Blog
About

0
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Large-area, high-resolution characterisation and classification of damage mechanisms in dual-phase steel using deep learning

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          High performance materials, from natural bone over ancient damascene steel to modern superalloys, typically possess a complex structure at the microscale. Their properties exceed those of the individual components and their knowledge-based improvement therefore requires understanding beyond that of the components’ individual behaviour. Electron microscopy has been instrumental in unravelling the most important mechanisms of co-deformation and in-situ deformation experiments have emerged as a popular and accessible technique. However, a challenge remains: to achieve high spatial resolution and statistical relevance in combination. Here, we overcome this limitation by using panoramic imaging and machine learning to study damage in a dual-phase steel. This high-throughput approach now gives us strain and microstructure dependent insights into the prevalent damage mechanisms and allows the separation of inclusions and deformation–induced damage across a large area of this heterogeneous material. Aiming for the first time at automated classification of the majority of damage sites rather than only the most distinct, the new method also encourages us to expand current research past interpretation of exemplary cases of distinct damage sites towards the less clear-cut reality.

          Related collections

          Most cited references 42

          • Record: found
          • Abstract: not found
          • Article: not found

          Gradient-based learning applied to document recognition

           Y Lecun,  L. Bottou,  Y Bengio (1998)
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            ImageNet Large Scale Visual Recognition Challenge

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Dermatologist-level classification of skin cancer with deep neural networks

              Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images—two orders of magnitude larger than previous datasets—consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.
                Bookmark

                Author and article information

                Affiliations
                [1 ] Institute of Physical Metallurgy and Metal Physics, RWTH Aachen University, Aachen, Germany
                [2 ] IUBH University of Applied Sciences, Bad Honnef, Germany
                Politechnika Krakowska im Tadeusza Kosciuszki, POLAND
                Author notes

                Competing Interests: The authors have declared that no competing interests exist.

                Contributors
                Role: Formal analysis, Role: Investigation, Role: Methodology, Role: Writing – original draft, Role: Writing – review & editing
                Role: Data curation, Role: Investigation, Role: Methodology, Role: Software, Role: Writing – review & editing
                Role: Data curation, Role: Formal analysis, Role: Writing – review & editing
                Role: Funding acquisition, Role: Methodology, Role: Supervision, Role: Writing – original draft, Role: Writing – review & editing
                Role: Conceptualization, Role: Investigation, Role: Methodology, Role: Software, Role: Supervision, Role: Writing – original draft, Role: Writing – review & editing
                ORCID: http://orcid.org/0000-0002-4143-5129, Role: Conceptualization, Role: Formal analysis, Role: Funding acquisition, Role: Methodology, Role: Supervision, Role: Writing – original draft, Role: Writing – review & editing
                Role: Editor
                Journal
                PLoS One
                PLoS ONE
                plos
                plosone
                PLoS ONE
                Public Library of Science (San Francisco, CA USA )
                1932-6203
                8 May 2019
                2019
                : 14
                : 5
                PONE-D-19-00613
                10.1371/journal.pone.0216493
                6505961
                31067239
                © 2019 Kusche et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                Counts
                Figures: 8, Tables: 2, Pages: 22
                Product
                Funding
                Funded by: funder-id http://dx.doi.org/10.13039/501100001659, Deutsche Forschungsgemeinschaft;
                Award ID: TRR188 - B02
                Award Recipient : ORCID: http://orcid.org/0000-0002-4143-5129
                Funded by: funder-id http://dx.doi.org/10.13039/501100001659, Deutsche Forschungsgemeinschaft;
                Award ID: TRR188 - B02
                Award Recipient :
                This work was supported by: SKK and TA, TRR188 - project B02, Deutsche Forschungsgemeinschaft, www.dfg.de. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Research Article
                Physical Sciences
                Physics
                Classical Mechanics
                Deformation
                Physical Sciences
                Physics
                Classical Mechanics
                Damage Mechanics
                Deformation
                Physical Sciences
                Materials Science
                Materials Physics
                Microstructure
                Physical Sciences
                Physics
                Materials Physics
                Microstructure
                Computer and Information Sciences
                Neural Networks
                Biology and Life Sciences
                Neuroscience
                Neural Networks
                Physical Sciences
                Physics
                Condensed Matter Physics
                Nucleation
                Physical Sciences
                Materials Science
                Metallurgy
                Alloys
                Steel
                Biology and Life Sciences
                Cell Biology
                Cellular Types
                Animal Cells
                Neurons
                Biology and Life Sciences
                Neuroscience
                Cellular Neuroscience
                Neurons
                Computer and Information Sciences
                Artificial Intelligence
                Artificial Neural Networks
                Biology and Life Sciences
                Computational Biology
                Computational Neuroscience
                Artificial Neural Networks
                Biology and Life Sciences
                Neuroscience
                Computational Neuroscience
                Artificial Neural Networks
                Research and Analysis Methods
                Mathematical and Statistical Techniques
                Mathematical Functions
                Convolution
                Custom metadata
                The data is available publicly at https://git.rwth-aachen.de/Sandra.Korte.Kerzel/DeepDamage.git.

                Uncategorized

                Comments

                Comment on this article