Background/Objectives: To determine the optimal reconstruction parameters for accurate visualization of peripheral in-stent restenosis using photon-counting detector CT (PCD-CT), and to evaluate its potential advantages over energy-integrated detector CT (EID-CT). Methods: Endovascular peripheral stents with varying degrees of in-stent restenosis were scanned in a custom-made phantom using EID-CT (Somatom Force) and PCD-CT (Naeotom Alpha) under clinical acquisition protocols. EID-CT images were reconstructed with Bv40 and Bv59 kernels at 512 matrices. PCD-CT data were acquired in standard-resolution (SR) and ultra-high-resolution (UHR) modes. In both modes, images were reconstructed with multiple kernels (Bv40, Bv56 and Bv72) and matrix sizes (512 and 1024 matrix). In SR mode, additional virtual monoenergetic images (40–100 keV) were generated, while UHR mode included only polychromatic reconstructions. Quantitative image quality (noise, contrast, contrast-to-noise ratio [CNR]) was measured, and two blinded readers performed qualitative assessments of restenosis visualization. Results: PCD-CT with SR mode at VMI 40 keV achieved the highest image contrast and CNR, significantly outperforming EID-CT and PCD-CT_UHR under matched conditions (all p < 0.05). The sharper reconstruction kernel further enhanced the image contrast and improved subjective visualization despite increased image noise. Both readers ranked PCD-CT_{SR-Bv72-40keV} at 1024 matrix highest for detecting all degrees of restenosis, with excellent inter-reader agreement (ρ > 0.80). Conclusions: PCD-CT in SR mode at VMI 40 keV, specifically using the Bv72 kernel with a 1024 matrix, optimizes the visualization of peripheral in-stent restenosis. Compared to EID-CT, PCD-CT provides superior image quality and detectability of restenosis.

Accurate MRI-to-CT translation promises the integration of complementary imaging information without the need for additional imaging sessions. Given the practical challenges associated with acquiring paired MRI and CT scans, the development of robust methods capable of leveraging unpaired datasets is essential for advancing the MRI-to-CT translation. Current unpaired MRI-to-CT translation methods, which predominantly rely on cycle consistency and contrastive learning frameworks, frequently encounter challenges in accurately translating anatomical features that are highly discernible on CT but less distinguishable on MRI, such as bone structures. This limitation renders these approaches less suitable for applications in radiation therapy, where precise bone representation is essential for accurate treatment planning. To address this challenge, we propose a path- and bone-contour regularized approach for unpaired MRI-to-CT translation. In our method, MRI and CT images are projected to a shared latent space, where the MRI-to-CT mapping is modeled as a continuous flow governed by neural ordinary differential equations. The optimal mapping is obtained by minimizing the transition path length of the flow. To enhance the accuracy of translated bone structures, we introduce a trainable neural network to generate bone contours from MRI and implement mechanisms to directly and indirectly encourage the model to focus on bone contours and their adjacent regions. Evaluations conducted on three datasets demonstrate that our method outperforms existing unpaired MRI-to-CT translation approaches, achieving lower overall error rates. Moreover, in a downstream bone segmentation task, our approach exhibits superior performance in preserving the fidelity of bone structures. Our code is available at: https://github.com/kennysyp/PaBoT.