Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
This work addresses the need for reliable and efficient emphysema subtype classification in radiology, though it appears incremental as it builds on existing unsupervised learning methods with a supervised approach.
The authors tackled the problem of slow and protocol-sensitive segmentation of lung texture patterns (sLTPs) for emphysema subtypes by developing a robust 3-D squeeze-and-excitation CNN, achieving accurate and reproducible segmentation across two independent cohorts and different scanner models.
Pulmonary emphysema, the progressive, irreversible loss of lung tissue, is conventionally categorized into three subtypes identifiable on pathology and on lung computed tomography (CT) images. Recent work has led to the unsupervised learning of ten spatially-informed lung texture patterns (sLTPs) on lung CT, representing distinct patterns of emphysematous lung parenchyma based on both textural appearance and spatial location within the lung, and which aggregate into 6 robust and reproducible CT Emphysema Subtypes (CTES). Existing methods for sLTP segmentation, however, are slow and highly sensitive to changes in CT acquisition protocol. In this work, we present a robust 3-D squeeze-and-excitation CNN for supervised classification of sLTPs and CTES on lung CT. Our results demonstrate that this model achieves accurate and reproducible sLTP segmentation on lung CTscans, across two independent cohorts and independently of scanner manufacturer and model.