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 base dataset
  4. You’ll then need to train a deep neural net, with simulated dataset, and the physical parameters in mind
  5. Please see slides at the beginning of Lecture 14 for some example topics and details about the project proposal

Your final report and materials will include the following:

  1. The project’s source code
  2. A short research-style paper (3 pages minimum, 6 pages maximum) that includes an introduction, results, a discussion section, references and at least 2 figures
  3. A completed web template containing the main results from the research paper
  4. An 8-minute presentation to deliver to the class with your group

Here are some important dates:

  • Project proposal due date: Thursday November 7, 2019
  • Revised project proposal due date: Tuesday November 12, 2019
  • Final report due and presentation: December 13, 7 pm – 10 pm

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

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)