Craniomaxillofacial Bony Structures Segmentation from MRI with Deep-Supervision Adversarial Learning

Abstract

Automatic segmentation of medical images finds abundant applications in clinical studies. Computed Tomography (CT) imaging plays a critical role in diagnostic and surgical planning of craniomaxillofacial (CMF) surgeries as it shows clear bony structures. However, CT imaging poses radiation risks for the subjects being scanned. Alternatively, Magnetic Resonance Imaging (MRI) is considered to be safe and provides good visualization of the soft tissues, but the bony structures appear invisible from MRI. Therefore, the segmentation of bony structures from MRI is quite challenging. In this paper, we propose a cascaded generative adversarial network with deep-supervision discriminator (Deep-supGAN) for automatic bony structures segmentation. The first block in this architecture is used to generate a high-quality CT image from an MRI, and the second block is used to segment bony structures from MRI and the generated CT image. Different from traditional discriminators, the deep-supervision discriminator distinguishes the generated CT from the ground-truth at different levels of feature maps. For segmentation, the loss is not only concentrated on the voxel level but also on the higher abstract perceptual levels. Experimental results show that the proposed method generates CT images with clearer structural details and also segments the bony structures more accurately compared with the state-of-the-art methods.

When medical images meet generative adversarial network: recent development and research opportunities

“…Differently, [23] used unpaired data, meaning that the MRI and CT images were not from the same patient at the same location, and CycleGAN was used to carry out the conversion between unpaired images. Zhao et al [37] designed a kind of depth supervision cascade GAN, which they applied for automatic segmentation of bone structures. The first module in the network is used to generate high quality CT images from MRI ones, and the second module is used to segment bones from the generated CT images.…”

MRI Intensity Standardization Evaluation Design for Head and Neck Quantitative Imaging Applications

“…where x and f(x) are the original and standardized intensities, respectively, and min(x) and max(x) are the minimum and maximum image intensity values per patient, respectively. This method is widely used among deep learning MRI pipelines [23][24][25][26][27] .…”

Deep Learning in the Biomedical Applications: Recent and Future Status

“…In [311], a novel real-time voxel-to-voxel conditional generative adversarial nets is used for 3D left ventricle segmentation on 3D echocardiography. For automatic bony structures segmentation, a cascaded generative adversarial network with deep-supervision discriminators was used by Zhao et al [312]. In [313], a novel transfer-learning framework using generative adversarial networks is proposed for robust segmentation of different HEp-2 datasets.…”