Med Phys
-
To develop a two-stage three-dimensional (3D) convolutional neural networks (CNNs) for fully automated volumetric segmentation of pancreas on computed tomography (CT) and to further evaluate its performance in the context of intra-reader and inter-reader reliability at full dose and reduced radiation dose CTs on a public dataset. ⋯ A 3D CNN developed on the largest dataset of CTs is accurate for fully automated volumetric pancreas segmentation and is generalizable across a wide range of CT slice thicknesses, radiation dose, and patient gender. This 3D CNN offers a scalable tool to leverage biomarkers from pancreas morphometrics and radiomics for pancreatic diseases including for early pancreatic cancer detection.
-
Parametric imaging using the Patlak model has been shown to provide improved lesion detectability and specificity. The Patlak model requires both tissue time-activity curves (TACs) after equilibrium and knowledge of the input function from the start of injection. Therefore, the conventional dynamic scanning protocol typically starts from the radiotracer injection all the way to equilibrium. In this paper, we propose the use of hybrid population-based and model-based input function estimation and evaluate its use for whole-body Patlak analysis, in order to reduce the total scan time and simplify clinical Patlak parametric imaging protocols. Possible quantitative errors caused by the simplified scanning protocol were also analyzed both theoretically and with the use of clinical data. ⋯ We have proposed a simplified whole-body scanning protocol that utilizes both population-based input function and model-based input function. The error from the population-based function was found to only affect the global scale and the overall quantitative impact can be predicted using our proposed formulas.
-
Quantification of left ventricular (LV) volume, ejection fraction and myocardial mass from multi-slice multi-phase cine MRI requires accurate segmentation of the LV in many images. We propose a stack attention-based convolutional neural network (CNN) approach for fully automatic segmentation from short-axis cine MR images. ⋯ We developed a CNN with a stack attention mechanism to automatically segment the LV chamber and myocardium from the multi-slice short-axis cine MRI. The experimental results demonstrate that the proposed approach exceeds existing state-of-the-art segmentation methods and verify its potential clinical applicability.
-
Computed tomography image reconstruction using truncated or sparsely acquired projection data to reduce radiation dose, iodine volume, and patient motion artifacts has been widely investigated. To continue these efforts, we investigated the use of machine learning-based reconstruction techniques using deep convolutional generative adversarial networks (DCGANs) and evaluated its effect using standard imaging metrics. ⋯ We demonstrated the use of DCGANs for CT-image correction from sparse and truncated simulated projection data, while preserving imaging quality of the fully sampled projection data.
-
Domain classification and analysis of national institutes of health-funded medical physics research.
The American Association of Physicists in Medicine (AAPM) previously developed a research database consisting of the National Institutes of Health (NIH) grants that were awarded to its members. The purpose of this report is to classify these NIH grants into various medical physics subdisciplines and analyze the scope of AAPM member research. ⋯ The percentage of AAPM member grants that included words relating to both imaging and therapy (image-guided therapy grants) increased from 13% (27/207) in 2002 to 27% (79/293) in 2019. The percentage of AAPM member grants utilizing words relating to artificial intelligence increased from 8% in 2002 to 20% in 2019. From 2002 to 2019, AAPM member grants referenced cancer more than all other diseases combined. The majority of AAPM member grants included words relating to clinical research (81% of grants in 2002 and 99% in 2019). When comparing AAPM member with non-AAPM member grants it was found that in 2019 AAPM members held a substantial fraction of all NIH grants that referenced stereotactic radiation therapies (41%), radionuclide therapies (10%), brachytherapies (35%), intensity-modulated radiation therapies (45%), and external beam particle therapies (55%). From 2002 to 2019, the percentage of AAPM membership holding NIH grants decreased for males (3.2% down to 2.3%) and increased for females (0.8% up to 1.3%) CONCLUSIONS: The majority of grants awarded to AAPM members focus on clinical research, which underlies the translational aspect of medical physics and suggests medical physicists are uniquely positioned to help translate new technologies such as artificial intelligence into the clinic. Since 2002, NIH grants awarded to AAPM members have increasingly referenced some form of image-guided therapy, suggesting opportunities for continued innovation of imaging technologies. A substantial fraction of all radiotherapy-related research grants were awarded to AAPM members, emphasizing the important role physicists have in developing radiotherapy-related treatments.