EE/CSE 577 Final Project

Assigned: Nov 1, 2017

Proposal due: Nov 6, 2017

Status reports due: Nov 27, 2017

Posters to Shu to print: Dec 9, 2017 11:59pm in Drop Box

Final poster presentation: Dec 11, 2017

Final reports due: Dec 13, 2017 NOON in Drop Box

Synopsis

For the final project, we anticipate that people will work in teams of two or three. 

There are two options for this project, which will take roughly five weeks:

1. Implement a state-of-the-art research paper from a recent computer vision/ medical imaging conference or journal (MICCAI, EMBC, SPIE, AAPM et al.).
2. Complete a short research project (more fun!).

You can devise your own project from scratch, or use one of the ideas suggested below. In either case, the purpose is to get a feel for doing research in medical image analysis.

Guidelines

Option 1

Start by searching through recent medical imaging conference proceedings or journal articles, and choosing a paper that interests you. You should select a paper that is appropriate for a four-week project. I.e., it should be more involved than one of the class assignments. Our expectation is that you will implement the method yourself rather than using any code that the authors make available .

Option 2

For this option we'd like you to do a research project with some novelty, i.e., something that no one has published before. Naturally we're not expecting PhD-level research in this amount of time, but since two or three of you will be working together you should be able to come up with exciting results :)

You can choose to work on the medical imaging datasets we provided (see Project ideas for details) or find a dataset for your own project. Here are some challenges for medical image analysis.

Following, are some examples of what we have in mind.

• An interesting extension of prior work. In most cases, we'd recommend implementing the prior method yourself, rather than downloading implementations available online, as this gives you a better understanding of how the method works (and you can avoid mucking around with some one else's code). But this is not a hard and fast rule -- if the extension is very significant you may use available code.
• A new application of prior work. Apply a known technique to a new application domain, and evaluate its performance.
• Develop a new solution (hopefully better!) to an existing problem. If you chose this option, you have to figure out the solution by the time you submit the proposal, to convince us that your method will work.
• Pose a new technical problem and solve it. Identify a new problem for which no known solution exists, devise a solution, and implement/test it. If you chose this option, you have to figure out both the problem and solution by the time you submit the proposal.

How ambitious/difficult should your project be? Each team member should count on committing substantially more effort than on the previous class assigments.
 

Requirements

Proposal

Each team will turn in a one-page proposal describing their project. It should specify:

• Your team members
• Project goals. Be specific. Describe the input and output.
• Milestones you anticipate reaching along the way.
• Dataset that you want to use.

Each team must submit a proposal, even if you choose one of the research ideas described below.

Status reports

Each team will post a status report in the middle summarizing progress to date. 

Final poster presentation

We will have a poster session a Dec 11, 2:30 to 4:30 in the EE Atrium, where each group will present their project to the class. Details will be announced closer to the time of the poster session.

Final Write-up

Turn in a writeup paper (by noon, Dec 13) describing your problem and approach. It should include the following:

• Title and team members
• Short intro
• Related work, with references to papers, web pages
• Technical description including algorithm
• Experimental results
• Discussion of results, strengths/weaknesses, what worked, what didn't.
• Future work and what you would do if you had more time

Turn in format

All the writeups should be submitted through Catalyst dropbox and in the NIPS format.

Project Ideas for Option 2

We also provide several medical imaging datasets and possible project ideas. Human subject training HSD is required to access the datasets. Please email Shu liangshu@cs.washington.edu with the certificate if you want to use the data. Feel free to use the dataset and choose variations of the ideas or to devise your own research problems that are not on this list. You can either leverage machine learning or not, depending on your skill set and target. We're happy to meet with you to discuss any of these (or other) project ideas in more detail.

1. 3dMD human head dataset. The database includes meshes of 1204 distinct Caucasian individuals, ages 3-40 obtained by a 3dMD digital stereophotogrammetry system. The database does not include texture or color information. Each mesh includes 15K-20K vertices. Subjects all face forward, have a neutral expression, and wear caps to remove hair occlusions. Meshes are cleaned by trained personnel. You can perform gender or age classification.

2. Cancer biopsy dataset. The task is to classify a given region of interest (ROI) from a whole slide biopsy to one of the four diagnostic categories: benign, atypia, DCIS and invasive. There are 428 ROIs marked and diagnosed by expert pathologists. ROIs have different sizes and shapes but each has only one diagnostic label. You can use different approaches to overcome size differences: sliding windows, resizing etc.

3. 3D Organ Reconstruction. The task is to reconstruct one of the online datasets such as LiTS and try to reconstruct 3D models of organs such as livers.