Abstract: The present invention discloses a method and a system of vertebral compression fracture detection. The method of vertebral compression fracture detection includes: recombining a plurality of anatomical images captured in at least a spine segment of a target individual into a 3D image; using a multi-planar reconstruction method to reformat the 3D image to obtain at least one sagittal reformatted image; using a classification model to determine whether the sagittal reformatted image covers the middle section of the vertebral column or not; using a vertebral detection method to detect each vertebral body in the sagittal reformatted image covering the middle section of the vertebral column; using a keypoint localization method to localize a plurality of keypoints of each vertebral body which was detected in the sagittal reformatted image; evaluating the compression fracture grade of each vertebral body in the sagittal reformatted image.

Abstract: The medical image recognition method includes the following steps: transmitting an accession number to a recognition module through a prediction unit; receiving an accession number and a human body image by a recognition model, and importing the human body image into a set of neural network models respectively; wherein each of the neural network models outputs at least one recognition result; the recognition module returns the recognition results to the prediction unit, and then the recognition results are stored in database.

Abstract: Systems and methods for programming field programmable gate array (FPGA) devices are provided. A trained model for a deep learning process is obtained and converted to design abstraction (DA) code defining logic block circuits for programming an FPGA device. Each of these logic block circuits represents one of a plurality of modules that executes a processing step between different layers of the deep learning process.

Abstract: Systems with a contouring method are provided for contouring one or more targets that correspond to specific organs and/or tumors in a three-dimensional medical image of a patient using neural networks. The contouring system includes a storage unit, a processing unit, and a plurality of modules that are computer operable. The processing unit is used to obtain the image, and then to generate one or more contouring images using a contouring method. The contouring method includes enhancing image features and improving contouring accuracy using an image preprocessing module, and extracting a plurality of multi-scale image representations and expanding these representations to one or more contouring images using a neural network-based contouring module.

Abstract: The present invention discloses a method and a system of vertebral compression fracture detection. The method of vertebral compression fracture detection includes: recombining a plurality of anatomical images captured in at least a spine segment of a target individual into a 3D image; using a multi-planar reconstruction method to reformat the 3D image to obtain at least one sagittal reformatted image; using a classification model to determine whether the sagittal reformatted image covers the middle section of the vertebral column or not; using a vertebral detection method to detect each vertebral body in the sagittal reformatted image covering the middle section of the vertebral column; using a keypoint localization method to localize a plurality of keypoints of each vertebral body which was detected in the sagittal reformatted image; evaluating the compression fracture grade of each vertebral body in the sagittal reformatted image.

Abstract: The medical image recognition method includes the following steps: transmitting an accession number to a recognition module through a prediction unit; receiving an accession number and a human body image by a recognition model, and importing the human body image into a set of neural network models respectively; wherein each of the neural network models outputs at least one recognition result; the recognition module returns the recognition results to the prediction unit, and then the recognition results are stored in database.

Abstract: Systems and methods for programming field programmable gate array (FPGA) devices are provided. A trained model for a deep learning process is obtained and converted to design abstraction (DA) code defining logic block circuits for programming an FPGA device. Each of these logic block circuits represents one of a plurality of modules that executes a processing step between different layers of the deep learning process.