Search

Search Results

UBC Dataverse Logo
Borealis
Berryman, Samuel; Matthews, Kerryn; Lee, Jeonghyun; Ma, Hongshen 2020-09-21 Abstract: The ability to phenotype cells is fundamentally important in biological research and medicine. Cur-rent methods rely primarily on fluorescence labeling of specific markers. However, there are many situations where this approach is unavailable or undesirable. Machine learning has been used for image cytometry but has been limited by cell agglomeration and it is currently unclear if this ap-proach can reliably phenotype cells that are difficult to distinguish by the human eye. Here, we show disaggregated single cells can be phenotyped with a high degree of accuracy using low-resolution bright-field and non-specific fluorescence images of the nucleus, cytoplasm, and cyto-skeleton. Specifically, we trained a convolutional neural network using automatically segmented images of cells from eight standard cancer cell-lines. These cells could be identified with an aver-age F1-score of 95.3%, tested using separately acquired images. Here we demonstrate the potential to develop an “electronic eye” to phenotype cells directly from microscopy images. Technical Info: 10X Fluorescent microscopy images of Trypsinized cells. Each Tiff image contains 6 different locations within a Greiner Sensoplate 96-well glass bottom imaging well. Channels are in order: Brightfield, Hoechst, SIR-Actin and Calcein Green. Images were taken on a Nikon TI2E with a DS-QI2 Camera.
FRDR Logo
Federated Research Data Repository / dépôt fédéré de données de recherche
Lamoureux, Erik S.; Islamzada, Emel; Wiens, Matthew V. J.; Matthews, Kerryn; Duffy, Simon P.; Ma, Hongshen 2022-06-16 Abstract: Red blood cell (RBC) deformability is a key biophysical property that enables their navigation through small spaces in the microvasculature. The loss of RBC deformability can be due to pathology, natural ageing, or storage, and can impede proper cell function. Established methods to assess RBC deformability require specialized equipment, long measurement time, and skilled personnel. To address this, we used a deep learning image classification approach to differentiate between softer and harder RBCs. Ground truth deformability assessment was conducted using a microfluidic ratchet sorting device. After microfluidic deformability sorting, cells were imaged in brightfield at 40X magnification. Our model predicted individual RBC deformability with 81 ± 11% accuracy averaged across ten donors. This produced RBC deformability assessments within 10.4 ± 6.8% of the value obtained using the microfluidic device. Measuring RBC deformability using imaging is desirable as it only requires a standard imaging microscope, expanding its accessibility to clinics or research groups where this evaluation would otherwise not be feasible. Technical Information: 40X brightfield microscopy images of red blood cells in a 96-well imaging plate. Full well image scans were conducted using a DS-Qi2 camera on a Nikon Ti-2E inverted microscope, capturing images of 2424 x 2424 pixels.

Map search instructions

1.Turn on the map filter by clicking the “Limit by map area” toggle.
2.Move the map to display your area of interest. Holding the shift key and clicking to draw a box allows for zooming in on a specific area. Search results change as the map moves.
3.Access a record by clicking on an item in the search results or by clicking on a location pin and the linked record title.
Note: Clusters are intended to provide a visual preview of data location. Because there is a maximum of 50 records displayed on the map, they may not be a completely accurate reflection of the total number of search results.