System and method for distinguishing between biological materials

An apparatus for distinguishing cells, comprising:

• an image receiving device configured to:
• provide at least one segmented image of at least two confluent cells;
• apply a distance transform to the at least one segmented image of the confluent cells;
• apply a region growing technique to the distance transform of the at least one segmented image to form a region grown image, wherein a plurality of regions are formed in the at least one segmented image;
• assign at least one label to at least one of the plurality of regions of the at least one segmented image;
• apply a merging technique to at least two of the plurality of regions of the segmented image of the confluent cells if it is determined that at least two of the plurality of regions of the at least one segmented image of the confluent cells are neighboring regions of the at least one segmented image of the confluent cells;
• determine whether to assign a same label to the neighboring regions of the at least one segmented image of the confluent cells or retain existing labels;
• and
• merge the neighboring regions if labels are changed of the region grown image into one image of at least one cell.

A system for distinguishing biological materials, comprising:

• an imaging system configured to receive an image of at least one cell in a previous frame, wherein the imaging system is connected to an image receiving device;
• an image receiving device configured to:
• provide at least one segmented image of at least two confluent cells;
• apply a distance transform to the at least one segmented image of the confluent cells;
• apply a region growing technique to the distance transform of the at least one segmented image of the confluent cells into a region grown image, wherein a plurality of regions are formed in the at least one segmented image of the confluent cells;
• assign at least one label to at least one of the plurality of regions of the at least one segmented image of the confluent cell;
• apply a merging technique to at least two of the plurality of regions of the segmented image of the confluent cell if it is determined that at least two of the plurality of regions of the at least one segmented image of the confluent cell are neighboring regions of the at least one segmented image of the confluent cells;
• determine whether to assign a same label to the neighboring regions of the at least one segmented image of the confluent cells or retain existing labels;
• and
• merge the neighboring regions if labels are changed of the region grown image of the confluent cells into one image of at least one cell.

A computer-implemented image processing method for distinguishing biological materials, the method comprising:

• providing at least one segmented image of at least two confluent cells;
• applying a distance transform to the at least one segmented image of the confluent cell;
• applying a region growing technique to the distance transform of the at least one segmented image of the confluent cells to form a region grown image, wherein a plurality of regions are formed in the at least one segmented image of the confluent cell;
• assigning at least one label to at least one of the plurality of regions of the at least one segmented image of the confluent cells;
• applying a merging technique to at least two of the plurality of regions of the segmented image of the confluent cell if it is determined that at least two of the plurality of regions of the at least one segmented image of the confluent cells are neighboring regions of the at least one segmented image of the confluent cells;
• determining whether to assign a same label to the neighboring regions of the at least one segmented image of the confluent cell or retain existing labels;
• and
• merging the neighboring regions if labels are changed of the region grown image into one image of at least one cell.