Deep Learning

Deep learning object detection

Version 3.0 integrates the deep learning framework Tensorflow for object detection. You can use a pre-trained model, like our glomeruli detection model available in our model zoo, or train your own deep learning model based on manually created object annotations. This new feature allows to detect arbitrary complex and heterogeneous objects like glomeruli, vessels, and[…]

Mumford-Shah Segmentation

Cell Cluster Segmentation

Segmenting cells in cell clusters is very challenging because they cannot be separated easily from the background – thus classical segmentation algorithms fail. Unfortunately in WSI (whole slide imaging) you will have to deal with these situations – especially if you don’t have a single cell layer, like e.g. in tumor tissue. A collaboration with[…]


Open Local Images

Today the new Orbit version 2.41 is released. The main achievement of this major version is the ability to work with whole slide images images in standalone mode, even without using an image server. In addition, many speed improvements (faster rendering) and bug-fixes are included. Orbit is designed to work with an image server, e.g.[…]

cell profiler logo

Cell Profiler integration

Orbit integrates Cell Profiler (CP). This means CP can be used for whole slide image analysis, in combination with Orbit exclusion maps and manual defined ROIs. You can use it to segment cells and combine it with tissue quantification to e.g. count stained cells and normalize it to the ROI area or stained cell area.[…]