Optimizing CNN Architectures for Advanced Thoracic Disease Classification

TL;DR

This paper evaluates different CNN architectures for thoracic disease classification in chest X-ray images, introducing advanced preprocessing and a novel loss function to improve accuracy amid dataset challenges.

Contribution

It presents a comprehensive evaluation of CNN models and introduces new techniques to handle dataset imbalance and image variability in medical imaging.

Findings

CNN architectures show promise for thoracic disease detection

Advanced preprocessing improves model robustness

Addressing dataset imbalance is crucial for optimal performance

Abstract

Machine learning, particularly convolutional neural networks (CNNs), has shown promise in medical image analysis, especially for thoracic disease detection using chest X-ray images. In this study, we evaluate various CNN architectures, including binary classification, multi-label classification, and ResNet50 models, to address challenges like dataset imbalance, variations in image quality, and hidden biases. We introduce advanced preprocessing techniques such as principal component analysis (PCA) for image compression and propose a novel class-weighted loss function to mitigate imbalance issues. Our results highlight the potential of CNNs in medical imaging but emphasize that issues like unbalanced datasets and variations in image acquisition methods must be addressed for optimal model performance.