Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations
In this text we propose a collection of enhanced quantum methods that would drastically enhance the efficiency and accuracy of biomedical image processing. There are four key methodologies that have been proposed in this work: Quantum Support Vector Machines with Enhanced Feature Extraction, Quantum...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845772/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575607041425408 |
|---|---|
| author | Lalitha Kumari Pappala Sai Babu Veesam Kannaiah Chattu Janapati Venkata Krishna Jyostna Devi Bodapati B. Tarakeswara Rao |
| author_facet | Lalitha Kumari Pappala Sai Babu Veesam Kannaiah Chattu Janapati Venkata Krishna Jyostna Devi Bodapati B. Tarakeswara Rao |
| author_sort | Lalitha Kumari Pappala |
| collection | DOAJ |
| description | In this text we propose a collection of enhanced quantum methods that would drastically enhance the efficiency and accuracy of biomedical image processing. There are four key methodologies that have been proposed in this work: Quantum Support Vector Machines with Enhanced Feature Extraction, Quantum Generative Adversarial Networks for Data Augmentation, Quantum Entanglement and Correlation Analysis for Feature Detection, and Quantum-Enhanced Image Reconstruction for Noisy Data Samples. Q-SVM-EFE is a Quantum Support Vector Machine-based framework that incorporates advanced feature extraction to map classical image data into high-dimensional quantum states, which should capture intricate patterns and therefore be more accurate for classification. This approach scored more than 95 percent in terms of classification accuracy and tenfold increased the speed of training compared to classical SVMs. QGAN-DA generates high-quality synthetic images to alleviate the scarcity of labeled medical data. It trains a generator network through quantum circuits for the generation of new samples and a discriminator network for real image and sample classification, thus ensuring high diversity and quality in synthetic data with SSIM values above 0.90. QECA-FD applies quantum entanglement in the analysis of biomedical image correlations and is therefore very effective in detecting subtle features and anomalies. This resulted in over 95% sensitivity in anomaly detection and increased the speed of the correlation analysis by five times. QIR-ND enables enhanced image reconstruction from sullied or incomplete data through quantum noise reduction and reconstruction techniques. This new approach gave a PSNR greater than 40 dB and an eightfold improvement in reconstruction delays. |
| format | Article |
| id | doaj-art-a55388b7b1af4429ba21c2449a7fdfe0 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a55388b7b1af4429ba21c2449a7fdfe02025-01-31T23:04:35ZengIEEEIEEE Access2169-35362025-01-0113204912051110.1109/ACCESS.2025.353140710845772Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based OptimizationsLalitha Kumari Pappala0https://orcid.org/0000-0003-3741-5771Sai Babu Veesam1https://orcid.org/0009-0000-5473-4681Kannaiah Chattu2Janapati Venkata Krishna3https://orcid.org/0009-0009-7360-3009Jyostna Devi Bodapati4https://orcid.org/0000-0002-5185-882XB. Tarakeswara Rao5School of Computer Science and Engineering, VIT-AP University, Amaravati, Andhra Pradesh, IndiaSchool of Computer Science and Engineering, VIT-AP University, Amaravati, Andhra Pradesh, IndiaSchool of Computer Science and Engineering, VIT-AP University, Amaravati, Andhra Pradesh, IndiaUnit Head of IoT and Robotics and AI and AR&VR Departments, Institute of Engineering and Technology, Srinivas University, Mangaluru, IndiaDepartment of Advanced Computer Science and Engineering, Vignan’s Foundation for Science, Technology and Research, Vadlamudi, Andhra Pradesh, IndiaDepartment of CSE, Kallam Haranadhareddy Institute of Technology, Guntur, Andhra Pradesh, IndiaIn this text we propose a collection of enhanced quantum methods that would drastically enhance the efficiency and accuracy of biomedical image processing. There are four key methodologies that have been proposed in this work: Quantum Support Vector Machines with Enhanced Feature Extraction, Quantum Generative Adversarial Networks for Data Augmentation, Quantum Entanglement and Correlation Analysis for Feature Detection, and Quantum-Enhanced Image Reconstruction for Noisy Data Samples. Q-SVM-EFE is a Quantum Support Vector Machine-based framework that incorporates advanced feature extraction to map classical image data into high-dimensional quantum states, which should capture intricate patterns and therefore be more accurate for classification. This approach scored more than 95 percent in terms of classification accuracy and tenfold increased the speed of training compared to classical SVMs. QGAN-DA generates high-quality synthetic images to alleviate the scarcity of labeled medical data. It trains a generator network through quantum circuits for the generation of new samples and a discriminator network for real image and sample classification, thus ensuring high diversity and quality in synthetic data with SSIM values above 0.90. QECA-FD applies quantum entanglement in the analysis of biomedical image correlations and is therefore very effective in detecting subtle features and anomalies. This resulted in over 95% sensitivity in anomaly detection and increased the speed of the correlation analysis by five times. QIR-ND enables enhanced image reconstruction from sullied or incomplete data through quantum noise reduction and reconstruction techniques. This new approach gave a PSNR greater than 40 dB and an eightfold improvement in reconstruction delays.https://ieeexplore.ieee.org/document/10845772/Biomedical imaginggenerative adversarial networksimage reconstructionquantum computingsupport vector machines |
| spellingShingle | Lalitha Kumari Pappala Sai Babu Veesam Kannaiah Chattu Janapati Venkata Krishna Jyostna Devi Bodapati B. Tarakeswara Rao Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations IEEE Access Biomedical imaging generative adversarial networks image reconstruction quantum computing support vector machines |
| title | Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations |
| title_full | Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations |
| title_fullStr | Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations |
| title_full_unstemmed | Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations |
| title_short | Design of an Iterative Model for Incremental Enhancements in Quantum Image Processing Using Reinforcement Learning-Based Optimizations |
| title_sort | design of an iterative model for incremental enhancements in quantum image processing using reinforcement learning based optimizations |
| topic | Biomedical imaging generative adversarial networks image reconstruction quantum computing support vector machines |
| url | https://ieeexplore.ieee.org/document/10845772/ |
| work_keys_str_mv | AT lalithakumaripappala designofaniterativemodelforincrementalenhancementsinquantumimageprocessingusingreinforcementlearningbasedoptimizations AT saibabuveesam designofaniterativemodelforincrementalenhancementsinquantumimageprocessingusingreinforcementlearningbasedoptimizations AT kannaiahchattu designofaniterativemodelforincrementalenhancementsinquantumimageprocessingusingreinforcementlearningbasedoptimizations AT janapativenkatakrishna designofaniterativemodelforincrementalenhancementsinquantumimageprocessingusingreinforcementlearningbasedoptimizations AT jyostnadevibodapati designofaniterativemodelforincrementalenhancementsinquantumimageprocessingusingreinforcementlearningbasedoptimizations AT btarakeswararao designofaniterativemodelforincrementalenhancementsinquantumimageprocessingusingreinforcementlearningbasedoptimizations |