X-ray fluorescence (XRF) microscopy maps elemental distributions, while optical microscopy can provide complementary morphological context. Localizing XRF fields of view (FOVs) in optical images is difficult because the two modalities differ in contrast mechanism and resolution. Most current workflows place each XRF tile independently, even when acquisition metadata already record the tiles'relative scan positions. This study formalizes XRF tile-group localization, in which one optical-frame placement is estimated for the whole group, constrained by acquisition geometry and quantified using group intersection-over-union (GroupIoU). In a controlled case study, independent localization failed with GroupIoU 0.000, whereas group localization achieved 0.931. Replacing the normalized cross-correlation (NCC) metric with mutual information (MI) gave nearly identical results, showing that the outcome is not specific to one local similarity metric. In another multiscale case study, using a coarse XRF survey scan to connect the fine-scale tile group to the optical image increased mean GroupIoU from 0.694 to 0.856. These case studies support using acquisition geometry as an explicit constraint when localizing related XRF tiles.
This paper evaluates training-free vision language model (VLM) localization on two datasets representing same-section high-correspondence and adjacent-section low-correspondence imaging and tests unconstrained and metadata-constrained search and VLMs with geometric controls, classical template matching, and two alternative training-free approaches.
Xiangyu Yin, T. Paunesku, Letonia Copeland-Hardin et al.· 0 citations
Infrared (IR) microscopy shows substantial potential for label-free tissue imaging in anatomic pathology, providing rich biochemical contrast. However, existing IR imaging technologies are constrained by slow acquisition speeds and limited spatial resolution. Here, we present a rapid, large-field bimodal imaging platform that integrates conventional brightfield microscopy with a lensless IR imaging scanner, enabling whole-slide IR image stack acquisition in minutes. Using a dedicated deep learning model, we implement an optical H&E staining strategy based on subcellular morpho-spectral fingerprinting. This approach achieves high-resolution visualization of tissue architecture with an effective spatial resolution of 500 nm, without chemical staining. Quantitative metrics, including PSNR (∼24), MS-SSIM (∼0.82), and LPIPS (∼0.22), validate the model's ability to accurately reproduce both the contrast and morphology of cellular structures. Additionally, an initial clinical evaluation on 110 regions of interest within 5 tissue sections demonstrates equivalence between our digital IR-based AI staining and conventional chemical staining, both in image quality and Gleason grading. Together, these results suggest that this IR-based virtual staining approach could provide a fast, chemical-free alternative for anatomic pathology workflows.
L. Duraffourg, H. Borges, M. Fernandes et al.· Frontiers in Bioengineering...· 0 citations
Confocal microscopy, with its exceptional optical sectioning capabilities and multimodal imaging capabilities, provides critical tools for morphological observation and quantitative analysis. As a label-free technique, confocal transmission mode offers rich information on cellular 3D structures; however, its optical transfer function suffers from an inherent “missing cone” problem, which causes severe degradation of axial resolution and generates stretching artifacts, thereby limiting detailed 3D quantitative analysis. The Gerchberg-Papoulis (GP) iterative algorithm can compensate for missing spectral information through frequency-domain extrapolation; however, its reconstruction performance is highly dependent on the accuracy of the spatial support domain, and transmission images themselves struggle to precisely extract the three-dimensional boundaries of complex biological samples. To address this issue, this paper proposes a 3D reconstruction method that integrates dual-modality imaging with the GP algorithm: leveraging the superior optical sectioning properties and 3D resolution of confocal fluorescence imaging, high-fidelity 3D support domains are obtained by specifically labeling the cell membrane; this support domain is then introduced as a core constraint into the GP algorithm to perform frequency-domain extrapolation and reconstruction of transmission images within the same field of view. Experimental results on cell models demonstrate that this method effectively suppresses axial stretching artifacts, significantly improves axial resolution and structural fidelity, and provides a robust and efficient new computational imaging strategy for the analysis of fine cellular structures.
Min Xu· International Conference on...· 1 citation
Gaining understanding of process-structure-property relationships in materials at a mechanistic level relies on correlative microscopy workflows. These workflows, in turn, fundamentally depend on image matching, i.e., a computer vision task with the objective of finding point correspondences in pairs of images. Matching models are difficult to evaluate quantitatively in the materials field due to a shortage of representative benchmark datasets. Nonetheless, prior research indicates that traditional rule-based image matching techniques such as the surface-invariant feature transform (SIFT) currently fall short on such matching tasks. We present a dataset for cross-modal image matching and data fusion in the materials microscopy domain, which we coin
AmalgaMatch
, to support model benchmarking and fine-tuning efforts. All images are micrographs captured using the most widely applied imaging techniques in materials science including light-optical, scanning electron, and transmission electron microscopy, as well as electron backscatter diffraction (EBSD). Therein, various detectors and imaging modes are employed to capture micrographs of diverse materials. While the majority of images are raw images, some underwent typical processing routes using digital image correlation or EBSD indexing. Common regions in image pairs are populated with hand-annotated keypoint correspondences. While mutual information is limited in cross-modal, multi-scale image pairs, we relied on characteristic defects such as dislocations, grain boundaries, triple junctions, inclusions, pores or topographic features for annotation. Furthermore, the dataset is divided into groups, defined by distinct registration use cases, and further into subsets, defined by the imaged material. The dataset covers many typical use cases for image matching in materials science, including slip partitioning, dislocation characterization, and surface fractography. In total, it comprises 6 groups and 19 subsets with 35 scenes and 187 annotated image pairs to support autonomous multimodal materials data fusion. For each image, we provide structured metadata to facilitate training of hybrid matching models which process textual alongside image-based inputs to improve the matching quality and robustness. A formal ontological model for correlative microscopy and image matching processes is proposed to express image contents, relationships, and transformations through knowledge graphs and to enable aligning with FAIR data principles.
A. Durmaz, James D. Lamb, Kamilla Zaripova et al.· Scientific Data· 1 citation
Direct-space and real-time coherent X-ray imaging (direct-CXI) enables visualization of magnetic-domain structures and dynamics over length scales exceeding the field of view of a single image. However, large-area measurements typically require raster scanning, producing hundreds of partially overlapping images that must be accurately aligned and combined before quantitative analysis can be performed. Here, we present Multi-image Overlap Stitching and Automatic Image Construction for coherent X-ray imaging (MOSAICX), an automated stitching workflow for large-area direct-space coherent X-ray imaging. The workflow consists of image centering, masking, trimming, binarization, hierarchical stitching, and post-processing. To demonstrate the method, we apply it to a dataset comprising 434 direct-CXI images of the antiferromagnetic topological insulator MnBi$_2$Te$_4$. The images are first combined into column reconstructions and subsequently stitched into a single large-area composite image. The resulting reconstruction reveals the complete magnetic-domain and domain-wall landscape over the scanned region while suppressing imaging artifacts and detector defects. The presented workflow provides an efficient approach for processing large direct-CXI datasets and enables visualization and analysis of magnetic-domain structures beyond the field of view of individual measurements.
S. Boney, Umeshika S Dissanayaka, L. Rutowski et al.· 0 citations
This survey provides the first bi-modality review covering both laboratory and synchrotron biomedical μCT segmentation, consolidates recent segmentation methodologies, identifies major trends in deep-learning techniques, and highlights current limitations across SR-PCI-μCT.
Hao Song, Ning Zhu· npj Imaging· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
