Cellmax, Ltd

XiaoMing Wang

Huangpin Ben Hsieh

Rui Mei

Jen-Chia Wu

Hung-Jen Shao

Jr-Ming Lai

Techniques for identifying and enumerating candidate target cells within a biological fluid specimen are described. A digital image of the biological fluid specimen is received, and one or more candidate regions of pixels in the digital image are identified by identifying connected regions of pixels of a minimum intensity having a size between a minimum size and a maximum size and an aspect ratio that meets a threshold. For each candidate region of at least one of the one or more candidate region, whether the portion of the image corresponding to the candidate region includes more than a threshold number of intensity levels is determined. If the portion of the image corresponding to the candidate region includes more than the threshold number of intensity levels the portion of the image is continued to be treated as a candidate for classification.

Identifying candidate cells using image analysis with intensity levels

A method for identifying candidate target cells within a biological fluid specimen includes a digital image of the biological fluid specimen with the digital image having a plurality of color channels, identifying first connected regions of pixels of a minimum first intensity in a first channel, identifying second connected regions of pixels of a minimum second intensity in a second channel, and determining first connected regions and second connected regions that spatially overlap. For a pair of a first connected region and a second connected region that spatially overlap, whether the second connected region overlaps the first connected region by a threshold amount is determined, and if the second connected region overlaps the first connected region by the threshold amount then the portion of the image corresponding to the overlap is continued to be treated as a candidate for classification.

Identifying candidate cells using image analysis with overlap thresholds

A method for identifying and enumerating candidate target cells within a biological fluid specimen is described. The method includes obtaining a biological fluid specimen, preparing the biological fluid specimen by staining cell features in the biological fluid specimen, capturing a digital image having a plurality of color channels of the biological fluid specimen, and applying image analysis to the digital image. A computer program product for identifying candidate target cells within a biological fluid specimen is also described. The computer program comprises instructions to cause a processor to carry out the image analysis.

Growing community of inventors

Dublin, CA, United States of America

XiaoMing Wang