Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities. Moeskops, P., Wolterink, J. M., van der Velden, B. H. M., Gilhuijs, K. G. A., Leiner, T., Viergever, M. A., & Išgum, I. arXiv:1704.03379 [cs], 9901:478–486, 2016. arXiv: 1704.03379
Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities [link]Paper  doi  abstract   bibtex   
Automatic 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 convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes. For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.
@article{moeskops_deep_2016,
	title = {Deep {Learning} for {Multi}-{Task} {Medical} {Image} {Segmentation} in {Multiple} {Modalities}},
	volume = {9901},
	url = {http://arxiv.org/abs/1704.03379},
	doi = {10.1007/978-3-319-46723-8_55},
	abstract = {Automatic 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 convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes. For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.},
	urldate = {2017-09-11},
	journal = {arXiv:1704.03379 [cs]},
	author = {Moeskops, Pim and Wolterink, Jelmer M. and van der Velden, Bas H. M. and Gilhuijs, Kenneth G. A. and Leiner, Tim and Viergever, Max A. and Išgum, Ivana},
	year = {2016},
	note = {arXiv: 1704.03379},
	keywords = {Computer Science - Computer Vision and Pattern Recognition},
	pages = {478--486},
}
Downloads: 0