Abstract: An acute kidney injury predicting system and a method thereof are proposed. A processor reads the data to be tested, the detection data, the machine learning algorithm and the risk probability comparison table from a main memory. The processor trains the detection data according to the machine learning algorithm to generate an acute kidney injury prediction model, and inputs the data to be tested into the acute kidney injury prediction model to generate an acute kidney injury characteristic risk probability and a data sequence table. The data sequence table lists the data to be tested in sequence according to a proportion of each of the data to be tested in the acute kidney injury characteristics. The processor selects one of the medical treatment data from the risk probability comparison table according to the acute kidney injury characteristic risk probability.

Abstract: A method for designing a bone plate to be used in an orthopedic surgery and to be placed on a bone structure includes: constructing a three-dimensional (3D) model of the bone structure; controlling a display screen to display an image that corresponds with the 3D model; in response to a plurality of designated points inputted on the image, calculating a plurality of sets of 3D coordinates respectively for the plurality of designated points, and generating an extension route based on the plurality of sets of 3D coordinates; and generating a 3D model of the bone plate based on the extension route and at least one pre-stored bone plate template.

Abstract: A surgical navigation system includes a first tracking unit, a second tracking unit and a processing unit. The first tracking unit captures a first infrared image of a position identification unit that includes a reference target fixed on a patient and an instrument target disposed on a surgical instrument. The second tracking unit captures a second infrared image of the position identification unit. The processing unit performs image recognition on the first and second infrared images with respect to the position identification unit, and uses, based on a result of the image recognition, a pathological image and one of the first and second infrared images to generate an augmented reality image. When both the first and second images have both the reference target and the instrument target, one of the first image and the second image with a higher accuracy is used to generate the augmented reality image.

Abstract: A surgery system includes a contactless control panel, an infrared camera, a computer and a display. The contactless control panel includes control areas which are arranged in a predetermined pattern and are coated with infrared reflective material to reflect infrared radiation. The infrared camera captures an infrared image of the control areas. The computer performs image recognition on the infrared image, determines, based on the predetermined pattern stored in advance and a result of the image recognition, which one of the control areas is masked, and generates a device control signal based on a function corresponding to the one of the control areas that is determined to be masked. The display device displays images based on the device control signal.

Abstract: A stereoscopic visualization system using shape from shading algorithm is an image conversion device connected between a monoscopic endoscope and a 3D monitor. The system applies the algorithm which generates a depth map for a 2D image of video frames. The algorithm first calculates a direction of a light source for the 2D image. Based upon the information of light distribution and shading for the 2D image, the depth map is generated. The depth map is used to calculate another view of the original 2D image by depth image based rendering algorithm in generation of stereoscopic images. After the new view is rendered, the stereoscopic visualization system also needs to convert the display format of the stereoscopic images for different kinds of 3D displays. Based on this method, it can replace the whole monoscopic endoscope with a stereo-endoscope system and no modification is required for the monoscopic endoscope.

Abstract: A surgical position calibration method for getting the augmented and mixed reality of a surgical instrument includes the following steps: placing a calibration plate under a C-ARM to take C-ARM images, with the calibration plate provided with geometric patterns; inputting the C-ARM images into a computer to make 2D image maps; finding the center point of each geometric pattern on the calibration plate; defining a first reference calibration point; finding the distance between the center point of each other geometric pattern and the first reference calibration point to set up a translation matrix formula to form a 3D space image map; placing a surgical instrument at any position above the calibration plate; using the translation matrix formula generating a spatial variation image for the displacement of the surgical instrument; and forming a new spatial variation image.

Abstract: An active calibration device is provided for obtaining parameters that are used to calibrate information contained in images captured by an infrared camera device. The active calibration device includes a base having at least one mounting surface; and a plurality of infrared (IR) light emitting components disposed on the mounting surface of the base. The IR light emitting components are arranged to form a predetermined pattern, and are configured to emit infrared light for receipt by a lens of the infrared camera device.

Abstract: A surgical navigation system includes a first tracking unit, a second tracking unit and a processing unit. The first tracking unit captures a first infrared image of a position identification unit that includes a reference target fixed on a patient and an instrument target disposed on a surgical instrument. The second tracking unit captures a second infrared image of the position identification unit. The processing unit performs image recognition on the first and second infrared images with respect to the position identification unit, and uses, based on a result of the image recognition, a pathological image and one of the first and second infrared images to generate an augmented reality image.

Abstract: A method for performing surgical imaging based on mixed reality (MR) includes: obtaining a 3D virtual model of a body part of a subject, the 3D virtual model including a plurality of model reference points; continuously capturing IR images of the body part, including a plurality of IR reference points; calculating a first projection matrix based on the IR images; continuously capturing color images of the body part; calculating a second projection matrix based on the color images; in response to a calibration operation, calculating a third projection matrix; and generating a to-be-projected model using the 3D virtual model and the projection matrices.

Abstract: A surgery system includes a contactless control panel, an infrared camera, a computer and a display. The contactless control panel includes control areas which are arranged in a predetermined pattern and are coated with infrared reflective material to reflect infrared radiation. The infrared camera captures an infrared image of the control areas. The computer performs image recognition on the infrared image, determines, based on the predetermined pattern stored in advance and a result of the image recognition, which one of the control areas is masked, and generates a device control signal based on a function corresponding to the one of the control areas that is determined to be masked. The display device displays images based on the device control signal.

Abstract: An active calibration device is provided for obtaining parameters that are used to calibrate information contained in images captured by an infrared camera device. The active calibration device includes a base having at least one mounting surface; and a plurality of infrared (IR) light emitting components disposed on the mounting surface of the base. The IR light emitting components are arranged to form a predetermined pattern, and are configured to emit infrared light for receipt by a lens of the infrared camera device.

Abstract: An implementation method for operating a surgical instrument using smart surgical glasses for a surgeon to perform an operation on an surgical site with at least one surgical instrument mainly comprises the steps of: the surgeon wearing a smart surgical glasses; using the sensors to sense the position of the surgical instrument held by the surgeon and the position of the surgical site; displaying a picture on a display of the smart surgical glasses, the picture comprising a plurality of sub-blocks; combining the medical image block, the instrument block and the surgical site block to form a mixed reality image; displaying an image of the surgical planning block in the mixed reality image; and the surgeon operating the surgical instrument according to the image of the surgical planning block.

Abstract: The invention discloses an object developing and calibrating method in a surgical environment. The method mainly includes the steps of: using at least one infrared LED (IR-LED) and at least one infrared sensor (IR-Sensor) on a surgical eyeglass, to have a surgical environment image; and retaining image signals within a first wavelength range and removing image signals not in the first wavelength range in the surgical environment image. The method helps the surgeon see only the object images on the surgical eyeglass without the interference of non-surgical environmental imaging noises.

Abstract: A stereoscopic visualization system using shape from shading algorithm is an image conversion device connected between a monoscopic endoscope and a 3D monitor. The system applies the algorithm which generates a depth map for a 2D image of video frames. The algorithm first calculates a direction of a light source for the 2D image. Based upon the information of light distribution and shading for the 2D image, the depth map is generated. The depth map is used to calculate another view of the original 2D image by depth image based rendering algorithm in generation of stereoscopic images. After the new view is rendered, the stereoscopic visualization system also needs to convert the display format of the stereoscopic images for different kinds of 3D displays. Based on this method, it can replace the whole monoscopic endoscope with a stereo-endoscope system and no modification is required for the monoscopic endoscope.

Abstract: The invention discloses an object developing and calibrating method in a surgical environment. The method mainly includes the steps of: using at least one infrared LED (IR-LED) and at least one infrared sensor (IR-Sensor) on a surgical eyeglass, to have a surgical environment image; and retaining image signals within a first wavelength range and removing image signals not in the first wavelength range in the surgical environment image. The method helps the surgeon see only the object images on the surgical eyeglass without the interference of non-surgical environmental imaging noises.

Abstract: A surgical position calibration method for getting the augmented and mixed reality of a surgical instrument includes the following steps: placing a calibration plate under a C-ARM to take C-ARM images, with the calibration plate provided with geometric patterns; inputting the C-ARM images into a computer to make 2D image maps; finding the center point of each geometric pattern on the calibration plate; defining a first reference calibration point; finding the distance between the center point of each other geometric pattern and the first reference calibration point to set up a translation matrix formula to form a 3D space image map; placing a surgical instrument at any position above the calibration plate; using the translation matrix formula generating a spatial variation image for the displacement of the surgical instrument; and forming a new spatial variation image.

Abstract: This present invention discloses an image guided augmented reality method, comprising the following steps of: obtaining a first conversion matrix of a camera and a marked point; obtaining a second conversion matrix of the eye and the camera; linking the first conversion matrix and the second conversion matrix to obtain a correct position corresponding matrix of the eye to the marked point; and linking the correct position corresponding matrix to a position feature of the marked point to obtain the correct position of the eye to the marked point. The present invention also discloses a surgical navigation method of wearable glasses, used for obtaining the correct position of the operator's eye to the marked point.

Abstract: Using the surgical instrument guidance system of the present invention, a doctor can instantly obtain a real field of view of a surgical site of a patient, a three-dimensional medical image that coincides with a surgical site of the patient, and a real-time positional relationship between the surgical instrument and the surgical site of the patient. The surgical instrument guidance system provides an entrance guiding interface, an angle guiding interface and a depth guiding interface to help the surgeon monitor whether the position relationship between the surgical instrument and the patient's surgical site conforms to the preoperative planning and specifically increases the accuracy of position, angle and depth of the surgical instrument on the surgical site of the patient.

Abstract: This present invention discloses an image guided augmented reality method, comprising the following steps of: obtaining a first conversion matrix of a camera and a marked point; obtaining a second conversion matrix of the eye and the camera; linking the first conversion matrix and the second conversion matrix to obtain a correct position corresponding matrix of the eye to the marked point; and linking the correct position corresponding matrix to a position feature of the marked point to obtain the correct position of the eye to the marked point. The present invention also discloses a surgical navigation method of wearable glasses, used for obtaining the correct position of the operator's eye to the marked point.