Icon

UNet_​Keras_​CellSegmentation

U-Net Encoder Decoder Architecture for Cell Segmentation

This workflow creates and trains a Unet for segmenting cell images. The trained network is used to predict the segmentation of unseen data.

Data:
The training data is a set of 30 sections from a serial section Transmission Electron Microscopy (ssTEM) data set of the Drosophila first instar larva ventral nerve cord (VNC). The microcube measures 2 x 2 x 1.5 microns approx., with a resolution of 4x4x50 nm/pixel.
The corresponding binary labels are provided in an in-out fashion, i.e. white for the pixels of segmented objects and black for the rest of pixels (which correspond mostly to membranes).
(Source: http://brainiac2.mit.edu/isbi_challenge/home)

The required extensions:
- KNIME Deep Learning - Keras Integration
- KNIME Image Processing - Deep Learning Extension

Unet Architecture Training data processing Test data processing Visualization of Test data Read in the images Cell SegmentationThis workflow creates and trains a Unet for segmenting cell images. The trained network is used to predict the segmentation of unseen data. convert labelings to byte U-Net 2D -Encoding Layer Keras Input Layer List Files Image Reader(Table) List Files Image Reader(Table) List Files Image Reader(Table) PreprocessingImages PreprocessingLabels PreprocessingImages Joiner Image Converter Image to Labeling Joiner InteractiveSegmentation View Keras Convolution2D Layer Keras NetworkLearner Keras NetworkExecutor U-Net 2D -Encoding Layer U-Net 2D -Encoding Layer U-Net 2D -Encoding Layer U-Net 2D -Encoding Layer U-Net 2D -Decoding Layer U-Net 2D -Decoding Layer U-Net 2D -Decoding Layer U-Net 2D -Decoding Layer Unet Architecture Training data processing Test data processing Visualization of Test data Read in the images Cell SegmentationThis workflow creates and trains a Unet for segmenting cell images. The trained network is used to predict the segmentation of unseen data. convert labelings to byte U-Net 2D -Encoding Layer Keras Input Layer List Files Image Reader(Table) List Files Image Reader(Table) List Files Image Reader(Table) PreprocessingImages PreprocessingLabels PreprocessingImages Joiner Image Converter Image to Labeling Joiner InteractiveSegmentation View Keras Convolution2D Layer Keras NetworkLearner Keras NetworkExecutor U-Net 2D -Encoding Layer U-Net 2D -Encoding Layer U-Net 2D -Encoding Layer U-Net 2D -Encoding Layer U-Net 2D -Decoding Layer U-Net 2D -Decoding Layer U-Net 2D -Decoding Layer U-Net 2D -Decoding Layer

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: 2020-07-02
On NodePit since: 2020-09-24
Last update: 2026-01-19
Created with KNIME version: v4.2.3
Tags: cell segmentationcell imageneural networkdeep learningkerasu-net encoderu-net decoder

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

Try NodePit Runner!