Segmentation Performance Analysis of Transfer Learning Models on X-Ray Pneumonia Images
DOI:
https://doi.org/10.62411/faith.2024-10Keywords:
Deep Learning, DeepLabV3, Pneumonia Segmentation, SegNet, U-NetAbstract
Segmentation of pneumonia areas on chest X-rays is essential to improve the accuracy of recognition tasks and subsequent diagnosis. The capabilities of deep learning techniques, U-Net, SegNet, and DeepLabV3, are assessed to achieve these purposes. Using transfer learning, these models were adapted to pneumonia-specific datasets. The evaluation focuses on Intersection over Union (IoU) and accuracy metrics. Results show that DeepLabV3 outperforms U-Net and SegNet, achieving 84.4% accuracy and 81% IoU. U-Net achieves 80.3% accuracy and 68% IoU, while SegNet achieves 81.0% accuracy and 70% IoU. These findings highlight the potential of transfer learning models to automate the segmentation of pneumonia-affected regions, thereby facilitating timely and accurate medical intervention.
Downloads
References
E. Sogancioglu, K. Murphy, E. Calli, E. T. Scholten, S. Schalekamp, and B. Van Ginneken, “Cardiomegaly Detection on Chest Radiographs: Segmentation Versus Classification,” IEEE Access, vol. 8, pp. 94631–94642, 2020, doi: 10.1109/ACCESS.2020.2995567.
T. Agrawal and P. Choudhary, “Segmentation and classification on chest radiography: a systematic survey,” Vis. Comput., vol. 39, no. 3, pp. 875–913, Mar. 2023, doi: 10.1007/s00371-021-02352-7.
P. A. Shamna and A. T. Nair, “Detection of COVID-19 Using Segmented Chest X-ray,” in Intelligent Data Communication Technologies and Internet of Things, 2022, pp. 585–598. doi: 10.1007/978-981-16-7610-9_43.
T. Peng, Y. Gu, and J. Wang, “Lung contour detection in Chest X-ray images using Mask Region-based Convolutional Neural Network and Adaptive Closed Polyline Searching Method,” in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Nov. 2021, pp. 2839–2842. doi: 10.1109/EMBC46164.2021.9630012.
L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking Atrous Convolution for Semantic Image Segmentation.” Jun. 17, 2017. [Online]. Available: http://arxiv.org/abs/1706.05587
V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” arXiv. arXiv, Nov. 02, 2015. [Online]. Available: http://arxiv.org/abs/1511.00561
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 2015, pp. 234–241. doi: 10.1007/978-3-319-24574-4_28.
R. T. Wahyuningrum, I. Yunita, I. A. Siradjuddin, B. D. Satoto, A. K. Sari, and A. D. Sensusiati, “Improvement of chest X-ray image segmentation accuracy based on FCA-Net,” Cogent Eng., vol. 10, no. 1, Dec. 2023, doi: 10.1080/23311916.2023.2229571.
M. S. Al Reshan et al., “Detection of Pneumonia from Chest X-ray Images Utilizing MobileNet Model,” Healthcare, vol. 11, no. 11, p. 1561, May 2023, doi: 10.3390/healthcare11111561.
M. F. Rahman et al., “Improving lung region segmentation accuracy in chest X-ray images using a two-model deep learning ensemble approach,” J. Vis. Commun. Image Represent., vol. 85, p. 103521, May 2022, doi: 10.1016/j.jvcir.2022.103521.
A. Singh et al., “Deep LF-Net: Semantic lung segmentation from Indian chest radiographs including severely unhealthy images,” Biomed. Signal Process. Control, vol. 68, p. 102666, Jul. 2021, doi: 10.1016/j.bspc.2021.102666.
A. Victor Ikechukwu, S. Murali, R. Deepu, and R. C. Shivamurthy, “ResNet-50 vs VGG-19 vs training from scratch: A comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images,” Glob. Transitions Proc., vol. 2, no. 2, pp. 375–381, Nov. 2021, doi: 10.1016/j.gltp.2021.08.027.
W. Liu, J. Luo, Y. Yang, W. Wang, J. Deng, and L. Yu, “Automatic lung segmentation in chest X-ray images using improved U-Net,” Sci. Rep., vol. 12, no. 1, p. 8649, May 2022, doi: 10.1038/s41598-022-12743-y.
F. Cao and H. Zhao, “Automatic Lung Segmentation Algorithm on Chest X-ray Images Based on Fusion Variational Auto-Encoder and Three-Terminal Attention Mechanism,” Symmetry (Basel)., vol. 13, no. 5, p. 814, May 2021, doi: 10.3390/sym13050814.
S. A. J. Naqvi, A. Tauqeer, R. Bhatti, and S. B. Ali, “Improved lung segmentation based on U-Net architecture and morphological operations.” Oct. 19, 2022. [Online]. Available: http://arxiv.org/abs/2210.10545
M. S. De Silva, B. N. Narayanan, and R. C. Hardie, “A Patient-Specific Algorithm for Lung Segmentation in Chest Radiographs,” AI, vol. 3, no. 4, pp. 931–947, Nov. 2022, doi: 10.3390/ai3040055.
M. Y. Kamil and S. A. Hashem, “Segmentation of Chest X-Ray Images Using U-Net Model,” MENDEL, vol. 28, no. 2, pp. 49–53, Dec. 2022, doi: 10.13164/mendel.2022.2.049.
E. Çallı, E. Sogancioglu, B. van Ginneken, K. G. van Leeuwen, and K. Murphy, “Deep learning for chest X-ray analysis: A survey,” Med. Image Anal., vol. 72, p. 102125, Aug. 2021, doi: 10.1016/j.media.2021.102125.
Y.-G. Kim et al., “Deep Learning-Based Four-Region Lung Segmentation in Chest Radiography for COVID-19 Diagnosis,” Diagnostics, vol. 12, no. 1, p. 101, Jan. 2022, doi: 10.3390/diagnostics12010101.
V. Singh, “DeepLabv3 & DeepLabv3+ The Ultimate PyTorch Guide,” learnopencv.com, 2022. https://learnopencv.com/deeplabv3-ultimate-guide/ (accessed Apr. 05, 2024).
P. Mooney, “Chest X-Ray Images (Pneumonia),” Kaggle.com, 2018. https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
D. S. Kermany et al., “Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning,” Cell, vol. 172, no. 5, pp. 1122-1131.e9, Feb. 2018, doi: 10.1016/j.cell.2018.02.010.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Kyi Pyar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
