Related Experiment Video
Updated: Oct 1, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.0K
Optimal Medical Image Size Reduction Model Creation Using Recurrent Neural Network and GenPSOWVQ
Chethana Sridhar1, Piyush Kumar Pareek2, R Kalidoss3
1Department of Computer Applications, Sivananda Sarma Memorial R.V. College, Bangalore, Karnataka, India.
Journal of Healthcare Engineering
|March 8, 2022
Summary
This study introduces GenPSOWVQ, a novel medical image compression method. It achieves precise compression and maintains image accuracy with reduced computational costs, outperforming existing techniques.
Area of Science:
- Medical imaging
- Image processing
- Artificial intelligence
Background:
- Medical diagnosis relies on accurate imaging, but large data sizes pose storage and transmission challenges.
- Current automation systems aim to improve efficiency, yet image compression balancing accuracy and cost remains a key issue.
- Optimizing medical imaging requires reducing inconsistencies and enhancing compression strategies.
Purpose of the Study:
- To introduce a novel image compression scheme, GenPSOWVQ, for clinical images.
- To develop a method that achieves precise compression while preserving image accuracy and reducing computational expenses.
- To evaluate the performance of the proposed method against existing techniques using standard metrics.
Main Methods:
- The GenPSOWVQ method utilizes a recurrent neural network integrated with wavelet vector quantization (VQ).
- A codebook for the VQ process is constructed using a hybrid approach combining fragment-based techniques and genetic algorithms.
- The model was tested on real-time medical imaging data.
Main Results:
- The GenPSOWVQ method demonstrated superior performance in maintaining image quality, evidenced by higher Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values at given compression ratios.
- The proposed method achieved lower Mean Squared Error (MSE) and Signal-to-Noise Ratio (SNR) compared to existing methods for equivalent compression levels.
- Experimental results confirmed the effectiveness of GenPSOWVQ in precise compression with reduced computational load.
Conclusions:
- The GenPSOWVQ method offers an effective solution for compressing clinical images, balancing compression rates with high fidelity.
- This approach significantly reduces computational costs associated with medical image processing and storage.
- GenPSOWVQ represents an advancement in automated medical imaging, improving efficiency and accuracy in diagnostic workflows.
