Conditional generative adversarial networks to generate pseudo low monoenergetic CT image from a single-tube voltage CT scanner

Deep learning-based correction for time truncation in cerebral computed tomography perfusion

Cerebral computed tomography perfusion (CTP) imaging requires complete acquisition of contrast bolus inflow and washout in the brain parenchyma; however, time truncation undoubtedly occurs in clinical practice. To overcome this issue, we proposed a three-dimensional (two-dimensional + time) convolutional neural network (CNN)-based approach to predict missing CTP image frames at the end of the series from earlier acquired image frames. Moreover, we evaluated three strategies for predicting multiple time points. Seventy-two CTP scans with 89 frames and eight slices from a publicly available dataset were used to train and test the CNN models capable of predicting the last 10 image frames. The prediction strategies were single-shot prediction, recursive multi-step prediction, and direct-recursive hybrid prediction.Single-shot prediction predicted all frames simultaneously, while recursive multi-step prediction used prior predictions as input for subsequent steps, and direct-recursive hybrid prediction employed separate models for each step with prior predictions as input for the next step. The accuracies of the predicted image frames were evaluated in terms of image quality, bolus shape, and clinical perfusion parameters. We found that the image quality metrics were superior when multiple CTP images were predicted simultaneously rather than recursively. The bolus shape also showed the highest correlation (r = 0.990, p < 0.001) and the lowest variance (95% confidence interval, -453.26-445.53) in the single-shot prediction. For all perfusion parameters, the single-shot prediction had the smallest absolute differences from ground truth. Our proposed approach can potentially minimize time truncation errors and support the accurate quantification of ischemic stroke.

Synthetic Low-Energy Monochromatic Image Generation in Single-Energy Computed Tomography System Using a Transformer-Based Deep Learning Model

While dual-energy computed tomography (DECT) technology introduces energy-specific information in clinical practice, single-energy CT (SECT) is predominantly used, limiting the number of people who can benefit from DECT. This study proposed a novel method to generate synthetic low-energy virtual monochromatic images at 50 keV (sVMI50keV) from SECT images using a transformer-based deep learning model, SwinUNETR. Data were obtained from 85 patients who underwent head and neck radiotherapy. Among these, the model was built using data from 70 patients for whom only DECT images were available. The remaining 15 patients, for whom both DECT and SECT images were available, were used to predict from the actual SECT images. We used the SwinUNETR model to generate sVMI50keV. The image quality was evaluated, and the results were compared with those of the convolutional neural network-based model, Unet. The mean absolute errors from the true VMI50keV were 36.5 ± 4.9 and 33.0 ± 4.4 Hounsfield units for Unet and SwinUNETR, respectively. SwinUNETR yielded smaller errors in tissue attenuation values compared with those of Unet. The contrast changes in sVMI50keV generated by SwinUNETR from SECT were closer to those of DECT-derived VMI50keV than the contrast changes in Unet-generated sVMI50keV. This study demonstrated the potential of transformer-based models for generating synthetic low-energy VMIs from SECT images, thereby improving the image quality of head and neck cancer imaging. It provides a practical and feasible solution to obtain low-energy VMIs from SECT data that can benefit a large number of facilities and patients without access to DECT technology.

Pseudo low-energy monochromatic imaging of head and neck cancers: Deep learning image reconstruction with dual-energy CT

PURPOSE

Low-energy virtual monochromatic images (VMIs) derived from dual-energy computed tomography (DECT) systems improve lesion conspicuity of head and neck cancer over single-energy CT (SECT). However, DECT systems are installed in a limited number of facilities; thus, only a few facilities benefit from VMIs. In this work, we present a deep learning (DL) architecture suitable for generating pseudo low-energy VMIs of head and neck cancers for facilities that employ SECT imaging.

METHODS

We retrospectively analyzed 115 patients with head and neck cancers who underwent contrast enhanced DECT. VMIs at 70 and 50 keV were used as the input and ground truth (GT), respectively. We divided them into two datasets: for DL (104 patients) and for inference with SECT (11 patients). We compared four DL architectures: U-Net, DenseNet-based, and two ResNet-based models. Pseudo VMIs at 50 keV (pVMI_50keV) were compared with the GT in terms of the mean absolute error (MAE) of Hounsfield unit (HU) values, peak signal-to-noise ratio (PSNR), and structural similarity (SSIM). The HU values for tumors, vessels, parotid glands, muscle, fat, and bone were evaluated. pVMI_50keV were generated from actual SECT images and the HU values were evaluated.

RESULTS

U-Net produced the lowest MAE (13.32 ± 2.20 HU) and highest PSNR (47.03 ± 2.33 dB) and SSIM (0.9965 ± 0.0009), with statistically significant differences (P < 0.001). The HU evaluation showed good agreement between the GT and U-Net. U-Net produced the smallest absolute HU difference for the tumor, at < 5.0 HU.

CONCLUSION

Quantitative comparisons of physical parameters demonstrated that the proposed U-Net could generate high accuracy pVMI_50keV in a shorter time compared with the established DL architectures. Although further evaluation on diagnostic accuracy is required, our method can help obtain low-energy VMI from SECT images without DECT systems.

Deep Learning and Domain-Specific Knowledge to Segment the Liver from Synthetic Dual Energy CT Iodine Scans

We map single energy CT (SECT) scans to synthetic dual-energy CT (synth-DECT) material density iodine (MDI) scans using deep learning (DL) and demonstrate their value for liver segmentation. A 2D pix2pix (P2P) network was trained on 100 abdominal DECT scans to infer synth-DECT MDI scans from SECT scans. The source and target domain were paired with DECT monochromatic 70 keV and MDI scans. The trained P2P algorithm then transformed 140 public SECT scans to synth-DECT scans. We split 131 scans into 60% train, 20% tune, and 20% held-out test to train four existing liver segmentation frameworks. The remaining nine low-dose SECT scans tested system generalization. Segmentation accuracy was measured with the dice coefficient (DSC). The DSC per slice was computed to identify sources of error. With synth-DECT (and SECT) scans, an average DSC score of 0.93±0.06 (0.89±0.01) and 0.89±0.01 (0.81±0.02) was achieved on the held-out and generalization test sets. Synth-DECT-trained systems required less data to perform as well as SECT-trained systems. Low DSC scores were primarily observed around the scan margin or due to non-liver tissue or distortions within ground-truth annotations. In general, training with synth-DECT scans resulted in improved segmentation performance with less data.