針對人體臟器及其病變的組織進行自動化腫瘤切割是進行準確臨床診斷及生物組織標記的重要步驟。大多數腫瘤分割演算法皆以三維腫瘤切割網絡作為其基礎結構，主要原因是三維腫瘤切割網絡可以由大量的人體器官影像中學習臟器紋理，包括橫向、縱向及深度的圖像特徵信息，而推導出影像中正常及非正常組織之位置。從實務面探討，三維腫瘤切割網絡佔用GPU記憶體多寡受訓練資料之解析度影響。因此，為了使三維腫瘤切割網絡可以正常運作，大多數的研究人員在訓練及測試三維腫瘤切割網絡時被迫降低資料之解析度使得模型可運行，但這使得部份影像特徵失真，導致三維腫瘤切割網絡切割複雜邊界的腫瘤組織或微小腫瘤區塊時，容易產生不佳的成果。為了解決這個問題，我們提出了聯級擴張雙聚焦U型深度網路。首先，我們提出的方法架構中一共包含了三維腫瘤切割網絡及二維腫瘤切割網絡。我們透過聯級的方式，將三維腫瘤切割網絡之預測成果向上採樣後串接至輸入影像，以保留影像體積的資訊。透過二維腫瘤切割網絡切割較高解析之聯級影像，提升解析度及精度。第二，我們提出了擴張編碼器，與普通編碼器相比，該結構能從斷層掃描圖像中提取更廣泛的圖像上下文特徵。第三，我們針對二維切割深度網路提出跨連接雙重聚焦閘，該結構可以學習聚焦臟器腫瘤之對應特徵，提高正相關特徵權重。我們在四個不同的數據集進行驗證，包括肝腫瘤分割基準，MSD肝臟和胰臟腫瘤分割資料集以及腎臟腫瘤分割基準。與其他腫瘤切割方法相比，我們提出的演算法的精度優於其他腫瘤切割方法，每個數據集中，我們所提出的方法之精度優於其他方法約4%~6%。

Automatic segmentation of the organs's tumor and lesion on computed tomography(CT) is an essential step towards clinical diagnosis, treatment planning and digital biomedical research. However, precise tumor segmentation on computed tomography images is still an open challenge due to the presence of noise in the imaging sequence, the similar tumor pixel intensity with its neighboring tissues, and heterogeneity between the human anatomy. Most state-of-the-art methods are architecturally dependent on 3D segmentation. The main reason for their success is that deep networks learn to accumulate contextual information over the very large receptive texture in organs. However, the primary concern with 3D convolution, it consumes large amount of GPU memory and suffer from high computational cost. In order to achieve a promising solution, we proposed a segmentation network called Cascaded Atrous Dual-Attention U-Net. First, our network structure concatenates features from 3D tumor segmentation to 2D tumor segmentation for preserving volumetric information as well as enlarging resolution with segmentation accuracy. Second, we propose atrous encoder which extract wider context feature from computed tomography as compared to normal encoder. Third, we inserted skips dual attention gate for 2D segmentation model, which learns to focus on the corresponding features corresponding the task of tumor segmentation in the different organs. We evaluated the proposed approach on four different datasets, including liver tumor segmentation benchmark, MSD liver, pancreas tumor segmentation and Kidney tumor segmentation(KiTS). Experimental results are compared with the other state-of-the-art segmentation methods; our proposed approach performs remarkably better than existing methods with around 4%~6% on each benchmark.

[1] P. Bilic, P. F. Christ, E. Vorontsov, G. Chlebus, H. Chen, Q. Dou, C.-W. Fu, X. Han, P.-A. Heng, J. Hesser, S. Kadoury, T. K. Konopczynski, M. Le, C. Li, X. Li, J. Lipková, J. S. Lowengrub, H. Meine, J. H. Moltz, C. J. Pal, M. Piraud, X. Qi, J. Qi, M. Rempfler, K. Roth, A. Schenk, A. Sekuboyina, P. Zhou, C. Hülsemeyer, M. J. Beetz, F. Ettlinger, F. Grün, G. A. Kaissis, F. Lohöfer, R. F. Braren, J. Holch, F. Hofmann, W. H. Sommer, V. Heinemann, C. Jacobs, G. E. H. Mamani, B. van Ginneken, G. Chartrand, A. Tang, M. Drozdzal, A. Ben-Cohen, E. Klang, M. M. Amitai, E. Konen, H. Greenspan, J. Moreau, A. Hostettler, L. Soler, R. Vivanti, A. Szeskin, N. LevCohain, J. Sosna, L. Joskowicz, and B. H. Menze, “The liver tumor segmentation benchmark (lits),” ArXiv, vol. abs/1901.04056, 2019.
[2] Y.-C. Liu, D. S. Tan, J.-C. Chen, W.-H. Cheng, and K.-L. Hua, “Segmenting hepatic lesions using residual attention u-net with an adaptive weighted dice loss,” in ICIP 2019, 2019.
[3] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” ArXiv, vol. abs/1505.04597, 2015.
[4] M. Z. Alom, M. Hasan, C. Yakopcic, T. M. Taha, and V. K. Asari, “Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation,” ArXiv, vol. abs/1802.06955, 2018.
[5] 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), pp. 565–571, 2016.
[6] V. Badrinarayanan, A. Kendall, and R. Cipolla, “Segnet: A deep convolutional encoder-decoder architecture for image segmentation,” ArXiv, vol. abs/1511.00561, 2015.
[7] Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger, “3d u-net: Learning dense volumetric segmentation from sparse annotation,” in MICCAI, 2016. 31
[8] L. Yu, X. Yang, H. Chen, J. Qin, and P.-A. Heng, “Volumetric convnets with mixed residual connections for automated prostate segmentation from 3d mr images,” in AAAI, 2017.
[9] A. L. Simpson, M. Antonelli, S. Bakas, M. Bilello, K. Farahani, B. van Ginneken, A. Kopp-Schneider, B. A. Landman, G. J. S. Litjens, B. H. Menze, O. Ronneberger, R. M. Summers, P. Bilic, P. F. Christ, R. K. G. Do, M. Gollub, J. Golia-Pernicka, S. Heckers, W. R. Jarnagin, M. McHugo, S. Napel, E. Vorontsov, L. Maier-Hein, and M. J. Cardoso, “A large annotated medical image dataset for the development and evaluation of segmentation algorithms,” ArXiv, vol. abs/1902.09063, 2019.
[10] N. Heller, N. J. Sathianathen, A. Kalapara, E. Walczak, K. Moore, H. Kaluzniak, J. Rosenberg, P. Blake, Z. Rengel, M. Oestreich, J. F. Dean, M. Tradewell, A. Shah, R. Tejpaul, Z. Edgerton, M. Peterson, S. Raza, S. Regmi, N. Papanikolopoulos, and C. J. Weight, “The kits19 challenge data: 300 kidney tumor cases with clinical context, ct semantic segmentations, and surgical outcomes,” ArXiv, vol. abs/ 1904.00445, 2019.
[11] R. L. Siegel, K. D. Miller, and A. Jemal, “Cancer statistics, 2018.,” CA: a cancer journal for clinicians, vol. 68 1, pp. 7–30, 2018.
[12] E. R. Velazquez, C. Parmar, M. Jermoumi, R. H. Mak, A. van Baardwijk, F. M. Fennessy, J. H. Lewis, D. K. M. D. Ruysscher, R. Kikinis, P. Lambin, and H. J. W. L. Aerts, “Volumetric ct-based segmentation of nsclc using 3d-slicer,” in Scientific reports, 2013.
[13] E. Gkika, S. Tanadini-Lang, S. Kirste, P. A. Holzner, H. P. Neeff, H. C. Rischke, T. F. Reese, F. Lohaus, M. N. Duma, K. U. Dieckmann, R. F. O. Semrau, M. Stockinger, D. Imhoff, N. A. W. Kremers, M. F. Haefner, N. Andratschke, U. Nestle, A. L. Grosu, M. Guckenberger, and T. B. Brunner, “Interobserver variability in target volume delineation of hepatocellular carcinoma,” Strahlentherapie und Onkologie, vol. 193, pp. 823–830, 2017.
[14] P. K. Tummala, O. Junaidi, and B. Agarwal, “Imaging of pancreatic cancer: An overview.,” Journal of gastrointestinal oncology, vol. 2 3, pp. 168–74, 2011.
[15] T. J. van Oostenbrugge, J. J. Fütterer, and P. F. A. Mulders, “Diagnostic imaging for solid renal tumors: A pictorial review,” in Kidney cancer, 2018.
[16] A. Hatamizadeh, H. Hosseini, Z. Liu, S. D. Schwartz, and D. Terzopoulos, “Deep dilated convolutional nets for the automatic segmentation of retinal vessels,” ArXiv, vol. abs/1905.12120, 2019.
[17] G. Li, X. Chen, F. Shi, W. Zhu, J. Tian, and D. Xiang, “Automatic liver segmentation based on shape constraints and deformable graph cut in ct images,” IEEE Transactions on Image Processing, vol. 24, pp. 5315–5329, 2015.
[18] M. G. Linguraru, W. J. Richbourg, J. Liu, J. M. Watt, V. Pamulapati, S. Wang, and R. M. Summers, “Tumor burden analysis on computed tomography by automated liver and tumor segmentation,” IEEE Transactions on Medical Imaging, vol. 31, pp. 1965–1976, 2012.
[19] M. Havaei, A. Davy, D. Warde-Farley, A. Biard, A. C. Courville, Y. Bengio, C. J. Pal, P.-M. Jodoin, and H. Larochelle, “Brain tumor segmentation with deep neural networks,” Medical image analysis, vol. 35, pp. 18–31, 2017.
[20] G. Snaauw, D. Gong, G. Maicas, A. van den Hengel, W. J. Niessen, J. Verjans, and G. Carneiro, “End-to-end diagnosis and segmentation learning from cardiac magnetic resonance imaging,” 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 802–805, 2018.
[21] F. Liao, M. Liang, Z. Li, X. Hu, and S. Song, “Evaluate the malignancy of pulmonary nodules using the 3-d deep leaky noisy-or network,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, pp. 3484–3495, 2019.
[22] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” CoRR, vol. abs/1409.1556, 2014.
[23] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2015.
[24] G. Huang, Z. Liu, and K. Q. Weinberger, “Densely connected convolutional networks,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269, 2016.
[25] E. Shelhamer, J. Long, and T. Darrell, “Fully convolutional networks for semantic segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 640–651, 2014.
[26] G. Lin, A. Milan, C. Shen, and I. D. Reid, “Refinenet: Multi-path refinement networks for high-resolution semantic segmentation,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5168–5177, 2016.
[27] D. Lin, G. Chen, D. Cohen-Or, P.-A. Heng, and H. Huang, “Cascaded feature network for semantic segmentation of rgb-d images,” 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1320–1328, 2017.
[28] Z. Cai and N. Vasconcelos, “Cascade r-cnn: Delving into high quality object detection,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6154–6162, 2017.
[29] P. Anderson, X. He, C. Buehler, D. Teney, M. Johnson, S. Gould, and L. Zhang, “Bottom-up and top-down attention for image captioning and visual question answering,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077–6086, 2017.
[30] Z. Yang, D. Yang, C. Dyer, X. He, A. J. Smola, and E. H. Hovy, “Hierarchical attention networks for document classification,” in HLT-NAACL, 2016.
[31] T. Edirisooriya, “Residual attention networks for image classification,” 2017.
[32] Y. Cao, J. Xu, S. Lin, F. Wei, and H. Hu, “Gcnet: Non-local networks meet squeezeexcitation networks and beyond,” ArXiv, vol. abs/1904.11492, 2019.
[33] Y. Zhang, K. Li, K. Li, B. Zhong, and Y. Fu, “Residual non-local attention networks for image restoration,” ArXiv, vol. abs/1903.10082, 2019.
[34] O. Oktay, J. Schlemper, L. L. Folgoc, M. C. H. Lee, M. P. Heinrich, K. Misawa, K. Mori, S. G. McDonagh, N. Y. Hammerla, B. Kainz, B. Glocker, and D. Rueckert, “Attention u-net: Learning where to look for the pancreas,” ArXiv, vol. abs/ 1804.03999, 2018.
[35] M. Holschneider, R. Kronland-Martinet, J. Morlet, and P. Tchamitchian, “A real-time algorithm for signal analysis with the help of the wavelet transform,” 1989.
[36] F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” CoRR, vol. abs/1511.07122, 2015.
[37] P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, “Overfeat: Integrated recognition, localization and detection using convolutional networks,” CoRR, vol. abs/1312.6229, 2013.
[38] G. Papandreou, I. Kokkinos, and P.-A. Savalle, “Modeling local and global deformations in deep learning: Epitomic convolution, multiple instance learning, and sliding window detection,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 390–399, 2015.
[39] A. Giusti, D. C. Ciresan, J. Masci, L. M. Gambardella, and J. Schmidhuber, “Fast image scanning with deep max-pooling convolutional neural networks,” 2013 IEEE International Conference on Image Processing, pp. 4034–4038, 2013.
[40] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, “Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, pp. 834–848, 2016.
[41] R. B. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587, 2013.
[42] T.-Y. Lin, P. Dollár, R. B. Girshick, K. He, B. Hariharan, and S. J. Belongie, “Feature pyramid networks for object detection,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936–944, 2016.
[43] L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in ECCV, 2018.
[44] L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking atrous convolution for semantic image segmentation,” ArXiv, vol. abs/1706.05587, 2017.
[45] K. Chen, J. Wang, L.-C. Chen, H. Gao, W. Xu, and R. Nevatia, “Abc-cnn: An attention based convolutional neural network for visual question answering,” ArXiv, vol. abs/1511.05960, 2015.
[46] A.-W. Jiang, B. Liu, and M.-W. Wang, “Deep multimodal reinforcement network with contextually guided recurrent attention for image question answering,” Journal of Computer Science and Technology, vol. 32, pp. 738–748, 2017.
[47] L. Sevilla-Lara, D. Sun, V. Jampani, and M. J. Black, “Optical flow with semantic segmentation and localized layers,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3889–3898, 2016.
[48] M. E. Fathy, Q.-H. Tran, M. Z. Zia, P. Vernaza, and M. K. Chandraker, “Hierarchical metric learning and matching for 2d and 3d geometric correspondences,” in ECCV, 2018.
[49] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440, 2015.
[50] C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. J. Cardoso, “Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations,” in DLMIA/ML-CDS@MICCAI, 2017.
[51] S. Chen, O. Hirohisa, O. Masahiro, H. Yuichiro, M. Kazunari, and M. Kensaku, “On the influence of dice loss function in multi-class organ segmentation of abdominal ct using 3d fully convolutional networks,” 2017.