Automated Segmentation of Knee MRI Using Hierarchical Classifiers and Just Enough Interaction Based Learning: Data from Osteoarthritis Initiative

Satyananda Kashyap; Ipek Oguz; Honghai Zhang; Milan Sonka

doi:10.1007/978-3-319-46723-8_40

Back

Automated Segmentation of Knee MRI Using Hierarchical Classifiers and Just Enough Interaction Based Learning: Data from Osteoarthritis Initiative

Book chapter

Open access

Peer reviewed

Automated Segmentation of Knee MRI Using Hierarchical Classifiers and Just Enough Interaction Based Learning: Data from Osteoarthritis Initiative

Satyananda Kashyap, Ipek Oguz, Honghai Zhang and Milan Sonka

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, pp.344-351

Lecture Notes in Computer Science, Springer International Publishing

10/02/2016

DOI: 10.1007/978-3-319-46723-8_40

PMCID: PMC5471813

PMID: 28626842

Files and links (1)

url

https://arxiv.org/pdf/1903.03929View

Open Access

Abstract

We present a fully automated learning-based approach for segmenting knee cartilage in presence of osteoarthritis (OA). The algorithm employs a hierarchical set of two random forest classifiers. The first is a neighborhood approximation forest, the output probability map of which is utilized as a feature set for the second random forest (RF) classifier. The output probabilities of the hierarchical approach are used as cost functions in a Layered Optimal Graph Segmentation of Multiple Objects and Surfaces (LOGISMOS). In this work, we highlight a novel post-processing interaction called just-enough interaction (JEI) which enables quick and accurate generation of a large set of training examples. Disjoint sets of 15 and 13 subjects were used for training and tested on another disjoint set of 53 knee datasets. All images were acquired using double echo steady state (DESS) MRI sequence and are from the osteoarthritis initiative (OAI) database. Segmentation performance using the learning-based cost function showed significant reduction in segmentation errors (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p< 0.05$$\end{document}) in comparison with conventional gradient-based cost functions.

Graph based segmentation

Just enough interaction

knee MRI

Neighborhood approximation forests

Random forest classifier

LOGISMOS

Osteoarthritis

Details

Title: Subtitle: Automated Segmentation of Knee MRI Using Hierarchical Classifiers and Just Enough Interaction Based Learning: Data from Osteoarthritis Initiative
Creators: Satyananda Kashyap - Iowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, USA
Ipek Oguz - Department of Radiology, University of Pennsylvania, Philadelphia, USA
Honghai Zhang - Iowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, USA
Milan Sonka - Iowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, USA
Resource Type: Book chapter
Publication Details: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, pp.344-351
Series: Lecture Notes in Computer Science
DOI: 10.1007/978-3-319-46723-8_40
PMID: 28626842
PMCID: PMC5471813
eISSN: 1611-3349
ISSN: 0302-9743
Publisher: Springer International Publishing; Cham
Language: English
Date published: 10/02/2016
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Psychiatry; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984047735902771

Metrics

77 Record Views