Cone beam CT (CBCT) imaging is becoming an indispensable tool in image guided interventions and many other clinical applications. The data processing method in current CBCT imaging is, however, deficient in multiple aspects, which often leads to severe artifacts and results in high imaging dose to the patients. The poor image quality causes much uncertainty in clinical decision-making and seriously impedes the maximal utilization of the technology. This project is directed at developing CBCT into a clinically accurate and reliable technique for delineation of tumor target, interventional guidance and radiation therapy treatment planning. In response to NIH PAR-09-218, we have assembled a team of investigators comprised of leaders in the fields of radiation oncology, medical physics, image and signal processing, optimization and applied mathematics and established research themes and projects that unify the common interests and expertise of these investigators. We draw on our extensive experience in CBCT imaging and scientific computing to develop the next generation of artifact-free and ultra-low dose CBCT. A number of innovative strategies to dealing with sparse, noisy, and missing data in CBCT imaging will be established.
Specific aims are: (1) To achieve ultra-low dose CBCT by utilization of patient-specific prior data and compressed sensing;(2) to develop a divide-and-conquer approach for metal artifact removal in CBCT reconstruction;and (3) to obtain motion artifact-free images by effective use of inter-phase correlation of the projections. Successful completion of this project will provide high quality CBCT images with orders of magnitude less imaging dose. For image guided radiation therapy, the improved image quality will make accurate CBCT-based dose calculation and replanning possible, which will lay the foundation for next generation of adaptive therapy to optimally compensate for the patient setup error and inter- fractional anatomy change. With the reduction in imaging dose, the proposed technique will significantly reduce the risk of radiation-induced secondary cancers and contribute to the safe and efficient use of volumetric X-ray imaging techniques in routine clinical practice.
Cone beam CT (CBCT) imaging is becoming an indispensable tool in image guided interventions and many other clinical applications. The computing method used in the current CBCT imaging is, however, deficient in many aspects, which often leads to severe artifacts and results in high imaging dose to the patients. This project is directed at developing CBCT into a clinically accurate and reliable technique for delineation of tumor target, interventional guidance and radiation therapy treatment planning. Successful completion of this project will provide a new CBCT paradigm with ultra-low dose and free of artifacts.
|Ibragimov, Bulat; Toesca, Diego; Chang, Daniel et al. (2018) Development of deep neural network for individualized hepatobiliary toxicity prediction after liver SBRT. Med Phys 45:4763-4774|
|Naczynski, Dominik Jan; Stafford, Jason H; Türkcan, Silvan et al. (2018) Rare-Earth-Doped Nanoparticles for Short-Wave Infrared Fluorescence Bioimaging and Molecular Targeting of ?V?3-Expressing Tumors. Mol Imaging 17:1536012118799131|
|Mo?nik, Domen; Ibragimov, Bulat; Xing, Lei et al. (2018) Segmentation of parotid glands from registered CT and MR images. Phys Med 52:33-41|
|King, Martin; Sensakovic, William F; Maxim, Peter et al. (2018) Line-Enhanced Deformable Registration of Pulmonary Computed Tomography Images Before and After Radiation Therapy With Radiation-Induced Fibrosis. Technol Cancer Res Treat 17:1533034617749419|
|Xing, Lei; Krupinski, Elizabeth A; Cai, Jing (2018) Artificial intelligence will soon change the landscape of medical physics research and practice. Med Phys 45:1791-1793|
|Qin, Wenjian; Wu, Jia; Han, Fei et al. (2018) Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation. Phys Med Biol 63:095017|
|Zhao, Wei; Xing, Lei; Zhang, Qiude et al. (2017) Segmentation-free x-ray energy spectrum estimation for computed tomography using dual-energy material decomposition. J Med Imaging (Bellingham) 4:023506|
|Ibragimov, Bulat; Xing, Lei (2017) Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks. Med Phys 44:547-557|
|Zhang, Guanglei; Liu, Fei; Liu, Jie et al. (2017) Cone Beam X-ray Luminescence Computed Tomography Based on Bayesian Method. IEEE Trans Med Imaging 36:225-235|
|Ibragimov, Bulat; Toesca, Diego; Chang, Daniel et al. (2017) Combining deep learning with anatomical analysis for segmentation of the portal vein for liver SBRT planning. Phys Med Biol 62:8943-8958|
Showing the most recent 10 out of 34 publications