Abstract: A semiconductor device, including a base and a semiconductor stack. The semiconductor stack includes a first semiconductor structure located on the base, a second semiconductor structure located on the first semiconductor structure, and an active structure located between the first semiconductor structure and the second semiconductor structure. The active structure includes two confinement layers and a well layer located between the two confinement layers. One of the confinement layers includes Alx1Ga1-x1As, and x1 is equal to or larger than 0.25 and equal to or smaller than 0.4. The well layer includes Inx2Ga1-x2As, and x2 is equal to or larger than 0.25 and equal to or smaller than 0.3. The one of the confinement layers and the well layer respectively have a first thickness in a range of 200 nm to 400 nm and a second thickness in a range of 3 nm to 6 nm.

Abstract: The present invention disclose a medical image-based system for predicting lesion classification and a method thereof. The system comprises a feature data extracting module for providing a raw feature data based on a medical image, and a predicting module for outputting a predicted class and a risk index according to the raw feature data. The predicting module comprises a classification unit for generating the predicted class and a prediction score corresponding thereto according to the raw feature data, and a risk evaluation unit for generating the risk index according to the prediction score. The system provides medical personnels a reference score and a risk index to determine progression of a certain disease.

Abstract: The present invention relates to a method for measuring muscle mass, including: a first selection step, wherein a frame selection information is obtained by using a frame to select a fascia region from a provided computed tomography image under the condition that the window width ranges from 300 HU to 500 HU and the window level ranges from 40 HU to 50 HU, wherein the selected range of the fascia region includes a muscle; and a second selection step, wherein a muscle information of the muscle is obtained by calculating a pixel value in the frame-selected fascia region under the condition that the HU value of the CT image ranges from ?29 HU to 150 HU.

Abstract: An image segmentation method includes the following steps: obtaining a target image; inputting the target image into a machine learning model to obtain an image segmentation parameter value corresponding to the target image; executing an image segmentation algorithm on the target image according to the image segmentation parameter value to obtain an image segmentation result, wherein the image segmentation result is segmenting the target image into object regions; and displaying the image segmentation result. In addition, an electronic device and storage medium using the method are also provided.

Abstract: An interactive image marking method is introduced. The interactive image marking method includes the following steps, displaying a target image and at least one marked region in the target image; receiving an interactive signal, where the interactive signal corresponds to a first pixel of the target image; calculating a correlation between the first pixel and pixels of the target image, and determining a correlation range in the target image according to the correlation; editing the marked region according to the correlate range; and displaying the edited marked region. In addition, an electronic device and a recording medium using the method are also introduced.

Abstract: The present invention discloses a medical image project management platform comprising a project management module and a radiomic feature extracting module. The project management module comprises a multi-module management interface and a labeling unit. An image is input by the multi-module management interface and received by the labeling unit. A first labeled image and a second labeled image are produced thereafter. The radiomic feature extracting module comprises an analysis unit and a feature extracting module. The analysis unit analyzes the first labeled image and gives the first labeled image a first labeling unit. The analysis unit analyzes the second labeled image and gives the second labeled image a second labeling unit. The radiomic feature extracting unit receives the first and the second labeling units and proceeds radiomic computation to output a radiomic feature.

Abstract: The present invention relates to a method for measuring muscle mass, including: a first selection step, wherein a frame selection information is obtained by using a frame to select a fascia region from a provided computed tomography image under the condition that the window width ranges from 300 HU to 500 HU and the window level ranges from 40 HU to 50 HU, wherein the selected range of the fascia region includes a muscle; and a second selection step, wherein a muscle information of the muscle is obtained by calculating a pixel value in the frame-selected fascia region under the condition that the HU value of the CT image ranges from -29 HU to 150 HU.

Abstract: A method for predicting cancer prognosis is disclosed, and the method comprises capturing a reference radiomics and obtaining reference pathological eigenvalues, wherein the reference pathological eigenvalues are based on pathological features of a reference patients, and the pathological features comprise genomic features, gene expression, test values or a combination of two or more thereof. Then, capturing a test radiomics and obtaining test pathological eigenvalues are performed, wherein the test pathological eigenvalues are based on pathological features of a test patients, and the pathological features comprise genomic features, gene expression, test values or a combination of two or more thereof. A mathematical formula is used to calculate a prognostic index based on the aforementioned reference radiomics, reference pathological eigenvalues, test radiomics and test pathological eigenvalues, and the prognostic change risk of the test patient is evaluated according to the prognostic index.

Abstract: The present invention discloses a medical image project management platform comprising a project management module and a radiomic feature extracting module. The project management module comprises a multi-module management interface and a labeling unit. An image is input by the multi-module management interface and received by the labeling unit. A first labeled image and a second labeled image are produced thereafter. The radiomic feature extracting module comprises an analysis unit and a feature extracting module. The analysis unit analyzes the first labeled image and gives the first labeled image a first labeling unit. The analysis unit analyzes the second labeled image and gives the second labeled image a second labeling unit. The radiomic feature extracting unit receives the first and the second labeling units and proceeds radiomic computation to output a radiomic feature.

Abstract: An interactive image marking method is introduced. The interactive image marking method includes the following steps, displaying a target image and at least one marked region in the target image; receiving an interactive signal, where the interactive signal corresponds to a first pixel of the target image; calculating a correlation between the first pixel and pixels of the target image, and determining a correlation range in the target image according to the correlation; editing the marked region according to the correlate range; and displaying the edited marked region. In addition, an electronic device and a recording medium using the method are also introduced.

Abstract: An image segmentation method includes the following steps: obtaining a target image; inputting the target image into a machine learning model to obtain an image segmentation parameter value corresponding to the target image; executing an image segmentation algorithm on the target image according to the image segmentation parameter value to obtain an image segmentation result, wherein the image segmentation result is segmenting the target image into object regions; and displaying the image segmentation result. In addition, an electronic device and storage medium using the method are also provided.

Abstract: A destructive web thickness measuring system of microdrills includes a computer device, a dual-axis motion platform module, a drill grinding module, a positioning vision module, and a web thickness measuring vision module. When the computer device controls the dual-axis motion platform module to move a microdrill to a first locating position, the computer device performs a positioning procedure according to a first image captured by the positioning vision module, and then performs a grinding procedure, so that the drill grinding module grinds the microdrill to a sectional position to be inspected. When the ground microdrill moves to an image measuring position, the computer device performs an image computing procedure according to a second image captured by the web thickness measuring vision module, so as to obtain a web thickness value. Therefore, the destructive web thickness measuring system of microdrills can automatically measure the web thickness value.