4.3 Article

Automatic semantic segmentation of kidney cysts in MR images of patients affected by autosomal-dominant polycystic kidney disease

Journal

ABDOMINAL RADIOLOGY
Volume 46, Issue 3, Pages 1053-1061

Publisher

SPRINGER
DOI: 10.1007/s00261-020-02748-4

Keywords

Autosomal-dominant polycystic kidney disease; Semantic cyst segmentation; Deep learning; Magnetic resonance imaging

Funding

  1. Mayo Clinic Robert M. and Billie Kelley Pirnie Translational PKD Center
  2. NIDDK [P30DK090728, K01DK110136]
  3. Mayo Clinic's Center for Individualized Medicine

Ask authors/readers for more resources

This study developed and validated a fully automated approach for semantic segmentation of renal cysts in MR images of patients with ADPKD. The automated method performed at the level of interobserver variability and showed comparable consistency with manual segmentation in terms of cyst volume.
Purpose For patients affected by autosomal-dominant polycystic kidney disease (ADPKD), successful differentiation of cysts is useful for automatic classification of patient phenotypes, clinical decision-making, and disease progression. The objective was to develop and evaluate a fully automated semantic segmentation method to differentiate and analyze renal cysts in patients with ADPKD. Methods An automated deep learning approach using a convolutional neural network was trained, validated, and tested on a set of 60 MR T2-weighted images. A three-fold cross-validation approach was used to train three models on distinct training and validation sets (n = 40). An ensemble model was then built and tested on the hold out cases (n = 20), with each of the cases compared to manual segmentations performed by two readers. Segmentation agreement between readers and the automated method was assessed. Results The automated approach was found to perform at the level of interobserver variability. The automated approach had a Dice coefficient (mean +/- standard deviation) of 0.86 +/- 0.10 vs Reader-1 and 0.84 +/- 0.11 vs. Reader-2. Interobserver Dice was 0.86 +/- 0.08. In terms of total cyst volume (TCV), the automated approach had a percent difference of 3.9 +/- 19.1% vs Reader-1 and 8.0 +/- 24.1% vs Reader-2, whereas interobserver variability was - 2.0 +/- 16.4%. Conclusion This study developed and validated a fully automated approach for performing semantic segmentation of kidney cysts in MR images of patients affected by ADPKD. This approach will be useful for exploring additional imaging biomarkers of ADPKD and automatically classifying phenotypes.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.3
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available