arXiv subjects

Paul Tafforeau

Publications and source records attributed to Paul Tafforeau.

8 recordsLinked to original sources

arXiv2026

LoRCA: LoRA Cycle Adaptation for Histology to HiP-CT Translation with DINOv3

Hierarchical Phase-Contrast Tomography (HiP-CT) is a synchrotron based X-ray imaging technique that enables non-destructive, volumetric imaging of intact organs with multi-resolutions bridging 20 $μm$/voxel for whole organs to near-cellular resolution ($\sim$0.8 $μm$/voxel) in local regions. This offers the opportunity to bring volumetric whole-organ context to histology. However, nonlinear registration between H\&E histology and HiP-CT volumes is challenging due to the differences in feature representations of different colour spaces. Synthesis-before-registration methods have shown strong results in histology-to-MRI and histology-to-CT alignment. However, existing approaches either rely on manual anatomical contours or are trained from scratch without semantic constraints, limiting their generalisability to soft tissue organs and novel modalities. We propose LoRCA (LoRA Cycle Adaptation), a cycle consistent style translation framework built on a shared frozen DINOv3 with modality-specific LoRA adapters, learning modality-specific representations that are decoded and adversarially trained. LoRCA enables structure-preserving translation without requiring paired training data. The frozen backbone is intended to be a structural anchor that prevents content drift by preserving pretrained semantic-extraction capability. We evaluate translation quality using Fréchet Inception Distance (FID) and structural fidelity via mutual information and Canny edge preservation. LoRCA outperforms CycleGAN in both translation quality and structural consistency. As a preliminary indicator of downstream registration utility, we find that style-translated images yield increased feature correspondences under MatchAnything on manually aligned HiP-CT and histology test pairs, suggesting that LoRCA-style translation is a promising step towards 2D histological sections to 3D HiP-CT volumes registration.

eess.IV↗

arXiv2026

Complete virtual unwrapping and reading of a rolled Herculaneum papyrus

The carbonized papyri from Herculaneum preserve the only large-scale library to survive from classical antiquity, but many unopened rolls remain unread because physical opening risks irreversible damage. X-ray computed microtomography ($μ$CT) and virtual unwrapping offer a non-invasive route to their texts, yet previous work on sealed Herculaneum scrolls has recovered only localized readings or limited surface regions. Here, using high-resolution phase-contrast $μ$CT acquired on the BM18 beamline at the European Synchrotron Radiation Facility (ESRF), together with improved computational unrolling and machine learning, we achieve the complete virtual unwrapping and reading of PHerc. 1667 under explicit coverage and papyrological-review criteria. This makes PHerc. 1667 the first Herculaneum papyrus to be fully digitally unrolled and read for extended scholarly study without physical opening. In PHerc. Paris 4, the optimized scan protocol makes ink directly visible in the tomographic volume, allowing three-dimensional ink segmentation and independent validation of surface-conditioned ink recovery. In PHerc. 139, we recover title and author-attribution evidence identifying the scroll as Philodemus, On Gods, Book 8. These results move virtual unwrapping of the Herculaneum scrolls beyond isolated demonstrations towards a scalable framework for systematic recovery of the still-unopened library.

eess.IV↗

arXiv2026

Fast Eikonal Phase Retrieval for High-Throughput Beamlines

We introduce a fast Eikonal Phase Retrieval (EPR) formulation that accelerates eikonal phase retrieval by more than two orders of magnitude while retaining controlled accuracy. The method is derived from a second-order asymptotic expansion in the propagation distance $L$ and complemented by the leading Wentzel--Kramers--Brillouin (WKB) wave-optics correction, yielding an efficient iterative correction scheme preconditioned by FFT-diagonal, energy-dependent inverse operators (Paganin-type filters). To ensure robustness across practical experimental regimes, we combine two complementary solvers: (i) a local $O(L^2)$ closure that is accurate when eikonal shifts remain sub-pixel, and (ii) a non-local formulation for multi-pixel shifts, in which intensity is propagated through an explicit eikonal ray mapping using a mass-conserving bilinear redisribution on the detector grid, and detector residuals are transferred back to the object grid by the corresponding adjoint (transpose), implemented as bilinear interpolation, before applying an approximate FFT-diagonal preconditioner to accelerate convergence. The same framework supports polychromatic data through a compact spectral discretisation, allowing energy-dependent transport and inversion while keeping the iteration GPU/FFT efficient. Overall, this unified approach enables accurate and computationally efficient phase retrieval across propagation conditions relevant to high-throughput PPC-$μ$CT experiments.

physics.optics↗

arXiv2025

Multispectral CT Denoising via Simulation-Trained Deep Learning: Experimental Results at the ESRF BM18

Multispectral computed tomography (CT) enables advanced material characterization by acquiring energy-resolved projection data. However, since the incoming X-ray flux is be distributed across multiple narrow energy bins, the photon count per bin is greatly reduced compared to standard energy-integrated imaging. This inevitably introduces substantial noise, which can either prolong acquisition times and make scan durations infeasible or degrade image quality with strong noise artifacts. To address this challenge, we present a dedicated neural network-based denoising approach tailored for multispectral CT projections acquired at the BM18 beamline of the ESRF. The method exploits redundancies across angular, spatial, and spectral domains through specialized sub-networks combined via stacked generalization and an attention mechanism. Non-local similarities in the angular-spatial domain are leveraged alongside correlations between adjacent energy bands in the spectral domain, enabling robust noise suppression while preserving fine structural details. Training was performed exclusively on simulated data replicating the physical and noise characteristics of the BM18 setup, with validation conducted on CT scans of custom-designed phantoms containing both high-Z and low-Z materials. The denoised projections and reconstructions demonstrate substantial improvements in image quality compared to classical denoising methods and baseline CNN models. Quantitative evaluations confirm that the proposed method achieves superior performance across a broad spectral range, generalizing effectively to real-world experimental data while significantly reducing noise without compromising structural fidelity.

eess.IV↗

arXiv2025

Eikonal phase retrieval: Unleashing the fourth generation sources potential for enhanced propagation based tomography on biological samples

The evolution of synchrotrons towards higher brilliance beams has increased the possible sample-to-detector propagation distances for which the source confusion circle does not lead to geometrical blurring. This makes it possible to push near-field propagation driven phase contrast enhancement to the limit, revealing low contrast features which would otherwise remain hidden under an excessive noise. Until today this possibility was hindered, in many objects of scientific interest, by the simultaneous presence of strong phase gradient regions and low contrast features. The strong gradients, when enhanced with the now possible long propagation distances, induce such strong phase effects that the linearisation assumptions of current state-of-the-art single-distance phase retrieval filters are broken, and the resulting image quality is jeopardized. Here, we introduce a new iterative phase-retrieval algorithm and compare it with the Paganin phase-retrieval algorithm, in both the monochromatic and polychromatic cases, obtaining superior image quality. In the polychromatic case the comparison was done with an extrapolated Paganin algorithm obtained by reintroducing, into our phase retrieval algorithm, the linearization approximations underlying the Paganin forward model. Our work provides an innovative algorithm which efficiently performs the phase retrieval task over the entire near-field range, producing images of exceptional quality for mixed attenuation objects.

physics.med-ph↗

arXiv2023

Deep Learning for Vascular Segmentation and Applications in Phase Contrast Tomography Imaging

Automated blood vessel segmentation is vital for biomedical imaging, as vessel changes indicate many pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. We present a thorough literature review, highlighting the state of machine learning techniques across diverse organs. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation in a new imaging modality, Hierarchical Phase Contrast Tomography (HiP CT). Introduced in 2020 at the European Synchrotron Radiation Facility, HiP CT enables 3D imaging of complete organs at an unprecedented resolution of ca. 20mm per voxel, with the capability for localized zooms in selected regions down to 1mm per voxel without sectioning. We have created a training dataset with double annotator validated vascular data from three kidneys imaged with HiP CT in the context of the Human Organ Atlas Project. Finally, utilising the nnU Net model, we conduct experiments to assess the models performance on both familiar and unseen samples, employing vessel specific metrics. Our results show that while segmentations yielded reasonably high scores such as clDice values ranging from 0.82 to 0.88, certain errors persisted. Large vessels that collapsed due to the lack of hydrostatic pressure (HiP CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors obstruct the understanding of the structures by interrupting vascular tree connectivity. Through our review and outputs, we aim to set a benchmark for subsequent model evaluations using various modalities, especially with the HiP CT imaging database.

eess.IV↗

arXiv2021

Automated segmentation of microtomography imaging of Egyptian mummies

Propagation Phase Contrast Synchrotron Microtomography (PPC-SR$μ$CT) is the gold standard for non-invasive and non-destructive access to internal structures of archaeological remains. In this analysis, the virtual specimen needs to be segmented to separate different parts or materials, a process that normally requires considerable human effort. In the Automated SEgmentation of Microtomography Imaging (ASEMI) project, we developed a tool to automatically segment these volumetric images, using manually segmented samples to tune and train a machine learning model. For a set of four specimens of ancient Egyptian animal mummies we achieve an overall accuracy of 94-98% when compared with manually segmented slices, approaching the results of off-the-shelf commercial software using deep learning (97-99%) at much lower complexity. A qualitative analysis of the segmented output shows that our results are close in terms of usability to those from deep learning, justifying the use of these techniques.

cs.CV↗

arXiv2013

PyHST2: an hybrid distributed code for high speed tomographic reconstruction with iterative reconstruction and a priori knowledge capabilities

We present the PyHST2 code which is in service at ESRF for phase-contrast and absorption tomography. This code has been engineered to sustain the high data flow typical of the third generation synchrotron facilities (10 terabytes per experiment) by adopting a distributed and pipelined architecture. The code implements, beside a default filtered backprojection reconstruction, iterative reconstruction techniques with a-priori knowledge. These latter are used to improve the reconstruction quality or in order to reduce the required data volume and reach a given quality goal. The implemented a-priori knowledge techniques are based on the total variation penalisation and a new recently found convex functional which is based on overlapping patches. We give details of the different methods and their implementations while the code is distributed under free license. We provide methods for estimating, in the absence of ground-truth data, the optimal parameters values for a-priori techniques.

math.NA↗