Ice-Core Micro-CT Image Segmentation With Deep Learning and Gaussian Mixture Model

• Published in: IEEE transactions on geoscience and remote sensing Vol. 61; pp. 1 - 11
• Main Authors: Bagherzadeh, Faramarz, Freitag, Johannes, Frese, Udo, Wilhelms, Frank
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Albedo; Archives; Computational modeling; Computed tomography; Cores; Deep learning; Density; Glaciation; Ice; ice core; Ice sheets; Image processing; Image segmentation; microcomputer tomography (CT); Microstructure; Mixtures; Polar environments; Polar regions; Porous materials; Probabilistic models; segmentation; Snow; Tomography; unsupervised learning; X-ray imaging
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2023.3334867

Ice cores of polar regions (ice sheets) are one of the most prominent natural archives that can reveal essential historical information from the past environment of our planet. The ice-core microstructure is a key feature in determining the principal properties of ice such as pore close-off, albedo, and melt events. Microcomputer tomography (CT) scans can provide valuable information about the microstructure of materials, although achieving a high-quality automated segmentation of porous materials, especially with phase/density changes is still a challenge. This work proposes a new method for improving the segmentation of porous microstructures where a weak segmentation [Gaussian mixture model (GMM)] on high-resolution (<inline-formula> <tex-math notation="LaTeX">30~\mu \text {m} </tex-math></inline-formula>) data is used as ground truth to train a deep-learning model (U-net) for segmentation of low-resolution (<inline-formula> <tex-math notation="LaTeX">60~\mu \text{m} </tex-math></inline-formula>) data. This approach has reached high segmentation accuracy in terms of quantitative metrics having the F1-score of 92.5% and an intersection over the union (IoU) of 91%, with a considerable improvement compared to thresholding and unsupervised methods. Also, the segmentation results of U-net are closer to the real weight, density, and specific surface area (SSA) of the specimen.