دورية أكاديمية
Semi-supervised segmentation of metal-artifact contaminated industrial CT images using improved CycleGAN.
| العنوان: | Semi-supervised segmentation of metal-artifact contaminated industrial CT images using improved CycleGAN. |
|---|---|
| المؤلفون: | Jiang SB; Institute of Nuclear and New Energy Technology, Tsinghua University, BeiJing, China.; Tsinghua University-Beijing Key Laboratory of Nuclear Detection Technology., Sun YW; Institute of Nuclear and New Energy Technology, Tsinghua University, BeiJing, China.; Tsinghua University-Beijing Key Laboratory of Nuclear Detection Technology., Xu S; Institute of Nuclear and New Energy Technology, Tsinghua University, BeiJing, China.; Tsinghua University-Beijing Key Laboratory of Nuclear Detection Technology., Zhang HX; Institute of Nuclear and New Energy Technology, Tsinghua University, BeiJing, China.; Tsinghua University-Beijing Key Laboratory of Nuclear Detection Technology., Wu ZF; Institute of Nuclear and New Energy Technology, Tsinghua University, BeiJing, China.; Tsinghua University-Beijing Key Laboratory of Nuclear Detection Technology. |
| المصدر: | Journal of X-ray science and technology [J Xray Sci Technol] 2024; Vol. 32 (2), pp. 271-283. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9000080 Publication Model: Print Cited Medium: Internet ISSN: 1095-9114 (Electronic) Linking ISSN: 08953996 NLM ISO Abbreviation: J Xray Sci Technol Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: Original Publication: San Diego [i.e. Duluth, MN] : Academic Press, [c1989- |
| مواضيع طبية MeSH: | Tomography, X-Ray Computed*/methods , Artifacts*, Image Processing, Computer-Assisted/methods |
| مستخلص: | Accurate segmentation of industrial CT images is of great significance in industrial fields such as quality inspection and defect analysis. However, reconstruction of industrial CT images often suffers from typical metal artifacts caused by factors like beam hardening, scattering, statistical noise, and partial volume effects. Traditional segmentation methods are difficult to achieve precise segmentation of CT images mainly due to the presence of these metal artifacts. Furthermore, acquiring paired CT image data required by fully supervised networks proves to be extremely challenging. To address these issues, this paper introduces an improved CycleGAN approach for achieving semi-supervised segmentation of industrial CT images. This method not only eliminates the need for removing metal artifacts and noise, but also enables the direct conversion of metal artifact-contaminated images into segmented images without the requirement of paired data. The average values of quantitative assessment of image segmentation performance can reach 0.96645 for Dice Similarity Coefficient(Dice) and 0.93718 for Intersection over Union(IoU). In comparison to traditional segmentation methods, it presents significant improvements in both quantitative metrics and visual quality, provides valuable insights for further research. |
| فهرسة مساهمة: | Keywords: CycleGAN; Industrial CT; dataset acquisition; image segmentation; metal artifact; semi-supervised |
| تواريخ الأحداث: | Date Created: 20240113 Date Completed: 20240401 Latest Revision: 20240401 |
| رمز التحديث: | 20240401 |
| DOI: | 10.3233/XST-230233 |
| PMID: | 38217629 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 1095-9114 |
|---|---|
| DOI: | 10.3233/XST-230233 |