Contents

This python toolbox performs registration between 2-D microscopy images from the same tissue section or serial sections in several ways to achieve imaging mass spectrometry (IMS) experimental goals.

This code supports the following works and enables others to perform the workflows outlined in the following works, please cite them if you use this toolbox:

NEUBIAS-WG5 workflow for nuclei segmentation using ilastik v1.3.2 and Python post-processing.

This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone.

NEUBIAS-WG5 workflow for nuclei segmentation using Mask-RCNN. The workflow uses Matterport Mask-RCNN. Keras implementation. The model was trained with Kaggle 2018 Data Science Bowl images.

This workflow predict landmark positions on images by using DMBL landmark detection models.

An implementation of Belief Propagation for factor graphs, also known as the sum-product algorithm

This workflow trains DMBL landmark detection models from a dataset of annotated images.

This workflow predict landmark positions on images by using LC landmark detection models.

This workflow trains LC landmark detection models from a dataset of annotated images.

This workflow predict landmark positions on images by using MSET landmark detection models.

This workflow trains MSET landmark detection models from a dataset of annotated images.

This is a (Cython-based) Python wrapper for Philipp Krähenbühl's Fully-Connected CRFs (version 2).

PyTorch is an open-source machine learning library for Python, based on Torch, used for applications such as natural language processing.

This workflow segments glands from H&E stained histopathological images
from the Gland Segmentation Challenge (GlaS2015) using deep learning (UNet).
UNet implementation largely inspired from PyTorch-UNet by Milesial. 

ImageJ/FIJI plugin generating contour lines with equal spacing on top of an image (using overlay).

The Binary Pattern Dictionary Learning (BPDL) package is suitable for image analysis on a set/sequence of images to determine an atlas of a compact region. In particular, the application can be maping gene activation accross many samples, brain activations in a time domain, etc.

The project introduces a cross-platform framework for comparison of image registration methods with landmark validation (registration precision is measured by user landmarks). The project contains a set of sample images with related landmark annotations and experimental evaluation of state-of-the-art image registration methods.

Some key features of the framework:

This dataset aims at the comparison of the automatic nonlinear image registration of 2D microscopy images of histopathology tissue samples stained with different dyes. 

jSLIC superpixels - is a segmentation method for clustering similar regions - superpixels - in the given image which are usually used for other segmentation techniques. The only two parameters are average (initial) size of each superpixel and rigidity parameter in range (0,1)

Collection of several basic standard image segmentation methods focusing on medical imaging. In particular, the key block/applications are (un)supervised image segmentation using superpixels, object centre detection and region growing with a shape prior. Besides the open-source code, there is also a few sample images.