Here is some information about the final project:

  1. You can work alone or in a group (up to 4 people), required effort will scale with # of people
  2. Select a “base” dataset (see examples below)
  3. You’ll need to simulate parameters of a physical (imaging) system with a base dataset to form a modified dataset
  4. You’ll then need to train a deep neural network, with the modified dataset, and the physical parameters in mind
  5. Please see slides from class for a number of examples and discussions

Here is a link to the final project instructions: Final project instructions

Here is a link to a template for the final project research-style paper: Template for research-style paper

Here is a link to a template for the final project short webpage: Template for final project webpage

Here is a link to the permission form: Permission form

Using the above files, you’ll thus turn in the following:

  1. An 7-minute presentation with slides that you will give to the class during the final period
  2. A short research-style paper (4 - 6 pages on average) that includes an abstract, introduction, related work, methods, results, a discussion, references and at least 3 figures.
  3. The project’s source code
  4. A completed web template containing the main results from the research paper
  5. A completed permission form

Here are some important dates:

  • Final code and presentation due via email: Sunday April 30 at 6pm
  • Final presentation time slots: Monday May 1, 9am - noon
  • Final presentation paper write-up, website template and permission form due: Friday May 5 at 6pm
  • Final presentations will occur via Zoom, please coordinate with team members and practice ahead of time!

Some datasets that might be helpful:

  1. Grand Challenge datasets - lots of datasets to choose from here!
  2. Label free prediction datasets from Allen Institute
  3. HAM10000 pigmented skin lesion dataset
  4. In-silico labeling dataset
  5. Publically labeled Cell Atlas dataset
  6. Large number of datasets from the Broad Institute
  7. Biological image synthesis
  8. IDR Open Microscopy datasets
  9. Tensorflow Datasets
  10. Fourier MNIST and malaria datasets
  11. Scene Flow datasets
  12. NYU depth dataset
  13. Scattering media dataset from Rice
  14. Flatcam Face dataset
  15. DeepLesion CT dataset
  16. The Cancer Imaging Archive
  17. Kaggle
  18. Augmented Cognition Laboratory(ACLAB) - northeastern university
  19. Zenodo
  20. Haravard Dataverse
  21. Mendeley Datasets
  22. ISIC challenge datasets
  23. Broad Institute
  24. Medical Imagery Datasets
  25. MICCAI
  26. Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving
  27. Multispectral Image Recognition
  28. COVID-NET
  29. Awesome Data
  30. Refocusing and Super Resolution dataset for Cytology, Original Paper Link

Here are a few useful datasets that were used in previous classes:

  1. Malaria-infected blood cells under variable-angle illumination
  2. Annotated microscope images of malaria-infected blood, tuberculosis in sputum, and other parasites
  3. Broad Institute Annotated Cell Image Datset
  4. Microwave Detection of Hand Gestures from the Smith Lab at Duke
  5. High Dynamic Range Color Image Dataset
  6. Optical Coherence Tomography Annotated Datasets from Farsiu Lab at Duke
  7. Chest X-ray images (pneumonia)