Deep Few-view High-resolution Photon-counting Extremity CT at Halved Dose for a Clinical Trial

Abstract

The latest X-ray photon-counting computed tomography (PCCT) for extremity allows multi-energy high-resolution (HR) imaging for tissue characterization and material decomposition. However, both radiation dose and imaging speed need improvement for contrast-enhanced and other studies. Despite the success of deep learning methods for 2D few-view reconstruction, applying them to HR volumetric reconstruction of extremity scans for clinical diagnosis has been limited due to GPU memory constraints, training data scarcity, and domain gap issues. In this paper, we propose a deep learning-based approach for PCCT image reconstruction at halved dose and doubled speed in a New Zealand clinical trial. Particularly, we present a patch-based volumetric refinement network to alleviate the GPU memory limitation, train network with synthetic data, and use model-based iterative refinement to bridge the gap between synthetic and real-world data. The simulation and phantom experiments demonstrate consistently improved results under different acquisition conditions on both in- and off-domain structures using a fixed network. The image quality of 8 patients from the clinical trial are evaluated by three radiologists in comparison with the standard image reconstruction with a full-view dataset. It is shown that our proposed approach is essentially identical to or better than the clinical benchmark in terms of diagnostic image quality scores. Our approach has a great potential to improve the safety and efficiency of PCCT without compromising image quality.

Keywords: Photon-counting CT; clinical trial; deep learning; dose reduction; few-view reconstruction; high resolution.

Fig. 1.

Overview of the deep few-view PCCT reconstruction workflow. (a) A less noisy structural prior is reconstructed from a virtual bin data, obtained by summing counts from all channels of few-view projections, with a multi-scale iterative reconstruction (MS-IR) technique. (b) For image reconstruction in each channel, the structural prior is iteratively refined with a Volumetric Sparse Representation Network (VSR-Net) and model-based guidance from the projection measurements in an Alternating Direction Method of Multipliers (ADMM) optimization framework. The network is trained with synthetic data and special techniques are used to address the domain gap issues. (c) The texture and appearance of the multi-channel images are further touched with a Residual Fourier Channel Attention Network (RFCAN) for feature enhancement and value alignment with MARS proprietary reconstructions, and followed by mixing with the result of further iterations with Simultaneous Iterative Reconstruction Technique (SIRT) for image sharpness and noise characteristics preferred by radiologists.

Fig. 2.

Architecture of our volumetric sparse representation network (VSR-Net). (a) This light weight network takes a small cubic patch as input and outputs a denoised patch. 3D pixel shuffle operations and grouped convolutions are used to promote speed and performance; and (b) The downscaling and upscaling of feature maps are achieved through 3D pixel unshuffle and shuffle operations (illustrated in (c)) combined with two 3D grouped convolutional layers. Note that Conv, grouped convolutional layer; ReLU, rectified linear unit; a color-coded number above each convolutional operation denotes the number of groups used, while the number underneath the feature map indicates the number of channels.

Fig. 3.

Architecture of the residual Fourier channel attention network (RFCAN), consisting of 15 Fourier channel attention residual blocks (FCA-ResBlocks) built upon attention layers with FCA (FCA-Layer).

Fig. 4.

Interleaved updating for large volume reconstruction: (a) partitioning the projections and reconstruction volume to form a batch of reconstruction tasks on sub-volumes; and (b) combining the results in an interleaved pattern with slices at one or both ends trimmed off to ensure data completeness and avoid overlapping.

Fig. 5.

Representative images reconstructed using competing methods on simulated data. (a) The full-view reconstructions with FDK, SIRT-TV, and our method displayed against the ground truth, with exemplary axial, coronal, and sagittal views included from top to bottom; (b) the reconstructions from halved views; and (c) magnified regions from the coronal and sagittal views as indicated by the green and orange boxes respectively and displayed in the descent order of image sharpness and structural fidelity: ground truth (GT), our full-view and half-view reconstructions (FV-P, HV-P), and full-view and half-view reconstructions with SIRT-TV (FV-TV, HV-TV) from top to bottom. The display window is W/L:400/50 HU. The red arrows indicate the structural details are easy to recover for our methods but challenging for SIRT-TV.

Fig. 6.

Out-of-domain generalization on phantom study. Comparisons between noisy input, DIR, BM3D, and VSR-Net against the long-exposure reference in: (a) axial slices from results with 0.5-second exposure; (b) sagittal slices from results with 0.15-second exposure; (c) the same magnified region as that in (a) but from results with exposures of 0.15, 0.5, 0.1, and 2.0 seconds; and (d) distributions of PSNR and SSIM values of the axial slices and sagittal slices from volumes visualized in violin plots. The display window is [0, 0.45] for axial view and [0, 1.05] for sagittal view, in unit of cm⁻¹. The mean and standard deviation values of a flat water region are listed for reference as well as the SSIM and PSNR values of the image.

Fig. 7.

Sagittal reformat of a wrist joint reconstructed using standard and proposed methods respectively. (a) From left to right are 3D rendering of standard reconstruction, half-view and full-view images of channel 50–60keV. The arrow points to scaphoid fracture. (b) Color visualization of our three-channel reconstruction via linear blending [50] in reference to standard full-view result and noise2sim half-view result. Our result demonstrates high fidelity in both spectral values (same color tone and brightness as the full-view reference) and spatial structures (sharp and accurate fine details as pointed by the red arrow).

Fig. 8.

Quantitative evaluation of image quality of our half-view reconstruction against proprietary reconstruction from the full-view dataset.

Fig. 9.

Subjective evaluation on seven image quality (IQ) criteria comparing our proposed half-view reconstruction and clinical full-view reconstruction. (a) Violin plot of combined radiologists’ ratings on half-view results against full-view results; (b) Slightly better than 0.5 AUC_VGC (the performance neutral threshold) from the proposed method over the conventional method for most image quality metrics, and (c) half-view versus full-view VGC plots generated from combining all the image quality metrics indicate most VGC points above the diagonal line (the performance neutral line) for all the three radiologists and combined ratings. However, to show that the AUC_VGC is significantly better than 0.5 in the 95% interval sense, more data would be needed.