Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Improving Dental Diagnostics: Enhanced Convolution with Spatial Attention Mechanism

Shahriar Rezaie, Neda Saberitabar, Elnaz Salehi

TL;DR

The study addresses limited contrast and computational demands in dental imaging by augmenting a ResNet-50 backbone with the SimAM attention module after the second block to refine spatial features. The proposed approach demonstrates superior performance across feature-extraction techniques, achieving an F1 score of $0.676$ and outperforming conventional CNNs such as VGG, EfficientNet, DenseNet, and AlexNet. The results indicate that combining residual learning with spatial attention enhances diagnostic accuracy and robustness in dental image analysis, with practical implications for faster, more reliable AI-assisted dentistry. This work supports the broader adoption of attention-augmented CNNs in dental diagnostics, potentially improving patient outcomes through more accurate screening and monitoring.

Abstract

Deep learning has emerged as a transformative tool in healthcare, offering significant advancements in dental diagnostics by analyzing complex imaging data. This paper presents an enhanced ResNet50 architecture, integrated with the SimAM attention module, to address the challenge of limited contrast in dental images and optimize deep learning performance while mitigating computational demands. The SimAM module, incorporated after the second ResNet block, refines feature extraction by capturing spatial dependencies and enhancing significant features. Our model demonstrates superior performance across various feature extraction techniques, achieving an F1 score of 0.676 and outperforming traditional architectures such as VGG, EfficientNet, DenseNet, and AlexNet. This study highlights the effectiveness of our approach in improving classification accuracy and robustness in dental image analysis, underscoring the potential of deep learning to enhance diagnostic accuracy and efficiency in dental care. The integration of advanced AI models like ours is poised to revolutionize dental diagnostics, contributing to better patient outcomes and the broader adoption of AI in dentistry.

Improving Dental Diagnostics: Enhanced Convolution with Spatial Attention Mechanism

TL;DR

The study addresses limited contrast and computational demands in dental imaging by augmenting a ResNet-50 backbone with the SimAM attention module after the second block to refine spatial features. The proposed approach demonstrates superior performance across feature-extraction techniques, achieving an F1 score of and outperforming conventional CNNs such as VGG, EfficientNet, DenseNet, and AlexNet. The results indicate that combining residual learning with spatial attention enhances diagnostic accuracy and robustness in dental image analysis, with practical implications for faster, more reliable AI-assisted dentistry. This work supports the broader adoption of attention-augmented CNNs in dental diagnostics, potentially improving patient outcomes through more accurate screening and monitoring.

Abstract

Deep learning has emerged as a transformative tool in healthcare, offering significant advancements in dental diagnostics by analyzing complex imaging data. This paper presents an enhanced ResNet50 architecture, integrated with the SimAM attention module, to address the challenge of limited contrast in dental images and optimize deep learning performance while mitigating computational demands. The SimAM module, incorporated after the second ResNet block, refines feature extraction by capturing spatial dependencies and enhancing significant features. Our model demonstrates superior performance across various feature extraction techniques, achieving an F1 score of 0.676 and outperforming traditional architectures such as VGG, EfficientNet, DenseNet, and AlexNet. This study highlights the effectiveness of our approach in improving classification accuracy and robustness in dental image analysis, underscoring the potential of deep learning to enhance diagnostic accuracy and efficiency in dental care. The integration of advanced AI models like ours is poised to revolutionize dental diagnostics, contributing to better patient outcomes and the broader adoption of AI in dentistry.
Paper Structure (15 sections, 5 equations, 3 figures, 1 table)

This paper contains 15 sections, 5 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Convolutional Neural Networks
  4. Transformers
  5. METHODOLOGY
  6. Revisiting ResNet
  7. Residual Learning
  8. Residual Block
  9. Bottleneck Design
  10. ResNet-50 Architecture
  11. Integration of SimAM
  12. Experiments
  13. Dataset
  14. RESULTS
  15. Conclusion

Figures (3)

  • Figure 1: Convolution attention module.
  • Figure 2: Convolution attention module.
  • Figure 3: Convolution attention module.