Method of detecting presences of different antinuclear antibody fluorescence pattern types without counterstaining and apparatus therefor
Inventors
Krause, Christopher • KRAUTH, Jens • Gerlach, Stefan • MARZAHL, Christian • Hahn, Melanie • VOIGT, Joern
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12209965-B2
Publication Date
2025-01-28
Expiration Date
Abstract
A method and apparatus are provided for detecting respective potential presences of respective different cellular fluorescence pattern types on a biological cellular substrate including human epithelioma cells (HEp cells), wherein the fluorescence pattern types include different antinuclear antibody fluorescence pattern types. A method is also provided for detecting potential presences of different cellular fluorescence pattern types on a biological cellular substrate including human epithelioma cells by means of digital image processing, as well as a computing unit, a data network device, a computer program product and a data carrier signal therefor.
Core Innovation
The invention relates to detecting respective potential presences of different cellular fluorescence pattern types on a biological cellular substrate comprising human epithelioma cells, wherein the cellular fluorescence pattern types comprise a plurality of different antinuclear antibody fluorescence pattern types. The method incubates the cellular substrate with a liquid patient sample which potentially comprises primary antibodies and with secondary antibodies labelled with a fluorescent dye, and acquires a total image that represents staining of the cellular substrate due to the fluorescent dye. A segmented image is determined by segmentation of the total image.
Image segments are detected in the segmented image, where each image segment represents a metaphase plate of a mitosis cell in a metaphase stage. Sub-images of the total image are selected, each comprising at least one mitotic cell, and corresponding sub-images of the segmented image are selected on the basis of the detected image segments. Respective actual presences of the cellular fluorescence pattern types are then detected by means of a convolutional neural network on the basis of the selected sub-images of the total image and the selected sub-images of the segmented image.
The convolutional neural network processes, in each case, a tuple of sub-images at the same time, which comprises at least one selected sub-image of the total image and a corresponding selected sub-image of the segmented image. Segmentation enables detection of metaphase plate segments so that mitotic sub-images are selected, and the paired sub-images are jointly processed by the convolutional neural network to detect actual presences of the different cellular fluorescence pattern types.
Claims Coverage
The provided material includes four independent claims covering a method, an apparatus, and additional method and digital image processing/computing unit variants. Across these independent claims, the main inventive features are segmentation-based detection of metaphase plate regions for selecting mitotic sub-images, and CNN processing of paired sub-image tuples consisting of total-image and corresponding segmented-image sub-images.
Metaphase plate segmentation for sub-image selection
Detect image segments in the segmented image wherein a respective image segment represents a respective metaphase plate of a mitosis cell in a metaphase stage, and select sub-images of the total image each comprising at least one mitotic cell together with corresponding sub-images of the segmented image on the basis of the detected image segments.
Paired tuple processing of total and segmented sub-images by a convolutional neural network
Detect respective actual presences of the respective cellular fluorescence pattern types by means of a convolutional neural network on the basis of the selected sub-images of the total image and the selected sub-images of the segmented image, wherein the convolutional neural network processes, in each case, a tuple of sub-images at the same time comprising at least one selected sub-image of the total image and a corresponding selected sub-image of the segmented image.
Fluorescence staining imaging on human epithelioma cells with liquid patient sample antibodies
Incubate the cellular substrate with a liquid patient sample which potentially comprises primary antibodies and secondary antibodies labelled with a fluorescent dye, and acquire a total image which represents staining of the cellular substrate due to the fluorescent dye.
Computing unit configured for segmentation, metaphase plate detection, sub-image selection, and CNN presences detection
A computing unit which is configured to receive a total image, determine a segmented image by segmentation of the total image, detect image segments representing metaphase plates of mitosis cells in a metaphase stage, select sub-images and corresponding sub-images of the segmented image based on the detected segments, and detect respective actual presences of the cellular fluorescence pattern types by means of a convolutional neural network processing paired sub-image tuples at the same time.
The independent claims consistently cover segmentation of the total fluorescence image to find metaphase plate segments of mitotic cells, selecting corresponding sub-images from both the total and segmented images, and using a convolutional neural network that processes paired total-image and segmented-image sub-image tuples simultaneously to detect actual presences of different cellular fluorescence pattern types.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?