Abstract
The role of deep learning is predominant in classifying medical images. Histopathological image classification involves classifying tumor and cancer tissue subtypes, but it has many challenges like complexity of image, labeled data availability. Overcoming these challenges and accurately classifying the images require better approach than traditional one. In this work, we use fine-tuning-based deep neural network in classifying the histopathological image into eight different classes. The obtained results are compared with different other CNN and machine learning models. In addition, we trained a model using early stopping function which monitors the validation accuracy during training and prevents overfit, which makes the model work trained efficiently. This approach is tested on colorectal cancer histology image dataset which contains 5000 labeled images belonging to eight different classes. In our result, fine-tuning with early stopping performed better than other methods with accuracy of 91.2%.
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
https://www.cnbc.com/2018/02/22/medical-errors-third-leading-cause-of-death-in-america.html
Key Statistics for Colorectal Cancer, https://www.cancer.org/cancer/colon-rectal-cancer/about/key-statistics.html
M. Ganz et al., Automatic segmentation of polyps in colonoscopic narrow-band imaging data. IEEE Trans. Biomed. Eng. 59(8), 2144–2151(2012). (440,000 death)
How Telemedicine Answers Global Pathology Demands, 2018, https://proscia.com/blog/2015/07/14/global-crisis-digitalsolution
https://www.expresshealthcare.in/lab-diagnostics/illegal-path-labs-indias-open-secret/413141/
H. Mittal et al., Classification of Histopathological Images Through Bag-of-Visual-Words and Gravitational Search Algorithm, LNSCPS (Springer, 2019), p. 231–241.
S. Pang et al., A novel fused convolutional neural network for biomedical image classification. Med. Biol. Eng. Comput. 57(1), 107–121 (2018)
Y. Zhang et al., Breast cancer diagnosis from biopsy images with highly reliable random subspace classifier ensembles. Springer MVA 24, 1405–1420 (2013)
H. Asri et al., Using machine learning algorithms for breast cancer risk prediction and diagnosis. Elsevier PCS 83, 1064–1069 (2016)
V. Rachapudi et al., Improved Convolutional Neural Network Based Histopathological Image Classification (Springer E.I. 2020).
Kermany et al., Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122–1131 (2018).
R. Pal et al., Enhanced bag of features using alexnet and improved biogeography-based optimization for histopathological image analysis, in Proceedings of IC3 (IEEE, 2018), p 1–6.
Neural Network Early Stopping, https://chrisalbon.com/deep_learning/keras/neural_network_early_stopping/
Yao et al., On early stopping in gradient descent learning. Constr. Approx. 26(2), 289–315 (2007).
Fine-tuning convolutional neural network on own data using keras tensorflow https://cv-tricks.com/keras/fine-tuning-tensorflow/
J.N. Kather et al., Multi-class texture analysis in colorectal cancer histology. Sci. Rep. 6, 27988 (2016)
Dropout Neural Network Layer In Keras Explained https://towardsdatascience.com/machine-learning-part-20-dropout-keras-layers-explained-8c9f6dc4c9ab
Further going on CNN, https://classroom.udacity.com/courses/ud187/lessons/1771027d-8685-496f-8891-d7786efb71e1/concepts/db0b93a6-402d-4f13-8869-cf5fc1fe89ad
J.D.J. Deng et al., ImageNet: a large-scale hierarchical image database, in Proceedings of IEEE ICCVPR, 2009, p. 2–9.
Transfer learning, https://classroom.udacity.com/courses/ud187/lessons/a915f824-ce4a-4f5e-9897-a78ccbff313d/concepts/7fd8f8d5-979a-44ac-8ead-6c19a359f767
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Vidyun, A.S., Srinivasa Rao, B., Harikiran, J. (2021). Histopathological Image Classification Using Deep Neural Networks with Fine-Tuning. In: Bhateja, V., Satapathy, S.C., Travieso-González, C.M., Aradhya, V.N.M. (eds) Data Engineering and Intelligent Computing. Advances in Intelligent Systems and Computing, vol 1407. Springer, Singapore. https://doi.org/10.1007/978-981-16-0171-2_17
Download citation
DOI: https://doi.org/10.1007/978-981-16-0171-2_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0170-5
Online ISBN: 978-981-16-0171-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)