Disease differentiation support method, disease differentiation support apparatus, and disease differentiation support computer program
View Patent ↗Disclosed is a disease differentiation support method for supporting disease differentiation, the disease differentiation support method including: obtaining a first parameter obtained by analyzing an image including a cell contained in a sample collected from a subject; obtaining a second parameter regarding a number of cells contained in the sample; and generating, by using a computer algorithm, differentiation support information for supporting disease differentiation, on the basis of the first parameter and the second parameter.
1. A system comprising:
a cell image analysis apparatus comprising a stage on which a smear preparation, on which a blood sample is smeared, is set, a microscope, and a camera configured to capture images of cells, enlarged by the microscope, in the blood sample smeared on the smear preparation on the stage, the cell image analysis apparatus configured to analyze the images of the cells captured by the camera, and configured to output a first parameter regarding an abnormal finding in the captured cells based on analysis results of the images, wherein the captured cells are contained in the blood sample collected from a subject;
a blood cell counter configured to measure a red blood cell count, a white blood cell count, a platelet count, a hemoglobin concentration, a hematocrit value, red blood cell indices, and white blood cell classification values, the blood cell counter comprising a flow cytometer and an electric resistance-type detector, the blood cell counter configured to analyze at least optical signals from the cells detected by the flow cytometer, and configured to output a second parameter regarding a number of the detected cells based on analysis results of the optical signals, wherein the detected cells are contained in the blood sample; and
a computer comprising a processor and a memory storing a computer program, wherein the computer program, when executed by the computer, causes the computer to perform:
obtaining the first parameter from the cell image analysis apparatus and the second parameter from the blood cell counter;
generating, by using a pre-trained computer algorithm, information supporting disease differentiation of the subject, on the basis of the first parameter and the second parameter, wherein the information supporting disease differentiation includes a plurality of values each indicating a provability of each disease, and
outputting the plurality of values.
2. The system of claim 1 , wherein
the cell image analysis apparatus is configured to analyze the images of the captured cells by a deep learning algorithm having a neural network structure and is configured to output the first parameter based on an output from the deep learning algorithm.
3. The system of claim 1 , wherein
the abnormal finding includes a finding related to nucleus morphology abnormality, granulation abnormality, cell size abnormality, cell malformation, cytoclasis, vacuole, immature cell, presence of inclusion body, Dohle body, satellitism, nucleoreticulum abnormality, petal-like nucleus, increased N/C ratio, bleb-like morphology, smudge, or hairy cell-like morphology.
4. The system of claim 3 , wherein
the nucleus morphology abnormality includes hypersegmentation, hyposegmentation, pseudo-Pelger anomaly, ring-shaped nucleus, spherical nucleus, elliptical nucleus, apoptosis, polynuclearity, karyorrhexis, enucleation, bare nucleus, irregular nuclear contour, nuclear fragmentation, internuclear bridging, multiple nuclei, cleaved nucleus, nuclear division, or nucleolus abnormality.
5. The system of claim 3 , wherein
the granulation abnormality includes degranulation, granule distribution abnormality, toxic granule, Auer rod, Fagott cell, or pseudo Chediak-Higashi granule-like granule.
6. The system of claim 3 , wherein
the cell size abnormality includes megathrombocyte.
7. The system of claim 1 , wherein
the abnormal finding includes a plurality of types of abnormal findings.
8. The system of claim 1 , wherein
the second parameter relates to numbers of a plurality of types of the detected cells.
9. The system of claim 1 , wherein
the second parameter relates to a number of red blood cell, a number of nucleated red blood cell, a number of small red blood cell, a number of platelet, a number of reticulocyte, a number of immature granulocyte, a number of neutrophil, a number of eosinophil, a number of basophil, a number of lymphocyte, or a number of monocyte.
10. The system of claim 1 , wherein
the computer algorithm includes a machine learning algorithm.
11. The system of claim 1 , wherein
the computer algorithm includes a deep learning algorithm having a neural network structure.
12. The system of claim 1 , wherein
the information supports differentiation of hematopoietic system diseases.
13. The system of claim 12 , wherein
the hematopoietic system diseases include myeloproliferative neoplasms.
14. The system of claim 13 , wherein
the myeloproliferative neoplasms include polycythemia vera, essential thrombocythemia, or primary myelofibrosis.
15. The system of claim 12 , wherein
the hematopoietic system diseases include leukemia, myelodysplastic syndrome, lymphoma, or myeloma.
16. The system of claim 1 , wherein
the blood sample is sample of a peripheral blood.
17. A method for supporting disease differentiation, comprising:
by a cell image analysis apparatus comprising a stage on which a smear preparation, on which a blood sample is smeared, is set, a microscope, and a camera configured to capture images of cells, enlarged by the microscope, in the blood sample smeared on the smear preparation on the stage, analyzing the images of the cells captured by the camera, and outputting a first parameter regarding an abnormal finding in the captured cells based on analysis results of the images, wherein the captured cells are contained in the blood sample collected from a subject;
by a blood cell counter configured to measure a red blood cell count, a white blood cell count, a platelet count, a hemoglobin concentration, a hematocrit value, red blood cell indices, and white blood cell classification values, the blood cell counter comprising a flow cytometer and an electric resistance-type detector, analyzing at least optical signals from cells detected by the flow cytometer, and outputting a second parameter regarding a number of the detected cells based on analysis results of the optical signals, wherein the detected cells are contained in the blood sample; and
by a computer comprising a processor and a memory storing a computer program,
obtaining the first parameter from the cell image analysis apparatus and the second parameter from the blood cell counter,
generating, by using a pre-trained computer algorithm, information supporting disease differentiation of the subject, on the basis of the first parameter and the second parameter, wherein the information supporting disease differentiation includes a plurality of values each indicating a provability of each disease, and
outputting the plurality of values.
18. The system of claim 1 , wherein
the blood cell counter is configured to analyze the optical signals from the cells detected by the flow cytometer and electric signals from the cells detected by the electric resistance-type detector, and output the second parameter based on the analysis results of the optical signals and analysis results of the electric signals.