The whole 3D structure of teeth and oral cavity can be reconstructed using the cone-beam computed tomography (CBCT) as a popular dental imaging technique. However, it has a risk of radiation and requires patients to pay a high cost. This project aims to develop and improve a deep learning models for reconstructing the 3D structure of teeth and oral cavity from a single panoramic dental X-ray image.

Deep learning has been increasingly applied to diagnostic dermatology. However, the absence of standards in dermatologic images as well as diverse artifacts make it difficult to achieve reliable performance, compatibility, and interpretability, and ultimately to have a practical use by clinicians. This project aims to develop and improve a deep learning algorithm for processing and diagnosis of dermatologic images. The state-of-the-arts technologies in deep learning will be exploited to resolve such problems.

As the number of pet owners increase around the world, the industry and market relevant to companion animals are rapidly expanding. While people do not always have enough time to take care of their pets at home, they need better and intelligent healthcare solutions which do not require human intervention.

We are actively developing intelligent pet healthcare solutions based on artificial intelligence (AI) technologies. By jointly analyzing sound and body language as well as scene, a pet's action, emotion and needs can be effectively recognized. Our ultimate goal is to develop a robust translator of animal language into human language. To achieve this goal, we have collaborated with animal experts, scientists, trainers, and veterinarians, and currently have developed advanced machine learning algorithms for pet pose estimation from videos which were collected from either smart phones or home security cameras. Such a solution may be beneficial to not only pet owners but also animal trainers and caregivers in zoos, livestock farms, and animal shelters.

Using the state-of-the-arts artificial intelligence (AI) and deep learning technologies, we have actively developed robust data processing pipelines and analyses for analyzing medical images such as magnetic resonance imaging (MRI).