在處理肺部的電腦斷層 (CT) 影像時，由於結節的形狀多變，部分外觀可能與其周圍背景相似，使得執行準確的肺部結節分割 (lung nodule segmentation) 為一件困難的任務。在本篇論文中，為了精確分割具有多種特徵的肺部結節，我們提出應用加權輪廓注意力圖之肺部結節分割網路 (WCNet)，由兩個簡單的U型網路 – 通道感知U-Net以加權輪廓產生器連接組成。第一個通道感知U-Net網路負責產生粗略的初始分割圖，加權輪廓產生器接著在此分割圖的輪廓部分給予較大的權重，產生注意力圖送入第二個通道感知U-Net網路，進而引導第二個網路給出更細緻的分割。另外，我們針對肺部結節資料集提出前處理方法，將目標補丁與其在 z 軸方向上前、後各一張的補丁串接。這兩張額外補充的補丁包含更多有關目標補丁的空間位移資訊。實驗展示提出的肺部結節分割網路利用細化分割的策略與更少的參數量勝過其他先進方法；資料集的前處理策略也可以使網路有效地利用額外資訊，提升分割性能。

For medical image processing, it is challenging to perform accurate lung nodule segmentation due to the diverse shapes of nodules and the similar outlooks between nodules and their surrounding areas. In this paper, we propose the weighted contour network (WCNet) that can properly segment the nodules with irregular shapes and ambiguous boundaries. The WCNet consists of two simple U-shaped neural networks, the channel-aware U-Net (CAU-Net), and the weighted contour generator (WCG). The WCG can generate attention maps that emphasize the contours of initially segmented nodules produced by the first CAU-Net. The second CAU-Net then follows the attention maps to produce more detailed segmentation results. Further, we derive a dataset from the publicly available lung image database consortium and image database resource initiative (LIDC-IDRI) dataset with our pre-processing method. We aggregate extra patches on both sides of the target patch along the z-direction, which can provide more spatial information for the target patch. Extensive experiments show that our proposed WCNet can achieve outstanding performance with moderate parameters compared to other state-of-the-art methods. The pre-processing strategy is also shown to be helpful for the network to achieve better segmentation results with additional information.

J. Shotton, M. Johnson, and R. Cipolla. "Semantic Texton Forests for Image Categorization and Segmentation." 2008 IEEE conference on computer vision and pattern recognition. IEEE, 2008.
J. Shotton, J. Winn, and C. Rother, et al. "TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context." International journal of computer vision 81.1 (2009): 2-23.
F. Rosenblatt. "The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain." Psychological review 65.6 (1958): 386.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams. "Learning Representations by Back-Propagating Errors." nature 323.6088 (1986): 533-536.
G. E. Hinton "Deep Belief Networks." Scholarpedia 4.5 (2009): 5947.
A. Krizhevsky, I. Sutskever, and G. E. Hinton. "ImageNet Classification with Deep Convolutional Neural Networks." Communications of the ACM 60.6 (2017): 84-90.
Y. LeCun, L. Bottou, and Y. Bengio, et al. "Gradient-Based Learning Applied to Document Recognition." Proceedings of the IEEE 86.11 (1998): 2278-2324.
M. D. Zeiler, D. Krishnan, and G. W. Taylor, et al. "Deconvolutional Networks." 2010 IEEE Computer Society Conference on computer vision and pattern recognition. IEEE, 2010.
H. Noh, S. Hong, and B. Han. "Learning Deconvolution Network for Semantic Segmentation." Proceedings of the IEEE international conference on computer vision. 2015.
V. Badrinarayanan, A. Kendall, and R. Cipolla. "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation." IEEE transactions on pattern analysis and machine intelligence 39.12 (2017): 2481-2495.
O. Ronneberger, P. Fischer, and T. Brox. "U-Net: Convolutional Networks for Biomedical Image Segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.
Z. W. Zhou, M. M. R. Siddiquee, and N. Tajbakhsh, et al. "UNet++: A Nested U-Net Architecture for Medical Image Segmentation." Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, 2018. 3-11.
F. Milletari, N. Navab, and S.-A. Ahmadi. "V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation." 2016 fourth international conference on 3D vision (3DV). IEEE, 2016.
D. Jha, P. H. Smedsrud, and M. A. Riegler, et al. "ResUNet++: An Advanced Architecture for Medical Image Segmentation." 2019 IEEE International Symposium on Multimedia (ISM). IEEE, 2019.
D.-P. Fan, G.-P. Ji, and T. Zhou, et al. "PraNet: Parallel Reverse Attention Network for Polyp Segmentation." International conference on medical image computing and computer-assisted intervention. Springer, Cham, 2020.
S.-H. Gao, M.-M. Cheng, and K. Zhao, et al. "Res2Net: A New Multi-Scale Backbone Architecture." IEEE transactions on pattern analysis and machine intelligence 43.2 (2019): 652-662.
G. Aresta, C. Jacobs, and T. Araújo, et al. "iW-Net: An Automatic and Minimalistic Interactive Lung Nodule Segmentation Deep Network." Scientific reports 9.1 (2019): 1-9.
J. Chen, Y. Lu, and Q. Yu, et al. "TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation." arXiv preprint arXiv:2102.04306 (2021).
N. K. Tomar, D. Jha, and M. A. Riegler, et al. "FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation." IEEE Transactions on Neural Networks and Learning Systems (2022).
A. Hatamizadeh, Y. Tang, and V. Nath, et al. "UNETR: Transformers for 3D Medical Image Segmentation." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2022.
H. Wang, P. Cao, and J. Wang, et al. "UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 36. No. 3. 2022.
A. Vaswani, N. Shazeer, N. Parmar, et al. "Attention Is All You Need." Advances in neural information processing systems 30 (2017).
Z. Gu, J. Cheng, H. Fu, et al. "CE-Net: Context Encoder Network for 2D Medical Image S Z.egmentation." IEEE transactions on medical imaging 38.10 (2019): 2281-2292.
J. M. J. Valanarasu, and V. M. Patel. "UNeXt: MLP-based Rapid Medical Image Segmentation Network." Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part V. Cham: Springer Nature Switzerland, 2022.
Y. Li, "Detecting Lesion Bounding Ellipses with Gaussian Proposal Networks." International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 2019.
J. Hu, L. Shen, and G. Sun. "Squeeze-and-Excitation Networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
C.-Y. Lee, S. Xie, and P. Gallagher, et al. "Deeply-Supervised Nets." Artificial intelligence and statistics. PMLR, 2015.
S. G. Armato III, G. McLennan, and L. Bidaut, et al. "Data From LIDC-IDRI." The cancer imaging archive 10 (2015): K9.
A. Paszke, S. Gross, and S. Chintala, et al. "Automatic differentiation in pytorch." (2017).
I. Loshchilov and F. Hutter. "Decoupled Weight Decay Regularization." arXiv preprint arXiv:1711.05101 (2017).
H. Sung, J. Ferlay, and R. L. Siegel, et al. "Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries." CA: a cancer journal for clinicians 71.3 (2021): 209-249.
S. H. Woo, J. Park, and J. Y. Lee, et al. "CBAM: Convolutional Block Attention Module." Proceedings of the European conference on computer vision (ECCV). 2018.
P.-T. De Boer, D. P. Kroese, and S. Mannor, et al. "A Tutorial on the Cross-Entropy Method." Annals of operations research 134.1 (2005): 19-67.
G. Máttyus, W. Luo, and R. Urtasun. "DeepRoadMapper: Extracting Road Topology From Aerial Images." Proceedings of the IEEE international conference on computer vision. 2017.
J. Wang, J. Wang, and Y. Wen, et al. "Pulmonary Nodule Detection in Volumetric Chest CT Scans Using CNNs-Based Nodule-Size-Adaptive Detection and Classification." IEEE access 7 (2019): 46033-46044.
R. Gu, G. Wang, and T. Song, et al. "CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation." IEEE transactions on medical imaging 40.2 (2020): 699-711.