Abstract
Deep learning and more specifically Convolutional Neural Network (CNN) is a cutting edge technique which has been applied to many fields including biomedical image classification. To further improve the classification performance for biomedical images, in this paper, a feature concatenation method and a feature concatenation and ensemble method are proposed to combine several CNNs with different depths and structures. Three datasets, namely 2D Hela dataset, PAP smear dataset, and Hep-2 cell image dataset, are used as benchmarks for testing the proposed methods. It is shown from experiments that the feature concatenation and ensemble method outperforms each individual CNN, and the feature concatenation method, as well as several state-of-the-art methods in terms of classification accuracy.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ambikapathy B, Krishnamurthy K (2018) Analysis of electromyograms recorded using invasive and noninvasive electrodes: a study based on entropy and Lyapunov exponents estimated using artificial neural networks. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0811-6
Ashtarian H, Mirzabeigi E, Mahmoodi E, Khezeli M (2017) Knowledge about cervical cancer and pap smear and the factors influencing the pap test screening among women. Int J Community Based Nurs Midwifery 5(2):188–195
Boland MV, Murphy RF (2001) A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells. Bioinformatics 17(12):1213–1223
Ciresan D, Giusti A, Gambardella LM, Schmidhuber J (2012) Deep neural networks segment neuronal membranes in electron microscopy images. Neural Inf Process Syst 2:2843–2851 (Lake Tahoe, Nevada, USA)
Ciresan DC, Giusti A, Gambardella LM, Schmidhuber J (2013) Mitosis detection in breast cancer histology images with deep neural networks. In: International conference on medical image computing and computer-assisted intervention. Nagoya, Japan: Springer, Berlin, Heidelberg, pp 411–418
Dietterich TG (1997) Machine learning research: four current directions. AI Mag 18(4):7–136
Duneja A, Puyalnithi T, Vankadara MV, Chilamkurti N (2018) Analysis of inter-concept dependencies in disease diagnostic cognitive maps using recurrent neural network and genetic algorithms in time series clinical data for targeted treatment. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-1116-5
Esteva A, Kuprel b, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118
Foggia P, Percannella G, Soda P, Vento M (2013) Benchmarking Hep-2 cells classification methods. IEEE Trans Med Imaging 32(10):1878–1889
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). Las Vegas, Nevada: IEEE, pp 770–778
Jantzen J, Norup J, Dounias G, Bjerregaard B (2005) PAP-smear benchmark data for pattern classification. In: 2005 Nature inspired smart information systems (NiSIS), Albufeira, Portugal
Jeon G (2017) Computational intelligence approach for medical images by suppressing noise. J Ambient Intell Humaniz Comput 1–11
Ju C, Bibaut A, van der Laan M (2018) The relative performance of ensemble methods with deep convolutional neural networks for image classification. J Appl Stat 45(15):2800–2818
Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, Glocker B et al. (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78
Kawahara J, Hamrneh G (2016) Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers. In: Machine learning in medical imaging MLMI 2016. Springer, Cham, pp 164–171
Krogh A, Vedelsby J (1995) Neural network ensembles, cross validation and active learning. In: Proceedings of the 7th international conference on neural information processing systems. MIT press, pp 231–238
Kumar A, Kim J, Lyndon D, Fulham M, Feng D (2017) An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE J Biomed Health Inform 21(1):31–40
Lin D, Sun L, Toh K-A, Zhang J, Lin Z (2018) Biomedical image classification based on a cascade of an SVM with a reject option and subspace analysis. Comput Biol Med 96:128–140
Litjens G, Kooi T, Bejnordi BE, Setio AA, Ciompi F, Ghafoorian M, Sánchez CI et al. (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Liu D, Wang S, Huang D, Deng G, Zeng F, Chen H (2016) Medical image classification using spatial adjacent histogram based on adaptive local binary patterns. Comput Biol Med 72:185–200
Nguyen LD, Lin D, Lin Z, Cao J (2018) Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation. In: 2018 IEEE International symposium on circuits and systems (ISCAS). Florence, Italy, May, 2018
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Computer vision and pattern recognition 2016. Las Vegas, Nevada, pp 2818–2826
Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: Advancement of artificial inteligence. San Francisco, California, USA
Zheng L, Zhao Y, Wang S, Wang J, Tian Q (2016) Good practice in CNN feature transfer. arXiv preprint, arXiv:1604.00133
Acknowledgements
We wish to acknowledge the funding support for this project from Nanyang Technological University under the Undergraduate Research Experience on Campus (URECA) program.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Nguyen, L.D., Gao, R., Lin, D. et al. Biomedical image classification based on a feature concatenation and ensemble of deep CNNs. J Ambient Intell Human Comput 14, 15455–15467 (2023). https://doi.org/10.1007/s12652-019-01276-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-019-01276-4