DeepEdit

What is a DeepEdit based App?

DeepEdit is an algorithm that combines the power of two models in one single architecture. It allows the user to perform inference, as a standard segmentation method, and also to interactively segment part of an image using clicks. DeepEdit aims to facilitate the user experience and to facilitate the development of new active learning techniques.

Training schema:

Inference schema:

Performance examples for left atrium and spleen DeepEdit App:

Left Atrium App:

Assumptions/conditions made to create this plot:

• We used the Heart MSD dataset (http://medicaldecathlon.com/). Four images for validation and 16 for training were used to obtain this validation plot.
• A skilled user takes 10 minutes to manually segment the left atrium in cardiac MR image
• One epoch using 2 images took aprox. 30 seconds. Adding an image makes the epoch take 10 more seconds

Spleen App:

Assumptions/conditions made to create this plot:

• We used the Spleen MSD dataset (http://medicaldecathlon.com/). Six images for validation and 35 for training were used to obtain this validation plot.
• A skilled user takes 10 minutes to manually segment the left atrium in cardiac MR image
• One epoch using 2 images took aprox. 50 seconds. Adding an image makes the epoch take 10 more seconds