Apparatus and method for analyzing a bodily sample
Apparatus and methods are described for use with a digital camera that is configured to acquire images of a bodily sample. Two or more stains are configured to stain the bodily sample. A computer processor drives the digital camera to acquire, for each of a plurality of imaging fields of the bodily sample, two or more digital images, at least one of the images being acquired under brightfield lighting conditions, and at least one of the images being acquired under fluorescent lighting conditions. The computer processor performs image processing on the digital images, by extracting visual classification features from the digital images and analyzing the extracted visual classification features. The computer processor outputs a result of the image processing that includes an indication of one or more entities that are contained within the sample. Other applications are also described.
1. A method comprising: staining a blood sample with at least two stains; subsequent to staining the blood sample with the at least two stains, acquiring, for each of a plurality of imaging fields of the blood sample, at least two digital images, at least one of the digital images being acquired under brightfield lighting conditions, and at least one of the digital images being acquired under fluorescent lighting conditions; and performing image processing on the digital images, by: identifying first visual features within the at least one of the digital images acquired under brightfield lighting conditions; identifying second visual features within the at least one of the digital images acquired under fluorescent lighting conditions; and determining locations of at least one of the first visual features with respect to locations of at least one of the second visual features; identifying at least one entity that is present within the blood sample, by analyzing the determined locations of the at least one of the first visual features and the locations of the at least one of the second visual features, the analyzing comprising processing said at least one of the first visual features and said at least one of the second visual features, using a machine-learning algorithm; and generating an output that includes an indication of the at least one entity that is present within the blood sample; wherein identifying at least one entity that is present within the blood sample comprises determining that at least one red blood cell within the blood sample is infected with a parasite, by analyzing the determined locations of the at least one of the first visual features and the locations of the at least one of the second visual features, further wherein determining that at least one red blood cell within the blood sample is infected with a parasite comprises identifying plasmodium as being contained within the at least one red blood cell within the blood sample, by analyzing the determined locations of the at least one of the first visual features and the locations of the at least one of the second visual features; The method further comprising placing the blood sample into a cartridge that includes at least one microfluidic channel, wherein acquiring at least two digital images for each of the plurality of imaging fields of the blood sample comprises acquiring at least two digital images, for each of the plurality of imaging fields of the blood sample, while the blood sample is housed within the cartridge; The method further comprising, wherein placing the blood sample into the cartridge comprises placing the blood sample into a cartridge that defines at least one microfluidic channel that defines a channel height that permits only a single layer of cells to fill each channel from among the at least one channel, such that the cells form a monolayer within the channel.
2. The method according to claim 1 , wherein staining the blood sample with at least two stains comprises staining the blood sample with Hoechst.
3. The method according to claim 1 , wherein staining the blood sample with at least two stains comprises staining the blood sample with acridine orange.
4. The method according to claim 1 , wherein staining the blood sample with at least two stains comprises staining the blood sample with at least one stain that differentially stains DNA.
5. The method according to claim 1 , wherein staining the blood sample with at least two stains comprises staining the blood sample with at least one stain that differentially stains RNA.
6. The method according to claim 1 , wherein:
performing the image processing on the digital images further comprises classifying the first and second visual features by determining at least one classification feature associated with the first and second visual features, the at least one classification feature being selected from the group consisting of: motion, size, shape, coloring, contrast, location in respect to additional biological structures, presence of internal structures, presence of extracellular structures, aspect ratio, optical density, fluorescence at predetermined wavelengths, optical birefringence, clustering behavior, and pattern matching, and
identifying at least one entity that is present within the blood sample further comprises identifying at least one entity that is present within the blood sample, at least partially based upon the determined classification features.
7. The method according to claim 1 , wherein performing the image processing on the digital images comprises performing image processing on the digital images, by utilizing at least one computer processor module selected from the group consisting of: a single frame classification cascade module, a multi-frame candidate construction module, a multi-frame candidate tracking module, a multi-frame candidate classification module, a sample classification module, a motion field construction module, an image verification module, a camera control model, and a masking module.
8. The method according to claim 1 , further comprising, based upon analyzing the at least one of the first visual features and the at least one of the second visual features, generating an output that includes an indication selected from the group consisting of: a finding of anemia, a finding of an unusual cell count, a cell count, a detection of red blood cells which contain a significant amount of DNA, and information on quality of the blood sample.
9. The method according to claim 1 , wherein generating an output that includes an indication of the at least one entity that is present within the blood sample comprises generating an output that includes an indication selected from the group consisting of: a presence of the parasite, a species of the parasite, a number of the parasite detected, a concentration of the parasite, and a life stage of the parasite.
10. The method according to claim 1 , wherein generating an output that includes an indication of the at least one entity that is present within the blood sample comprises generating an output that includes at least one image of the parasite.
11. The method according to claim 1 , wherein placing the blood sample into the cartridge comprises placing the blood sample into a cartridge in which at least one of the at least two stains is present within the cartridge in a form selected from the group consisting of: liquid, solid, a coating, and dried within the cartridge.
12. The method according to claim 1 , wherein placing the blood sample into the cartridge comprises placing the blood sample into a cartridge that includes an orifice, the method further comprising adding a reagent to the blood sample, via the orifice, after the blood sample has been placed within the cartridge.