1. Home
  2. Volume 03 Issue 03 March 2024
  3. March 2024

March 2024

Deep Learning Transfer Methods for Biomedical Classification of Images

Adel Al-Janabi
University of Kufa, Najaf, Iraq
DOI : https://doi.org/10.58806/ijirme.2024.v3i3n24

Abstract

Research using computers has been carried out on the effectiveness of applying deep learning transfer methods to solve the problem of identifying human brain tumors using MRI imaging. Various deep learning and fine-tuning methodologies of models have been proposed and implemented. The deep convolution networks MobileNetV2, VGG-16, Xception and ResNet-50, trained on the ImageNet image set, were used as basic models. A deep convolutional neural network 2D-CNN has also been developed and trained. A computer study of the performance indicators revealed that the fine-tuning method was effective On an enlarged data set, the Xception model outperformed other deep learning models in terms of accuracy: the clarity with which brain tumors are classified using MRI images was 94%, precision 97.7%, recall 94.01%, f1 score 96%, AUC 96.90%.

Keywords:

brain tumor, MRI images, Statistical modeling, convolution neural networks, transfer of deep learning

References:

1) Y. Li, Y. Han, Z. Li, Y. Zhong, and Z. Guo, "A transfer learning-based multimodal neural network combining metadata and multiple medical images for glaucoma type diagnosis," Scientific Reports, vol. 13, p. 12076, 2023, https://doi.org/10.1016/j.ophtha.2014.11.030.

2) G. Gulamhussene, M. Rak, O. Bashkanov, F. Joeres, J. Omari, M. Pech, et al., "Transfer-learning is a key ingredient to fast deep learning-based 4D liver MRI reconstruction," Scientific Reports, vol. 13, p. 11227, 2023, https://doi.org/10.24352/UB.OVGU-2019-093.

3) S. Asutkar and S. Tallur, "Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis," Scientific Reports, vol. 13, p. 6607, 2023, https://doi.org/10.1038/s41598-023-33887-5.

4) C. Yang, X. You, R. Yu, Y. Xu, J. Zhang, X. Fan, et al., "Semi-supervised deep transfer learning for the microstructure recognition in the high-throughput characterization of nickel-based superalloys," Materials Characterization, p. 113094, 2023, https://doi.org/10.1016/j.matchar.2023.113094.

5) A. Godlewski, M. Czajkowski, P. Mojsak, T. Pienkowski, W. Gosk, T. Lyson, et al., "A comparison of different machine-learning techniques for the selection of a panel of metabolites allowing early detection of brain tumors," Scientific Reports, vol. 13, p. 11044, 2023, https://doi.org/10.1016/j.bbcan.2022.188721.

6) U. Raghavendra, A. Gudigar, A. Paul, T. Goutham, M. A. Inamdar, A. Hegde, et al., "Brain tumor detection and screening using artificial intelligence techniques: Current trends and future perspectives," Computers in Biology and Medicine, p. 107063, 2023, https://doi.org/10.1016/j.compbiomed.2023.107063.

7) N. Farajzadeh, N. Sadeghzadeh, and M. Hashemzadeh, "Brain tumor segmentation and classification on MRI via deep hybrid representation learning," Expert Systems with Applications, vol. 224, p. 119963, 2023, https://doi.org/10.1016/j.eswa.2023.119963.

8) M. Aamir, Z. Rahman, W. A. Abro, U. A. Bhatti, Z. A. Dayo, and M. Ishfaq, "Brain tumor classification utilizing deep features derived from high-quality regions in MRI images," Biomedical Signal Processing and Control, vol. 85, p. 104988, 2023, https://doi.org/10.1016/j.bspc.2023.104988.

9) Y. Jiang, J. Sun, X. Ren, and H. Wang, "Nutritional Risk Assessment and Countermeasures for Stroke Patients Based on Deep Learning and Multimodal MRI Images," International Journal of Computational Intelligence Systems, vol. 16, p. 72, 2023, https://doi.org/10.1007/s44196-023-00258.

10) M. Potnuru and B. S. Naick, "Semantic Segmentation of MRI Images for Brain Tumour Detection with ShuffleNet-Based UNet," SN Computer Science, vol. 4, p. 445, 2023, https://doi.org/10.1007/s42979-023-01878-y.

11) P. Vakli, B. Weiss, J. Szalma, P. Barsi, I. Gyuricza, P. Kemenczky, et al., "Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics," Medical Image Analysis, vol. 88, p. 102850, 2023, https://doi.org/10.1016/j.media.2023.102850.

12) N. Aghazadeh, P. Moradi, G. Castellano, and P. Noras, "An automatic MRI brain image segmentation technique using edge–region-based level set," The Journal of Supercomputing, vol. 79, pp. 7337-7359, 2023, https://doi.org/10.1007/s11227-022-04948-9.

13) X. Cheng, S. H. Al-Khafaji, M. Hashemian, M. Ahmed, S. A. Eftekhari, A. I. Alanssari, et al., "Statistical analysis and Neural Network Modeling of functionally graded porous nanobeams vibration in an elastic medium by considering the surface effects," Engineering Applications of Artificial Intelligence, vol. 123, p. 106313, 2023, https://doi.org/10.1016/j.engappai.2023.106313.

14) N. Ramezani, "Modern statistical modeling in machine learning and big data analytics: Statistical models for continuous and categorical variables," in Research Anthology on Machine Learning Techniques, Methods, and Applications, ed: IGI Global, 2022, pp. 90-106, https://doi.org/10.4018/978-1-6684-6291-1.ch007.

15) S.-z. Li, R.-f. He, and B.-z. Pan, "Research on Statistical Characteristics Modeling of Matching Probability and Measurement Error Based on Machine Learning," International Journal of Information Systems in the Service Sector (IJISSS), vol. 14, pp. 1-13, 2022, https://doi.org/10.4018/IJISSS.290548.

16) T. Goswami and G. Sinha, "Statistical Modeling in Machine Learning: Concepts and Applications," 2022, https://doi.org/10.1016/C2021-0-01370-5.

17) B. S. Abd El-Wahab, M. E. Nasr, S. Khamis, and A. S. Ashour, "BTC-fCNN: Fast Convolution Neural Network for Multi-class Brain Tumor Classification," Health Information Science and Systems, vol. 11, p. 3, 2023, https://doi.org/10.1007/s13755-022-00203-w.

18) Y. Wang and G. Cao, "A multiscale convolution neural network for bearing fault diagnosis based on frequency division denoising under complex noise conditions," Complex & Intelligent Systems, vol. 9, pp. 4263-4285, 2023, https://doi.org/10.1007/s40747-022-00925-0.

19) C. Liu and X. Hu, "Deep neural network with deformable convolution and side window convolution for image denoising," Pattern Recognition Letters, vol. 171, pp. 92-98, 2023, https://doi.org/10.1016/j.patrec.2023.05.015.

20) J. Xie, S. Lin, Y. Zhang, and L. Luo, "Compressing convolutional neural networks with cheap convolutions and online distillation," Displays, vol. 78, p. 102428, 2023, https://doi.org/10.1016/j.displa.2023.102428.