Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Understanding important features of deep learning models for segmentation of high-resolution transmission electron microscopy images

Journal Article · · npj Computational Materials
 [1];  [2];  [3];  [1]
  1. Univ. of Pennsylvania, Philadelphia, PA (United States)
  2. Brookhaven National Lab. (BNL), Upton, NY (United States)
  3. Univ. of Puerto Rico, San Juan, PR (United States)
+ Show Author Affiliations

Cutting edge deep learning techniques allow for image segmentation with great speed and accuracy. However, application to problems in materials science is often difficult since these complex models may have difficultly learning meaningful image features that would enable extension to new datasets. In situ electron microscopy provides a clear platform for utilizing automated image analysis. In this work, we consider the case of studying coarsening dynamics in supported nanoparticles, which is important for understanding, for example, the degradation of industrial catalysts. By systematically studying dataset preparation, neural network architecture, and accuracy evaluation, we describe important considerations in applying deep learning to physical applications, where generalizable and convincing models are required. With a focus on unique challenges that arise in high-resolution images, we propose methods for optimizing performance of image segmentation using convolutional neural networks, critically examining the application of complex deep learning models in favor of motivating intentional process design.

Research Organization:
Brookhaven National Laboratory (BNL), Upton, NY (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22); National Science Foundation (NSF)
Grant/Contract Number:
SC0012704
OSTI ID:
1677672
Report Number(s):
BNL-219976-2020--JAAM
Journal Information:
npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 6; ISSN 2057-3960
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (24)

A Deep Learning Approach to Identify Local Structures in Atomic-Resolution Transmission Electron Microscopy Images journal July 2018
U-Net: Convolutional Networks for Biomedical Image Segmentation
  • Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas
  • Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28
book November 2015
Characteristic analysis of Otsu threshold and its applications journal May 2011
Current status and future directions for in situ transmission electron microscopy journal November 2016
Towards Real Time Quantitative Analysis of Supported Nanoparticle Ensemble Evolution Investigated by Environmental TEM journal August 2018
Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations journal October 2016
Sintering of Catalytic Nanoparticles: Particle Migration or Ostwald Ripening? journal April 2013
Direct Observations of Oxygen-induced Platinum Nanoparticle Ripening Studied by In Situ TEM journal June 2010
Deep learning for cellular image analysis journal May 2019
Automated single particle detection and tracking for large microscopy datasets journal May 2016
Big Data Deep Learning: Challenges and Perspectives journal January 2014
Fully convolutional networks for semantic segmentation conference June 2015
Classification of malignant and benign microcalcification using SVM classifier conference March 2011
On the size of Convolutional Neural Networks and generalization performance conference December 2016
Kernel-based methods and function approximation
  • Baudat, G.; Anouar, F.
  • International Joint Conference on Neural Networks (IJCNN'01), IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222) https://doi.org/10.1109/IJCNN.2001.939539
conference January 2001
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation journal December 2017
A Threshold Selection Method from Gray-Level Histograms journal January 1979
In Situ Studies of Chemistry and Structure of Materials in Reactive Environments journal January 2011
Overfitting and undercomputing in machine learning journal September 1995
Deep Learning in Medical Image Analysis journal June 2017
Frontiers of in situ electron microscopy journal January 2015
Materials science with large-scale data and informatics: Unlocking new opportunities journal May 2016
Automated analysis of evolving interfaces during in situ electron microscopy collection January 2016
scikit-image: image processing in Python journal January 2014

Figures / Tables (8)

Fig. 1(p. 5)figure Fig. 1
Fig. 2(p. 5)figure Fig. 2
Fig. 3(p. 6)figure Fig. 3
Fig. 4(p. 7)figure Fig. 4
Table 1(p. 7)table Table 1
Fig. 5(p. 8)figure Fig. 5
Fig. 6(p. 9)figure Fig. 6
Fig. 7(p. 9)figure Fig. 7

Similar Records

Machine-Learning-based Algorithms for Automated Image Segmentation Techniques of Transmission X-ray Microscopy (TXM)
Journal Article · Tue May 11 00:00:00 EDT 2021 · JOM. Journal of the Minerals, Metals & Materials Society · OSTI ID:1834598
Artificial neural network approach for multiphase segmentation of battery electrode nano-CT images
Journal Article · Tue Feb 08 23:00:00 EST 2022 · npj Computational Materials · OSTI ID:1894650
Automated correlative segmentation of large Transmission X-ray Microscopy (TXM) tomograms using deep learning
Journal Article · Wed Aug 15 00:00:00 EDT 2018 · Materials Characterization · OSTI ID:22805091

Related Subjects

36 MATERIALS SCIENCE