Abstract: The present specification provides a tissue pathology reading support device and a method therefor, which, with respect to an artificial intelligence model, divide, into a plurality of patches, a slide tissue image for learning that indicates a lesion site if a lesion is present, infer the classification of each of the plurality of patches so as to learn patch classification results, integrate the plurality of patches and the patch classification results so as to infer the classification of the reconstructed slide tissue image, thereby learning slide tissue image classification results, use the trained artificial intelligence model so as to infer the classification of each of the plurality of patches, thereby generating patch classification results, and integrate the plurality of patches and the patch classification results so as to infer the classification of the reconstructed slide tissue image, thereby generating slide tissue image classification results.

Abstract: A method for isolating and/or detecting apolipoproteins from a biological sample by pretreatment with an organic solvent are disclosed. Matrix and internal standard compositions for mass spectrometry of proteins containing ruminant serum are also disclosed. The method, matrix and internal standard compositions not only enable direct quantification of various proteoforms without enzymatic cleavage, but also simple maintenance of the substrate in the sample without removing the target protein by using animal serum as a substrate.

Abstract: The present specification discloses an image diagnosis apparatus using a deep learning model and a method therefor, wherein tissue included in an input medical image is classified as being one of normal and abnormal for a disease by using the trained deep learning model using a weighted loss function in which different weights are assigned to a probability distribution of determining that a picture extracted from the input medical image is abnormal even though it is normal and a probability distribution of determining that the picture is normal even though it is abnormal.

Abstract: A method for isolating proteins from prokaryotes is disclose. The method enables easy break down of bacterial cell walls to obtain intact proteins without damage by a simple process of adding organic solvents including lower alcohols or nitrile derivatives; or applying osmotic stimulation to samples containing pathogenic bacteria or the like. The method may be usefully applied to rapid and accurate identification of periplasmic proteins of gram-negative bacteria without additional purification process.

Abstract: The present invention relates to a method for detecting a pathogenic strain having resistance to carbapenem antibiotics in a biological sample. According to the present invention, it is possible to directly identify carbapenemases, specifically KPC, OXA, NDM, IMP, VIM and/or GES protein, by mass spectrometry, thereby making it possible to quickly determine not only whether a pathogenic strain has resistance to antibiotics, but also the type of protein involved in the resistance. According to the present invention, the physical and chemical properties of each carbapenemase in vivo, such as the unique N-terminal truncation length, methionine residue oxidation and disulfide bond formation in each type of carbapenemase, are identified and are reflected on reference mass values.

Abstract: The present invention relates to a method for detecting a pathogenic strain having resistance to ?-lactam antibiotics in a biological sample, and a method for identifying a protein involved in resistance in ?-lactam antibiotics, which is contained in a biological sample. According to the present invention, it is possible to quickly and accurately determine not only whether a pathogenic strain has resistance to antibiotics, but also the type of protein involved in the resistance, by directly identifying an extended spectrum ?-lactamase (ESBL) protein with a truncated N-terminus through mass spectrometry. Accordingly, the present invention can be effectively utilized to quickly establish an appropriate antibiotic administration strategy at the initial stage of infection.

Abstract: The present specification discloses an image diagnosis apparatus using a deep learning model and a method therefor, wherein tissue included in an input medical image is classified as being one of normal and abnormal for a disease by using the trained deep learning model using a weighted loss function in which different weights are assigned to a probability distribution of determining that a picture extracted from the input medical image is abnormal even though it is normal and a probability distribution of determining that the picture is normal even though it is abnormal.