WO2023282462A1 - Blood cell detection and classification method based on examination area designation - Google Patents
Blood cell detection and classification method based on examination area designation Download PDFInfo
- Publication number
- WO2023282462A1 WO2023282462A1 PCT/KR2022/007448 KR2022007448W WO2023282462A1 WO 2023282462 A1 WO2023282462 A1 WO 2023282462A1 KR 2022007448 W KR2022007448 W KR 2022007448W WO 2023282462 A1 WO2023282462 A1 WO 2023282462A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- designation
- cell
- blood cell
- method based
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 33
- 210000000601 blood cell Anatomy 0.000 title claims abstract description 26
- 210000004027 cell Anatomy 0.000 claims abstract description 47
- 238000003384 imaging method Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 19
- 238000007689 inspection Methods 0.000 claims description 17
- 238000010186 staining Methods 0.000 abstract description 16
- 230000015556 catabolic process Effects 0.000 abstract description 6
- 238000006731 degradation reaction Methods 0.000 abstract description 6
- 238000010191 image analysis Methods 0.000 abstract description 5
- 238000011109 contamination Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 210000000265 leukocyte Anatomy 0.000 description 8
- 210000003743 erythrocyte Anatomy 0.000 description 5
- 230000001788 irregular Effects 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004820 blood count Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007447 staining method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Definitions
- the present invention relates to an image analysis method, and more particularly, to a blood cell detection and classification method.
- Slide biospecimens are usually subjected to biocompatible staining prior to imaging.
- staining is performed manually, when staining is performed by a method other than a standardized staining method, when the stained slide is contaminated, or when special staining (eg, Iron staining, MPO staining) is performed, Staining conditions can lead to poor observation results.
- special staining eg, Iron staining, MPO staining
- an image area suitable for the inspection area is defined as an ideal zone
- the detection rate of the ideal zone greatly depends on the state of the smeared slide.
- the detection rate of the ideal zone is significantly lowered, which may cause problems in observing cells necessary for diagnosis.
- staining requires standardization of staining time, buffer type, and amount used, but in actual medical settings, workers often work manually, so irregular smearing and staining inevitably occur in slide specimens, and leukocytes in areas other than the ideal zone. and image quality degradation of red blood cells.
- the hand-smeared slide sample image has a very narrow and shallow ideal zone, and there are frequent situations in which a large number of scratches and foreign substances exist on the slide.
- the present invention was derived based on the above needs, and in situations where quality degradation or errors may occur in automated image analysis due to defects or contamination of the smear or staining state of the slide, the user directly designates the inspection area to create an ideal zone.
- the designation of the user's examination area can be guided, it is intended to provide a blood cell counting and classification method based on the designation of the examination area that can provide convenience to the user and supplement the user's inexperience.
- the present invention as described above, obtaining a whole slide image (Whole-Slide Imgae) corresponding to the entire area of the slide sample (S110); dividing all slide images into one or more image regions and generating a confidence map for the one or more divided image regions (S120); Selecting an ideal zone corresponding to the designation of the inspection area in all slide images (S130); and detecting and classifying the cell image in the selected ideal zone (S140).
- a whole slide image Whole-Slide Imgae
- S110 whole slide image
- S130 Selecting an ideal zone corresponding to the designation of the inspection area in all slide images
- S140 detecting and classifying the cell image in the selected ideal zone
- all slide images may be obtained by stitching a plurality of tile-shaped divided images.
- the confidence map generation step ( S120 ) may be a step of generating a confidence map having test priority information for one or more divided image regions based on the number of cells and the degree of cell distribution.
- the ideal zone selection step (S130) includes displaying the generated confidence map (S1310); Marking one or more inspection areas on the displayed confidence map (S1320); and setting the marked inspection area as an ideal zone (S1330).
- the confidence map displaying step ( S1310 ) may be a step of displaying one or more divided image regions with differentiated level values based on the inspection priority information.
- the cell image detection and classification step (S140) includes detecting candidate cells for high-magnification imaging in the selected ideal zone (S1410); a path planning step of calculating an imaging path for imaging the detected high-magnification imaging candidate cells (S1420); obtaining a high-magnification cell image corresponding to a high-magnification imaging candidate cell selected based on the calculated imaging path (S1430); and performing classification on the acquired high-magnification cell image (S1440).
- the user directly designates the inspection area and selects the ideal zone, thereby selecting the ideal zone. Accuracy can be attributed to detection, cell counting and cell clasification.
- 1 is a diagram showing an example of an irregular slide for explaining irregular smearing and staining conditions in specimen production
- FIG. 2 (a) is a diagram showing an example of a white blood cell image with reduced image quality, (b) is a diagram showing an example of a damaged red blood cell image,
- FIG. 3 is a flowchart sequentially showing an embodiment of a blood cell detection and classification method based on designation of a test area according to the present invention
- FIG. 4 is a flowchart sequentially showing the process of selecting an ideal zone in an embodiment of the blood cell detection and classification method based on designation of the test area according to the present invention
- FIG. 5 is a flow chart sequentially showing the blood cell image detection and classification process in one embodiment of the blood cell detection and classification method based on the designation of the test area of the present invention
- FIG. 6 is a view (a) showing a stitching combination of whole-slide images obtained in an embodiment of a blood cell detection and clasification method based on designation of a test area according to the present invention and among a plurality of divided image areas It is an enlarged drawing (b) of one,
- FIG. 7 is a diagram showing a display state of a confidence map generated in an embodiment of a blood cell detection and classification method based on designation of a test area according to the present invention
- FIG. 8 is a diagram showing a screen for designating two test areas in an embodiment of a blood cell detection and classification method based on test area designation according to the present invention
- FIG. 9 is a view showing a cell clasification result screen within a test area according to an embodiment of the blood cell detection and clasification method based on designation of a test area according to the present invention.
- FIG. 1 is a diagram showing an example of an irregular slide for explaining irregular smear and staining conditions in specimen production
- FIG. 2 (a) is a diagram showing an example of a leukocyte image with reduced image quality
- (b) is a diagram showing an example of a damaged white blood cell image. It is a diagram showing an example of a red blood cell image.
- irregularities in smear and staining conditions, image quality degradation due to the limitation of the wavelength of illumination sensitive to cell thickness, and image quality degradation due to abnormal blood cells limit the automated image analysis of slide specimens. show
- one embodiment of the present invention in a situation where the experience of a user such as a surgeon or a diagnostician (eg, an image analyzer user) is prioritized, it is possible to increase the accuracy of slide sample inspection while guiding inexperienced users. acts to provide
- FIG. 3 is a flowchart sequentially illustrating an embodiment of a method of detecting and classifying blood cells based on designation of a test area according to the present invention.
- a whole-slide image corresponding to the entire area of the slide specimen is acquired (S110).
- the entire slide image may be obtained by stitching a plurality of tile-shaped divided images.
- each of the divided images may be an enlarged low-magnification captured image as shown in FIG. 6 (b).
- the confidence map generating step (S120) may be a step of generating a confidence map having test priority information for one or more divided image regions based on the number of cells and the degree of cell distribution.
- an embodiment of the blood cell detection and classification method based on the designation of the test area can be performed by detecting and classifying the cell image in the selected ideal zone (S140).
- FIG. 4 is a flow chart sequentially illustrating a process of selecting an ideal zone in an embodiment of a blood cell detection and classification method based on designation of a test area according to the present invention.
- a step (S1310) of displaying the generated confidence map is performed, followed by a step (S1320) of marking one or more inspection areas on the displayed confidence map. and finally setting the marked inspection area as an ideal zone (S1330).
- the confidence map displaying step (S1310) may be a step of displaying one or more divided image regions with differentiated level values based on the inspection priority information. For example, as shown in FIG. 7, when the priority information is high (High), it is set to a red color, and when it is low (Low), it is set to a blue color, and the level between them is a differentiated color value. can get angry Of course, various color codes such as RGB and HSB may be used to level these color values. In addition, priority information may be displayed based on a level value other than color or by giving a number.
- the generated confidence map displays the divided image areas as differentiated level values and displays them through a display device, and as shown in FIG. 8, one or more inspection areas are displayed on the displayed confidence map. to mark Such marking may be performed by a method in which a user clicks or drags an appropriate inspection area while monitoring the confidence map with a display device.
- two or more divided image regions may be marked as a test region (or region of interest) and a set button is pressed. Press to complete the ideal zone setting. Clicking the set button may be an execution command for automatic detection and classification of cells for the simultaneously selected ideal zone.
- FIG. 5 is a flow chart sequentially showing blood cell image detection and classification processes in one embodiment of the blood cell detection and classification method based on the test area designation of the present invention.
- the blood cell image detection and classification step (S140) referring to FIG. 5, high-magnification imaging candidate cells are first detected in a selected ideal zone (S1410).
- image processing techniques such as color equalization for ideal zones, color temperature correction, and color-brightness normalization may be performed.
- background subtraction for extracting cells based on color characteristics, morphology for correcting continuous phenomena using neighboring pixel information, and integral image method At least one image processing technique may be performed.
- path planning is a technique of calculating a high-magnification imaging path of scattered high-magnification imaging candidate cells, and it is preferable to plan an efficient imaging path to reduce tact time.
- a high-magnification cell image corresponding to the selected high-magnification imaging candidate cell based on the computed imaging path is obtained (S1430), and then the obtained high-magnification cell image is subjected to classification (S1440).
- a classification result for the acquired high-magnification cell image is displayed.
- the displayed high-magnification cell images and classification results are displayed along with a plurality of high-magnification blood cell images and class classification information and counting information for RBCs (Red Blood Cells) and WBCs (White Blood Cells). do.
- RBCs Red Blood Cells
- WBCs White Blood Cells
- WBC differential count information may also be provided.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
According to one embodiment of the present invention, in situations where quality degradation or errors may occur in automated image analysis due to poor smearing or staining, contamination, etc. of slides, a user directly designates an examination area and selects an ideal zone, and thus can ensure accuracy in cell detection, cell counting, and cell classification. To this end, one embodiment of the present invention includes a blood cell detection and classification method based on examination area designation, the method comprising the steps of: acquiring a whole slide image corresponding to the whole area of a slide sample (S110); dividing the whole slide image into one or more image areas and generating a confidence map for the one or more divided image areas (S120); selecting an ideal zone in response to designation of an examination area in the whole slide image (S130); and detecting and classifying a cell image in the selected ideal zone (S140).
Description
본 발명은 이미지 분석방법에 관한 것으로서, 보다 상세하게는 혈구 디텍션 및 클래시피케이션 방법에 관한 것이다.The present invention relates to an image analysis method, and more particularly, to a blood cell detection and classification method.
슬라이드 생체 표본은 이미지 촬상 전에 생체에 적합한 염색을 수행하는 것이 일반적이다. 수동으로 염색을 수행하거나, 표준화된 염색 방법이 아닌 방법으로 염색을 수행하거나, 염색한 슬라이드가 오염된 경우 또는 특수 염색(예를 들어, Iron 염색, MPO 염색)을 수행하는 경우에 있어서, 슬라이드의 염색 상태는 관찰에 좋지 않은 결과로 이어질 수 있다.Slide biospecimens are usually subjected to biocompatible staining prior to imaging. When staining is performed manually, when staining is performed by a method other than a standardized staining method, when the stained slide is contaminated, or when special staining (eg, Iron staining, MPO staining) is performed, Staining conditions can lead to poor observation results.
검사영역에 적합한 이미지 영역을 아이디얼 존(ideal zone)으로 정의한다면 아이디얼 존의 검출율은 도말된 슬라이드의 상태에 크게 의존한다. 결국 자동화된 이미지 분석에서는 아이디얼 존의 검출율이 현저히 떨어지고 이로 인해 진단에 필요한 세포를 관찰하는 데 문제가 발생할 수 있다.If an image area suitable for the inspection area is defined as an ideal zone, the detection rate of the ideal zone greatly depends on the state of the smeared slide. As a result, in automated image analysis, the detection rate of the ideal zone is significantly lowered, which may cause problems in observing cells necessary for diagnosis.
한편 염색은 염색 시간, 버퍼 종류, 사용량의 표준화가 필요함에도 실제 의료 현장에서는 작업자가 수동으로 작업하는 경우가 빈번하므로 슬라이드 표본은 불규칙적인 도말과 염색이 필연적으로 발생하고, 아이디얼 존이 아닌 영역에서는 백혈구 및 적혈구의 이미지 품질 저하가 발생한다.On the other hand, staining requires standardization of staining time, buffer type, and amount used, but in actual medical settings, workers often work manually, so irregular smearing and staining inevitably occur in slide specimens, and leukocytes in areas other than the ideal zone. and image quality degradation of red blood cells.
또한 수작업으로 도말된 슬라이드 표본 이미지는 아이디얼 존이 매우 좁고 얕으며 슬라이드 상에 스크래치 및 이물질이 다수 존재하는 상황도 빈번하다.In addition, the hand-smeared slide sample image has a very narrow and shallow ideal zone, and there are frequent situations in which a large number of scratches and foreign substances exist on the slide.
따라서 전술한 슬라이드 표본에 대한 품질 문제는, 자동화된 세포 카운팅 및 클래시피케이션에 있어서 진단의 또는 유저의 만족도를 떨어뜨리는 결과로 이어지므로 이에 대한 보완의 필요성이 대두된다.Therefore, since the quality problem of the above-mentioned slide specimen leads to a decrease in the satisfaction of the diagnosis or the user in the automated cell counting and clasification, the need to supplement this problem arises.
본 발명은 상기와 같은 필요성에 기하여 도출된 것으로서, 슬라이드의 도말 또는 염색 상태의 불량, 오염 등으로 자동화된 이미지 분석에 품질저하 또는 오류가 발생할 수 있는 상황에서 유저가 직접 검사영역을 지정하여 아이디얼 존을 선정함으로써 세포 디텍션, 세포 카운팅 및 세포 클래시피케이션에 정확성을 기할 수 있는 검사영역 지정 기반 혈구 디텍션 및 클래시피케이션 방법을 제공하고자 한다.The present invention was derived based on the above needs, and in situations where quality degradation or errors may occur in automated image analysis due to defects or contamination of the smear or staining state of the slide, the user directly designates the inspection area to create an ideal zone. By selecting , we intend to provide a blood cell detection and classification method based on the designation of the test area that can ensure accuracy in cell detection, cell counting, and cell classification.
또한 유저의 검사영역 지정을 가이드할 수 있으므로 유저에게 편의성을 제공하고 유저의 경험 미숙을 보완할 수 있는 검사영역 지정 기반 혈구 카운팅 및 클래시피케이션 방법을 제공하고자 한다.In addition, since the designation of the user's examination area can be guided, it is intended to provide a blood cell counting and classification method based on the designation of the examination area that can provide convenience to the user and supplement the user's inexperience.
상기와 같은 본 발명은, 슬라이드 표본의 전 영역에 대응하는 전 슬라이드 이미지(Whole-Slide Imgae)를 획득하는 단계(S110); 전 슬라이드 이미지에 대하여 1 이상의 이미지 영역으로 분할하고 1 이상의 분할된 이미지 영역에 대하여 컨피던스 맵을 생성하는 단계(S120); 전 슬라이드 이미지에서 검사영역의 지정에 대응하여 아이디얼 존을 선정하는 단계(S130); 및 선정된 아이디얼 존에서 세포 이미지를 디텍션(detection) 및 클래시피케이션(classification)하는 단계(S140)를 포함하는 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법으로 제공될 수 있다.The present invention as described above, obtaining a whole slide image (Whole-Slide Imgae) corresponding to the entire area of the slide sample (S110); dividing all slide images into one or more image regions and generating a confidence map for the one or more divided image regions (S120); Selecting an ideal zone corresponding to the designation of the inspection area in all slide images (S130); and detecting and classifying the cell image in the selected ideal zone (S140).
전 슬라이드 이미지 획득단계(S110)에서, 전 슬라이드 이미지는 다수의 타일 형태 분할 이미지를 스티칭한 것일 수 있다.In the acquiring all slide images ( S110 ), all slide images may be obtained by stitching a plurality of tile-shaped divided images.
컨피던스 맵 생성단계(S120)는, 세포 갯수와 세포의 분포 정도에 기반하여 1 이상의 분할된 이미지 영역에 대하여 검사 우선순위 정보를 가지는 컨피던스 맵을 생성하는 단계일 수 있다.The confidence map generation step ( S120 ) may be a step of generating a confidence map having test priority information for one or more divided image regions based on the number of cells and the degree of cell distribution.
아이디얼 존 선정단계(S130)는, 생성된 컨피던스 맵이 디스플레이되는 단계(S1310); 디스플레이된 컨피던스 맵 상에서 1 이상의 검사영역을 마크하는 단계(S1320); 및 마킹된 검사영역을 아이디얼 존으로 세팅하는 단계(S1330)를 포함할 수 있다.The ideal zone selection step (S130) includes displaying the generated confidence map (S1310); Marking one or more inspection areas on the displayed confidence map (S1320); and setting the marked inspection area as an ideal zone (S1330).
컨피던스 맵 디스플레이단계(S1310)는, 검사 우선순위 정보에 기반하여 1 이상의 분할된 이미지 영역을 차등화된 레벨값으로 표시하는 단계일 수 있다.The confidence map displaying step ( S1310 ) may be a step of displaying one or more divided image regions with differentiated level values based on the inspection priority information.
세포 이미지 디텍션 및 클래시피케이션단계(S140)는, 선정된 아이디얼 존에서 고배율 촬상 후보세포를 디텍션하는 단계(S1410); 디텍션된 고배율 촬상 후보세포들의 촬상을 위한 촬상 경로를 연산하는 패스 플래닝단계(S1420); 연산된 촬상 경로에 기반하여 선정된 고배율 촬상 후보세포에 대응하는 고배율 세포 이미지를 획득하는 단계(S1430); 및 획득된 고배율 세포 이미지에 대하여 클래시피케이션을 수행하는 단계(S1440)를 포함할 수 있다.The cell image detection and classification step (S140) includes detecting candidate cells for high-magnification imaging in the selected ideal zone (S1410); a path planning step of calculating an imaging path for imaging the detected high-magnification imaging candidate cells (S1420); obtaining a high-magnification cell image corresponding to a high-magnification imaging candidate cell selected based on the calculated imaging path (S1430); and performing classification on the acquired high-magnification cell image (S1440).
본 발명의 일 실시예에 의하면, 슬라이드의 도말 또는 염색 상태의 불량, 오염 등으로 자동화된 이미지 분석에 품질저하 또는 오류가 발생할 수 있는 상황에서 유저가 직접 검사영역을 지정하여 아이디얼 존을 선정함으로써 세포 디텍션, 세포 카운팅 및 세포 클래시피케이션에 정확성을 기할 수 있다.According to one embodiment of the present invention, in a situation where quality degradation or errors may occur in automated image analysis due to defects or contamination of the smear or staining state of the slide, the user directly designates the inspection area and selects the ideal zone, thereby selecting the ideal zone. Accuracy can be attributed to detection, cell counting and cell clasification.
또한 본 발명의 일 실시예에 의하면 유저의 검사영역 지정을 가이드할 수 있으므로 유저에게 편의성을 제공하고 유저의 경험 미숙을 보완할 수 있다.In addition, according to an embodiment of the present invention, since it is possible to guide the designation of the user's inspection area, convenience is provided to the user and inexperience of the user can be compensated.
도 1은 표본 제작에 있어서 불규칙적인 도말 및 염색 상태를 설명하기 위한 불규칙적 슬라이드의 예시를 나타낸 도면이고,1 is a diagram showing an example of an irregular slide for explaining irregular smearing and staining conditions in specimen production,
도 2 (a)는 영상 품질 저하된 백혈구 이미지의 예시를 나타낸 도면이고, (b)는 손상된 적혈구 이미지의 예시를 나타낸 도면이며,2 (a) is a diagram showing an example of a white blood cell image with reduced image quality, (b) is a diagram showing an example of a damaged red blood cell image,
도 3은 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예를 순차적으로 나타낸 순서도이고,3 is a flowchart sequentially showing an embodiment of a blood cell detection and classification method based on designation of a test area according to the present invention;
도 4는 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 아이디얼 존 선정 과정을 순차적으로 나타낸 순서도이고,4 is a flowchart sequentially showing the process of selecting an ideal zone in an embodiment of the blood cell detection and classification method based on designation of the test area according to the present invention;
도 5는 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 혈구 이미지 디텍션 및 클래시피케이션 과정을 순차적으로 나타낸 순서도이고,5 is a flow chart sequentially showing the blood cell image detection and classification process in one embodiment of the blood cell detection and classification method based on the designation of the test area of the present invention;
도 6은 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 획득된 전 슬라이드 이미지(Whole-Slide Imgae)의 스티칭 조합을 나타낸 도면(a)과 다수의 분할된 이미지 영역 중 하나를 확대한 도면(b)이며,6 is a view (a) showing a stitching combination of whole-slide images obtained in an embodiment of a blood cell detection and clasification method based on designation of a test area according to the present invention and among a plurality of divided image areas It is an enlarged drawing (b) of one,
도 7은 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 생성된 컨피던스 맵의 디스플레이 상태를 나타낸 도면이고,7 is a diagram showing a display state of a confidence map generated in an embodiment of a blood cell detection and classification method based on designation of a test area according to the present invention;
도 8은 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 2 개의 검사영역을 지정하는 화면을 나타낸 도면이고,8 is a diagram showing a screen for designating two test areas in an embodiment of a blood cell detection and classification method based on test area designation according to the present invention;
도 9는 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예에 따라 검사영역 내에서 세포 클래시피케이션 결과 화면을 나타낸 도면이다.9 is a view showing a cell clasification result screen within a test area according to an embodiment of the blood cell detection and clasification method based on designation of a test area according to the present invention.
이하 첨부 도면들 및 첨부 도면들에 기재된 내용들을 참조하여 본 발명의 실시예를 상세하게 설명하지만, 본 발명이 실시예에 의해 제한되거나 한정되는 것은 아니다.Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and the contents described in the accompanying drawings, but the present invention is not limited or limited by the embodiments.
아래 설명하는 실시예들에는 다양한 변경이 가해질 수 있다. 아래 설명하는 실시예들은 실시 형태에 대해 한정하려는 것이 아니며, 이들에 대한 모든 변경, 균등물 내지 대체물을 포함하는 것으로 이해되어야 한다.Various changes may be made to the embodiments described below. The embodiments described below are not intended to be limiting on the embodiments, and should be understood to include all modifications, equivalents or substitutes thereto.
한편, 본 발명을 설명함에 있어서, 관련된 공지 기능 또는 구성에 대한 구체적인 설명이 본 발명의 요지를 불필요하게 흐릴 수 있다고 판단되는 경우에는, 그 상세한 설명을 생략할 것이다. 그리고, 본 명세서에서 사용되는 용어(terminology)들은 본 발명의 실시예를 적절히 표현하기 위해 사용된 용어들로서, 이는 사용자, 운용자의 의도 또는 본 발명이 속하는 분야의 관례 등에 따라 달라질 수 있다. 따라서, 본 용어들에 대한 정의는 본 명세서 전반에 걸친 내용을 토대로 내려져야 할 것이다.Meanwhile, in describing the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terminology used in this specification is a term used to appropriately express the embodiment of the present invention, which may vary according to the intention of a user or operator or customs in the field to which the present invention belongs. Therefore, definitions of these terms will have to be made based on the content throughout this specification.
검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법Blood cell detection and classification method based on test area designation
도 1은 표본 제작에 있어서 불규칙적인 도말 및 염색 상태를 설명하기 위한 불규칙적 슬라이드의 예시를 나타낸 도면이고, 도 2 (a)는 영상 품질 저하된 백혈구 이미지의 예시를 나타낸 도면이고, (b)는 손상된 적혈구 이미지의 예시를 나타낸 도면이다. 도 1 및 2에 도시된 바와 같이, 도말 및 염색 상태의 불규칙성, 세포 두께에 민감한 조명의 파장 한계로 인한 영상 품질 저하, 비정상적 혈구로 인한 영상 품질저하는, 슬라이드 표본의 자동화된 이미지 분석의 한계를 보여준다.1 is a diagram showing an example of an irregular slide for explaining irregular smear and staining conditions in specimen production, FIG. 2 (a) is a diagram showing an example of a leukocyte image with reduced image quality, and (b) is a diagram showing an example of a damaged white blood cell image. It is a diagram showing an example of a red blood cell image. As shown in FIGS. 1 and 2, irregularities in smear and staining conditions, image quality degradation due to the limitation of the wavelength of illumination sensitive to cell thickness, and image quality degradation due to abnormal blood cells, limit the automated image analysis of slide specimens. show
따라서 본 발명의 일 실시예는, 검사의 또는 진단의와 같은 유저(예를 들어 이미지 분석기의 유저)의 경험이 우선 시 되는 상황에서 슬라이드 표본 검사의 정확도를 높일 수 있으면서 경험이 미숙한 유저에게 가이드를 제공하도록 작용한다.Therefore, one embodiment of the present invention, in a situation where the experience of a user such as a surgeon or a diagnostician (eg, an image analyzer user) is prioritized, it is possible to increase the accuracy of slide sample inspection while guiding inexperienced users. acts to provide
도 3은 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예를 순차적으로 나타낸 순서도이다. 도 3을 참조하면, 본 실시예는 우선 슬라이드 표본의 전 영역에 대응하는 전 슬라이드 이미지(Whole-Slide Imgae)를 획득한다(S110). 전 슬라이드 이미지는 도 6 (a)에 도시된 바와 같이, 다수의 타일 형태 분할 이미지를 스티칭한 것일 수 있다. 또한 분할 이미지 각각은 도 6 (b)에 도시된 바와 같이 확대된 저배율 촬상 이미지일 수 있다.3 is a flowchart sequentially illustrating an embodiment of a method of detecting and classifying blood cells based on designation of a test area according to the present invention. Referring to FIG. 3 , in this embodiment, first, a whole-slide image corresponding to the entire area of the slide specimen is acquired (S110). As shown in FIG. 6 (a), the entire slide image may be obtained by stitching a plurality of tile-shaped divided images. Also, each of the divided images may be an enlarged low-magnification captured image as shown in FIG. 6 (b).
다음, 전 슬라이드 이미지에 대하여 1 이상의 이미지 영역으로 분할하고 1 이상의 분할된 이미지 영역에 대하여 컨피던스 맵을 생성한다(S120). 이러한 컨피던스 맵 생성단계(S120)는, 세포 갯수와 세포의 분포 정도에 기반하여 1 이상의 분할된 이미지 영역에 대하여 검사 우선순위 정보를 가지는 컨피던스 맵을 생성하는 단계일 수 있다.Next, all slide images are divided into one or more image regions, and a confidence map is generated for the one or more divided image regions (S120). The confidence map generating step (S120) may be a step of generating a confidence map having test priority information for one or more divided image regions based on the number of cells and the degree of cell distribution.
다음, 전 슬라이드 이미지에서 검사영역의 지정에 대응하여 아이디얼 존을 선정한다(S130).Next, an ideal zone is selected corresponding to the designation of the inspection area in all slide images (S130).
마지막으로, 선정된 아이디얼 존에서 세포 이미지를 디텍션(detection) 및 클래시피케이션(classification)함으로써(S140) 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예가 수행될 수 있다.Finally, an embodiment of the blood cell detection and classification method based on the designation of the test area can be performed by detecting and classifying the cell image in the selected ideal zone (S140).
도 4는 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 아이디얼 존 선정 과정을 순차적으로 나타낸 순서도이다. 도 4를 참조하면, 우선 아이디얼 존 선정단계(S130)는, 생성된 컨피던스 맵이 디스플레이되는 단계(S1310)가 수행되고, 이후에 디스플레이된 컨피던스 맵 상에서 1 이상의 검사영역을 마크하는 단계(S1320)가 수행되며, 마지막으로 마킹된 검사영역을 아이디얼 존으로 세팅하는 단계(S1330)를 포함할 수 있다. 4 is a flow chart sequentially illustrating a process of selecting an ideal zone in an embodiment of a blood cell detection and classification method based on designation of a test area according to the present invention. Referring to FIG. 4 , in the step of selecting an ideal zone (S130), a step (S1310) of displaying the generated confidence map is performed, followed by a step (S1320) of marking one or more inspection areas on the displayed confidence map. and finally setting the marked inspection area as an ideal zone (S1330).
여기서 컨피던스 맵 디스플레이단계(S1310)는, 검사 우선순위 정보에 기반하여 1 이상의 분할된 이미지 영역을 차등화된 레벨값으로 표시하는 단계일 수 있다. 예를 들어 도 7에 도시된 바와 같이, 우선순위 정보가 높은 경우(High)에는 레드 컬러(color)로 낮은 경우(Low)에는 블루 컬러(color)로 하고, 그 사이를 차등화된 색상 값으로 레벨화할 수 있다. 물론 이러한 색상 값의 레벨화는 RGB, HSB 등의 다양한 색상코드를 이용할 수 있을 것이다. 이 밖에 컬러가 아닌 다른 레벨값에 기초하거나 숫자를 부여해서 우선순위 정보를 표시할 수도 있을 것이다.Here, the confidence map displaying step (S1310) may be a step of displaying one or more divided image regions with differentiated level values based on the inspection priority information. For example, as shown in FIG. 7, when the priority information is high (High), it is set to a red color, and when it is low (Low), it is set to a blue color, and the level between them is a differentiated color value. can get angry Of course, various color codes such as RGB and HSB may be used to level these color values. In addition, priority information may be displayed based on a level value other than color or by giving a number.
생성된 컨피던스 맵은, 도 7에 도시된 바와 같이, 분할된 이미지 영역을 차등화된 레벨값으로 표시하여 디스플레이 장치를 통해 디스플레이하고, 도 8에 도시된 바와 같이, 디스플레이된 컨피던스 맵 상에서 1 이상의 검사영역을 마크한다. 이러한 마킹은, 유저가 컨피던스 맵을 디스플레이 장치로 모니터하면서 적절한 검사영역을 클릭하거나 드래그하는 방법으로 수행될 수 있다.As shown in FIG. 7, the generated confidence map displays the divided image areas as differentiated level values and displays them through a display device, and as shown in FIG. 8, one or more inspection areas are displayed on the displayed confidence map. to mark Such marking may be performed by a method in which a user clicks or drags an appropriate inspection area while monitoring the confidence map with a display device.
아이디얼 존 세팅단계(S1330)는, 하나의 분할된 이미지 영역 뿐만 아니라 도 8에 도시된 바와 같이, 2 이상의 분할된 이미지 영역이 검사영역(또는 관심 영역)으로 마킹될 수 있고 세트(Set) 버튼을 눌러 아이디얼 존 세팅이 완료된다. 세트 버튼의 클릭은, 동시에 선정된 아이디얼 존에 대한 세포의 자동 디텍션 및 클래시피케이션의 실행 명령일 수 있다.In the ideal zone setting step (S1330), as shown in FIG. 8 as well as one divided image region, two or more divided image regions may be marked as a test region (or region of interest) and a set button is pressed. Press to complete the ideal zone setting. Clicking the set button may be an execution command for automatic detection and classification of cells for the simultaneously selected ideal zone.
도 5는 본 발명인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법의 일 실시예 중 혈구 이미지 디텍션 및 클래시피케이션 과정을 순차적으로 나타낸 순서도이다. 혈구 이미지 디텍션 및 클래시피케이션단계(S140)는, 도 5를 참조하면, 우선 선정된 아이디얼 존에서 고배율 촬상 후보세포를 디텍션한다(S1410). 후보세포 디텍션단계(S1410)는, 아이디얼 존에 대한 색의 균등화, 컬러 템퍼러처 커렉션(Color Temperature Correction), 컬러 브라이트니스 정규화(Color-Brightness Normalization) 등의 이미지 처리 기법이 수행될 수 있다. 또한 후보세포 디텍션단계(S1410)는, 색 특징 기준으로 세포를 추출하는 백그라운드 서브트랙션(Background Subtraction), 이웃 픽셀 정보를 활용하여 끊임 현상을 보정하는 모폴로지(Morphology), 적분 이미지 방식(Integral Image Method) 중 적어도 하나의 이미지 처리 기법이 수행될 수 있다.5 is a flow chart sequentially showing blood cell image detection and classification processes in one embodiment of the blood cell detection and classification method based on the test area designation of the present invention. In the blood cell image detection and classification step (S140), referring to FIG. 5, high-magnification imaging candidate cells are first detected in a selected ideal zone (S1410). In the candidate cell detection step (S1410), image processing techniques such as color equalization for ideal zones, color temperature correction, and color-brightness normalization may be performed. In addition, in the candidate cell detection step (S1410), background subtraction for extracting cells based on color characteristics, morphology for correcting continuous phenomena using neighboring pixel information, and integral image method At least one image processing technique may be performed.
다음, 디텍션된 고배율 촬상 후보세포들의 고배율 촬상을 위한 촬상 경로를 연산하는 패스 플래닝단계(S1420)가 수행된다. 여기서 패스 플래닝(Path Planning)은 흩어져 있는 고배율 촬상 후보세포의 고배율 촬상 경로를 연산하는 기법인데, 택타임(tact time)을 줄일 수 있도록 효율적인 촬상 경로를 플래닝하는 것이 바람직하다.Next, a path planning step (S1420) of calculating an imaging path for high-magnification imaging of the detected high-magnification imaging candidate cells is performed. Here, path planning is a technique of calculating a high-magnification imaging path of scattered high-magnification imaging candidate cells, and it is preferable to plan an efficient imaging path to reduce tact time.
다음, 연산된 촬상 경로에 기반하여 선정된 고배율 촬상 후보세포에 대응하는 고배율 세포 이미지를 획득하고(S1430), 이후 획득된 고배율 세포 이미지에 대하여 클래시피케이션을 수행함으로써(S1440) 완료될 수 있다.Next, a high-magnification cell image corresponding to the selected high-magnification imaging candidate cell based on the computed imaging path is obtained (S1430), and then the obtained high-magnification cell image is subjected to classification (S1440).
최적의 촬상 경로에 기반하여 고배율 촬상이 수행되고 고배율 세포 이미지를 획득하면, 획득된 고배율 세포 이미지에 대한 클래시피케이션 결과를 디스플레이한다. 디스플레이된 고배율 세포 이미지 및 클래시피케이션 결과는, 도 9에 도시된 바와 같이, RBC(Red Blood Cell) 및 WBC(White Blood Cell)에 대한 클래스 분류 정보 및 카운팅 정보가 다수의 고배율 혈구 이미지와 함께 디스플레이된다. 아울러 백혈구의 경우에는 백혈구 감별 계산(WBC differential count) 정보도 함께 제공될 수 있다.When high-magnification imaging is performed based on the optimal imaging path and a high-magnification cell image is acquired, a classification result for the acquired high-magnification cell image is displayed. As shown in FIG. 9 , the displayed high-magnification cell images and classification results are displayed along with a plurality of high-magnification blood cell images and class classification information and counting information for RBCs (Red Blood Cells) and WBCs (White Blood Cells). do. In addition, in the case of leukocytes, WBC differential count information may also be provided.
이상 첨부된 도면을 참조하여 본 발명의 실시 예를 설명하였지만, 상술한 본 발명의 기술적 구성은 본 발명이 속하는 기술 분야의 당 업자가 본 발명의 그 기술적 사상이나 필수적 특징을 변경하지 않고서 다른 구체적인 형태로 실시될 수 있다는 것을 이해할 수 있을 것이다. 그러므로 이상에서 기술한 실시 예들은 모든 면에서 예시적인 것이며 한정적인 것이 아닌 것으로서 이해되어야 한다. 아울러, 본 발명의 범위는 상기의 상세한 설명보다는 후술하는 특허청구범위에 의하여 나타내어진다. 또한, 특허청구범위의 의미 및 범위 그리고 그 등가 개념으로부터 도출되는 모든 변경 또는 변형된 형태가 본 발명의 범위에 포함되는 것으로 해석되어야 한다.Although the embodiments of the present invention have been described with reference to the accompanying drawings, the technical configuration of the present invention described above is another specific form without changing the technical spirit or essential features of the present invention by those skilled in the art to which the present invention belongs. It will be understood that it can be implemented as. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. In addition, the scope of the present invention is indicated by the claims to be described later rather than the detailed description above. In addition, all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention.
Claims (6)
- 슬라이드 표본의 전 영역에 대응하는 전 슬라이드 이미지(Whole-Slide Imgae)를 획득하는 단계(S110);Acquiring a whole-slide image corresponding to the entire area of the slide specimen (S110);상기 전 슬라이드 이미지에 대하여 1 이상의 이미지 영역으로 분할하고 1 이상의 상기 분할된 이미지 영역에 대하여 컨피던스 맵을 생성하는 단계(S120);dividing the entire slide image into one or more image areas and generating a confidence map for the one or more divided image areas (S120);상기 전 슬라이드 이미지에서 검사영역의 지정에 대응하여 아이디얼 존을 선정하는 단계(S130); 및Selecting an ideal zone corresponding to the designation of an inspection area in the entire slide image (S130); and상기 선정된 아이디얼 존에서 세포 이미지를 디텍션(detection) 및 클래시피케이션(classification)하는 단계(S140)를 포함하는 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법.The blood cell detection and classification method based on the designation of the examination area including the step of detecting and classifying the cell image in the selected ideal zone (S140).
- 제1 항에 있어서,According to claim 1,상기 전 슬라이드 이미지 획득단계(S110)에서,In the all-slide image acquisition step (S110),상기 전 슬라이드 이미지는 다수의 타일 형태 분할 이미지를 스티칭한 것을 특징으로 하는 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법.The whole slide image is a blood cell detection and classification method based on designation of the examination area, characterized in that a plurality of tile-shaped divided images are stitched.
- 제1 항에 있어서,According to claim 1,상기 컨피던스 맵 생성단계(S120)는,In the confidence map generating step (S120),세포 갯수와 세포의 분포 정도에 기반하여 1 이상의 상기 분할된 이미지 영역에 대하여 검사 우선순위 정보를 가지는 상기 컨피던스 맵을 생성하는 단계인 것을 특징으로 하는 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법.The step of generating the confidence map having test priority information for one or more of the divided image regions based on the number of cells and the degree of cell distribution.
- 제1 항에 있어서,According to claim 1,상기 아이디얼 존 선정단계(S130)는,In the ideal zone selection step (S130),상기 생성된 컨피던스 맵이 디스플레이되는 단계(S1310);displaying the generated confidence map (S1310);상기 디스플레이된 컨피던스 맵 상에서 1 이상의 검사영역을 마크하는 단계(S1320); 및marking one or more inspection areas on the displayed confidence map (S1320); and상기 마킹된 검사영역을 아이디얼 존으로 세팅하는 단계(S1330)를 포함하는 것인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법.The blood cell detection and classification method based on the designation of the examination area comprising setting the marked examination area as an ideal zone (S1330).
- 제4 항에 있어서,According to claim 4,상기 컨피던스 맵 디스플레이단계(S1310)는,In the confidence map display step (S1310),검사 우선순위 정보에 기반하여 1 이상의 상기 분할된 이미지 영역을 차등화된 레벨값으로 표시하는 것을 특징으로 하는 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법.A blood cell detection and classification method based on designation of an examination area, characterized in that displaying one or more of the divided image areas as a differentiated level value based on examination priority information.
- 제1 항에 있어서,According to claim 1,상기 세포 이미지 디텍션 및 클래시피케이션단계(S140)는,The cell image detection and clasification step (S140),상기 선정된 아이디얼 존에서 고배율 촬상 후보세포를 디텍션하는 단계(S1410);detecting candidate cells for high-magnification imaging in the selected ideal zone (S1410);상기 디텍션된 고배율 촬상 후보세포들의 고배율 촬상을 위한 촬상 경로를 연산하는 패스 플래닝단계(S1420);a path planning step of calculating an imaging path for high-magnification imaging of the detected high-magnification imaging candidate cells (S1420);상기 연산된 촬상 경로에 기반하여 상기 선정된 고배율 촬상 후보세포에 대응하는 고배율 세포 이미지를 획득하는 단계(S1430); 및obtaining a high-magnification cell image corresponding to the selected high-magnification imaging candidate cell based on the calculated imaging path (S1430); and상기 획득된 고배율 세포 이미지에 대하여 클래시피케이션을 수행하는 단계(S1440)를 포함하는 것인 검사영역 지정에 기반한 혈구 디텍션 및 클래시피케이션 방법.The blood cell detection and classification method based on the designation of the examination area comprising the step of performing classification on the obtained high-magnification cell image (S1440).
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020210090455A KR20230009718A (en) | 2021-07-09 | 2021-07-09 | Blood-cell detecion and classification method based on designation of inspection area |
| KR10-2021-0090455 | 2021-07-09 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023282462A1 true WO2023282462A1 (en) | 2023-01-12 |
Family
ID=84801924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2022/007448 WO2023282462A1 (en) | 2021-07-09 | 2022-05-25 | Blood cell detection and classification method based on examination area designation |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR20230009718A (en) |
| WO (1) | WO2023282462A1 (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190022026A (en) * | 2017-08-25 | 2019-03-06 | (주)뉴옵틱스 | Cytometry apparatus and method |
| KR102105489B1 (en) * | 2018-12-31 | 2020-04-28 | (주)유아이엠디 | Microscopy based slide scanning system for bone marrow interpretation |
| US20200134858A1 (en) * | 2018-10-29 | 2020-04-30 | Samsung Sds Co., Ltd. | Apparatus and method for extracting object information |
| KR20200054555A (en) * | 2018-11-12 | 2020-05-20 | 라온프렌즈 주식회사 | Apparatus for medical image processing |
| KR20200082746A (en) * | 2018-12-31 | 2020-07-08 | (주)유아이엠디 | Cell-zone labeling apparatus and cell-zone detecting system including the same apparatus |
-
2021
- 2021-07-09 KR KR1020210090455A patent/KR20230009718A/en not_active Application Discontinuation
-
2022
- 2022-05-25 WO PCT/KR2022/007448 patent/WO2023282462A1/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190022026A (en) * | 2017-08-25 | 2019-03-06 | (주)뉴옵틱스 | Cytometry apparatus and method |
| US20200134858A1 (en) * | 2018-10-29 | 2020-04-30 | Samsung Sds Co., Ltd. | Apparatus and method for extracting object information |
| KR20200054555A (en) * | 2018-11-12 | 2020-05-20 | 라온프렌즈 주식회사 | Apparatus for medical image processing |
| KR102105489B1 (en) * | 2018-12-31 | 2020-04-28 | (주)유아이엠디 | Microscopy based slide scanning system for bone marrow interpretation |
| KR20200082746A (en) * | 2018-12-31 | 2020-07-08 | (주)유아이엠디 | Cell-zone labeling apparatus and cell-zone detecting system including the same apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20230009718A (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7458519B2 (en) | Image analysis method, image analysis device, program, method for producing trained deep learning algorithm, and trained deep learning algorithm | |
| CN101339185B (en) | Automatic microscopic imager for detecting cast-off cells and detection method | |
| JP4550415B2 (en) | Quantitative video microscopy and related system and computer software program products | |
| KR20000064473A (en) | Boundary Mapping System and Method | |
| CN113667584A (en) | Colony contrast collection | |
| EP2040218B1 (en) | Image processing device and image processing program | |
| US9607372B2 (en) | Automated bone marrow cellularity determination | |
| WO2020141812A1 (en) | Region of interest labeling device for bone marrow interpretation, and region of interest detection system comprising same | |
| WO2012041333A1 (en) | Automated imaging, detection and grading of objects in cytological samples | |
| CN108319815B (en) | Method and system for virtually staining cells | |
| KR20200100062A (en) | Histological image analysis | |
| RU2504777C2 (en) | Method for cellular analysis of probe by means of virtual analytical plate | |
| WO2023282462A1 (en) | Blood cell detection and classification method based on examination area designation | |
| US20090141979A1 (en) | Image processing device and recording medium storing image processing program | |
| CN102203657B (en) | Prepare the step of treated Virtual Analysis image | |
| US20100221765A1 (en) | Microtube reader device for the analysis of blood samples | |
| KR101106386B1 (en) | System for classifying slides using scatter plot distributions | |
| CN111583186A (en) | Pathological ER/PR (ER/PR) cell nucleus counting method and system for clinical application | |
| WO2012126346A1 (en) | Method for rapidly determining dna content in cell nucleus | |
| US8744827B2 (en) | Method for preparing a processed virtual analysis plate | |
| EP2075757A2 (en) | Image processing device and image processing program | |
| WO2022124832A1 (en) | Method for determining cell zone of sample image of slide smeared with bone marrow, and method for imaging cell zone at high magnification | |
| KR101704690B1 (en) | Apparatus and method for analyzing cell | |
| Murakami et al. | Color processing in pathology image analysis system for liver biopsy | |
| WO2023234602A1 (en) | Method for providing image analysis information of blood sample |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22837816 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |