Lung segmentation with NASNet-Large-Decoder Net
This addresses lung cancer diagnosis by improving segmentation accuracy, though it appears incremental as it combines existing encoder-decoder approaches with post-processing.
The authors tackled lung region segmentation for cancer analysis by proposing a NASNet-Large encoder with decoder architecture and post-processing, achieving a dice score of 0.92 that outperforms state-of-the-art methods.
Lung cancer has emerged as a severe disease that threatens human life and health. The precise segmentation of lung regions is a crucial prerequisite for localizing tumors, which can provide accurate information for lung image analysis. In this work, we first propose a lung image segmentation model using the NASNet-Large as an encoder and then followed by a decoder architecture, which is one of the most commonly used architectures in deep learning for image segmentation. The proposed NASNet-Large-decoder architecture can extract high-level information and expand the feature map to recover the segmentation map. To further improve the segmentation results, we propose a post-processing layer to remove the irrelevant portion of the segmentation map. Experimental results show that an accurate segmentation model with 0.92 dice scores outperforms state-of-the-art performance.