Paper Info
Title
Active learning with noise modeling for medical image annotation
Abstract
Active learning is an effective solution to select informative training datasets (examples) from which a pre-defined classifier learns for optimizing its performance. It has been widely applied for information extraction, classification, and filtering. Most existing active learning methods do not consider image noise separately to guide the selection of informative examples, which might lead to sub-optimal annotation. Due to the intrinsic presence of noise in images, large amount of images, and varied imaging modalities, using active learning for medical image annotation is an even more challenging task. In this study, we develop a novel low-rank modeling-based multi-label active learning (LRMMAL) method for effective medical image annotation. Different to those traditional active learning methods, the LRMMAL method innovatively measures image noise and combines it with the measures of example label uncertainty and label correlation into a new sampling process to determine most informative examples for annotation. Experimental results on thoracic CT images and comparisons with other four multi-label active learning methods illustrate the superior performance of the LRMMAL method.
Year
DOI
Venue
2018
10.1109/ISBI.2018.8363578
2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
Keywords
Field
DocType
Medical image,image annotation,multi-label image,active learning
Sampling process,Automatic image annotation,Annotation,Active learning,Pattern recognition,Computer science,Filter (signal processing),Image noise,Information extraction,Artificial intelligence,Classifier (linguistics)
Conference
ISSN
ISBN
Citations 
1945-7928
978-1-5386-3637-4
0
PageRank 
References 
Authors
0.34
0
6
Name
Order
Citations
PageRank
Jian Wu111.05
Ruan Su255953.00
Chunfeng Lian313222.61
Sasa Mutic411.39
Mark A. Anastasio510525.53
Hua Li6459.03