Title :
Spatial codification of label predictions in multi-scale stacked sequential learning: a case study on multi-class medical volume segmentation
Author :
Sampedro, Frederic ; Escalera, Sergio
Author_Institution :
Fac. of Med., Autonomous Univ. of Barcelona, Barcelona, Spain
Abstract :
In this study, the authors propose the spatial codification of label predictions within the multi-scale stacked sequential learning (MSSL) framework, a successful learning scheme to deal with non-independent identically distributed data entries. After providing a motivation for this objective, they describe its theoretical framework based on the introduction of the blurred shape model as a smart descriptor to codify the spatial distribution of the predicted labels and define the new extended feature set for the second stacked classifier. They then particularise this scheme to be applied in volume segmentation applications. Finally, they test the implementation of the proposed framework in two medical volume segmentation datasets, obtaining significant performance improvements (with a 95% of confidence) in comparison to standard Adaboost classifier and classical MSSL approaches.
Keywords :
image classification; image coding; image segmentation; learning (artificial intelligence); medical image processing; MSSL framework; blurred shape model; distributed data entries; extended feature set; label predictions; multiclass medical volume segmentation; multiscale stacked sequential learning scheme; second stacked classifler; smart descriptor; spatial distribution codiflcation;
Journal_Title :
Computer Vision, IET
DOI :
10.1049/iet-cvi.2014.0067