Comparative Analysis of Denoising Methods to Improve Image Quality for Medical Visual Question Answering

##plugins.themes.academic_pro.article.sidebar##

Published Dec 17, 2024
https://doi.org/10.47164/ijngc.v15i3.1773
Download
Requires Subscription PDF
Statistic

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...
Volume 15, Issue 3, November 2024

##plugins.themes.academic_pro.article.main##

Rikita D. Parekh
Information Technology, Gujarat Technological University, Ahmedabad, India
Hiteishi M. Diwanji
Information Technology Department, L.D.College of Enggineering, Ahmedabad, India

Abstract

Medical Visual Question Answering (MedVQA) is a dual research field that intersects medical imaging and natural language processing, for better interpretability and accessibility of medical image data.Medical image quality is paramount for accurate diagnostics and subsequent medical visual question answering (MedVQA) tasks. This research focuses on applying and then analyzing results of different denoising methods on VQA-RAD, Medical VQA dataset to enhance quality of images. This study explores effectiveness of different traditional and deep learning based methods to reduce noise within medical images, thereby improving the accuracy and reliability of MedVQA task. We applied different traditional denoising filtering methods such as, gaussian filter, median filter, average filter, bilateral filter and convolutional autoencoder (CAE) based on deep learning on a VQA-RAD dataset to compare effectiveness of each denoising methods to improve image quality. Through comprehensive experiments and evaluations, this paper demonstrates that the convolutional autoencoder is potentially enhancing quality of medical images with an emphasis on preserving essential diagnostic information while suppressing unwanted noise with compare to other traditional denoising filters. The denoised images are then employed as input to improve accuracy for MedVQA tasks. The results of this research will help in optimizing medical imaging pipelines, ultimately benefiting clinical decision-making and healthcare outcomes.

##plugins.themes.academic_pro.article.details##

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite
Parekh, R. D., & Diwanji, H. M. (2024). Comparative Analysis of Denoising Methods to Improve Image Quality for Medical Visual Question Answering. International Journal of Next-Generation Computing, 15(3). https://doi.org/10.47164/ijngc.v15i3.1773
Crossref
Scopus
Google Scholar
Europe PMC

References

  1. Ahmed, H., Zhang, Q., Donnan, R., and Alomainy, A. 2024. Denoising of optical coherence tomography images in ophthalmology using deep learning: A systematic review. Journal of Imaging 10, 4, 86. DOI: https://doi.org/10.3390/jimaging10040086
  2. Arshaghi, A., Ashourian, M., and Ghabeli, L. 2021. Denoising medical images using machine learning, deep learning approaches: a survey. Current Medical Imaging 17, 5, 578–594. DOI: https://doi.org/10.2174/1573405616666201118122908
  3. Baccarelli, E., Scarpiniti, M., and Momenzadeh, A. 2023. Twinned residual auto-encoder (trae)—a new dl architecture for denoising super-resolution and task-aware feature learning from covid-19 ct images. Expert Systems with Applications 225, 120104. DOI: https://doi.org/10.1016/j.eswa.2023.120104
  4. Bazi, Y., Rahhal, M. M. A., Bashmal, L., and Zuair, M. 2023. Vision–language model for visual question answering in medical imagery. Bioengineering 10, 3, 380. DOI: https://doi.org/10.3390/bioengineering10030380
  5. Chen, M., Shi, X., Zhang, Y., Wu, D., and Guizani, M. 2017. Deep feature learning for medical image analysis with convolutional autoencoder neural network. IEEE Transactions on Big Data 7, 4, 750–758. DOI: https://doi.org/10.1109/TBDATA.2017.2717439
  6. Chiang, H.-T., Hsieh, Y.-Y., Fu, S.-W., Hung, K.-H., Tsao, Y., and Chien, S.-Y. 2019. Noise reduction in ecg signals using fully convolutional denoising autoencoders. Ieee Access 7, 60806–60813. DOI: https://doi.org/10.1109/ACCESS.2019.2912036
  7. El-Shafai, W., El-Nabi, S. A., El-Rabaie, E.-S. M., Ali, A. M., Soliman, N. F., Algarni, A. D., El-Samie, A., and Fathi, E. 2022. Efficient deep-learning-based autoencoder denoising approach for medical image diagnosis. Computers, Materials & Continua 70, 3. DOI: https://doi.org/10.32604/cmc.2022.020698
  8. Gaidamavicius, D. and Ie ˇ ˇsmantas, T. 2022. Deep learning method for visual question answering in the digital radiology domain. Mathematical Models in Engineering 8, 2, 58–71. DOI: https://doi.org/10.21595/mme.2022.22737
  9. Gondara, L. 2016. Medical image denoising using convolutional denoising autoencoders. In 2016 IEEE 16th international conference on data mining workshops (ICDMW). IEEE, 241–246. DOI: https://doi.org/10.1109/ICDMW.2016.0041
  10. Goyal, B., Agrawal, S., and Sohi, B. 2018. Noise issues prevailing in various types of medical images. Biomedical & Pharmacology Journal 11, 3, 1227. DOI: https://doi.org/10.13005/bpj/1484
  11. Huang, Z., Zhang, J., Zhang, Y., and Shan, H. 2021. Du-gan: Generative adversarial networks with dual-domain u-net-based discriminators for low-dose ct denoising. IEEE Transactions on Instrumentation and Measurement 71, 1–12. DOI: https://doi.org/10.1109/TIM.2021.3128703
  12. Kaur, A. and Dong, G. 2023. A complete review on image denoising techniques for medical images. Neural Processing Letters 55, 6, 7807–7850. DOI: https://doi.org/10.1007/s11063-023-11286-1
  13. Kumar, N. and Nachamai, M. 2017. Noise removal and filtering techniques used in medical images. Orient. J. Comput. Sci. Technol 10, 1, 103–113. DOI: https://doi.org/10.13005/ojcst/10.01.14
  14. Lau, J. J., Gayen, S., Ben Abacha, A., and Demner-Fushman, D. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5, 1, 1–10. DOI: https://doi.org/10.1038/sdata.2018.251
  15. Lin, H., Liu, R., and Liu, Z. 2023. Ecg signal denoising method based on disentangled autoencoder. Electronics 12, 7, 1606. DOI: https://doi.org/10.3390/electronics12071606
  16. Liu, H. 2023. Oct image denoising based on bayesian non-local mean filter and deep learning network. In International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023). Vol. 12707. SPIE, 100–109. DOI: https://doi.org/10.1117/12.2681319
  17. Nazir, N., Sarwar, A., and Saini, B. S. 2024. Recent developments in denoising medical images using deep learning: an overview of models, techniques, and challenges. Micron, 103615. DOI: https://doi.org/10.1016/j.micron.2024.103615
  18. Wang, Z., Liu, J., Li, G., and Han, H. 2022. Blind2unblind: Self-supervised image denoising with visible blind spots. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2027–2036. DOI: https://doi.org/10.1109/CVPR52688.2022.00207
  19. Yang, C., Ye, J., Wang, Y., and Song, C. 2022. X-ray breast images denoising method based on the convolutional autoencoder. Mathematical Problems in Engineering 2022, 1, 2362851. DOI: https://doi.org/10.1155/2022/2362851
  20. Yaroshchak, S., Smaida, M., and El Barg, Y. 2021. Medical image enhancement based on convolutional denoising autoencoders and gmd model. In MoMLeT+ DS. 96–106.
  21. Zhang, Y., Li, D., Law, K. L., Wang, X., Qin, H., and Li, H. 2022. Idr: Self-supervised image denoising via iterative data refinement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2098–2107. DOI: https://doi.org/10.1109/CVPR52688.2022.00214