A Feature-Based Approach to Big Data Analysis of Medical Images

• Published in: Information Processing in Medical Imaging Vol. 24; pp. 339 - 350
• Main Authors: Toews, Matthew, Wachinger, Christian, Estepar, Raul San Jose, Wells, William M.
• Format: Book Chapter Journal Article
• Language: English
• Published: Cham Springer International Publishing 2015
• Series: Lecture Notes in Computer Science
• Subjects: Algorithms; Breathing State; Data Interpretation, Statistical; Databases, Factual; Humans; Image Patch; Imaging, Three-Dimensional - methods; Information Storage and Retrieval - methods; Kernel Density Estimation; Lung - diagnostic imaging; Medical Image Data; Near Neighbor; Pattern Recognition, Automated - methods; Pulmonary Disease, Chronic Obstructive - diagnostic imaging; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Reproducibility of Results; Sensitivity and Specificity; Tomography, X-Ray Computed - methods
• ISBN: 9783319199917; 3319199919
• ISSN: 0302-9743; 1011-2499; 1611-3349
• DOI: 10.1007/978-3-319-19992-4_26

This paper proposes an inference method well-suited to large sets of medical images. The method is based upon a framework where distinctive 3D scale-invariant features are indexed efficiently to identify approximate nearest-neighbor (NN) feature matches in O(log N) computational complexity in the number of images N. It thus scales well to large data sets, in contrast to methods based on pair-wise image registration or feature matching requiring O(N) complexity. Our theoretical contribution is a density estimator based on a generative model that generalizes kernel density estimation and K-nearest neighbor (KNN) methods. The estimator can be used for on-the-fly queries, without requiring explicit parametric models or an off-line training phase. The method is validated on a large multi-site data set of 95,000,000 features extracted from 19,000 lung CT scans. Subject-level classification identifies all images of the same subjects across the entire data set despite deformation due to breathing state, including unintentional duplicate scans. State-of-the-art performance is achieved in predicting chronic pulmonary obstructive disorder (COPD) severity across the 5-category GOLD clinical rating, with an accuracy of $$89\,\%$$ if both exact and one-off predictions are considered correct.