TY - JOUR
T1 - An adversarial learning approach to medical image synthesis for lesion detection
AU - Sun, Liyan
AU - Wang, Jiexiang
AU - Huang, Yue
AU - Ding, Xinghao
AU - Greenspan, Hayit
AU - Paisley, John
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - The identification of lesion within medical image data is necessary for diagnosis, treatment and prognosis. Segmentation and classification approaches are mainly based on supervised learning with well-paired image-level or voxel-level labels. However, labeling the lesion in medical images is laborious requiring highly specialized knowledge. We propose a medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN) to generate a normal-looking medical image based on its abnormal-looking counterpart without the need for paired training data. Unlike typical GANs, whose aim is to generate realistic samples with variations, our more restrictive model aims at producing a normal-looking image corresponding to one containing lesions, and thus requires a special design. Being able to provide a 'normal' counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments. In the other aspect, the ANT-GAN model is also capable of producing highly realistic lesion-containing image corresponding to the healthy one, which shows the potential in data augmentation verified in our experiments.
AB - The identification of lesion within medical image data is necessary for diagnosis, treatment and prognosis. Segmentation and classification approaches are mainly based on supervised learning with well-paired image-level or voxel-level labels. However, labeling the lesion in medical images is laborious requiring highly specialized knowledge. We propose a medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN) to generate a normal-looking medical image based on its abnormal-looking counterpart without the need for paired training data. Unlike typical GANs, whose aim is to generate realistic samples with variations, our more restrictive model aims at producing a normal-looking image corresponding to one containing lesions, and thus requires a special design. Being able to provide a 'normal' counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments. In the other aspect, the ANT-GAN model is also capable of producing highly realistic lesion-containing image corresponding to the healthy one, which shows the potential in data augmentation verified in our experiments.
KW - Medical image synthesis
KW - generative adversarial network
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85089206502&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2020.2964016
DO - 10.1109/JBHI.2020.2964016
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 31905155
AN - SCOPUS:85089206502
SN - 2168-2194
VL - 24
SP - 2303
EP - 2314
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 8
M1 - 8950113
ER -