Comparing Different Deep Learning Architectures for Classification of Chest Radiographs

Abstract

Chest radiographs are among the most frequently acquired images in radiology and are often the subject of computer vision research. However, most of the models used to classify chest radiographs are derived from openly available deep neural networks, trained on large image-datasets. These datasets routinely differ from chest radiographs in that they are mostly color images and contain several possible image classes, while radiographs are greyscale images and often only contain fewer image classes. Therefore, very deep neural networks, which can represent more complex relationships in image-features, might not be required for the comparatively simpler task of classifying grayscale chest radiographs. We compared fifteen different architectures of artificial neural networks regarding training-time and performance on the openly available CheXpert dataset to identify the most suitable models for deep learning tasks on chest radiographs. We could show, that smaller networks such as ResNet-34, AlexNet or VGG-16 have the potential to classify chest radiographs as precisely as deeper neural networks such as DenseNet-201 or ResNet-151, while being less computationally demanding.

arXiv comment15 pages, 6 figures, 3 tables

References in corpus (3)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• fastai: A Layered API for Deep Learning
• PadChest: A large chest x-ray image dataset with multi-label annotated reports

Cited by in corpus (6)

• Multiclass Wound Image Classification using an Ensemble Deep CNN-based Classifier
• DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays
• CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation
• Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
• Do Sharpness-based Optimizers Improve Generalization in Medical Image Analysis?
• Towards retrieving dispersion profiles using quantum-mimic Optical Coherence Tomography and Machine Learnin