Share Email Print
cover

Proceedings Paper

Optimal reinforcement of training datasets in semi-supervised landmark-based segmentation
Author(s): Bulat Ibragimov; Boštjan Likar; Franjo Pernuš; Tomaž Vrtovec
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

During the last couple of decades, the development of computerized image segmentation shifted from unsupervised to supervised methods, which made segmentation results more accurate and robust. However, the main disadvantage of supervised segmentation is a need for manual image annotation that is time-consuming and subjected to human error. To reduce the need for manual annotation, we propose a novel learning approach for training dataset reinforcement in the area of landmark-based segmentation, where newly detected landmarks are optimally combined with reference landmarks from the training dataset and therefore enriches the training process. The approach is formulated as a nonlinear optimization problem, where the solution is a vector of weighting factors that measures how reliable are the detected landmarks. The detected landmarks that are found to be more reliable are included into the training procedure with higher weighting factors, whereas the detected landmarks that are found to be less reliable are included with lower weighting factors. The approach is integrated into the landmark-based game-theoretic segmentation framework and validated against the problem of lung field segmentation from chest radiographs.

Paper Details

Date Published: 20 March 2015
PDF: 6 pages
Proc. SPIE 9413, Medical Imaging 2015: Image Processing, 94132K (20 March 2015); doi: 10.1117/12.2082321
Show Author Affiliations
Bulat Ibragimov, Univ. of Ljubljana (Slovenia)
Boštjan Likar, Univ. of Ljubljana (Slovenia)
Franjo Pernuš, Univ. of Ljubljana (Slovenia)
Tomaž Vrtovec, Univ. of Ljubljana (Slovenia)


Published in SPIE Proceedings Vol. 9413:
Medical Imaging 2015: Image Processing
Sébastien Ourselin; Martin A. Styner, Editor(s)

© SPIE. Terms of Use
Back to Top