The material for the Quantitative Big Imaging course at ETHZ for the Spring Semester 2019
The data for the example can be downloaded from here and extract the train.zip file
Open the file in Archive Manager and extract the data to /scratch
(only on D61.1 machines)
For each .tif file there is an associated _mask.tif corresponding to the ground truth
Many of these workflows are fairly complicated and would be time consuming to reproduce, follow the instructions here for how to import a workflow from the zip files on this site
If you load a workflow and get an error message, click on the details button. If it says ‘Node … not available’ it means you need to update your ‘Image Processing Extensions’ follow the instructions below to perform this update: instructions
Steps are shown in normal text, comments are shown in italics.
Knime Basics: here
Use workflow variables: here
The task from the lecture of identifying the nerve in the ultrasound image .
We thus have these data loaded in the workflow as the image and ground truth respectively.
The ROC curve’s discussed in the last lecture we will use as a tool for evaluating our accuracy for the rest of the course. An example work-flow is below to generate the above curve.
Download the workflows here
Parameter Optimization Loop Start
node to find the best filter size to maximize the ROC area