Iteration 3 LCP

Iteration goals:

In this iteration we will make a progress in the project. After making DeepMedic work, and only reading about Cascaded-FCN for RCF and Faster-RNNLM for classifier, we will dive into those 2 projects, understanding what's going on there. Plus, taking what we need - RCF and classifier. Please review the important links found downstairs and see all the work we've done.

Lists of goals:

• Improve DeepMedic work
• Improve Yolo work
• Finish project
• Project book
• Getting ready for final exam.

use cases:

• Learning.
• Classifying.

Retro prospective - goals and results:

• We have achieved most of our goals.
• We got nice results in deep medic - segmentations of the ribs, and even more bones.
• From yolo - the system detected all the bones we wanted, but labeling is not good - "person".

Roles:

Team: Alon and stav
Generally:

• Alon - Classifier
• Stav - DeepMedic

Issue Management:

Issue Board

Iteration 3 Issues

Tests:

• According to tests plan as shown on report - functional and non-functional tests, being documented.
• Checks for synthetic data if needed.
• Evaluate Segmentation

Points Summary:

• Yolo - data modification - 13 points
• DeepMedic - accuracy - 13 points
  
• Final video - 5 points
  
• Project book - 8 points
  
• Expanding examinations - 5 points
  
• Code tests - 5 points
• Exam preparations - 8 points
  
• Code factoring - 5 points
  
• Yolo experiments - 2 points
  

Total: 64 points

LCF - Learning, Classifying and Presentation

This stage actually finishes the learning and classifying stage. Plus, it deals with the presentation on June 19 2017.

Important Links

• Working Document - All information gathered through this iteration.
• Research Blog

Iteration Summary:

• As a summary, We almost done, and it is almost perfect for us. We want to make deep medic more accurate, and try to label yolo better. This is up to Iteration 4.

To improve:

• Deepmedic more accurate.
• Yolo's labeling

To sum it up:

• Now start the learning for the exam.
• Making more small improvements.

Next Iteration:

Iteration 4 FPS