Nephroblastoma analysis in MRI images

Djibril Kaba, Nigel McFarlane, Feng Dong, Norbert Graf, Xujiong Ye

Research output: Contribution to journalArticle

5 Downloads (Pure)

Abstract

The annotation of the tumour from medical scans is a crucial step in nephroblastoma treatment. Therefore, an accurate and reliable segmentation method is needed to facilitate the evaluation and the treatments of the tumour. The proposed method serves this purpose by performing the segmentation of nephroblastoma in MRI scans. The segmentation is performed by adapting and a 2D free hand drawing tool to select a region of interest in the scan slices. Results from 24 patients show a mean root-mean-square error of 0.0481±0.0309, an average Dice coefficient of 0.9060±0.0549 and an average accuracy of 99.59% ±0.0039. Thus the proposed method demonstrated an effective agreement with manual annotations.
Original languageEnglish
Pages (from-to)173-183
Number of pages11
JournalImage Analysis and Stereology
Volume38
Issue number2
DOIs
Publication statusPublished - 31 Jul 2019

Keywords

  • continuous max-flow
  • graph segmentation
  • kernel induced space
  • MRI image
  • nephroblastoma
  • Wilms tumour

Fingerprint Dive into the research topics of 'Nephroblastoma analysis in MRI images'. Together they form a unique fingerprint.

  • Cite this

    Kaba, D., McFarlane, N., Dong, F., Graf, N., & Ye, X. (2019). Nephroblastoma analysis in MRI images. Image Analysis and Stereology , 38(2), 173-183. https://doi.org/10.5566/ias.2000