Within the field of cellular pathology digitalisation is becoming widely implemented through systems called Whole Slide Image (WSI) Scanners. WSI scanners are systems made for digitising tissue samples, traditionally studied through light microscopes, by scanning them with a high-resolution camera. The system acquires images covering small parts of the sample, which are then stitched together to reconstruct an image of the tissue sample.
Lumito specialises in pathology using Up-Converting Nanoparticles (UCNP) that bind to markers in tissue samples and thus, for example, identify cancer cells. The nanoparticles undergo excitation by a near-infrared laser, resulting in an emission of light in the visible spectra, which is then captured by a camera. More specifically, the Lumito Scanner first acquires an image showing the tissue morphology, then excites the nanoparticles with the laser to acquire an image of the marker information. By overlaying these images, it is possible to showcase both morphological details and crucial tissue marker information.
Within whole slide imaging, focusing the camera is one of the main difficulties and a critical time-consuming component. Conventional methods collect stacks of images at selected z-positions in the sample and then calculate which z-position to use for image acquisition. Recently, methods have been presented using a single image to estimate how much out of focus an image is and in which direction focus should be adjusted. These methods provide substantial acceleration of sample acquisition or entirely remove the need to do focusing when scanning a sample. This will considerably reduce the scan time. Single shot focus evaluation could also be used for quality control of images by measuring perceived focus accuracy over the tissue sample.
- Develop methods to detect, measure, and minimise focus offsets from one tissue image.
- Evaluate how well this method could be transferred to UCNP images acquired by Lumito systems.
- Sun et al. (2005) – Autofocusing Algorithm Selection in Computer Microscopy
- Bian et al. (2020) – Autofocusing technologies for whole slide imaging and automated microscopy
- Senaras et al. (2018) – DeepFocus: Detection of out-of-focus regions in whole slide digital images using deep learning
- Ivanov et al. (2020) – DeepFocus: a deep learning model for focusing microscope systems
- Zhang et al. (2022) – Correction of out-of-focus microscopic images by deep learning
Who are you:
As an applicant for this master thesis project, you should be driven, creative and not afraid to take initiatives. You should be someone partaking in a master level education with experience in programming, mathematics, image analysis and machine learning. An interest in the field also adds value to your application.
To apply, please submit your CV, cover letter, and transcripts of records through our career page on our website.
To know more about the project, please contact:
Adam Belfrage, firstname.lastname@example.org