Automated method of identifying a structure
AssigneeLa Trobe University
InventorsBrian Abbey, Eugeniu Balaur
Life of this patent
Estimating the term…
Abstract
An automated method of identifying a structure in a sample is disclosed. The method includes receiving at least one digital image of a sample wherein at least one localised structural property of the sample is visible in the image based on the colour of received light. The method involves processing the at least one image, based on the received colour information to selectively identify said structure. The method can include colour and/or morphology based image analysis.
Claims20
An automated method of identifying a structure in a sample, the method comprising:
- receiving at least one digital image of a sample wherein at least one localised structural property of the sample is visible in the image based on the colour of received light captured in the at least one digital image, said digital image comprising a plurality of pixels;
- processing the at least one image, based on the received colour information to selectively identify said structure.
The method as claimed in any one of the preceding claims wherein the at least one image includes a plurality of pixels, and said method includes segmenting the at least one image based on a colour of received light captured in the image.
The method as claimed in any one of the preceding claims which includes any one or more of:
- determining a colour distribution of the received image;
- determining a colour histogram of the received image;
- performing spectral analysis of at least part of the received digital image.
The method as claimed in any one of the preceding claims which includes performing a feature extraction method to identify one or more structures in the image.
The method as claimed in any one of the preceding claims wherein the method includes processing the digital image with an image recognition system.
The method as claimed in any one of the preceding claims wherein in the received digital image, the localised structural property of the sample is a localised refractive index.
The method as claimed in any one of the preceding claims wherein the sample is a biological sample.
The method as claimed in any one of the preceding claims wherein the method includes identifying a feature based on colour differentiation.
The method as claimed in any one of the preceding claims wherein the method includes identifying a feature based on morphology differentiation.
The method as claimed in any one of the preceding claims wherein the method includes identifying a feature based on a combination of colour differentiation and morphology differentiation.
The method as claimed in any one of the preceding claims wherein receiving at least one digital image of a sample, includes receiving more than one image of the sample captured with any one or more of the following differences:
- a different illumination characteristics
- different illumination spectrum
- different illumination polarisation
- different magnification.
The method of any one of the preceding claims wherein the structure includes any one or more of a neoplastic cell, cancer cell, healthy cell, cell of a given type, cell state, parasite, group of cells, abnormal cell, infected cell, tissue of a given type.
A method of imaging a sample and automatically generating an indication of a presence of at least one structure in the sample, the method includes:
- providing a sample holder having a plasmonic layer including a periodic array of sub-micron structures;
- placing the sample on the sample holder adjacent the plasmonic layer;
- illuminating the sample and sample holder and capturing at least one colour digital image thereof;
- performing a method of identifying a structure in the sample according to any one of the preceding claims.
Dependencies are inferred from the claim text.