Integrating Dimension Reduction and Out-of-Sample Extension in Automated Classification of Ex Vivo Human Patellar Cartilage on Phase Contrast X-Ray Computed Tomography

• Published in: PloS one Vol. 10; no. 2; p. e0117157
• Main Authors: Nagarajan, Mahesh B., Coan, Paola, Huber, Markus B., Diemoz, Paul C., Wismüller, Axel
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 24.02.2015; Public Library of Science (PLoS)
• Subjects: Adult; Algorithms; Area Under Curve; Artificial intelligence; Automation; Biocompatibility; Biomedical engineering; Biomedical materials; Bus interconnections; Cartilage; Cartilage - diagnostic imaging; Cartilage diseases; Chondrocytes; Classification; Computation; Computed tomography; Computer science; Feature extraction; Humans; Learning algorithms; Life Sciences; Machine learning; Medical imaging; Methods; Neural networks; Osteoarthritis; Osteoarthritis - classification; Osteoarthritis - diagnostic imaging; Patella; Pattern Recognition, Automated; Phase contrast; Principal Component Analysis; Radiographic Image Interpretation, Computer-Assisted; Reduction; Representations; ROC Curve; Scaling; Spatial resolution; Support Vector Machine; Support vector machines; Tomography; Tomography, X-Ray Computed; New York; France; United States > US; Germany
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0117157

Phase contrast X-ray computed tomography (PCI-CT) has been demonstrated as a novel imaging technique that can visualize human cartilage with high spatial resolution and soft tissue contrast. Different textural approaches have been previously investigated for characterizing chondrocyte organization on PCI-CT to enable classification of healthy and osteoarthritic cartilage. However, the large size of feature sets extracted in such studies motivates an investigation into algorithmic feature reduction for computing efficient feature representations without compromising their discriminatory power. For this purpose, geometrical feature sets derived from the scaling index method (SIM) were extracted from 1392 volumes of interest (VOI) annotated on PCI-CT images of ex vivo human patellar cartilage specimens. The extracted feature sets were subject to linear and non-linear dimension reduction techniques as well as feature selection based on evaluation of mutual information criteria. The reduced feature set was subsequently used in a machine learning task with support vector regression to classify VOIs as healthy or osteoarthritic; classification performance was evaluated using the area under the receiver-operating characteristic (ROC) curve (AUC). Our results show that the classification performance achieved by 9-D SIM-derived geometric feature sets (AUC: 0.96 ± 0.02) can be maintained with 2-D representations computed from both dimension reduction and feature selection (AUC values as high as 0.97 ± 0.02). Thus, such feature reduction techniques can offer a high degree of compaction to large feature sets extracted from PCI-CT images while maintaining their ability to characterize the underlying chondrocyte patterns.