{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-modular-u-net-for-automated-segmentation-of","title":"A modular U-Net for automated segmentation of X-ray tomography images in composite materials","arxiv_id":"2107.07468","date":"2021-07-15","proceeding":null,"authors":["João P C Bertoldo","Etienne Decencière","David Ryckelynck","Henry Proudhon"],"abstract":"X-ray Computed Tomography (XCT) techniques have evolved to a point that high-resolution data can be acquired so fast that classic segmentation methods are prohibitively cumbersome, demanding automated data pipelines capable of dealing with non-trivial 3D images. Deep learning has demonstrated success in many image processing tasks, including material science applications, showing a promising alternative for a humanfree segmentation pipeline. In this paper a modular interpretation of UNet (Modular U-Net) is proposed and trained to segment 3D tomography images of a three-phased glass fiber-reinforced Polyamide 66. We compare 2D and 3D versions of our model, finding that the former is slightly better than the latter. We observe that human-comparable results can be achievied even with only 10 annotated layers and using a shallow U-Net yields better results than a deeper one. As a consequence, Neural Network (NN) show indeed a promising venue to automate XCT data processing pipelines needing no human, adhoc intervention.","url_abs":"https://arxiv.org/abs/2107.07468v2","url_pdf":"https://arxiv.org/pdf/2107.07468v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-modular-u-net-for-automated-segmentation-of","repo_url":"https://github.com/joaopcbertoldo/tomo2seg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"2d-semantic-segmentation","task_name":"2D Semantic Segmentation"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[{"slug":"gf-pa66-3d-xct-latest","name":"GF-PA66 3D XCT (latest)","full_name":"Glass fiber-reinforced polyamide 66 3D X-ray Computed Tomography"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-semantic-segmentation-on-gf-pa66-3d-xct","task":"2D Semantic Segmentation","dataset":"GF-PA66 3D XCT","model":"Modular U-Net (2D)","rank_in_archive_order":1,"of":1,"metrics":{"Jaccard (Mean)":"87"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}