Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying the predicted type of one or more microorganisms. In one aspect, a system comprises a phase-contrast microscope and a microorganism classification system. The phase-contrast microscope is configured to generate a three-dimensional quantitative phase image of one or more microorganisms. The microorganism classification system is configured to process the three-dimensional quantitative phase image using a neural network to generate a neural network output characterizing the microorganisms, and thereafter identify the predicted type of the microorganisms using the neural network output.

Abstract: A non-label diagnosis apparatus for a hematologic malignancy may include a 3-D refractive index cell imaging unit configured to generate a 3-D refractive index slide image of a blood smear specimen by capturing a 3-D refractive index image in the form of the blood smear specimen in which blood (including a bone-marrow or other body fluids) of a patient has been smeared on a slide glass, an ROI detection unit configured to sample a suspected cell segment in the blood smear specimen based on the 3-D refractive index slide image and to determine, as ROI patches, cells determined as abnormal cells, and a diagnosis unit configured to determine a sub-classification of a cancer cell corresponding to each of the ROI patches using a cancer cell sub-classification determination model constructed based on a deep learning algorithm and to generate hematologic malignancy diagnosis results by gathering sub-classification results of the ROI patches.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying the predicted type of one or more microorganisms. In one aspect, a system comprises a phase-contrast microscope and a microorganism classification system. The phase-contrast microscope is configured to generate a three-dimensional quantitative phase image of one or more microorganisms. The microorganism classification system is configured to process the three-dimensional quantitative phase image using a neural network to generate a neural network output characterizing the microorganisms, and thereafter identify the predicted type of the microorganisms using the neural network output.

Abstract: A non-label diagnosis apparatus for a hematologic malignancy may include a 3-D refractive index cell imaging unit configured to generate a 3-D refractive index slide image of a blood smear specimen by capturing a 3-D refractive index image in the form of the blood smear specimen in which blood (including a bone-marrow or other body fluids) of a patent has been smeared on a slide glass, an ROI detection unit configured to sample a suspected cell segment in the blood smear specimen based on the 3-D refractive index slide image and to determine, as ROI patches, cells determined as abnormal cells, and a diagnosis unit configured to determine a sub-classification of a cancer cell corresponding to each of the ROI patches using a cancer cell sub-classification determination model constructed based on a deep learning algorithm and to generate hematologic malignancy diagnosis results by gathering sub-classification results of the ROI patches.

Abstract: An image interpolation apparatus to interpolate an input image signal having a first resolution into an output image signal having a second resolution according to a predetermined resolution conversion ratio includes a frequency determiner to detect a variation in a frequency of the input image signal to determine a frequency domain that corresponds to the input image signal, a controller to calculate interpolation positions of the input image signal according to the predetermined resolution conversion ratio, a coefficient storage to store interpolation coefficients that correspond to the interpolation positions, an interpolation filter to receive the interpolation coefficients from the coefficient storage and to interpolate the input image signal accordingly, and an interpolation value corrector to correct the output image signal interpolated from the input image signal output from the interpolation filter based on information as to the frequency domain of the input image signal determined by the frequency d

Abstract: A resolution conversion apparatus and method. The apparatus includes an image analysis unit analyzing frequency characteristics of an input image signal, a filter coefficient determination unit setting a filter coefficient according to the frequency characteristics, and a noise shaper unit performing noise shaping with respect to an error generated by quantizing the input image signal, according to the filter coefficient. Accordingly, an image can be naturally realized by performing noise shaping according to characteristics of the input image signal.

Abstract: An image interpolation apparatus to interpolate an input image signal having a first resolution into an output image signal having a second resolution according to a predetermined resolution conversion ratio includes a frequency determiner to detect a variation in a frequency of the input image signal to determine a frequency domain that corresponds to the input image signal, a controller to calculate interpolation positions of the input image signal according to the predetermined resolution conversion ratio, a coefficient storage to store interpolation coefficients that correspond to the interpolation positions, an interpolation filter to receive the interpolation coefficients from the coefficient storage and to interpolate the input image signal accordingly, and an interpolation value corrector to correct the output image signal interpolated from the input image signal output from the interpolation filter based on information as to the frequency domain of the input image signal determined by the frequency d