Material-SAM: Adapting SAM for Material XCT
Source abstract
Abstract
X-ray Computed Tomography (XCT) enables non-destructive acquisition of the internal structure of materials, and image segmentation plays a crucial role in analyzing material XCT images. This paper proposes an image segmentation method based on the Segment Anything model (SAM). We constructed a dataset of carbide in nickel-based single crystal superalloys XCT images and preprocessed the images using median filtering, histogram equalization, and gamma correction. Subsequently, SAM was fine-tuned to adapt to the task of material XCT image segmentation, resulting in Material-SAM. We compared the performance of threshold segmentation, SAM, U-Net model, and Material-SAM. Our method achieved 88.45% Class Pixel Accuracy (CPA) and 88.77% Dice Similarity Coefficient (DSC) on the test set, outperforming SAM by 5.25% and 8.81%, respectively, and achieving the highest evaluation. Material-SAM demonstrated lower input requirements compared to SAM, as it only required three reference points for completing the segmentation task, which is one-fifth of the requirement of SAM. Material-SAM exhibited promising results, highlighting its potential as a novel method for material XCT image segmentation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced X-ray and CT Imaging · Cultural Heritage Materials Analysis · Electron and X-Ray Spectroscopy Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Cyclic plasticity at pores and inclusions in cast Al-Si alloys10.1016/S0013-7944(02)00097-8 ↗
2. A micro-cell model of the effect of microstructure and defects on fatigue resistance in cast aluminum alloys10.1016/j.actamat.2004.07.035 ↗
3. The effect of casting conditions on the high-cycle fatigue properties of the single-crystal nickel-base superalloy PWA 148310.1007/s11661-007-9188-4 ↗
4. Benefits of high gradient solidification for creep and low cycle fatigue of AM1 single crystal superalloy10.1016/j.msea.2015.07.045 ↗
5. VHCF life evolution after microstructure degradation of a Ni-based single crystal superalloy10.1016/j.ijfatigue.2017.07.021 ↗
6. Crack formation and microstructure-sensitive propagation in low cycle fatigue of a polycrystalline nickel-based superalloy with different heat treatments10.1016/j.ijfatigue.2017.10.012 ↗
7. Strain accumulation and fatigue crack initiation at pores and carbides in an SX superalloy at room temperature10.1016/j.ijfatigue.2018.05.003 ↗
8. High cycle fatigue data transferability of MAR-M 247 superalloy from separately cast specimens to real gas turbine blade10.3390/met10111460 ↗
9. 3D Fe-rich phases evolution and its effects on the fracture behavior of Al-7.0 Si-1.2 Fe alloys by Mn neutralization10.1007/s40195-021-01299-x ↗
10. Hou · Constr. Build. Mater. · 2023 · 372 · 13071510.1016/j.conbuildmat.2023.130715 ↗
11. Synthetic data generation for automatic segmentation of X-ray computed tomography reconstructions of complex microstructures10.3390/jimaging9020022 ↗
12. Stress sensitivity of fractured and vuggy carbonate: An X-ray computed tomography analysis
13. Characterization of the convoluted 3D intermetallic phases in a recycled Al alloy by synchrotron X-ray tomography and machine learning10.1007/s40195-021-01312-3 ↗
14. Liu · Mater. Charact. · 2021 · 177 · 11118010.1016/j.matchar.2021.111180 ↗
15. Quantifying the influences of carbides and porosities on the fatigue crack evolution of a Ni-based single-crystal superalloy using X-ray tomography10.1007/s40195-021-01273-7 ↗
16. A. Kirillov et al., “Segment anything,” arXiv preprint arXiv:2304.02643, 2023.
17. R. Deng et al., “Segment anything model (SAM) for digital pathology: Assess zero-shot segmentation on whole slide imaging,” arXiv preprint arXiv:2304.04155, 2023.
18. S. He, R. Bao, J. Li, P. E. Grant, and Y. Ou, “Accuracy of segment-anything model (SAM) in medical image segmentation tasks,” arXiv preprint arXiv:2304.09324, 2023.
19. D. Han, C. Zhang, and Y. Qiao, “Segment anything model (SAM) meets glass: Mirror and transparent objectscannot be easily detected,” arXiv preprint arXiv:2305.00278, 2023.
20. Gradient-based phase segmentation method for characterization of hydrating cement paste microstructures obtained from X-ray micro-CT10.1016/j.jobe.2021.103721 ↗
21. Optimizing convolutional neural networks to perform semantic segmentation on large materials imaging datasets: X-ray tomography and serial sectioning10.1016/j.matchar.2020.110119 ↗
22. Deep learning method for analysis and segmentation of fatigue damage in X-ray computed tomography data for fiber-reinforced polymers10.1016/j.compscitech.2022.109781 ↗
23. PoreSeg: An unsupervised and interactive-based framework for automatic segmentation of X-ray tomography of porous materials10.1016/j.advwatres.2023.104495 ↗
24. Fully convolutional networks for semantic segmentation
25. U-Net: Convolutional networks for biomedical image segmentation
26. Brain tumor augmentation using the U-net architecture
27. SegNet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
28. Pyramid scene parsing network
29. L. C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking atrous convolution for semantic image segmentation,” arXiv preprint arXiv:1706.05587, 2017.
30. Dual attention network for scene segmentation
31. C. Hu and X. Li, “When SAM meets medical images: An investigation of segment anything model (SAM) on multi-phase liver tumor segmentation,” arXiv preprint arXiv:2304.08506, 2023.
32. S. Mohapatra, A. Gosai, and G. Schlaug, “Brain extraction comparing segment anything model (SAM) and FSL brain extraction tool,” arXiv preprint arXiv:2304.04738, 2023.
33. A large, open source dataset of stroke anatomical brain images and manual lesion segmentations10.1038/sdata.2018.11 ↗
34. Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge10.1109/TMI.2019.2905770 ↗
35. D. Cheng, Z. Qin, Z. Jiang, S. Zhang, Q. Lao and K. Li, “SAM on medical images: A comprehensive study on three prompt modes,” arXiv preprint arXiv:2305.00035, 2023.
36. J. Wu et al., “Medical SAM adapter: Adapting segment anything model for medical image segmentation,” arXiv preprint arXiv:2304.12620, 2023.
37. T. Chen et al., “SAM fails to segment anything?—SAM-Adapter: Adapting SAM in underperformed scenes: Camouflage, shadow, and more,” arXiv preprint arXiv:2304.09148, 2023.10.1109/ICCVW60793.2023.00361 ↗
38. Camouflaged object detection
39. P. Skurowski, H. Abdulameer, J. Błaszczyk, T. Depta, A. Kornacki and P. Kozieł, “Animal camouflage analysis: Chameleon database,” Katedra Grafiki Wizji Komputerowej I Systemów Cyfrowych, Politechnika Śląska, 2018.
40. Anabranch network for camouflaged object segmentation10.1016/j.cviu.2019.04.006 ↗
41. Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal
42. Effect of cooling rate on carbides in directionally solidified nickel-based single crystal superalloy: X-ray tomography and U-Net CNN quantification10.1016/j.jallcom.2021.160723 ↗
43. Kvasir-SEG: A segmented polyp dataset
44. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv: 1412. 6980, 2014.
45. Quantifying the influence of secondary phases on corrosion in multicomponent Mg alloys using X-ray computed microtomography10.1016/j.corsci.2021.110010 ↗