Designing a Convolutional Neural Network for High-Accuracy Oral Cavity Squamous Cell Carcinoma (OCSCC) Detection

2025-10-17

AI Summary

Oral squamous cell carcinoma (OSCC) exhibits low early detection rates and high mortality due to its nonspecific initial symptoms and deep anatomical location. Method: This paper proposes a high-accuracy, hardware–algorithm co-designed framework for early OSCC detection. It introduces an integrated convolutional neural network (CNN), coupled with a dedicated image enhancement hardware system. The study systematically quantifies the impact of image resolution on detection performance and incorporates an RGB kernel matrix optimization technique to enhance feature discriminability. Contribution/Results: We first empirically reveal the marginal diminishing returns in OSCC detection accuracy with increasing image resolution—a previously unreported phenomenon—and achieve end-to-end hardware–software co-optimization. Evaluated on a multi-resolution benchmark dataset, the proposed model achieves state-of-the-art (SOTA) performance in precision, recall, and mean average precision (mAP). These results demonstrate the framework’s feasibility and practicality for improving screening efficacy in primary-care settings and enabling clinical deployment.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Search and Optimization: Algorithm Configuration
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Oral Cavity Squamous Cell Carcinoma (OCSCC) is the most common type of head and neck cancer. Due to the subtle nature of its early stages, deep and hidden areas of development, and slow growth, OCSCC often goes undetected, leading to preventable deaths. However, properly trained Convolutional Neural Networks (CNNs), with their precise image segmentation techniques and ability to apply kernel matrices to modify the RGB values of images for accurate image pattern recognition, would be an effective means for early detection of OCSCC. Pairing this neural network with image capturing and processing hardware would allow increased efficacy in OCSCC detection. The aim of our project is to develop a Convolutional Neural Network trained to recognize OCSCC, as well as to design a physical hardware system to capture and process detailed images, in order to determine the image quality required for accurate predictions. A CNN was trained on 4293 training images consisting of benign and malignant tumors, as well as negative samples, and was evaluated for its precision, recall, and Mean Average Precision (mAP) in its predictions of OCSCC. A testing dataset of randomly assorted images of cancerous, non-cancerous, and negative images was chosen, and each image was altered to represent 5 common resolutions. This test data set was thoroughly analyzed by the CNN and predictions were scored on the basis of accuracy. The designed enhancement hardware was used to capture detailed images, and its impact was scored. An application was developed to facilitate the testing process and bring open access to the CNN. Images of increasing resolution resulted in higher-accuracy predictions on a logarithmic scale, demonstrating the diminishing returns of higher pixel counts.

Problem

• Developing a CNN for high-accuracy oral cancer detection from medical images
• Designing hardware system to capture detailed images for reliable diagnosis
• Determining optimal image resolution requirements for accurate tumor classification

Innovation

• Convolutional Neural Network for oral cancer detection
• Hardware system capturing high-resolution medical images
• Application enabling open access to cancer screening