Material-SAM: Adapting SAM for Material XCT

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.