ABSTRACT
In this paper, we find a network which can achieve better result than the state of the art for Head and Neck Organ at Risks (OARs) segmentation. At first, we enumerate the popular networks, and sum up their characteristic. We extract the main components from these popular networks and we design experiment to evaluate these components. We split the experiment into two stage. At the first stage experiment, we try to find out which components and constructions can let the network achieve better result than baseline model, Unet, for H&N OAR segmentation. After finding out the useful components and constructions, we try to mix them up to build a novel network which absorbs all their merits. At last, we get a hybrid network, Attention-W-net which gets the best result and defeat the state of the art. All networks are evaluated on 16th CSTRO conference H&N OAR segmentation competition dataset.
- Wilke M, de Haan B, Juenger H, et al. Manual, semi-automated, and automated delineation of chronic brain lesions: a comparison of methods[J]. NeuroImage, 2011, 56(4): 2038--2046.Google ScholarCross Ref
- Wu K, Ung Y C, Hwang D, et al. Autocontouring and Manual Contouring: Which Is the Better Method for Target Delineation Using 18F-FDG PET/CT in Non-Small Cell Lung Cancer? [J]. Journal of Nuclear Medicine, 2010, 51(10): 1517--1523.Google ScholarCross Ref
- Shanthi K J, Kumar M S. Skull stripping and automatic segmentation of brain MRI using seed growth and threshold techniques[C]//2007 International conference on intelligent and advanced systems. IEEE, 2007: 422--426.Google Scholar
- Hojjatoleslami S A, Kittler J. Region growing: a new approach[J]. IEEE Transactions on Image processing, 1998, 7(7): 1079--1084.Google ScholarDigital Library
- Hojjatoleslami S A, Kruggel F. Segmentation of large brain lesions[J]. IEEE Transactions on Medical Imaging, 2001, 20(7): 666--669.Google ScholarCross Ref
- Wan S Y, Higgins W E. Symmetric region growing[J]. IEEE Transactions on Image processing, 2003, 12(9): 1007--1015.Google ScholarDigital Library
- Kong J, Wang J, Lu Y, et al. A novel approach for segmentation of MRI brain images[C]//MELECON 2006-2006 IEEE Mediterranean Electrotechnical Conference. IEEE, 2006: 525--528.Google Scholar
- Supot S, Thanapong C, Chuchart P, et al. Segmentation of magnetic resonance images using discrete curve evolution and fuzzy clustering[C]//2007 IEEE International Conference on Integration Technology. IEEE, 2007: 697--700.Google Scholar
- Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015: 234--241.Google Scholar
- Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3431--3440.Google Scholar
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.Google Scholar
- Drozdzal M, Vorontsov E, Chartrand G, et al. The importance of skip connections in biomedical image segmentation[M]//Deep Learning and Data Labeling for Medical Applications. Springer, Cham, 2016: 179-187Google Scholar
- Alom M Z, Hasan M, Yakopcic C, et al. Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation[J]. arXiv preprint arXiv: 1802.06955, 2018.Google Scholar
- Alom M Z, Hasan M, Yakopcic C, et al. Improved inception-residual convolutional neural network for object recognition [J]. Neural Computing and Applications, 2018: 1--15.Google Scholar
- Zhou Z, Siddiquee M M R, Tajbakhsh N, et al. Unet++: A nested u-net architecture for medical image segmentation[M]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer, Cham, 2018: 3--11.Google Scholar
- Iandola F, Moskewicz M, Karayev S, et al. Densenet: Implementing efficient convnet descriptor pyramids[J]. arXiv preprint arXiv:1404.1869, 2014.Google Scholar
- Gu Z, Cheng J, Fu H, et al. CE-Net: context encoder network for 2D medical image segmentation[J]. IEEE transactions on medical imaging, 2019, 38(10): 2281--2292.Google Scholar
- Xia X, Kulis B. W-net: A deep model for fully unsupervised image segmentation[J]. arXiv preprint arXiv:1711.08506, 2017.Google Scholar
- Schlemper J, Oktay O, Schaap M, et al. Attention gated networks: Learning to leverage salient regions in medical images[J]. Medical image analysis, 2019, 53: 197--207.Google Scholar
- Jaderberg M, Simonyan K, Zisserman A. Spatial transformer networks[C]//Advances in neural information processing systems. 2015: 2017--2025.Google Scholar
- Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132--7141.Google Scholar
- Sudre C H, Li W, Vercauteren T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations[M]//Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, 2017: 240--248.Google Scholar
- Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 801--818.Google Scholar
Index Terms
- A Novel Hybrid Network for H&N Organs at Risk Segmentation
Recommendations
A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation
In medical field, it remains challenging to accurately segment medical images due to low contrast, complex noises and intensity inhomogeneity. To overcome these obstacles, this paper provides a novel edge-based active contour model (ACM) for medical ...
Automatic segmentation of vertebral contours from CT images using fuzzy corners
Automatic segmentation of bone in computed tomography (CT) images is critical for the implementation of computer-assisted diagnosis which has increasing potential in the evaluation of various spine disorders. Of the many techniques available for ...
Neural Network Based Brain Tumor Segmentation
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain InjuriesAbstractGlioblastoma is the most common and lethal primary brain tumor in adults. Magnetic resonance imaging (MRI) is a critical diagnostic tool for glioblastoma. Besides MRI, histopathology features and molecular subtypes like MGMT methylation, IDH ...
Comments