Jansen-MIDAS: A multi-level photomicrograph segmentation software based on isotropic undecimated wavelets

Abstract

Image segmentation, the process of separating the elements within a picture, is frequently used for obtaining information from photomicrographs. Segmentation methods should be used with reservations, since incorrect results can mislead when interpreting regions of interest (ROI). This decreases the success rate of extra procedures. Multi-Level Starlet Segmentation (MLSS) and Multi-Level Starlet Optimal Segmentation (MLSOS) were developed to be an alternative for general segmentation tools. These methods gave rise to Jansen-MIDAS, an open-source software. A scientist can use it to obtain several segmentations of hers/his photomicrographs. It is a reliable alternative to process different types of photomicrographs: previous versions of Jansen-MIDAS were used to segment ROI in photomicrographs of two different materials, with an accuracy superior to 89%.

Here we present Jansen-MIDAS, an open source segmentation software. Using ground truth images, one can train it to obtain high accuracy segmentations for an image dataset. Scientists can use it to acquire several segmentations of their photomicrographs.

from # All Medicine by Alexandros G. Sfakianakis via Alexandros G.Sfakianakis on Inoreader http://ift.tt/2yWtb12
via IFTTT