Icon

Training Spheroid Detection Model

This workflow reads and processes raw images taken with CytoSMART Lux2 and Lux 3 BR microscopes. The images are joined with labels provided by technical experts indicating if a spheroid is present in the corresponding image, yes (1) or no (0). The Resnet50 model is used and the last 1/3 of the layers are retrained to adjust the model to this particular use case.

**IMPORTANT**
This workflow only contains a subset of the data that was used for the training of the original model. The remaining data was only provided for training and not for publication.

Duplicate grayscaleto RGB channelsLoad Resnet50mactrain 1/3best_model.h5List Files/Folders Excel Reader Path to String Column Expressions Column Expressions Joiner Image Reader(Table) Image Resizer Gray to RGB DL PythonNetwork Creator Conda EnvironmentPropagation DL PythonNetwork Editor Keras Freeze Layers DL PythonNetwork Learner DL Python NetworkExecutor Scorer View Partitioning Duplicate grayscaleto RGB channelsLoad Resnet50mactrain 1/3best_model.h5List Files/Folders Excel Reader Path to String Column Expressions Column Expressions Joiner Image Reader(Table) Image Resizer Gray to RGB DL PythonNetwork Creator Conda EnvironmentPropagation DL PythonNetwork Editor Keras Freeze Layers DL PythonNetwork Learner DL Python NetworkExecutor Scorer View Partitioning

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: janinamothes
Created at: 2022-02-11
On NodePit since: 2022-05-16
Last update: 2026-01-20
Created with KNIME version: v4.5.2

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!