Performance Evaluation of the U-Net Model for Medical Image Segmentation Using Dice Coefficient, IOU, and Loss Metrics
DOI:
https://doi.org/10.17720/5jwcb838Keywords:
U-net architecture, , Lungs Segmentation, Medical image segmentation, Intersection over Union (IOU), Dice Coefficient, COVID-19 pneumonia diagnosisAbstract
The U-Net model for lung area segmentation in medical images is considered in this work. A preprocessed and enhanced dataset was used to train the U-Net model across 70 epochs using an encoder-decoder architecture with skip connections. To estimate the accuracy of the model, important performance indicators such as the Dice coefficient, Intersection over Union (IOU), and training/validation loss were observed. The coefficient for the dice went up from 0.5 to 0.9 in the results, while the IOU value calmed at 0.9, representing the model’s efficiency in proper segmentation. Strong generalization to previously unseen data and minimal overfitting were shown by the loss metrics’ in accordance reduction. In agreement to the study, U-Net has the potential to be used in real-world medical applications. Further study is recommended to enhance performance through the application of transfer learning and consideration devices.
Downloads
References
Shen, D.; Wu, G.; Suk, H.-I. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng.2017, 19, 221–248.
Razzak, M. I.; Naz, S.; Zaib, A. Deep learning for medical image processing: Overview, challenges, and the future. Classif. BioApps 2018, 4, 323–350.
Litjens, G.; et al. A survey on deep learning in medical image analysis. Med. Image Anal.2017, 42, 60–88.
Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional networks for biomedical image segmentation. Med. Image Comput. Comput.-Assist. Interv.2015,234, 234–241.
Çiçek, Ö.; et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. Med. Image Comput. Comput.-Assist. Interv.2016, 9901,424–432.
Hofmanninger, J.; et al. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur. Radiol. Exp.2020, 4, 50.
Zhou, Z.; Rahman Siddiquee, M. M.; Tajbakhsh, N.; Liang, J. UNet++: A nested U-Net architecture for medical image segmentation. Deep Learning Med. Image Anal. Multimodal Learn. Clin. Decis. Support 2020, 3–11.
Kumar, A.; et al. Lung segmentation in chest radiographs using deep learning methods: A survey. J. Med. Imaging Health Inform.2020, 10, 12–20.
Taha, A. A.; Hanbury, A. Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Med. Imaging2015, 15, 29.
Rahman, M. A.; Wang, Y. Optimizing intersection-over-union in deep neural networks for image segmentation. Int. Symp. Vis. Comput.2016, 2, 234–244.
Ghosal, A.; et al. A survey of the performance evaluation metrics for medical image segmentation. J. Imaging 2020, 6, 37.
Zhang, Y.; et al. A review on metrics for evaluating deep learning models in medical image segmentation. Comput. Biol. Med.2019, 106, 198–209.
Chang, J.; et al. Loss functions for medical image segmentation: A review. Comput. Methods Programs Biomed. 2020,198, 105757.
Isensee, F.; et al. NiftyNet: a deep learning platform for medical imaging. computer Methods and Programs in Bio-medicine 2018, 158, 99–105.
Alshahrani, A.; et al. The importance of data augmentation for medical imaging. J. Med. Imaging Health In-form.2019, 9, 1234–1242.
Kofler, J.; et al. Early stopping in deep learning for medical image analysis: The effectiveness of different strategies. BMC Med. Imaging 2020, 20, 1–12.
Ahsan, M. F.; et al. Deep learning for automated lung segmentation in chest X-rays: A systematic review. J. Biomed. Inform.2021, 118, 103769.
Mazurowski, M. A.; et al. Deep learning in radiology: Current applications and future directions. Radiology
Ahsan, M. F.; et al. Deep learning for automated lung segmentation in chest X-rays: A systematic review. J. Biomed. Inform.2021, 118, 103769.
Mazurowski, M. A.; et al. Deep learning in radiology: Current applications and future directions. Radiology 2019, 293, 210–216.
Ghosal, A.; et al. A survey of the performance evaluation metrics for medical image segmentation. J. Imaging 2020, 6, 37.
Zhang, Y.; et al. A review on metrics for evaluating deep learning models in medical image segmentation. Comput. Biol. Med.2019, 106, 198–209.
Chang, J.; et al. Loss functions for medical image segmentation: A review. *Comput. Methods Programs Biomed. 2020, 198, 105757.
Isensee, F.; et al. NiftyNet: a deep learning platform for medical imaging. *Comput. Methods Biomed. Eng.2018, 158, 99–105.
Alshahrani, A.; et al. The importance of data augmentation for medical imaging. J. Med. Imaging Health Inform. 2019, 9, 1234–1242
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Author
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
