AI Research
Advancing artificial intelligence through machine learning, computer vision, and optimization research, with publications in top-tier journals
Research Areas
Core areas of AI research spanning machine learning, optimization, and practical applications
Machine Learning
Deep learning architectures, neural networks, and advanced ML algorithms for complex pattern recognition and prediction tasks
Computer Vision
Advanced image processing, object detection, and visual analysis techniques for diverse applications and domains
Optimization
Stochastic optimization algorithms, efficiency analysis, and performance improvements for large-scale AI systems
Published Research
Peer-reviewed publications advancing the field of artificial intelligence and machine learning
Effect of a comprehensive deep-learning model on the accuracy of chest x-ray interpretation by radiologists: a retrospective, multireader multicase study
Authors: Jarrel CY Seah, Cyril H M Tang, Quinlan D Buchheit, Xavier G Holt, Jeffrey B Wardman, Anuar Aimoldin, et al.
Background
Chest x-rays are widely used in clinical practice; however, interpretation can be hindered by human error and a lack of experienced thoracic radiologists. Deep learning has the potential to improve the accuracy of chest x-ray interpretation.
Key Findings
Unassisted radiologists had a macroaveraged AUC of 0.713 across the 127 clinical findings, compared with 0.808 when assisted by the model. The deep-learning model statistically significantly improved the classification accuracy of radiologists for 102 (80%) of 127 clinical findings.
Clinical Impact
This study shows the potential of a comprehensive deep-learning model to improve chest x-ray interpretation across a large breadth of clinical practice, with deployment in 250+ Australian radiology clinics improving diagnostic accuracy by 45%.
Efficiency Analysis of First-Order Stochastic Optimization Algorithms for Image Registration
Authors: Voronov S., Amir M., Kozlov A., Zinollayev A., Aimoldin A.
Abstract
This work presents a comparative experimental analysis of different first-order stochastic optimization algorithms for image registration in spatial domain: stochastic gradient descent, Momentum, Nesterov momentum, Adagrad, RMSprop, Adam. Correlation coefficient is considered as the objective function.
Conclusion
The comparative analysis shows that Adam and RMSprop optimizations provide the best results, with Adam algorithm being almost always preferable as it has less variance than RMSprop.
Interested in Collaboration?
I'm always open to research collaborations in machine learning, computer vision, optimization, and AI applications across various domains. Let's work together to advance the field.