Loading...
Please wait, while we are loading the content...
Similar Documents
Performance-Based Classifier Combination in Atlas-Based Image Segmentation Using Expectation-Maximization Parameter Estimation (2004)
| Content Provider | CiteSeerX |
|---|---|
| Author | Rohlfing, Torsten Russakoff, Daniel B. Maurer, Calvin R. |
| Abstract | It is well known in the pattern recognition community that the accuracy of classifications obtained by combining decisions made by independent classifiers can be substantially higher than the accuracy of the individual classifiers. We have previously shown this to be true for atlas-based segmentation of biomedical images. The conventional method for combining individual classifiers weights each classifier equally (vote or sum rule fusion). In this paper, we propose two methods that estimate the performances of the individual classifiers and combine the individual classifiers by weighting them according to their estimated performance. The two methods are multiclass extensions of an expectation-maximization (EM) algorithm for ground truth estimation of binary classification based on decisions of multiple experts (Warfield et al., 2004). The first method performs parameter estimation independently for each class with a subsequent integration step. The second method considers all classes simultaneously. We demonstrate the efficacy of these performance-based fusion methods by applying them to atlas-based segmentations of three-dimensional confocal microscopy images of bee brains. In atlas-based image segmentation, multiple classifiers arise naturally by applying different registration methods to the same atlas, or the same registration method to different atlases, or both. We perform a validation study designed to quantify the success of classifier combination methods in atlas-based segmentation. By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images. In a second evaluation study, multiple actual atlas-based segmentations are combined and their ... |
| File Format | |
| Volume Number | 23 |
| Journal | IEEE Trans. Med. Imag |
| Language | English |
| Publisher Date | 2004-01-01 |
| Access Restriction | Open |
| Subject Keyword | Performance-based Classifier Combination Atlas-based Segmentation Individual Classifier Sum Rule Fusion Individual Classifier Weight Validation Study Bee Brain Biomedical Image Random Deformation Atlas-based Image Segmentation Multiple Segmentation First Method Performs Multiclass Extension Subsequent Integration Step Multiple Expert Second Evaluation Study Registration Method Binary Classification Multiple Classifier Different Atlas Conventional Method Atlas Image Multiple Actual Atlas-based Segmentation Different Registration Method Combination Method Ground Truth Estimation Ground Truth Atlas Imperfect Registration Independent Classifier Second Method Considers Pattern Recognition Community Performance-based Fusion Method Three-dimensional Confocal Microscopy Image |
| Content Type | Text |
| Resource Type | Article |
