Research

The evolution of civilization is driven by the need for extending our capabilities. A most important way for us to sense the world is by vision. Biomedical imaging systems outperform our natural vision and become indispensible “eyes” in the fields of biology and medicine. A fascinating puzzle in history was how to achieve “an inner vision” of opaque objects. X-ray computed tomography (CT) is the first imaging modality to enable non-destructive sectional or volumetric image reconstruction of an object from x-ray shadows. Since the introduction of x-ray CT, biomedical imaging technology has been under rapid development for predictive, preventive and personalized medicine and should dramatically improve our longevity and quality of life. Our currently funded projects target x-ray CT and optical molecular tomography, multimodality and emerging possibilities.

Learn More

Translational research is transforming the way science has operated for decades, bridging the gaps that separate basic scientists and clinical researchers. To improve human health, scientific discoveries must be translated into practical applications. Such discoveries typically begin at “the bench” with basic research, in which scientists study disease at a molecular or cellular level, and then progress to the clinical level, or the patient’s “bedside”.

Optical imaging technologies, which exploit the physics of optical propagation in tissue, add many important advantages to the imaging options currently available to physicians and researchers.

Learn More

Multimodality imaging systems such as positron emission tomography-computed tomography (PET-CT) and MRI-PET are widely available, but a simultaneous CT-MRI instrument has not been developed. Synergies between independent modalities, e.g., CT, MRI, and PET/SPECT can be realized with image registration, but such postprocessing suffers from registration errors that can be avoided with synchronized data acquisition. The clinical potential of simultaneous CT-MRI is significant, especially in cardiovascular and oncologic applications where studies of the vulnerable plaque, response to cancer therapy, and kinetic and dynamic mechanisms of targeted agents are limited by current imaging technologies. Also, CT-MRI may guide radiation therapy and robotic surgery. For more details, please click our vision 20/20 paper on simultaneous CT-MRI.

Read full article

Computer vision and image analysis are great examples of machine learning, especially deep learning. While computer vision and image analysis deal with existing images and produce features of these images (images to features), tomographic image reconstruction produces images of internal structures from measurement data, which are various features (attenuated/non-attenuated line integrals, Fourier/harmonic components, echoed/scattered/transmitted ultrasound signatures, diffused/excited/interfered light signals, and so on) of the underlying images (features to images). Recently, machine learning, especially deep learning, techniques are being actively developed worldwide for tomographic image reconstruction, which has become a new area of research as evidenced by the 20 high-quality papers included in the IEEE Trans. on Medical Imaging special issue published in June 2018, as well as similar publications in other journals and conferences. In addition to well-known analytic and iterative methods for tomographic image reconstruction, machine learning is an emerging approach for image reconstruction, and likewise image reconstruction is a new frontier of machine learning. Please also see our perspective on deep imaging published in IEEE Access in 2016. There are exciting research and application opportunities ahead for smart imaging and precision medicine.

Given unprecedented progresses in the engineering field over the past decade or so, the development of AVATAR is timely to integrate cutting-edge machine learning, auto-driving, medical imaging, robot, computer vision, virtual/mixed reality, high-performance computing, and internet technologies, and change the landscape of the imaging world. This is particularly helpful for cancer screening, diagnosis, and follow-up in underdeveloped countries. We are open to collaborate with those who are interested to address the healthcare needs in low-middle income countries (LMIC).

For more details, please click the following links:

1. The white paper on AVATAR used in an RPI's internal session for brainstorming about potential engineering research centers (ERC);
2. The bilingual blog on AVATAR in Chinese (upper part) and English (lower part) respectively;
3. Our relevant work on how to create a low-cost CT scanner;
4. Our relevant work on how to create a cost-effective yet flexible hybrid x-ray and MR imager (MRX);
5. Those who are interested, please contact Dr. Ge Wang for further discussion.