Optimization of Photon Counting CT Myelography for the Detection of CSF-venous Fistulas Using Convolutional Neural Network Denoising: A Comparative Analysis of Reconstruction Techniques.

Abstract

Background and purpose: Photon counting detector CT myelography is a recently described technique used for detecting spinal CSF leaks, including CSF-venous fistulas. Various image reconstruction techniques, including smoother versus sharper kernels and virtual monoenergetic images, are available with photon counting CT. Moreover, denoising algorithms have shown promise in improving sharp kernel images. No prior studies have compared image quality of these different reconstructions on photon counting CT myelography. Here, we sought to compare several image reconstructions using various parameters important for the detection of CSF-venous fistulas.

Materials and methods: We performed a retrospective review of all consecutive decubitus photon counting CT myelograms performed between 2/1/2022 and 8/1/2024 at one institution. We included patients whose studies had the following reconstructions: Br48-40 keV virtual monoenergetic reconstruction, Br56 low energy threshold (T3D), Qr89-T3D denoised with quantum iterative reconstruction, and Qr89-T3D denoised with a convolutional neural network algorithm. We excluded patients who had extradural CSF on preprocedural imaging or a technically unsatisfactory myelogram. All four reconstructions were independently reviewed by two neuroradiologists. Each reviewer rated spatial resolution, noise, presence of artifacts, image quality, and diagnostic confidence (whether positive or negative) on a 1-5 scale. These metrics were compared using the Friedman test. Additionally, noise and contrast were quantitatively assessed by a third reviewer and compared.

Results: The Qr89 reconstructions demonstrated higher spatial resolution than their Br56 or Br48-40keV counterparts. Qr89 with convolutional neural network denoising had less noise, better image quality, and improved diagnostic confidence compared to Qr89 with quantum iterative reconstruction denoising. The Br48-40keV reconstruction had the highest contrast-to-noise ratio quantitatively.

Conclusions: In our study, the sharpest quantitative kernel (Qr89-T3D) with convolutional neural network denoising demonstrated the best performance with regards to spatial resolution, noise level, image quality, and diagnostic confidence for detecting or excluding the presence of a CSF-venous fistula.

Abbreviations: CNR = contrast-to-noise ratio; CVF = CSF-venous fistula; EID = energy integrating detector; PCD = photon counting detector; PCD-CTM = photon counting detector CT myelography; ROI = region of interest; SNR = signal-to-noise ratio; SIH = spontaneous intracranial hypotension; T3D = low-energy threshold; UHR = ultra-high resolution.