TY - GEN
T1 - Transforming Intensity Distribution of Brain Lesions Via Conditional Gans for Segmentation
AU - Hamghalam, Mohammad
AU - Wang, Tianfu
AU - Qin, Jing
AU - Lei, Baiying
N1 - Funding Information:
This work was supported partly by National Natural Science Foundation of China (Nos. 61871274 and U1909209), Key Laboratory of Medical Image Processing of Guangdong Province (No. K217300003), Guangdong Pearl River Talents Plan (2016ZT06S220), Shenzhen Peacock Plan (Nos. KQTD 2016053112051497 and KQTD2015033016104926), and Shen-zhen Key Basic Research Project (Nos. JCYJ20180507184 647636 and JCYJ20170818094109846).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/4
Y1 - 2020/4
N2 - Brain lesion segmentation is crucial for diagnosis, surgical planning, and analysis. Owing to the fact that pixel values of brain lesions in magnetic resonance (MR) scans are distributed over the wide intensity range, there is always a considerable overlap between the class-conditional densities of lesions. Hence, an accurate automatic brain lesion segmentation is still a challenging task. We present a novel architecture based on conditional generative adversarial networks (cGANs) to improve the lesion contrast for segmentation. To this end, we propose a novel generator adaptively calibrating the input pixel values, and a Markovian discriminator to estimate the distribution of tumors. We further propose the Enhancement and Segmentation GAN (Enh-Seg-GAN) which effectively incorporates the classifier loss into the adversarial one during training to predict the central labels of the sliding input patches. Particularly, the generated synthetic MR images are a substitute for the real ones to maximize lesion contrast while suppressing the background. The potential of proposed frameworks is confirmed by quantitative evaluation compared to the state-of-the-art methods on BraTS'13 dataset.
AB - Brain lesion segmentation is crucial for diagnosis, surgical planning, and analysis. Owing to the fact that pixel values of brain lesions in magnetic resonance (MR) scans are distributed over the wide intensity range, there is always a considerable overlap between the class-conditional densities of lesions. Hence, an accurate automatic brain lesion segmentation is still a challenging task. We present a novel architecture based on conditional generative adversarial networks (cGANs) to improve the lesion contrast for segmentation. To this end, we propose a novel generator adaptively calibrating the input pixel values, and a Markovian discriminator to estimate the distribution of tumors. We further propose the Enhancement and Segmentation GAN (Enh-Seg-GAN) which effectively incorporates the classifier loss into the adversarial one during training to predict the central labels of the sliding input patches. Particularly, the generated synthetic MR images are a substitute for the real ones to maximize lesion contrast while suppressing the background. The potential of proposed frameworks is confirmed by quantitative evaluation compared to the state-of-the-art methods on BraTS'13 dataset.
KW - Brain lesion segmentation
KW - conditional GANs
KW - distribution transformation
KW - image synthesis
KW - MRI
UR - http://www.scopus.com/inward/record.url?scp=85085858350&partnerID=8YFLogxK
U2 - 10.1109/ISBI45749.2020.9098347
DO - 10.1109/ISBI45749.2020.9098347
M3 - Conference article published in proceeding or book
AN - SCOPUS:85085858350
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1499
EP - 1502
BT - ISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
T2 - 17th IEEE International Symposium on Biomedical Imaging, ISBI 2020
Y2 - 3 April 2020 through 7 April 2020
ER -