Abstract: Some embodiments of the disclosure provide an artificial neural network system for recognizing a lesion in a fundus image. The system includes a pre-processing module configured to pre-process a target fundus image and a reference fundus image taken from one person separately, a first neural network (12) configured to generate a first advanced feature set from the target fundus image, a second neural network (22) configured to generate a second advanced feature set from the reference fundus image, a feature combination module (13) configured to combine the first advanced feature set and the second advanced feature set to form a feature combination set, and a third neural network (14) configured to generate, according to the feature combination set, a judgmental result of lesions.

Abstract: A scleral lens with a fenestration and pockets. One fenestration or a plurality of annularly-distributed fenestrations are provided in an optic zone of the scleral lens; and two or more pockets are provided in a pocket annular zone on a posterior surface of the optic zone. The pockets are configured to trap gas bubbles near the fenestration, where the fenestration is located radially outward from the pocket annular zone and not located in a transition zone of the scleral lens, and the transition zone is configured to be located above the limbus of the eyeball during wearing of the scleral lens. The lens of the present invention will not be adsorbed to the cornea and can be worn comfortably and maintain clear visual acuity for up to 12 hours.

Abstract: The present invention provides a scleral lens with a fenestration and pockets. One fenestration or a plurality of annularly-distributed fenestrations are provided in an optic zone of the scleral lens; and two or more pockets are provided in a pocket annular zone on a posterior surface of the optic zone. The pockets are configured to trap gas bubbles near the fenestration, where the fenestration is located radially outward from the pocket annular zone and not located in a transition zone of the scleral lens, and the transition zone is configured to be located above the limbus of the eyeball during wearing of the scleral lens. The lens of the present invention will not be adsorbed to the cornea, and can be worn comfortably and maintain clear visual acuity for up to 12 hours.

Abstract: The present invention provides a scleral lens with a fenestration and pockets. One fenestration or a plurality of annularly-distributed fenestrations are provided in an optic zone of the scleral lens; and two or more pockets are provided in a pocket annular zone on a posterior surface of the optic zone. The pockets are configured to trap gas bubbles near the fenestration, where the fenestration is located radially outward from the pocket annular zone and not located in a transition zone of the scleral lens, and the transition zone is configured to be located above the limbus of the eyeball during wearing of the scleral lens. The lens of the present invention will not be adsorbed to the cornea, and can be worn comfortably and maintain clear visual acuity for up to 12 hours.

Abstract: A cross-clock-domain processing circuit configured to implement data processing between asynchronous clock domains with a relatively low latency. The cross-clock-domain processing circuit includes a jitter filtering circuit and a synchronization circuit. The jitter filtering circuit is configured to: perform jitter filtering on a clock recovered from input data; adjust a jitter-filtered clock phase; and output a processed input data clock as an output data clock to the synchronization circuit. The synchronization circuit is configured to perform cross-clock-domain synchronization on the input data based on the input data clock and the output data clock.

Abstract: Some embodiments of the disclosure provide an artificial neural network system for recognizing a lesion in a fundus image. The system includes a pre-processing module configured to pre-process a target fundus image and a reference fundus image taken from one person separately, a first neural network (12) configured to generate a first advanced feature set from the target fundus image, a second neural network (22) configured to generate a second advanced feature set from the reference fundus image, a feature combination module (13) configured to combine the first advanced feature set and the second advanced feature set to form a feature combination set, and a third neural network (14) configured to generate, according to the feature combination set, a judgmental result of lesions.

Abstract: Some embodiments of the disclosure provide a diabetic retinopathy recognition system (S) based on fundus image. According to an embodiment, the system includes an image acquisition apparatus (1) configured to collect fundus images. The fundus images include target fundus images and reference fundus images taken from a person. The system further includes an automatic recognition apparatus (2) configured to process the fundus images from the image acquisition apparatus by using a deep learning method. The automatic recognition apparatus automatically determines whether a fundus image has a lesion and outputs the diagnostic result. According to another embodiment, the diabetic retinopathy recognition system (S) utilizes a deep learning method to automatically determine the fundus images and output the diagnostic result.

Abstract: The present disclosure provides an artificial neural network system for identifying a lesion in a retinal fundus image that comprises a pre-processing module configured to separately pre-process a target retinal fundus image and a reference retinal fundus image taken from a same person; a first neural network (12) configured to generate a first advanced feature set from the target retinal fundus image; a second neural network (22) configured to generate a second advanced feature set from the reference retinal fundus image; a feature combination module (13) configured to combine the first advanced feature set and the second advanced feature set to form a feature combination set; and a third neural network (14) configured to generate, according to the feature combination set, a diagnosis result.

Abstract: Some embodiments of the disclosure provide a diabetic retinopathy recognition system (S) based on fundus image. According to an embodiment, the system includes an image acquisition apparatus (1) configured to collect fundus images. The fundus images include target fundus images and reference fundus images taken from a person. The system further includes an automatic recognition apparatus (2) configured to process the fundus images from the image acquisition apparatus by using a deep learning method. The automatic recognition apparatus automatically determines whether a fundus image has a lesion and outputs the diagnostic result. According to another embodiment, the diabetic retinopathy recognition system (S) utilizes a deep learning method to automatically determine the fundus images and output the diagnostic result.

Abstract: A cross-clock-domain processing circuit configured to implement data processing between asynchronous clock domains with a relatively low latency. The cross-clock-domain processing circuit includes a jitter filtering circuit and a synchronization circuit. The jitter filtering circuit is configured to: perform jitter filtering on a clock recovered from input data; adjust a jitter-filtered clock phase; and output a processed input data clock as an output data clock to the synchronization circuit. The synchronization circuit is configured to perform cross-clock-domain synchronization on the input data based on the input data clock and the output data clock.

Abstract: A method and an apparatus for creating a desktop widget. The method includes acquiring a desktop widget framework of a desktop widget. The desktop widget framework is used to hold at least two desktop widget units, and the desktop widget framework includes at least two desktop widget configuration areas. The method further includes controlling, according to a first movement operation performed on a first desktop widget unit, the first desktop widget unit to move along a movement track of the first movement operation. The first movement operation is used to move the first desktop widget unit. The method further includes positioning the first desktop widget unit in a first specified desktop widget configuration area when the first movement operation ends.

Abstract: Some embodiments of the disclosure provide a diabetic retinopathy recognition system (S) based on fundus image. According to an embodiment, the system includes an image acquisition apparatus (1) configured to collect fundus images. The fundus images include target fundus images and reference fundus images taken from a person. The system further includes an automatic recognition apparatus (2) configured to process the fundus images from the image acquisition apparatus by using a deep learning method. The automatic recognition apparatus automatically determines whether a fundus image has a lesion and outputs the diagnostic result. According to another embodiment, the diabetic retinopathy recognition system (S) utilizes a deep learning method to automatically determine the fundus images and output the diagnostic result.

Abstract: The present disclosure provides an artificial neural network system for identifying a lesion in a retinal fundus image that comprises a pre-processing module configured to separately pre-process a target retinal fundus image and a reference retinal fundus image taken from a same person; a first neural network (12) configured to generate a first advanced feature set from the target retinal fundus image; a second neural network (22) configured to generate a second advanced feature set from the reference retinal fundus image; a feature combination module (13) configured to combine the first advanced feature set and the second advanced feature set to form a feature combination set; and a third neural network (14) configured to generate, according to the feature combination set, a diagnosis result.

Abstract: A method and an apparatus for creating a desktop widget. The method includes acquiring a desktop widget framework of a desktop widget. The desktop widget framework is used to hold at least two desktop widget units, and the desktop widget framework includes at least two desktop widget configuration areas. The method further includes controlling, according to a first movement operation performed on a first desktop widget unit, the first desktop widget unit to move along a movement track of the first movement operation. The first movement operation is used to move the first desktop widget unit. The method further includes positioning the first desktop widget unit in a first specified desktop widget configuration area when the first movement operation ends.

Abstract: A method and an apparatus for creating a desktop widget are provided that pertain to the terminal device field. The method includes acquiring a desktop widget framework of a desktop widget, where the desktop widget framework is used to hold at least two desktop widget units, and the desktop widget framework includes at least two desktop widget configuration areas; controlling, according to a first movement operation performed on a first desktop widget unit, the first desktop widget unit to move along a movement track of the first movement operation, where the first movement operation is used to move the first desktop widget unit; and positioning the first desktop widget unit in a first specified desktop widget configuration area when the first movement operation ends. The present invention achieves a purpose of implementing multiple Widgets in one desktop widget framework, which improves personalization of terminal device configuration.