Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks
This addresses a specific bottleneck in medical imaging for healthcare applications, offering an incremental improvement over existing CNN methods.
The paper tackles the problem of CNNs losing spatial information and global relations between features in pulmonary disease classification, which can hinder distinguishing similar conditions like COVID-19 and viral pneumonia, by introducing an auxiliary attention mechanism that preserves CNN inductive biases while extracting global correlations.
Convolutional neural networks (CNN) are now being widely used for classifying and detecting pulmonary abnormalities in chest radiographs. Two complementary generalization properties of CNNs, translation invariance and equivariance, are particularly useful in detecting manifested abnormalities associated with pulmonary disease, regardless of their spatial locations within the image. However, these properties also come with the loss of exact spatial information and global relative positions of abnormalities detected in local regions. Global relative positions of such abnormalities may help distinguish similar conditions, such as COVID-19 and viral pneumonia. In such instances, a global attention mechanism is needed, which CNNs do not support in their traditional architectures that aim for generalization afforded by translation invariance and equivariance. Vision Transformers provide a global attention mechanism, but lack translation invariance and equivariance, requiring significantly more training data samples to match generalization of CNNs. To address the loss of spatial information and global relations between features, while preserving the inductive biases of CNNs, we present a novel technique that serves as an auxiliary attention mechanism to existing CNN architectures, in order to extract global correlations between salient features.