Ensemble Learning Based Segmentation of Metastatic Liver Tumours in Contrast-Enhanced Computed Tomography

Akinobu SHIMIZU  Takuya NARIHIRA  Hidefumi KOBATAKE  Daisuke FURUKAWA  Shigeru NAWANO  Kenji SHINOZAKI  

IEICE TRANSACTIONS on Information and Systems   Vol.E96-D   No.4   pp.864-868
Publication Date: 2013/04/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E96.D.864
Print ISSN: 0916-8532
Type of Manuscript: Special Section LETTER (Special Section on Medical Imaging)
Category: Medical Image Processing
CT image,  liver tumour,  segmentation,  ensemble learning,   U-boost,  

Full Text: FreePDF(793.2KB)

This paper presents an ensemble learning algorithm for liver tumour segmentation from a CT volume in the form of U-Boost and extends the loss functions to improve performance. Five segmentation algorithms trained by the ensemble learning algorithm with different loss functions are compared in terms of error rate and Jaccard Index between the extracted regions and true ones.