Cooperative strategy for a dynamic ensemble of classification models in clinical applications: the case of MRI vertebral compression fractures

被引:11
作者
Casti, Paola [1 ]
Mencattini, Arianna [1 ]
Nogueira-Barbosa, Marcello H. [2 ]
Frighetto-Pereira, Lucas [2 ]
Azevedo-Marques, Paulo Mazzoncini [2 ]
Martinelli, Eugenio [1 ]
Di Natale, Corrado [1 ]
机构
[1] Univ Roma Tor Vergata, Dept Elect Engn, I-00133 Rome, Italy
[2] Univ Sao Paulo, Ribeirao Preto Med Sch, Ribeirao Preto, Brazil
基金
巴西圣保罗研究基金会;
关键词
Cooperative classification; Dynamic ensemble; Vertebral compression fractures; Magnetic resonance imaging; IMAGE SEGMENTATION; SPACE; SHAPE; CT;
D O I
10.1007/s11548-017-1625-2
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In clinical practice, the constructive consultation among experts improves the reliability of the diagnosis and leads to the definition of the treatment plan for the patient. Aggregation of the different opinions collected by many experts can be performed at the level of patient information, abnormality delineation, or final assessment. In this study, we present a novel cooperative strategy that exploits the dynamic contribution of the classification models composing the ensemble to make the final class assignment. As a proof of concept, we applied the proposed approach to the assessment of malignant infiltration in 103 vertebral compression fractures in magnetic resonance images. The results obtained with repeated random subsampling and receiver operating characteristic analysis indicate that the cooperative system statistically improved () the classification accuracy of individual modules as well as of that based on the manual segmentation of the fractures provided by the experts. The performances have been also compared with those obtained with those of standard ensemble classification algorithms showing superior results.
引用
收藏
页码:1971 / 1983
页数:13
相关论文
共 37 条
[1]   SEEDED REGION GROWING [J].
ADAMS, R ;
BISCHOF, L .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (06) :641-647
[2]  
[Anonymous], 2004, Machine vision: theory, algorithms, practicalities
[3]  
[Anonymous], 2010, PATTERN CLASSIFICATI
[4]   Cardiac Multi-detector CT Segmentation Based on Multiscale Directional Edge Detector and 3D Level Set [J].
Antunes, Sofia ;
Esposito, Antonio ;
Palmisano, Anna ;
Colantoni, Caterina ;
Cerutti, Sergio ;
Rizzo, Giovanna .
ANNALS OF BIOMEDICAL ENGINEERING, 2016, 44 (05) :1487-1501
[5]  
Barbieri PD, 2015, P IEEE CBMS
[6]  
Benamrane N, 2007, LECT NOTES COMPUT SC, V4687, P49
[7]  
Bezdek J. C., 1981, Pattern recognition with fuzzy objective function algorithms
[8]   User-Agent Cooperation in Multiagent IVUS Image Segmentation [J].
Bovenkamp, E. G. P. ;
Dijkstra, J. ;
Bosch, J. G. ;
Reiber, J. H. C. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2009, 28 (01) :94-105
[9]  
Brejl M, 2000, IEEE T MED IMAGING, V19, P973, DOI 10.1109/42.887613
[10]   Contour-independent detection and classification of mammographic lesions [J].
Casti, P. ;
Mencattini, A. ;
Salmeri, M. ;
Ancona, A. ;
Mangeri, F. ;
Pepe, M. L. ;
Rangayyan, R. M. .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2016, 25 :165-177