Informatics and Applications
2021, Volume 15, Issue 4, pp 59-64
ON TRANSFER LEARNING METHODS IN BIOMEDICAL IMAGES CLASSIFICATION TASKS
- E. Yu. Shchetinin
- L. A. Sevastianov
Abstract
Computer studies of the effectiveness of deep transfer learning methods for solving the problem of human brain tumors recognition based on magtetic resonance imaging (MRI) are carried out. Various strategies of transfer learning and fine-tuning of the models are proposed and implemented. Deep convolutional networks VGG-16, ResNet-50, Xception, and MobileNetV2 were used as the baseline models, pre-trained on ImageNet. Also, a deep convolutional neural network 2D_CNN was built and trained from scratch. Computer analysis of their performance metrics showed that when using the strategy of fine-tuning models on augmented MRI-scans data set, Xception model demonstrated higher accuracy values compared to other deep learning models. For Xception model, the accuracy of classification of MRI-scans with brain tumors was 96%, precision 99.43%, recall 96.03%, f1-score 97.7%, and AUC 98.92%.
[+] References (15)
- Louis, D.N., H. Ohgaki, O. D. Wiestler, W K. Cavenee, P. C. Burger, A. Jouvet, B. W. Scheithauer, and P. Kleihues.
2007. The 2007 WHO classification of tumours of the Central Nervous System. Acta Neuropathol. 114(2):97-109.
- Bakas, S., H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Freymann, K. Farahani, and C. Davatzikos. 2017. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and ra- diomic features. Scientific Data 4:170117. 13 p.
- Gillies, R. J., P. E. Kinahan, and H. Hricak. 2015. Radiomics: Images are more than pictures, they are data. Radiology 278:563-577.
- Sebastian, Th., and L. Pratt, eds. 2012. Learning to learn. Berlin: Springer Science and Business Media. 354 p.
- Shin, H.-C., H. R. Roth, M. Gao, L. Lu, Z.Xu, I. Nogues, J. Yao, D. Mollura, and R. M. Summers. 2016. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE T. Med. Imaging 35(5):1285- 1298.
- Krizhevsky, A., I. Sutskever, and G.E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Adv. Neur In. 25:1097-1105.
- Liang, H., W Fu, and F Yi. 2019. A survey of recent advances in transfer learning. 19th Conference (International) on Communication Technology Proceedings. IEEE. 1516-1523.
- Chakrabarty, N. 2019. Brain MRI images for brain tumor detection. Available at: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection (accessed November 9, 2021).
- Sevastyanov, L. A., and E. Yu. Shchetinin. 2020. O metodakh povysheniya tochnosti v mnogoklassovoy klassifikatsii na nesbalansirovannykh dannykh [On methods of improving the accuracy of multiclass classification on unbalanced data]. Informatika i ee Primeneniya - Inform. Appl. 14(1):63-70.
- Shorten, C., and T. M. Khoshgoftaar. 2019. A survey on image data augmentation for deep learning. J. Big Data 6(1):1-48.
- Simonyan, K., and A. Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv.org. 14 p. Available at: https://arxiv.org/abs/ 1409.1556 (accessed November 9, 2021).
- He, K., X. Zhang, Sh. Ren, and J. Sun. 2016. Deep residual learning for image recognition. Conference on Computer Vision and Pattern Recognition Proceedings. IEEE. 770778.
- Szegedy, C., V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. 2016. Rethinking the inception architecture for computer vision. Conference on Computer Vision and Pattern Recognition Proceedings. IEEE. 2818-2826.
- Sandler, M., A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen. 2019. MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.org. 14 p. Available at: https://arxiv.org/abs/1801.04381 (accessed November 9, 2021).
- Chollet, F 2017. Deep learning with Python. New York, NY: Manning. 384 p.
[+] About this article
Title
ON TRANSFER LEARNING METHODS IN BIOMEDICAL IMAGES CLASSIFICATION TASKS
Journal
Informatics and Applications
2021, Volume 15, Issue 4, pp 59-64
Cover Date
2021-12-30
DOI
10.14357/19922264210408
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
MRI scans; brain tumor; deep learning transfer; convolutional neural networks
Authors
E. Yu. Shchetinin  and L. A. Sevastianov  , 
Author Affiliations
Financial University under the Government of the Russian Federation, 49 Leningradsky Prospekt, Moscow 125993, Russian Federation
Peoples' Friendship University of Russia (RUDN University), 6 Miklukho-Maklaya Str., Moscow 117198, Russian Federation
Joint Institute for Nuclear Research, 6 Joliot-Curie Str., Dubna, Moscow Region 141980, Russian Federation
|