, 3–16 (2015). https://doi.org/10.1016/j.neucom.2014.08.091
Tarekegn, A.N., Giacobini, M., Michalak, K.: A review of methods for imbalanced multi-label classification. Pattern Recogn. 118 (2021). https://doi.org/10.1016/j.patcog.2021.107965
Bernardo, A., Della Valle, E.: An extensive study of C-SMOTE, a continuous synthetic minority oversampling technique for evolving data streams. Expert Syst. Appl. 196, 116630 (2022)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv (2020). https://doi.org/10.48550/arxiv.2004.10934
Acknowledgements
We extend out thanks Technical Education Quality Improvement Program (TEQIP), the World Bank project, for providing a state of the art Center of Excellence in Signal and Image Processing research lab. Also, we thank the authors of “Retinal Fundus Multi-Disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research” for making their dataset RFMiD publicly available.
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
Panchal, S., Kokare, M. (2023). Logarithmic Progressive-SMOTE: Oversampling Minorities in Retinal Fundus Multi-disease Image Dataset. In: Gupta, D., Bhurchandi, K., Murala, S., Raman, B., Kumar, S. (eds) Computer Vision and Image Processing. CVIP 2022. Communications in Computer and Information Science, vol 1776. Springer, Cham. https://doi.org/10.1007/978-3-031-31407-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-31407-0_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31406-3
Online ISBN: 978-3-031-31407-0
eBook Packages: Computer ScienceComputer Science (R0)