Developing an Automated Microscope Integrated with Deep Learning Postprocessing to Conduct Preliminary Cancer Diagnosis
PublicDownloadable Content
open in viewerCancer is a disease that affects nearly 40% of the United States population. The current diagnosis process can take several days, and requires a highly trained pathologists. Occasionally, biopsy samples do not have enough cellular material to make a proper diagnosis, and the patients must undergo a secondary procedure before a confident cancer diagnosis can be composed. This project aims to accelerate the process by using an automated microscope outfitted with image-processing artificial intelligence to complete a preliminary stage of diagnosis to determine if adequate amounts of cell clusters have been collected from the procedure. A prototype integrated with RCNN was constructed that images microscope slides and identifies cell clusters found in fine needle aspirations.
- This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
- Creator
- Publisher
- Identifier
- E-project-042618-091622
- Advisor
- Year
- 2018
- Date created
- 2018-04-26
- Resource type
- Major
- Rights statement
Relations
- In Collection:
Items
Items
Thumbnail | Title | Visibility | Embargo Release Date | Actions |
---|---|---|---|---|
bwestgate_jlaroche_mqp.pdf | Public | Download |
Permanent link to this page: https://digital.wpi.edu/show/6q182n781