摘要:
In the context of the early detection and monitoring of eye diseases, such as glaucoma and diabetic retinopathy, the use of optical coherence tomography presents the difficulty, with respect to blood vessel segmentation, of weak visibility of vessel pattern in the OCT fundus image. To address this problem, a boosting learning approach uses three-dimensional (3D) information to effect automated segmentation of retinal blood vessels. The automated blood vessel segmentation technique described herein is based on 3D spectral domain OCT and provides accurate vessel pattern for clinical analysis, for retinal image registration, and for early diagnosis and monitoring of the progression of glaucoma and other retinal diseases. The technique employs a machine learning algorithm to identify blood vessel automatically in 3D OCT image, in a manner that does not rely on retinal layer segmentation.
摘要:
In the context of the early detection and monitoring of eye diseases, such as glaucoma and diabetic retinopathy, the use of optical coherence tomography presents the difficulty, with respect to blood vessel segmentation, of weak visibility of vessel pattern in the OCT fundus image. To address this problem, a boosting learning approach uses three-dimensional (3D) information to effect automated segmentation of retinal blood vessels. The automated blood vessel segmentation technique described herein is based on 3D spectral domain OCT and provides accurate vessel pattern for clinical analysis, for retinal image registration, and for early diagnosis and monitoring of the progression of glaucoma and other retinal diseases. The technique employs a machine learning algorithm to identify blood vessel automatically in 3D OCT image, in a manner that does not rely on retinal layer segmentation.
摘要:
A fully automated optic nerve head assessment system, based on spectral domain optical coherence tomography, provides essential disc parameters for clinical analysis, early detection, and monitoring of progression.
摘要:
A fully automated optic nerve head assessment system, based on spectral domain optical coherence tomography, provides essential disc parameters for clinical analysis, early detection, and monitoring of progression.
摘要:
Search queries for images are received from users. An original order of responsive images to the query is determined. Duplicate images and words associated with the duplicate images are identified for each of the responsive images. Common words associated with the duplicate images are identified. The responsive images are annotated with the common words and an annotated order is determined. A re-ranked order is determined based on the original order and the annotated order. Responsive images are presented to the user in the re-ranked order.
摘要:
An energy storage system for balancing the load of a power grid, said energy storage system comprising: a controller; a plurality of energy storage tanks connected in parallel; and a plurality of controllable switches connected to the plurality of energy storage tanks, wherein the controller is configured to detect a frequency and a phase of the power grid, and to balance the load of the power grid based on the frequency and the phase of the power grid, by controlling the plurality of controllable switches to charge the plurality of energy storage tanks using power from the power grid or to input power from the plurality of energy storage tanks to the power grid.
摘要:
A pressing mechanism is adapted for use in an image shake suppressing optical device that includes a driving unit and an image capturing unit. The pressing mechanism is adapted to be disposed between the driving unit and the image capturing unit, and includes an arm body and a press head unit. The arm body has a driven end that is adapted to be connected to the driving unit, and a connecting end that is opposite to the driven end. The press head unit is adapted to be disposed between the connecting end of the arm body and the image capturing unit, and is adapted for providing a resilient pressing force on the image capturing unit when the driven end of the arm body is driven by the driving unit to move the connecting end in a pressing direction.
摘要:
A support bracket includes at least three supporting rods, a middle rod, at least three first connecting rods and at least three second connecting rods. For each supporting rod, one end of it is configured to be supported on a supporting surface, the other end of it is configured to support a campfire assembly. One end of the middle rod is provided with a first pivot, and the other end of the middle rod is provided with a second pivot. For each first connecting rods, one end of it is pivotably connected to corresponding one of the at least three supporting rods, the other end of it is pivotably connected to the first pivot. For each second connecting rods, one end of it is pivotably connected to corresponding one of the at least three supporting rods, the other end of it is pivotably connected to the second pivot.