TY - GEN
T1 - MS-GAN
T2 - 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018
AU - Zhang, Chaoyi
AU - Song, Yang
AU - Liu, Sidong
AU - Lill, Scott
AU - Wang, Chenyu
AU - Tang, Zihao
AU - You, Yuyi
AU - Gao, Yang
AU - Klistorner, Alexander
AU - Barnett, Michael
AU - Cai, Weidong
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/16
Y1 - 2019/1/16
N2 - Automated segmentation of multiple sclerosis (MS) lesions in brain imaging is challenging due to the high variability in lesion characteristics. Based on the generative adversarial network (GAN), we propose a semantic segmentation framework MS-GAN to localize MS lesions in multimodal brain magnetic resonance imaging (MRI), which consists of one multimodal encoder-decoder generator G and multiple discriminators D corresponding to the multiple input modalities. For the design of the generator, we adopt an encoder-decoder deep learning architecture with bypass of spatial information from encoder to the corresponding decoder, which helps to reduce the network parameters while improving the localization performance. Our generator is also designed to integrate multimodal imaging data in end-to-end learning with multi-path encoding and cross-modality fusion. An additional classification-related constraint is proposed for the adversarial training process of the GAN model, with the aim of alleviating the hard-to-converge issue in classification-based image-to-image translation problems. For evaluation, we collected a database of 126 cases from patients with relapsing MS. We also experimented with other semantic segmentation models as well as patch-based deep learning methods for performance comparison. The results show that our method provides more accurate segmentation than the state-of-the-art techniques.
AB - Automated segmentation of multiple sclerosis (MS) lesions in brain imaging is challenging due to the high variability in lesion characteristics. Based on the generative adversarial network (GAN), we propose a semantic segmentation framework MS-GAN to localize MS lesions in multimodal brain magnetic resonance imaging (MRI), which consists of one multimodal encoder-decoder generator G and multiple discriminators D corresponding to the multiple input modalities. For the design of the generator, we adopt an encoder-decoder deep learning architecture with bypass of spatial information from encoder to the corresponding decoder, which helps to reduce the network parameters while improving the localization performance. Our generator is also designed to integrate multimodal imaging data in end-to-end learning with multi-path encoding and cross-modality fusion. An additional classification-related constraint is proposed for the adversarial training process of the GAN model, with the aim of alleviating the hard-to-converge issue in classification-based image-to-image translation problems. For evaluation, we collected a database of 126 cases from patients with relapsing MS. We also experimented with other semantic segmentation models as well as patch-based deep learning methods for performance comparison. The results show that our method provides more accurate segmentation than the state-of-the-art techniques.
KW - GAN
KW - Image-to-image Translation
KW - Multiple Sclerosis
KW - Semantic Segmentation
UR - https://www.scopus.com/pages/publications/85062235873
U2 - 10.1109/DICTA.2018.8615771
DO - 10.1109/DICTA.2018.8615771
M3 - 会议稿件
AN - SCOPUS:85062235873
T3 - 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018
BT - 2018 International Conference on Digital Image Computing
A2 - Pickering, Mark
A2 - Zheng, Lihong
A2 - You, Shaodi
A2 - Rahman, Ashfaqur
A2 - Murshed, Manzur
A2 - Asikuzzaman, Md
A2 - Natu, Ambarish
A2 - Robles-Kelly, Antonio
A2 - Paul, Manoranjan
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 10 December 2018 through 13 December 2018
ER -