Method and device for detecting at least one fluorescence pattern on an immunofluorescence image of a biological cell substrate
A method is proposed for detecting at least one fluorescence pattern on an immunofluorescence image of a biological cell substrate, comprising the following steps: incubating the cell substrate with a liquid patient sample, which potentially includes primary antibodies, and furthermore with secondary antibodies, which are marked using a fluorescence stain, irradiating the cell substrate using excitation radiation and capturing the immunofluorescence image, determining segmentation information comprising at least one first and one second segmentation area, wherein the segmentation areas each represent a respective cell substrate area, via segmentation of the immunofluorescence image using a first neural network, determining a boundary area, which represents a transition from the first cell substrate area towards the second cell substrate area in the fluorescence image, on the basis of the segmentation information, selecting multiple partial images from the immunofluorescence image along the boundary area, determining a confidence measure of a presence of the fluorescence pattern on the basis of the multiple partial images via a second neural network.
1 . Method for detecting at least one fluorescence pattern on an immunofluorescence image of a biological cell substrate, comprising:
incubating the cell substrate(S) with a liquid patient sample, which potentially includes primary antibodies, and furthermore with secondary antibodies, which are marked using a fluorescence stain, irradiating the cell substrate using excitation radiation, and capturing the immunofluorescence image (FB), wherein the cell substrate is a skin substrate in the form of a salt-split skin comprising an epidermis, a dermis and a bubble between the epidermis and the dermis,
determining segmentation information (SEG) comprising at least one first and one second segmentation area (SEG 1 , SEG 2 ), wherein the segmentation areas each represent a respective cell substrate area (D, BL), via segmentation of the immunofluorescence image (FB) using a first neural network (NN 1 ),
determining a boundary area (GB 1 ), which represents a transition from the first cell substrate area (D) towards the second cell substrate area (BL) in the fluorescence image (FB), on the basis of the segmentation information (SEG), wherein the boundary area is a bubble roof between the epidermis and the bubble or a bubble floor between the dermis and the bubble,
selecting multiple partial images (TB 1 , . . . , TBX) from the immunofluorescence image (FB) along the boundary area (GB 1 ),
determining a confidence measure (KM) of a presence of the fluorescence pattern on the basis of the multiple partial images (TB 1 , . . . , TBX) via a second neural network (NN 2 ).
2 . Method according to claim 1 ,
furthermore comprising outputting the confidence measure (KM).
3 . Method according to claim 1 , furthermore comprising
determining a respective partial image confidence measure (TBKM 1 , . . . , TBKMX) for a respective partial image (TB 1 , . . . , TBX) via the second neural network (NN 2 )
and determining the confidence measure (KM) on the basis of the partial image confidence measures (TBKMX).
4 . Method according to claim 1 ,
furthermore comprising randomly based selection of the multiple partial images (TB 1 , . . . , TBX) from the immunofluorescence image (FB) along the boundary area (GB 1 ).
5 . Method according to claim 1 , furthermore comprising
determining a respective brightness value (TBHM 1 , . . . , TBHMX) for a respective partial image (TB 1 , . . . , TBX) via the second neural network (NN 2 ),
determining an overall brightness value (HM) on the basis of the brightness values.
6 . Method according to claim 1 ,
wherein the multiple partial images (TB 1 , . . . , TBX) are partial images of a first type, furthermore comprising
determining the segmentation information (SEG), comprising at least the first, the second, and furthermore a third segmentation area (SEG 1 , SEG 2 , SEG 3 ), which represents a third cell substrate area (DE), via segmentation of the immunofluorescence image (FB) using the first neural network (NN 1 ),
determining a second boundary area (GB 2 ), which represents a second transition from the second cell substrate area (BL) towards the third cell substrate area (DE) in the fluorescence image (FB), on the basis of the segmentation information (SEG),
selecting multiple partial images of a second type from the immunofluorescence image along the second boundary area (GB 2 ),
determining a second confidence measure of a presence of a second fluorescence pattern on the basis of the multiple partial images of the second type via a third neural network (NN 3 ).
7 . Method for digital image processing, comprising:
providing an immunofluorescence image (FB), which represents a staining of a biological cell substrate by a fluorescence stain, wherein the biological cell substrate is a skin substrate in the form of a salt-split skin comprising an epidermis, a dermis and a bubble between the epidermis and the dermis,
determining segmentation information (SEG) comprising at least one first and one second segmentation area (SEG 1 , SEG 2 ), wherein the segmentation areas each represent a respective cell substrate area, via segmentation of the immunofluorescence image (FB) using a first neural network (NN 1 ),
determining a boundary area (GB 1 ), which represents a transition from the first cell substrate area towards the second cell substrate area (BL) in the fluorescence image (FB), on the basis of the segmentation information (SEG), wherein the boundary area is a bubble roof between the epidermis and the bubble or a bubble floor between the dermis and the bubble,
selecting multiple partial images (TB 1 , . . . , TBX) from the immunofluorescence image (FB) along the boundary area (GB 1 ),
determining a confidence measure (KM) of a presence of the fluorescence pattern on the basis of the multiple partial images (TB 1 , . . . , TBX) via a second neural network (NN 2 ).
8 . Computer program product (CPP), comprising commands which, upon the execution of the program by a computer, prompt it to carry out the method for digital image processing according to claim 7 .
9 . Data carrier signal (SI 2 ), which transmits the computer program product (CPP) according to claim 8 .
10 . Device for detecting at least one fluorescence pattern on an immunofluorescence image (FB) of a biological cell substrate, comprising:
a holder (H) for an object carrier having the cell substrate(S), which was incubated with a patient sample, including the autoantibodies, and furthermore with secondary antibodies, which are each marked using a fluorescence stain, wherein the cell substrate(S) is a skin substrate in the form of a salt-split skin comprising an epidermis, a dermis and a bubble between the epidermis and the dermis,
at least one camera (K 1 ) for capturing a fluorescence image (SG) of the cell substrate(S)
and furthermore comprising at least one computing unit (R), which is designed to execute the following steps
determining segmentation information (SEG) comprising at least one first and one second segmentation area (SEG 1 , SEG 2 ), wherein the segmentation areas each represent a respective cell substrate area, via segmentation of the immunofluorescence image (FB) using a first neural network (NN 1 ),
determining a boundary area (GB 1 ), which represents a transition from the first cell substrate area (D) towards the second cell substrate area (BL) in the fluorescence image (FB) on the basis of the segmentation information (SEG), wherein the boundary area is a bubble roof between the epidermis and the bubble or a bubble floor between the dermis and the bubble,
selecting multiple partial images (TB 1 , . . . , TBX) from the immunofluorescence image (FB) along the boundary area (GB 1 ),
determining a confidence measure (KM) of a presence of the fluorescence pattern on the basis of the multiple partial images (TB 1 , . . . , TBX) via a second neural network (NN 2 ).
11 . Data network device (DV),
comprising at least one data interface (DS 4 ) for accepting a fluorescence image (FB), which represents a staining of a cell substrate by a fluorescence stain, wherein the cell substrate is a skin substrate in the form of a salt-split skin comprising an epidermis, a dermis and a bubble between the epidermis and the dermis,
and furthermore comprising at least one computing unit (R), which is designed to execute the following steps in the course of digital image processing
determining segmentation information (SEG) comprising at least one first and one second segmentation area (SEG 1 , SEG 2 ), wherein the segmentation areas each represent a respective cell substrate area, via segmentation of the immunofluorescence image (FB) using a first neural network (NN 1 ),
determining a boundary area (GB 1 ), which represents a transition from the first cell substrate area (D) towards the second cell substrate area (BL) in the fluorescence image (FB), on the basis of the segmentation information (SEG), wherein the boundary area is a bubble roof between the epidermis and the bubble or a bubble floor between the dermis and the bubble,
selecting multiple partial images (TB 1 , . . . , TBX) from the immunofluorescence image (FB) along the boundary area (GB 1 ),
determining a confidence measure (KM) of a presence of the fluorescence pattern on the basis of the multiple partial images (TB 1 , . . . , TBX) via a second neural network (NN 2 ).