Abstract: Systems and methods for post processing cardiac magnetic resonance images are described that utilize a machine-learning algorithm. Embodiments of the systems and methods maximize physician and technologist efficiency by minimizing the necessary manual labor that is required to post-process medical images through smart-automation, thereby improving consistency and reproducibility of post-processing results by minimizing operator bias.

Abstract: Systems and methods for post processing cardiac magnetic resonance images are described that utilize a machine-learning algorithm. Embodiments of the systems and methods maximize physician and technologist efficiency by minimizing the necessary manual labor that is required to post-process medical images through smart-automation, thereby improving consistency and reproducibility of post-processing results by minimizing operator bias.

Abstract: A method uses a computer and software to measure bone density and structure of the proximal femur of the hip from a volumetric set of images containing pixels representing x-ray attenuation of the subject which are acquired with three-dimensional X-ray imaging devices. The method automatically locates anatomical markers of the hip without operator interaction, automatically positions regions of interest (ROIs) for measurement, automatically determines bone density measures of the ROIs, and automatically reports the results for individual subjects. Bone density measurements of ROIs include the integral bone of the total hip and neck as well as trabecular bone. The method automatically identifies a three-dimensional region-of-interest (ROI) volume which includes the hip, determines a three-dimensional coordinate system referenced to the anatomy of the subject, analyzes the ROI volume to identify voxels in the volume which satisfy defined criteria, and determines a measure of bone structure.

Abstract: An automated method measures coronary calcium in a living subject using x-ray computed tomography (CT). The method acquires at least one CT image containing voxels representing x-ray attenuation of the subject which may or may not be calibrated. The method of analysis may or may not require operator interactions and includes analyzing the images in a computer to identify the boundaries of the heart. The method further includes identifying the approximate location of at least one coronary artery without operator interaction. The method further includes placing a region-of-interest (ROI) surrounding the artery location automatically. The method further includes analyzing the ROI to identify voxels above a threshold value. The method further includes determining the calcium content in mass units.

Abstract: A method automatically segments the heart and abdominal aorta from volumetric images without the need to inject iodine contrast media into the subject. The method automatically quantifies arterial plaque (hard plaque, soft plaque or both) in the cardiovascular system. Plaque definitions include subject specific in vivo blood/muscle density measurements, subject specific voxel statistical parameters and 2-D and 3-D voxel connectivity criteria, which are used to automatically identify the plaques. The locations and outlines of the major arteries are determined in a 3-D coordinate system and the specific coordinates of the detected plaques are displayed in a plaque map for follow-up exams or ease in plaque review and reporting the results.

Abstract: A method automatically scores calcium in the aorta and other arteries of the body using calcium plaque definitions that include subject specific in vivo blood/muscle density measurements, subject specific voxel statistical parameters and 2D and 3D voxel connectivity criteria to automatically identify the plaques. The images are optionally calibrated with external phantoms or internal reference tissue. Aortic calcium is identified automatically without manual marking. Potential false plaques from bone are automatically excluded. A 3D coordinate system provides the specific coordinates of the detected plaques, which are displayed in a plaque map for follow-up exams or ease in plaque review.

Abstract: A method automatically detects and quantifies arterial plaque (hard plaque, soft plaque or both) in the coronary arteries of the heart from CT images. The method uses plaque definitions based on subject specific in vivo blood/muscle and fat density measurements, subject specific voxel statistical parameters and 2-D and 3-D voxel connectivity criteria to automatically identify the plaques. The locations of the major arteries are determined in a 3-D coordinate system; and the specific coordinates of the detected plaques are displayed in a plaque map for follow-up exams or ease in plaque review, editing and reporting the results.

Abstract: The present invention relates to x-ray analysis apparatus for bone density measurements. Bone Densitometry is the preferred method of diagnosing low bone density such as osteoporosis. The invention is a low cost x-ray bone densitometer capable of measuring bone density in the human body. It is particularly designed to measure the extremities, phalanges, calcaneous or radius, but similar techniques and a modified device could measure in larger body parts. The device can also have application in small animals or animal parts. The use of photodiodes of larger size at fixed locations provides a mechanically positioned Region of Interest (ROI) which reduces software and hardware requirements. The low cost bone densitometer serves as a screening device in primary care physician's offices. The present invention provides a highly automated bone mineral density measurement achieved by simple positioning of the hand, and push button operation.