National Central University

Techeverst Co., Ltd.

Hui-Yang Huang

Chung-Wei Lee

Chung-Yi Yang

Hon-Man Liu

Norden E Huang

Pa-Chun Wang

Victoria Y Wang

Meng-Tsung Lo

The present disclosure provides a system for predicting diabetic retinopathy progression. The system includes an image-capturing module and a processing unit. The image-capturing module is configured to capture a first fundus image of a user at a first time and a second fundus image of the user at a second time different from the first time. The processing unit is configured to receive the first fundus image and the second fundus image, compare the first fundus image and the second fundus image and indicate a difference between the first fundus image and the second fundus image. The processing unit is also configured to provide a prediction in a diabetic retinopathy progression of the user based on the difference. A method for predicting diabetic retinopathy progression is also provided in the present disclosure.

System and method for predicting diabetic retinopathy progression

A noninvasive arterial condition detecting system includes a processing device and an electronic stethoscope configured for auscultating carotid artery to receive sound signals. The processing device is connected to the electronic stethoscope. The processing device records the sound signals, preprocesses the sound signal to reduce noise, measures a trough-peak distance and a trough-peak time, and generates an estimate result of arterial conditions according to the trough-peak distance and the trough-peak time. The trough-peak distance and the trough-peak time are related to the health of the carotid artery walls.

Noninvasive arterial condition detecting method, system, and non-transitory computer readable storage medium

The present invention discloses a method for generating a bone mask. The method comprises the following steps: performing a noncontrast computed tomography scan on a subject in axial mode to get a first data set; after the subject injected with a contrast medium, performing a postcontrast computer tomography angiography scanning on the subject in helical mode to get a second data set; reconstructing the two mentioned data set to acquire a first reconstruction image and a second reconstruction image respectively; resampling the first reconstruction image based on the second reconstruction image by using a computer to get a third reconstruction image; and thresholding values of data which are greater than or equal to a scheduled Hounsfield unit in the third reconstruction image to get a bone mask.

Method for generating bone mask

Growing community of inventors

Taipei, Taiwan

Hui-Yang Huang