International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Noise Reduction in Low-Light Spinal Images using CNN-Based Spinal Net Approach |
|---|---|
| ABSTRACT | Spinal imaging plays a crucial role in diagnosing medical conditions such as spinal cord injuries, disc degeneration, and tumors. Techniques like MRI and CT scans provide detailed images, but achieving high quality often requires longer scanning time or higher radiation exposure. To address this, low-light or low-dose imaging methods are used, which reduce risk but introduce noise, low contrast, and loss of fine details. To overcome these challenges, this project proposes a deep learning-based approach using a Convolutional Neural Network (CNN) called SpinalNet. The model is designed to effectively remove noise while preserving important anatomical structures. It uses a gradual feature input mechanism and residual learning, allowing the network to focus on noise removal instead of reconstructing the entire image. The performance of the model is evaluated using image quality metrics such as PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). Results show significant improvement in image clarity and detail preservation. This enhances diagnostic accuracy and also helps in reducing scan time and radiation exposure, making it suitable for real-world healthcare applications. |
| AUTHOR | J.KOMALIKA, Y.KEERTHI ABHINAYA, G.PRAISE PRAVEEN, B.PAVAN SANDEEP, N.NAGARAJU U.G. Student, Department of ECE, SVIET Engineering College, Nandamuru, Pedana, Andhra Pradesh, India Assistant Professor, Department of ECE, SVIET Engineering College, Nandamuru, Pedana, Andhra Pradesh, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1403127 |
| pdf/127_Noise Reduction in Low-Light Spinal Images using CNN-Based Spinal Net Approach.pdf | |
| KEYWORDS | |
| References | 1) K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising,” IEEE Transactions on Image Processing, 2017. 2) S. Gu, L. Zhang, W. Zuo, and X. Feng, “Weighted Nuclear Norm Minimization with Application to Image Denoising,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. 3) Zamir et al., “Restormer: Efficient Transformer for High-Resolution Image Restoration,” CVPR, 2022. 4) Liang et al., “SwinIR: Image Restoration Using Swin Transformer,” IEEE International Conference on Computer Vision (ICCV), 2021. 5) Jain, “Fundamentals of Digital Image Processing,” Prentice Hall, 1989. 6) R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Pearson Education, 3rd Edition. 7) Goodfellow, Y. Bengio, and A. Courville, “Deep Learning,” MIT Press, 2016. 8) “TensorFlow Official Documentation,” Available: https://www.tensorflow.org 9) “PyTorch Official Documentation,” Available: https://pytorch.org 10) “OpenCV Documentation,” Available: https://opencv.org |
