QuPath: Open source software for digital pathology image analysis

Breast cancer is one of the most common cancer diseases in the world among women. The reliability of histological verification of breast cancer depends on pathologist’s experience, knowledge, his willingness to self-improve and study specialized literature. Digital pathology is also widely used for educational purposes, in telepathology, teleconsultation and research projects. Recently developed Whole Slide Image (WSI) system opens great opportunities in the histopathological diagnosis quality improvement. Digital whole-slide images provide the effective use of morphometry and various imaging techniques to assist pathologists in quantitative and qualitative evaluation of histopathological preparations. The development of software for morphological diagnosis is important for improving the quality of histological verification of diagnosis in oncopathology. The purpose of this work is to find and benchmark existing open-source software for the whole-slide histological images processing. Choosing an open source program is an important step in developing an automated breast cancer diagnosis program. The result is a detailed study of open-source software: ASAP, Orbit, Cytomine and QuPath. Their features and methods of image processing were analyzed. QuPath software has the best characteristics for extending it with an automated module for the cancer diagnosis. QuPath combines a user-friendly, easy-to-use interface, customizable functionality, and moderate computing power requirements. Besides, QuPath works with whole-slide images with immunohistochemical markers; features implemented in this software allow making a morphometric analysis. QuPath saves time for a graphical user interface development and provides a scalable system to add new key features. QuPath supports third-party MATLAB and Python extensions.

Download Full-text

The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis

Computers in Biology and Medicine ◽

10.1016/j.compbiomed.2020.104129 ◽

2021 ◽

Vol 128 ◽

pp. 104129

Author(s):

Massimo Salvi ◽

U. Rajendra Acharya ◽

Filippo Molinari ◽

Kristen M. Meiburger

Keyword(s):

Image Processing ◽

Image Analysis ◽

Deep Learning ◽

Digital Pathology ◽

Comprehensive Review ◽

Image Processing Techniques ◽

Processing Techniques ◽

The Impact ◽

Learning Frameworks ◽

Pathology Image

Download Full-text

AutoRoot: open-source software employing a novel image analysis approach to support fully-automated plant phenotyping

Plant Methods ◽

10.1186/s13007-017-0161-y ◽

2017 ◽

Vol 13 (1) ◽

Cited By ~ 8

Author(s):

Michael P. Pound ◽

Susan Fozard ◽

Mercedes Torres Torres ◽

Brian G. Forde ◽

Andrew P. French

Keyword(s):

Image Analysis ◽

Open Source ◽

Open Source Software ◽

Analysis Approach ◽

Plant Phenotyping

Download Full-text

A Novel 3-Dimensional technique in measuring pericoronary epicardial adipose tissue radiodensity

10.1101/2020.10.29.20222679 ◽

2020 ◽

Author(s):

Lingyu Xu ◽

Stanislau Hrybouski ◽

Yuancheng Xu ◽

Richard Coulden ◽

Emer Sonnex ◽

...

Keyword(s):

Image Analysis ◽

Adipose Tissue ◽

Open Source ◽

Open Source Software ◽

Epicardial Adipose Tissue ◽

Full Length ◽

Imaging Biomarker ◽

List Type ◽

Similarity Coefficients ◽

Analysis Pipeline

ABSTRACTObjectivesThis study aimed to investigate a novel semi-automated three-dimensional (3D) quantification of the pericoronary epicardial adipose tissue radiodensity (PCATrd).MethodsTwenty-four subjects who previously underwent contrast-enhanced cardiac CT scans were retrospectively identified. The PCATrd was measured in ITK-SNAP imaging software using a Hounsfield unit threshold (−190,-3) to define epicardial adipose tissue (EAT). A spherical 3D brush tool was used on multiplanar reformatted images to segment the PCAT. We defined the PCATrd as EAT within the orthogonal distance from the coronary artery (CA) outer wall equal to the diameter of the corresponding CA segment. The segmentation followed the path of major CAs. Additionally, the PCAT of twenty-five calcified segments were segmented. Reliability of this novel segmentation protocol was assessed using Dice Similarity Coefficients (DSCs) and intraclass coefficient (ICC).ResultsThe segmentation reproducibility for the PCAT was high, with intraobserver DSC 0.86±0.04 for the full length of major CAs and 0.85±0.07 for the calcified segments, and interobserver DSC 0.84±0.04 for the full length of major CAs and 0.83±0.05 for the calcified segments. The reproducibility of the PCATrd value assessed by ICC was also excellent, with intraobserver ICC 0.99 for the full length of major CAs and 0.99 for the calcified segments, and interobserver ICC 0.99 for the full length of major CAs and 0.99 for the calcified segments.ConclusionsOur novel 3D PCATrd quantification technique is reliable and reproducible. The availability of the open source software and detailed image analysis pipeline will enable reliable replications and broad uptake of our technique.Key pointsWe have produced a novel, semiautomated technique to comprehensively quantify pericoronary epicardial adipose tissue radiodensity (PCATrd) which is a novel imaging biomarker of coronary inflammation.Our method of PCAT segmentation has excellent reproducibility.We use open source software and provide detailed image analysis pipeline of quantifying PCATrd, which will allow easy replication and broad uptake of our technique.

Download Full-text