TY - GEN
T1 - Active relearning for robust supervised classification of pulmonary emphysema
AU - Raghunath, Sushravya
AU - Rajagopalan, Srinivasan
AU - Karwoski, Ronald A.
AU - Bartholmai, Brian J.
AU - Robb, Richard A.
PY - 2012
Y1 - 2012
N2 - Radiologists are adept at recognizing the appearance of lung parenchymal abnormalities in CT scans. However, the inconsistent differential diagnosis, due to subjective aggregation, mandates supervised classification. Towards optimizing Emphysema classification, we introduce a physician-in-the-loop feedback approach in order to minimize uncertainty in the selected training samples. Using multi-view inductive learning with the training samples, an ensemble of Support Vector Machine (SVM) models, each based on a specific pair-wise dissimilarity metric, was constructed in less than six seconds. In the active relearning phase, the ensemble-expert label conflicts were resolved by an expert. This just-in-time feedback with unoptimized SVMs yielded 15% increase in classification accuracy and 25% reduction in the number of support vectors. The generality of relearning was assessed in the optimized parameter space of six different classifiers across seven dissimilarity metrics. The resultant average accuracy improved to 21%. The co-operative feedback method proposed here could enhance both diagnostic and staging throughput efficiency in chest radiology practice.
AB - Radiologists are adept at recognizing the appearance of lung parenchymal abnormalities in CT scans. However, the inconsistent differential diagnosis, due to subjective aggregation, mandates supervised classification. Towards optimizing Emphysema classification, we introduce a physician-in-the-loop feedback approach in order to minimize uncertainty in the selected training samples. Using multi-view inductive learning with the training samples, an ensemble of Support Vector Machine (SVM) models, each based on a specific pair-wise dissimilarity metric, was constructed in less than six seconds. In the active relearning phase, the ensemble-expert label conflicts were resolved by an expert. This just-in-time feedback with unoptimized SVMs yielded 15% increase in classification accuracy and 25% reduction in the number of support vectors. The generality of relearning was assessed in the optimized parameter space of six different classifiers across seven dissimilarity metrics. The resultant average accuracy improved to 21%. The co-operative feedback method proposed here could enhance both diagnostic and staging throughput efficiency in chest radiology practice.
KW - Active relearning
KW - Emphysema
KW - HRCT
KW - SVM
KW - Supervised classification
UR - http://www.scopus.com/inward/record.url?scp=84874837997&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84874837997&partnerID=8YFLogxK
U2 - 10.1117/12.911648
DO - 10.1117/12.911648
M3 - Conference contribution
AN - SCOPUS:84874837997
SN - 9780819489647
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2012
T2 - Medical Imaging 2012: Computer-Aided Diagnosis
Y2 - 7 February 2012 through 9 February 2012
ER -