PyHIST : A Histological Image Segmentation Tool
Muñoz-Aguirre, Manuel (Universitat Politècnica de Catalunya)
Ntasis, Vasilis F. (Institut de Ciència i Tecnologia de Barcelona. Institut de Recerca en Biomedicina)
Rojas, Santiago (Universitat Autònoma de Barcelona. Departament de Ciències Morfològiques)
Guigó, Roderic (Universitat Pompeu Fabra)

Data:	2020
Resum:	The development of increasingly sophisticated methods to acquire high-resolution images has led to the generation of large collections of biomedical imaging data, including images of tissues and organs. Many of the current machine learning methods that aim to extract biological knowledge from histopathological images require several data preprocessing stages, creating an overhead before the proper analysis. Here we present PyHIST (), an easy-to-use, open source whole slide histological image tissue segmentation and preprocessing command-line tool aimed at tile generation for machine learning applications. From a given input image, the PyHIST pipeline i) optionally rescales the image to a different resolution, ii) produces a mask for the input image which separates the background from the tissue, and iii) generates individual image tiles with tissue content. Histopathology images are an essential tool to assess and quantify tissue composition and its relationship to disease. The digitization of slides and the decreasing costs of computation and data storage have fueled the development of new computational methods, especially in the field of machine learning. These methods seek to make use of the histopathological patterns encoded in these slides with the aim of aiding clinicians in healthcare decision-making, as well as researchers in tissue biology. However, in order to prepare digital slides for usage in machine learning applications, researchers usually need to develop custom scripts from scratch in order to reshape the image data in a way that is suitable to train a model, slowing down the development process. With PyHIST, we provide a toolbox for researchers that work in the intersection of machine learning, biology and histology to effortlessly preprocess whole slide images into image tiles in a standardized manner for usage in external applications.
Ajuts:	Agencia Estatal de Investigación PGC2018-094017-B-I00
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Publicat a:	PLoS computational biology, Vol. 16 (october 2020) , ISSN 1553-7358

DOI: 10.1371/journal.pcbi.1008349
PMID: 33075075

9 p, 1.7 MB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats