Han Yang
ABSTRACT
Medical image segmentation plays an important role in the computer-aided screening of many diseases. Different from popular deep learning-based segmentation methods that mainly focus on the whole target, recent studies pay more attention to target contour by making use of the distance transform of the object boundary. In this paper, to learn both the object content and the boundary information, we incorporate a regression task that estimates a distance map of target contour into a CNN-based segmentation network. The segmentation task and the regression task share most parts of the backbone network. Moreover, we introduce a channel information exchange module that dynamically exchanges feature maps between the segmentation and the regression tasks. The proposed information exchange module is parameter-free and controlled by the batch normalization scaling factor. In addition, the output feature maps of the two tasks are further integrated to provide fused segmentation results.We evaluate our method on three popular datasets, including the 2D ultrasound thyroid nodule segmentation dataset, the 3D MRI left atrial segmentation dataset and 2017 MM-WHS whole heart segmentation Challenge datasets. Experimental results show that our method achieves promising performance compared to the state-of-the-art approaches.
- 2018. MICCAI 2018 left atrial segmentation. http://atriaseg2018.cardiacatlas.org/.Google Scholar
- Shusil Dangi, Cristian A Linte, and Ziv Yaniv. 2019. A distance map regularized CNN for cardiac cine MR image segmentation. Medical physics 46, 12 (2019), 5637–5651.Google Scholar
- Gaetan Galisot, Thierry Brouard, and Jean-Yves Ramel. 2017. Local probabilistic atlases and a posteriori correction for the segmentation of heart images. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 207–214.Google Scholar
- Chao Huang, Hu Han, Qingsong Yao, Shankuan Zhu, and S Kevin Zhou. 2019. 3D U2-Net: A 3D Universal U-Net for Multi-domain Medical Image Segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 291–299.Google Scholar
- Lei Li, Xin Weng, Julia A Schnabel, and Xiahai Zhuang. 2020. Joint left atrial segmentation and scar quantification based on a DNN with spatial encoding and shape attention. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 118–127.Google ScholarDigital Library
- Yu Liu, Fuhao Mu, Yu Shi, and Xun Chen. 2022. Sf-net: A multi-task model for brain tumor segmentation in multimodal mri via image fusion. IEEE Signal Processing Letters 29 (2022), 1799–1803.Google ScholarCross Ref
- Jun Ma, Zhan Wei, Yiwen Zhang, Yixin Wang, Rongfei Lv, Cheng Zhu, Gaoxiang Chen, Jianan Liu, Chao Peng, Lei Wang, Yunpeng Wang, and Jianan Chen. 2020. How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study. In Medical Imaging with Deep Learning(Proceedings of Machine Learning Research, Vol. 121), Tal Arbel, Ismail Ben Ayed, Marleen de Bruijne, Maxime Descoteaux, Herve Lombaert, and Christopher Pal (Eds.). PMLR, 479–492. http://proceedings.mlr.press/v121/ma20b.htmlGoogle Scholar
- Wang Mingyu. 2020. 1st place solution in MICCAI 2020 TN-SCUI challenge. https://github.com/WAMAWAMA/TNSCUI2020-Seg-Rank1st.Google Scholar
- Aliasghar Mortazi, Jeremy Burt, and Ulas Bagci. 2017. Multi-planar deep segmentation networks for cardiac substructures from MRI and CT. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 199–206.Google Scholar
- Fernando Navarro, Suprosanna Shit, Ivan Ezhov, Johannes Paetzold, Andrei Gafita, Jan C Peeken, Stephanie E Combs, and Bjoern H Menze. 2019. Shape-aware complementary-task learning for multi-organ segmentation. In International Workshop on Machine Learning in Medical Imaging. Springer, 620–627.Google ScholarDigital Library
- Christian Payer, Darko Štern, Horst Bischof, and Martin Urschler. 2017. Multi-label whole heart segmentation using CNNs and anatomical label configurations. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 190–198.Google Scholar
- Lina Pedraza, Carlos Vargas, Fabián Narváez, Oscar Durán, Emma Muñoz, and Eduardo Romero. 2015. An open access thyroid ultrasound image database. In 10th International Symposium on Medical Information Processing and Analysis, Vol. 9287. International Society for Optics and Photonics, 92870W.Google Scholar
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.Google ScholarCross Ref
- Rukhmini Roy, Pranavesh Banerjee, and Ananda S Chowdhury. 2020. A level set based unified framework for pulmonary nodule segmentation. IEEE Signal Processing Letters 27 (2020), 1465–1469.Google ScholarCross Ref
- Tianyu Shen, Chao Gou, Jiangong Wang, and Fei-Yue Wang. 2019. Simultaneous segmentation and classification of mass region from mammograms using a mixed-supervision guided deep model. IEEE Signal Processing Letters 27 (2019), 196–200.Google ScholarCross Ref
- Zenglin Shi, Guodong Zeng, Le Zhang, Xiahai Zhuang, Lei Li, Guang Yang, and Guoyan Zheng. 2018. Bayesian voxdrn: A probabilistic deep voxelwise dilated residual network for whole heart segmentation from 3d mr images. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 569–577.Google ScholarDigital Library
- Jun-Ding Sun, Chong Yao, Jie Liu, Weifan Liu, and Ze-Kuan Yu. 2022. GNAS-U 2 Net: A New Optic Cup and Optic Disc Segmentation Architecture With Genetic Neural Architecture Search. IEEE Signal Processing Letters 29 (2022), 697–701.Google ScholarCross Ref
- Qianqian Tong, Munan Ning, Weixin Si, Xiangyun Liao, and Jing Qin. 2017. 3D deeply-supervised U-net based whole heart segmentation. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 224–232.Google Scholar
- Sulaiman Vesal, Nishant Ravikumar, and Andreas Maier. 2018. Dilated convolutions in neural networks for left atrial segmentation in 3D gadolinium enhanced-MRI. In International workshop on statistical atlases and computational models of the heart. Springer, 319–328.Google Scholar
- Chengjia Wang, Tom MacGillivray, Gillian Macnaught, Guang Yang, and David Newby. 2018. A two-stage 3D Unet framework for multi-class segmentation on full resolution image. arXiv preprint arXiv:1804.04341 (2018).Google Scholar
- Chunliang Wang and Örjan Smedby. 2017. Automatic whole heart segmentation using deep learning and shape context. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 242–249.Google Scholar
- Yikai Wang, Wenbing Huang, Fuchun Sun, Tingyang Xu, Yu Rong, and Junzhou Huang. 2020. Deep multimodal fusion by channel exchanging. Advances in Neural Information Processing Systems 33 (2020).Google Scholar
- Yuan Xue, Hui Tang, Zhi Qiao, Guanzhong Gong, Yong Yin, Zhen Qian, Chao Huang, Wei Fan, and Xiaolei Huang. 2020. Shape-aware organ segmentation by predicting signed distance maps. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 12565–12572.Google ScholarCross Ref
- Wenjun Yan, Yuanyuan Wang, Menghua Xia, and Qian Tao. 2019. Edge-guided output adaptor: Highly efficient adaptation module for cross-vendor medical image segmentation. IEEE Signal Processing Letters 26, 11 (2019), 1593–1597.Google ScholarCross Ref
- Guanyu Yang, Chenchen Sun, Yang Chen, Lijun Tang, Huazhong Shu, and Jean-Louis Dillenseger. 2017. Automatic whole heart segmentation in CT images based on multi-atlas image registration. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 250–257.Google Scholar
- Xin Yang, Cheng Bian, Lequan Yu, Dong Ni, and Pheng-Ann Heng. 2017. 3D convolutional networks for fully automatic fine-grained whole heart partition. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 181–189.Google Scholar
- Xin Yang, Cheng Bian, Lequan Yu, Dong Ni, and Pheng-Ann Heng. 2017. Hybrid loss guided convolutional networks for whole heart parsing. In International workshop on statistical atlases and computational models of the heart. Springer, 215–223.Google Scholar
- Shi Yin, Qinmu Peng, Hongming Li, Zhengqiang Zhang, Xinge You, Katherine Fischer, Susan L Furth, Gregory E Tasian, and Yong Fan. 2020. Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks. Medical image analysis 60 (2020), 101602.Google Scholar
- Xiahai Zhuang, Lei Li, Christian Payer, Darko Štern, Martin Urschler, Mattias P Heinrich, Julien Oster, Chunliang Wang, Örjan Smedby, Cheng Bian, 2019. Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Medical image analysis 58 (2019), 101537.Google Scholar
Index Terms
- Distance Transform Guided Medical Image Segmentation With Channel Information Exchange
Recommendations
Incorporating priors for medical image segmentation using a genetic algorithm
Medical image segmentation is typically performed manually by a physician to delineate gross tumor volumes for treatment planning and diagnosis. Manual segmentation is performed by medical experts using prior knowledge of organ shapes and locations but ...
Medical image segmentation with transform and moment based features and incremental supervised neural network
In this study, a novel incremental supervised neural network (ISNN) is proposed for the segmentation of medical images. Performance of the ISNN is investigated for tissue segmentation in medical images obtained from various imaging modalities. Two ...
Deep Learning for Multi-task Medical Image Segmentation in Multiple Modalities
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016AbstractAutomatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single ...
Comments