Novel Architecture of RPA In Oral Cancer Lesion Detection

arXiv cs.CV / 3/12/2026

📰 NewsDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

The study evaluates two RPA approaches, OC-RPAv1 and OC-RPAv2, on a test set of 31 oral cancer lesion images.
OC-RPAv1 averages 0.29 seconds per prediction, while OC-RPAv2 uses a Singleton design pattern with batch processing to achieve 0.06 seconds per image.
This 60-100x efficiency improvement over standard RPA methods demonstrates how design patterns and batching can enhance scalability and reduce costs in medical image analysis.
The findings highlight the significant impact of architectural choices on the performance of RPA-based lesion detection pipelines.

Abstract

Accurate and early detection of oral cancer lesions is crucial for effective diagnosis and treatment. This study evaluates two RPA implementations, OC-RPAv1 and OC-RPAv2, using a test set of 31 images. OC-RPAv1 processes one image per prediction in an average of 0.29 seconds, while OCRPAv2 employs a Singleton design pattern and batch processing, reducing prediction time to just 0.06 seconds per image. This represents a 60-100x efficiency improvement over standard RPA methods, showcasing that design patterns and batch processing can enhance scalability and reduce costs in oral cancer detection