FDA: Feature Decomposition and Aggregation for Robust Airway Segmentation

TL;DR

This paper introduces a dual-stream CNN that effectively segments airways in noisy CT scans by leveraging clean and limited noisy data, improving robustness and accuracy over existing methods.

Contribution

The proposed dual-stream network with feature recalibration and SDM regression enhances airway segmentation in noisy CT scans, addressing dataset variability and label coarseness.

Findings

Improved segmentation accuracy on noisy CT scans.

Better bronchi detection compared to state-of-the-art methods.

Robust feature extraction for noisy and clean domains.

Abstract

3D Convolutional Neural Networks (CNNs) have been widely adopted for airway segmentation. The performance of 3D CNNs is greatly influenced by the dataset while the public airway datasets are mainly clean CT scans with coarse annotation, thus difficult to be generalized to noisy CT scans (e.g. COVID-19 CT scans). In this work, we proposed a new dual-stream network to address the variability between the clean domain and noisy domain, which utilizes the clean CT scans and a small amount of labeled noisy CT scans for airway segmentation. We designed two different encoders to extract the transferable clean features and the unique noisy features separately, followed by two independent decoders. Further on, the transferable features are refined by the channel-wise feature recalibration and Signed Distance Map (SDM) regression. The feature recalibration module emphasizes critical features and the SDM pays more attention to the bronchi, which is beneficial to extracting the transferable topological features robust to the coarse labels. Extensive experimental results demonstrated the obvious improvement brought by our proposed method. Compared to other state-of-the-art transfer learning methods, our method accurately segmented more bronchi in the noisy CT scans.