Segmentation of tomography datasets using 3D convolutional neural networks

Jim James, Nathan Pruyne, Tiberiu Stan, Marcus Schwarting*, Jiwon Yeom, Seungbum Hong, Peter Voorhees, Ben Blaiszik, Ian Foster

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Dendritic microstructures are ubiquitous in nature and are the primary solidification morphologies in metallic materials. Techniques such as X-ray computed tomography (XCT) have provided new insights into dendritic phase transformation phenomena. However, manual identification of dendritic morphologies in microscopy data can be both labor intensive and potentially ambiguous. The analysis of 3D datasets is particularly challenging due to their large sizes (terabytes) and the presence of artifacts scattered within the imaged volumes. In this study, we trained 3D convolutional neural networks (CNNs) to segment 3D datasets. Three CNN architectures were investigated, including a new version of FCDenseNet which we extended to 3D. We show that using hyperparameter optimization (HPO) and fine-tuning techniques, both 2D and 3D CNN architectures outperform the previous state of the art. The 3D U-Net architecture trained in this study produced the best segmentations according to quantitative metrics (intersection-over-union of 95.56% and a boundary displacement error of 0.58 pixels), while 3D FCDense produced the smoothest boundaries and best segmentations according to visual inspection. The trained 3D CNNs are able to segment entire 852 × 852 × 250 voxel 3D volumes in only ∼60 s, thus hastening the progress towards a deeper understanding of phase transformation phenomena such as dendritic solidification.

Original languageEnglish (US)
Article number111847
JournalComputational Materials Science
StatePublished - Jan 5 2023


  • 3D image analysis
  • Artificial neural networks
  • Dendritic formation
  • Solidification microstructure
  • X-ray computed tomography

ASJC Scopus subject areas

  • General Computer Science
  • General Chemistry
  • General Materials Science
  • Mechanics of Materials
  • General Physics and Astronomy
  • Computational Mathematics


Dive into the research topics of 'Segmentation of tomography datasets using 3D convolutional neural networks'. Together they form a unique fingerprint.

Cite this