Ultra-Low Dose CT Image Reconstruction Based on Big Data Priors

Abstract

1 Executive summary This project will develop a dramatically improved approach to low-dose X-ray CT image formation by extracting and using information from a big-data corpus of regular dose CT images. X-Ray Computed Tomography (CT) provides high-resolution images of anatomical structures for diagnosis and management of human diseases and disorders. For example, CT has had a tremendous impact on cancer [1]. CT data are used routinely to help detect abnormal growths, diagnose tumors, plan treatment for radiation oncology, guide biopsy procedures, assess of tumor responses to treatment and monitor for recurrence [2]. CT scans that performed in the emergency department help reduce the frequency of hospitalization or transfer to another facility [1]. The medical importance of CT is evidenced by the dramatic increase in the number of CT scans ordered over the past several decades [3]. CT scans now are responsible for nearly 50% of the radiation exposure from medical imaging in the U.S. [1]. The ionizing radiation in the form of X-rays used in CT scans is energetic enough to directly or indirectly damage DNA, putting patients at a higher risk for radiation-induced cancer [1, 4]. Studies have suggested that current CT usage may be responsible for 1.5%-2% of all cancers in the U.S. [5]. Significantly lowering radiation dosages from CT has become a growing concern both in the public and professional societies. Ultra-low dose CT (ULDCT) scans that still provide the superior image quality could shift the benefits of CT scans further to the benefit side and open up numerous entirely new clinical applications [1]. U.S. Preventive Services Task Force (USPSTF) recommends annual screening for lung cancer with LDCT in highrisk adults which is currently the only recommended screening test [6]. If the dose is further reduced to an ultra-low level, ULDCT screening could be prescribed to a wider population of adults to help with detection and treatment of early-stage lung cancer, and preventing a substantial number of lung cancer-related deaths. ULDCT screening for lung cancer is highly needed in China where lung cancer is the most common cancer and the leading cause of cancer-related death. The death rate of lung cancer patients in China has increased by 465% over the past thirty years. Patients suffering from lung cancer in China could top one million by 2025 [7]. Currently most commercial CT scanners use a technique called filter-back projection (FBP) for image reconstruction. FBP requires high doses of radiation to produce high-quality diagnostic images. FBP produces unacceptable image quality when operating at significantly lowered doses. For example, streak artifacts increase severely as radiation dose is reduced [8]. CT image reconstruction method improvements that could realistically and significantly reduce patient radiation exposure while maintaining high image quality is an important area of research to achieve low dose CT imaging and is highly encouraged by national agencies, such as NIH [1]. CT manufacturers have introduced innovative reconstruction methods to begin reducing radiation doses [9]. Model-based image reconstruction (MBIR) methods, also known as statistical image reconstruction methods [10, 11], improve the ability to produce high-quality and accurate images, while greatly reducing patient exposure to potentially harmful lev-

1 Figure or Table

Cite this paper

@inproceedings{Fessler2015UltraLowDC, title={Ultra-Low Dose CT Image Reconstruction Based on Big Data Priors}, author={Jeffrey A. Fessler and Yong Long}, year={2015} }