cs.CVFeb 27, 2026

Unsupervised Semantic Segmentation in Synchrotron Computed Tomography with Self-Correcting Pseudo Labels

Authors: Austin Yunker, Peter Kenesei, Hemant Sharma, Jun-Sang Park, Antonino Miceli, Rajkumar Kettimuthu

Organizations: Data Science and Learning Division, Argonne National Laboratory, Lemont, IL USA · X-Ray Science Division, Argonne National Laboratory, Lemont, IL USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

X-ray computed tomography (CT) is a widely used imaging technique that provides detailed examinations into the internal structure of an object with synchrotron CT (SR-CT) enabling improved data quality by using higher energy, monochromatic X-rays. While SR-CT allows for improved resolution, time-resolved experimentation, and reduced imaging artifacts, it also produces significantly larger datasets than conventional CT. Accurate and efficient evaluation of these datasets is a critical component of these workflows; yet is often done manually representing a major bottleneck in the analysis phase. While deep learning has emerged as a powerful tool capable of providing a wide range of purely data-driven solutions, it requires a substantial amount of labeled data for training and manual annotation of SR-CT datasets is impractical in practice. In this paper, we introduce a novel framework that enables automatic segmentation of large, high-resolution SR-CT datasets by eliminating the need to hand label images for deep learning training. First, we generate pseudo labels by clustering on the voxel values identifying regions in the volume with similar attenuation coefficients producing an initial semantic map. Afterwards, we train a segmentation model on the pseudo labels before utilizing the Unbiased Teacher approach to self-correct them ensuring accurate final segmentations. We find our approach improves pixel-wise accuracy and mIoU by 13.31% and 15.94%, respectively, over the baseline pseudo labels when using a magnesium crystal SR-CT sample. Additionally, we extensively evaluate the different components of our workflow including segmentation model, loss function, pseudo labeling strategy, and input type. Finally, we evaluate our approach on to two additional samples highlighting our frameworks ability to produce segmentations that are considerably better than the original pseudo labels.

Figures & tables

Fig. 1 : Three stage approach for unsupervised semantic segmentation in synchrotron computed tomography (SR-CT) with self-correcting pseudo labels. In the first stage, we cluster voxel values to generate initial pseudo labels on unlabeled SR-CT images which are then used in the second stage to train a segmentation model. Finally, in the self-correction stage, we adapt the Unbiased Teacher [ 32 ] approach to refine the segmentation model.
Fig. 2 : Adaptation of the Unbiased Teacher [ 32 ] approach for unsupervised semantic segmentation.
Fig. 3 : Evaluating the necessity of the self-correction stage.
Fig. 4 : Stage 3 model predictions for U-Net and ResUNet both with no skip connections, DeepLabv3+, and SegFormer.
Fig. 5 : Stage 3 model predictions when using cross entropy loss with label smoothing and bootstrapping and focal loss.
Fig. 6 : Stage 3 model predictions when using 3, 5, 7, and 9 adjacent slices as input following the 2.5D approach.
Fig. 7 : Stage 3 model predictions when using Multi-Otsu and Gaussian Mixture Models to generate the initial pseudo labels for stage 2
Fig. 8 : Stage 3 model predictions when training for 100, 500, and 1000 epochs in stage 2.
Fig. 9 : Qualitative results for over-segmented SR-CT image consisting of 5 classes.
Fig. 10 : Qualitative results for over-segmented SR-CT image consisting of 10 classes.
Fig. 11 : Grad-CAM [ 33 ] scores for magnesium dataset. Higher intensity values indicate regions that strongly contribute to the model’s prediction for the target class.
Fig. 12 : Results of the silica sand dataset showing an example SR-CT image, pseudo label, and stage 3 prediction.
Fig. 13 : Results of the ceramic dataset showing an SR-CT image, pseudo label, and stage 3 prediction.
More in this topic

Unsupervised Image Segmentation

Unsupervised image segmentation discovers meaningful regions, objects, or instances in images without relying on dense human-labeled masks.

See all 23 papers

Explore similar work

CardsList
Oct 20, 2026

TEMPL: A Resource-Efficient and Transparent Model-Free Framework for Pseudo-Label Generation in Material CT Scans

The scarcity of large annotated datasets limits deep learning (DL) segmentation in material CT analysis. DL-based pseudo-labeling can help, but it is often computationally expensive and hard to interpret. We introduce a multi-stage, model-free framework that generates pseudo-labels directly from grayscale CT scans. It combines thresholding, morphological dilation, and a custom breadth-first search region-growing algorithm to produce polygonal annotations without pre-trained weights, labeled data, or a GPU. We compare it against the zero-shot Segment Anything Model (SAM), a fully supervised 3D U-Net, and classical baselines. On a dendrite dataset with ground truth, our method reaches 63.19% IoU versus 10.74% for zero-shot SAM, with four times the instance recall at 0.5 IoU (33.3% versus 8.3%). The supervised 3D U-Net serves as a reference ceiling that requires expert labels. On a silica sand specimen, YOLO models trained on our labels performed comparably to models trained on SAM labels in a qualitative comparison. Across 1,053 extracted grains, the median equivalent diameter was 163.8 micrometers, near the specimen's known 106 to 150 micrometers sieve range, compared with 219.5 micrometers for SAM, whose labels merge adjacent particles and add spurious detections. A sensitivity analysis shows a stable operating range for the key threshold and a sharp, predictable failure point linked to phase contrast. Our method needs 15s per image on a standard CPU versus 28s for SAM on a GPU. These results support our transparent approach as a tool for annotation bootstrapping and microstructural quantification in resource-limited settings.

Ashiqur Rahman, Venkata Devesh Reddy Seethi, Austin Yunker +2

Department of Computer Science, Northern Illinois University, DeKalb, IL, USA · Argonne National Laboratory, Lemont, IL, USA

Image SegmentationPseudo-LabelingInstance SegmentationComputed Tomography
AskPDF
Jul 13, 2026

From Reconstruction to Interpretation: Zero-Setup Multi-Phase Segmentation of X-ray Tomography Data

X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction. However, rapid interpretation remains limited by image segmentation, which often requires manual thresholding, user prompting, or material-specific model training. We present a zero-setup framework for multi-phase segmentation of synchrotron X-ray tomography data that generates interpretable masks for previously unseen datasets without user input or retraining during deployment. The framework combines a material-agnostic mask preparation strategy with a pretrained semantic segmentation network. It represents commonly occurring structural regions as background, sample, bright, dark-gray, light-gray, and porosity masks. Unlike conventional deep learning pipelines that require dataset-specific annotations and retraining, the proposed framework can be applied directly to new scans and produce diagnostic-level segmentations within minutes of reconstruction. This enables rapid assessment of scan quality, sample morphology, porosity, and attenuation variations during ongoing beamline experiments. The generated masks can later be manually refined or used to fine-tune application-specific models when greater accuracy or material-specific labeling is required. Evaluation on held-out synchrotron micro-CT images and qualitative testing on additional datasets demonstrate consistent and physically meaningful segmentations across varying samples and imaging conditions. The framework also substantially outperforms conventional intensity-based thresholding. By connecting high-speed reconstruction with immediate interpretation, the approach supports near-real-time beamline feedback and scalable AI-assisted scientific imaging workflows.

Pradyumna Elavarthi, Arun J. Bhattacharjee, Harrison Lisabeth +4

Department of Computer Science, University of Cincinnati. · Energy Geosciences Division, Lawrence Berkeley National Laboratory. · Center for Advanced Mathematics in Energy Research Applications, Lawrence Berkeley National Laboratory. +1

Image SegmentationZero-Shot Referring Image SegmentationComputed TomographySemantic Segmentation
AskPDF
Aug 15, 2025

Subcortical Masks Generation in CT Images via Ensemble-Based Cross-Domain Label Transfer

Subcortical segmentation in neuroimages plays an important role in understanding brain anatomy and facilitating computer-aided diagnosis of traumatic brain injuries and neurodegenerative disorders. However, training accurate automatic models requires large amounts of labelled data. Despite the availability of publicly available subcortical segmentation datasets for Magnetic Resonance Imaging (MRI), a significant gap exists for Computed Tomography (CT). This paper proposes an automatic ensemble framework to generate high-quality subcortical segmentation labels for CT scans by leveraging existing MRI-based models. We introduce a robust ensembling pipeline to integrate them and apply it to unannotated paired MRI-CT data, resulting in a comprehensive CT subcortical segmentation dataset. Extensive experiments on multiple public datasets demonstrate the superior performance of our proposed framework. Furthermore, using our generated CT dataset, we train segmentation models that achieve improved performance on related segmentation tasks. To facilitate future research, we make our source code, generated dataset, and trained models publicly available at https://github.com/alxw0671/CT_Subcortical_Segmentation, marking the first open-source release for CT subcortical segmentation to the best of our knowledge.

Augustine X. W. Lee, Pak-Hei Yeung, Jagath C. Rajapakse

College of Computing and Data Science, Nanyang Technological University, Singapore

Cross-Modality Medical Image SegmentationMedical Image SegmentationComputed TomographyMedical Image Benchmarks
AskPDF