Robust automated lymph node segmentation with random forests

David Allen; Le Lu; Jianhua Yao; Jiamin Liu; Evrim Turkbey; Ronald M. Summers

doi:10.1117/12.2043926

21 March 2014 Robust automated lymph node segmentation with random forests

David Allen, Le Lu, Jianhua Yao, Jiamin Liu, Evrim Turkbey, Ronald M. Summers

Proceedings Volume 9034, Medical Imaging 2014: Image Processing; 90343X (2014) https://doi.org/10.1117/12.2043926
Event: SPIE Medical Imaging, 2014, San Diego, California, United States

Abstract

Enlarged lymph nodes may indicate the presence of illness. Therefore, identification and measurement of lymph nodes provide essential biomarkers for diagnosing disease. Accurate automatic detection and measurement of lymph nodes can assist radiologists for better repeatability and quality assurance, but is challenging as well because lymph nodes are often very small and have a highly variable shape. In this paper, we propose to tackle this problem via supervised statistical learning-based robust voxel labeling, specifically the random forest algorithm. Random forest employs an ensemble of decision trees that are trained on labeled multi-class data to recognize the data features and is adopted to handle lowlevel image features sampled and extracted from 3D medical scans. Here we exploit three types of image features (intensity, order-1 contrast and order-2 contrast) and evaluate their effectiveness in random forest feature selection setting. The trained forest can then be applied to unseen data by voxel scanning via sliding windows (11×11×11), to assign the class label and class-conditional probability to each unlabeled voxel at the center of window. Voxels from the manually annotated lymph nodes in a CT volume are treated as positive class; background non-lymph node voxels as negatives. We show that the random forest algorithm can be adapted and perform the voxel labeling task accurately and efficiently. The experimental results are very promising, with AUCs (area under curve) of the training and validation ROC (receiver operating characteristic) of 0.972 and 0.959, respectively. The visualized voxel labeling results also confirm the validity.

Citation Download Citation

David Allen, Le Lu, Jianhua Yao, Jiamin Liu, Evrim Turkbey, and Ronald M. Summers "Robust automated lymph node segmentation with random forests", Proc. SPIE 9034, Medical Imaging 2014: Image Processing, 90343X (21 March 2014); https://doi.org/10.1117/12.2043926

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available