Author name cluster

Hui Ding

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ECAI Conference 2024 Conference Paper

Sinogram-Image Dual-Domain Network for Robust Metal Artifact Reduction in CT Image

Chong Liu
Yuhan Huang
Bo Li
Hui Ding

Computed tomography (CT) utilizes X-ray technology for internal body imaging. However, the presence of metal objects often results in artifacts due to their significant absorption and scattering of X-rays, thus obstructing lesion diagnosis, especially in the presence of multiple metals. Existing artifact reduction methods often suffer from deficiencies in completeness and preservation of fine detail. To address this limitation, we propose a novel sinogram and image dual-domain network. Specifically, in the sinogram domain, two enhancement modules are designed: one for extracting information from regions affected by metal traces, and the other for learning to restore the sinogram corresponding to these metal traces. Subsequently, utilizing filtered back projection (FBP), artifact removal images are reconstructed in the image domain. Quantitative and qualitative analyses of synthetic images show our framework’s superiority over conventional Metal Artifact Reduction (MAR) methods in both synthetic and clinical settings.

Details

AAAI Conference 2018 Conference Paper

A Deep Cascade Network for Unaligned Face Attribute Classification

Hui Ding
Hao Zhou
Shaohua Zhou
Rama Chellappa

Humans focus attention on different face regions when recognizing face attributes. Most existing face attribute classiﬁcation methods use the whole image as input. Moreover, some of these methods rely on ﬁducial landmarks to provide de- ﬁned face parts. In this paper, we propose a cascade network that simultaneously learns to localize face regions speciﬁc to attributes and performs attribute classiﬁcation without alignment. First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) speciﬁc to attributes. Then multiple part-based networks and a whole-image-based network are separately constructed and combined together by the region switch layer and attribute relation layer for ﬁnal attribute classiﬁcation. A multi-net learning method and hint-based model compression is further proposed to get an effective localization model and a compact classiﬁcation model, respectively. Our approach achieves signiﬁcantly better performance than state-of-the-art methods on unaligned CelebA dataset, reducing the classiﬁcation error by 30. 9%.

PDF Details

AAAI Conference 2018 Conference Paper

ExprGAN: Facial Expression Editing With Controllable Expression Intensity

Hui Ding
Kumar Sricharan
Rama Chellappa

Facial expression editing is a challenging task as it needs a high-level semantic understanding of the input face image. In conventional methods, either paired training data is required or the synthetic face’s resolution is low. Moreover, only the categories of facial expression can be changed. To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity. An expression controller module is specially designed to learn an expressive and compact expression code in addition to the encoder-decoder network. This novel architecture enables the expression intensity to be continuously adjusted from low to high. We further show that our ExprGAN can be applied for other tasks, such as expression transfer, image retrieval, and data augmentation for training improved face expression recognition models. To tackle the small size of the training database, an effective incremental learning scheme is proposed. Quantitative and qualitative evaluations on the widely used Oulu-CASIA dataset demonstrate the effectiveness of ExprGAN.

PDF Details

YNIMG Journal 2011 Journal Article

Nanoplatforms for constructing new approaches to cancer treatment, imaging, and drug delivery: What should be the policy?

Babak Kateb
Katherine Chiu
Keith L. Black
Vicky Yamamoto
Bhavraj Khalsa
Julia Y. Ljubimova
Hui Ding
Rameshwar Patil

Nanotechnology is the design and assembly of submicroscopic devices called nanoparticles, which are 1–100 nm in diameter. Nanomedicine is the application of nanotechnology for the diagnosis and treatment of human disease. Disease-specific receptors on the surface of cells provide useful targets for nanoparticles. Because nanoparticles can be engineered from components that (1) recognize disease at the cellular level, (2) are visible on imaging studies, and (3) deliver therapeutic compounds, nanotechnology is well suited for the diagnosis and treatment of a variety of diseases. Nanotechnology will enable earlier detection and treatment of diseases that are best treated in their initial stages, such as cancer. Advances in nanotechnology will also spur the discovery of new methods for delivery of therapeutic compounds, including genes and proteins, to diseased tissue. A myriad of nanostructured drugs with effective site-targeting can be developed by combining a diverse selection of targeting, diagnostic, and therapeutic components. Incorporating immune target specificity with nanostructures introduces a new type of treatment modality, nano-immunochemotherapy, for patients with cancer. In this review, we will discuss the development and potential applications of nanoscale platforms in medical diagnosis and treatment. To impact the care of patients with neurological diseases, advances in nanotechnology will require accelerated translation to the fields of brain mapping, CNS imaging, and nanoneurosurgery. Advances in nanoplatform, nano-imaging, and nano-drug delivery will drive the future development of nanomedicine, personalized medicine, and targeted therapy. We believe that the formation of a science, technology, medicine law–healthcare policy (STML) hub/center, which encourages collaboration among universities, medical centers, US government, industry, patient advocacy groups, charitable foundations, and philanthropists, could significantly facilitate such advancements and contribute to the translation of nanotechnology across medical disciplines.

Details DOI