Generative Adversarial Network for Medical Images (MI-GAN)

• Published in: Journal of medical systems Vol. 42; no. 11; pp. 231 - 11
• Main Authors: Iqbal, Talha, Ali, Hazrat
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2018; Springer Nature B.V
• Subjects: Advanced Computational Intelligence and Soft Computing in Medical Imaging; Algorithms; Annotations; Computer vision; Data processing; Datasets; Deep Learning; Diagnostic Techniques, Ophthalmological; Generative adversarial networks; Health Informatics; Health Sciences; Image & Signal Processing; Image analysis; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Learning algorithms; Machine learning; Masks; Medical imaging; Medicine; Medicine & Public Health; Retina; Retina - diagnostic imaging; Retinal images; State of the art; Statistics for Life Sciences; Style transfer; Deep learning; Retinal images; Medical imaging; GAN
• ISSN: 0148-5598; 1573-689X; 1573-689X
• DOI: 10.1007/s10916-018-1072-9

Deep learning algorithms produces state-of-the-art results for different machine learning and computer vision tasks. To perform well on a given task, these algorithms require large dataset for training. However, deep learning algorithms lack generalization and suffer from over-fitting whenever trained on small dataset, especially when one is dealing with medical images. For supervised image analysis in medical imaging, having image data along with their corresponding annotated ground-truths is costly as well as time consuming since annotations of the data is done by medical experts manually. In this paper, we propose a new Generative Adversarial Network for Medical Imaging (MI-GAN). The MI-GAN generates synthetic medical images and their segmented masks, which can then be used for the application of supervised analysis of medical images. Particularly, we present MI-GAN for synthesis of retinal images. The proposed method generates precise segmented images better than the existing techniques. The proposed model achieves a dice coefficient of 0.837 on STARE dataset and 0.832 on DRIVE dataset which is state-of-the-art performance on both the datasets.