Iterative multi-class multi-scale stacked sequential learning: Definition and application to medical volume segmentation

In this work we present the iterative multi-class multi-scale stacked sequential learning framework (IMMSSL), a novel learning scheme that is particularly suited for medical volume segmentation applications. This model exploits the inherent voxel contextual information of the structures of interest in order to improve its segmentation performance results. Without any feature set or learning algorithm prior assumption, the proposed scheme directly seeks to learn the contextual properties of a region from the predicted classifications of previous classifiers within an iterative scheme. Performance results regarding segmentation accuracy in three two-class and multi-class medical volume datasets show a significant improvement with respect to state of the art alternatives. Due to its easiness of implementation and its independence of feature space and learning algorithm, the presented machine learning framework could be taken into consideration as a first choice in complex volume segmentation scenarios.

[1]  R. Zemel,et al.  Multiscale conditional random fields for image labeling , 2004, CVPR 2004.

[2]  Sergio Escalera,et al.  Automatic Tumor Volume Segmentation in Whole-Body PET/CT Scans: A Supervised Learning Approach , 2015 .

[3]  Yadong Wang,et al.  Automatic segmentation technique for acetabulum and femoral head in CT images , 2013, Pattern Recognit..

[4]  Daphne Koller,et al.  Learning Spatial Context: Using Stuff to Find Things , 2008, ECCV.

[5]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[6]  Martial Hebert,et al.  Discriminative random fields: a discriminative framework for contextual interaction in classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Sergio Escalera,et al.  Generalized multi-scale stacked sequential learning for multi-class classification , 2015, Pattern Analysis and Applications.

[8]  David Zhang,et al.  A survey of graph theoretical approaches to image segmentation , 2013, Pattern Recognit..

[9]  Thomas G. Dietterich.  Machine Learning for Sequential Data: A Review , 2002, SSPR/SPR.

[10]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[11]  Sergio Escalera,et al.  Intelligent GPGPU Classification in Volume Visualization: A framework based on Error‐Correcting Output Codes , 2011, Comput. Graph. Forum.

[12]  Ronen Basri,et al.  Shape Based Detection and Top-Down Delineation Using Image Segments , 2009, International Journal of Computer Vision.

[13]  Carlo Gatta,et al.  Multi-scale stacked sequential learning , 2011, Pattern Recognit..

[14]  Yao-Tien Chen,et al.  A level set method based on the Bayesian risk for medical image segmentation , 2010, Pattern Recognit..

[15]  Desire Sidibé,et al.  A supervised learning framework of statistical shape and probability priors for automatic prostate segmentation in ultrasound images , 2013, Medical Image Anal..

[16]  Sergio Escalera,et al.  On the Decoding Process in Ternary Error-Correcting Output Codes , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Mark W. Schmidt,et al.  Accelerated training of conditional random fields with stochastic gradient methods , 2006, ICML.

[18]  Sergio Escalera,et al.  Subclass Problem-Dependent Design for Error-Correcting Output Codes , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Ayman El-Baz,et al.  Kidney segmentation using graph cuts and pixel connectivity , 2013, Pattern Recognit. Lett..

[20]  Sang Hyun Park,et al.  Hierarchical MRF of globally consistent localized classifiers for 3D medical image segmentation , 2013, Pattern Recognit..

[21]  Jianbo Shi,et al.  Recognizing objects by piecing together the Segmentation Puzzle , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.