RAR-U-Net: a Residual Encoder to Attention Decoder by Residual Connections Framework for Spine Segmentation under Noisy Labels
This work addresses segmentation for medical imaging, specifically spine CTs, with incremental improvements to handle noisy labels.
The authors tackled medical image segmentation under noisy labels by proposing RAR-U-Net, which achieved competitive performance against state-of-the-art methods on a spine CT benchmark database.
Segmentation algorithms for medical images are widely studied for various clinical and research purposes. In this paper, we propose a new and efficient method for medical image segmentation under noisy labels. The method operates under a deep learning paradigm, incorporating four novel contributions. Firstly, a residual interconnection is explored in different scale encoders to transfer gradient information efficiently. Secondly, four copy-and-crop connections are replaced by residual-block-based concatenation to alleviate the disparity between encoders and decoders. Thirdly, convolutional attention modules for feature refinement are studied on all scale decoders. Finally, an adaptive denoising learning strategy (ADL) is introduced into the training process to avoid too much influence from the noisy labels. Experimental results are illustrated on a publicly available benchmark database of spine CTs. Our proposed method achieves competitive performance against other state-of-the-art methods over a variety of different evaluation measures.