Image quality improvement with deep learning-based reconstruction on abdominal ultrahigh-resolution CT: A phantom study

Towards safer imaging: A comparative study of deep learning-based denoising and iterative reconstruction in intraindividual low-dose CT scans using an in-vivo large animal model

PURPOSE

Computed tomography (CT) scans are a significant source of medically induced radiation exposure. Novel deep learning-based denoising (DLD) algorithms have been shown to enable diagnostic image quality at lower radiation doses than iterative reconstruction (IR) methods. However, most comparative studies employ low-dose simulations due to ethical constraints. We used real intraindividual animal scans to investigate the dose-reduction capabilities of a DLD algorithm in comparison to IR.

MATERIALS AND METHODS

Fourteen veterinarian-sedated alive pigs underwent 2 CT scans on the same 3rd generation dual-source scanner with two months between each scan. Four additional scans ensued each time, with mAs reduced to 50 %, 25 %, 10 %, and 5 %. All scans were reconstructed ADMIRE levels 2 (IR2) and a novel DLD algorithm, resulting in 280 datasets. Objective image quality (CT numbers stability, noise, and contrast-to-noise ratio) was measured via consistent regions of interest. Three radiologists independently rated all possible dataset combinations per time point for subjective image quality (-1 = inferior, 0 = equal, 1 = superior). The points were averaged for a semiquantitative score, and inter-rater agreement was measured using Spearman's correlation coefficient and adequately corrected mixed-effects modeling analyzed objective and subjective image quality.

RESULTS

Neither dose-reduction nor reconstruction method negatively impacted CT number stability (p > 0.999). In objective image quality assessment, the lowest radiation dose achievable by DLD when comparing noise (p = 0.544) and CNR (p = 0.115) to 100 % IR2 was 25 %. Overall, inter-rater agreement of the subjective image quality ratings was strong (r ≥ 0.69, mean 0.93 ± 0.05, 95 % CI 0.92-0.94; each p < 0.001), and subjective assessments corroborated that DLD at 25 % radiation dose was comparable to 100 % IR2 in image quality, sharpness, and contrast (p ≥ 0.281).

CONCLUSIONS

The DLD algorithm can achieve image quality comparable to the standard IR method but with a significant dose reduction of up to 75%. This suggests a promising avenue for lowering patient radiation exposure without sacrificing diagnostic quality.

Prediction of Anemia From Cerebral Venous Sinus Attenuation on Deep-Learning Reconstructed Brain Computed Tomography Images

OBJECTIVE

The aim of the study is to evaluate whether the prediction of anemia is possible using quantitative analyses of unenhanced cranial computed tomography (CT) with deep learning reconstruction (DLR) compared with conventional methods.

METHODS

This cross-sectional retrospective study included 116 participants (76 males; mean age, 66.7) who had hemoglobin (Hb) levels obtained within 24 hours of unenhanced cranial CT, which included 2 reconstruction methods: DLR and hybrid iterative reconstruction. Regions of interest were the confluence of sinuses (CoS) and the right and left transverse sinuses. In addition, edge rise distance of cerebrospinal fluid and venous was measured.

RESULTS

Spearman rank correlation coefficient demonstrated a positive association between Hb levels and sinus attenuation values. Among these, the CoS in DLR had the best correlation ( r = 0.703, P < 0.001). For the prediction of anemia (Hb < 11 g/dL), the area under the curve of CoS in DLR (area under the curve = 0.874; 95% confidence interval, 0.798-0.949; P < 0.001) was the highest; however, there were no significant differences among reconstruction method and sinus. The attenuation values of DLR were significantly higher than those of hybrid iterative reconstruction ( P < 0.001, paired t test), and the differences between the 2 methods were 4.1 (standard deviation [SD], 1.6) for CoS, 5.2 (SD, 2.2) for right transverse sinuses, and 5.8 (SD, 2.4) for left transverse sinuses. The signal-to-noise ratio ( P < 0.001, paired t test) and edge rise distance ( P < 0.001, Wilcoxon signed rank test) of DLR was significantly higher.

CONCLUSIONS

Higher CT attenuation values should be considered for predicting anemia based on brain DLR images.

Improvement of diagnostic performance of hyperacute ischemic stroke in head CT using an image-based noise reduction technique with non-black-boxed process

PURPOSE

This study aims to investigate whether an image-based noise reduction (INR) technique with a conventional rule-based algorithm involving no black-boxed processes can outperform an existing hybrid-type iterative reconstruction (HIR) technique, when applied to brain CT images for diagnosis of early CT signs, which generally exhibit low-contrast lesions that are difficult to detect.

METHODS

The subjects comprised 27 patients having infarctions within 4.5 h of onset and 27 patients with no change in brain parenchyma. Images with thicknesses of 5 mm and 0.625 mm were reconstructed by HIR. Images with a thickness of 0.625 mm reconstructed by filter back projection (FBP) were processed by INR. The contrast-to-noise ratios (CNRs) were calculated between gray and white matters; lentiform nucleus and internal capsule; infarcted and non-infarcted areas. Two radiologists subjectively evaluated the presence of hyperdense artery signs (HASs) and infarctions and visually scored three properties regarding image quality (0.625-mm HIR images were excluded because of their notably worse noise appearances).

RESULTS

The CNRs of INR were significantly better than those of HIR with P < 0.001 for all the indicators. INR yielded significantly higher areas under the curve for both infarction and HAS detections than HIR (P < 0.001). Also, INR significantly improved the visual scores of all the three indicators.

CONCLUSION

The INR incorporating a simple and reproducible algorithm was more effective than HIR in detecting early CT signs and can be potentially applied to CT images from a large variety of CT systems.

Noise power spectrum properties of deep learning-based reconstruction and iterative reconstruction algorithms: Phantom and clinical study

PURPOSE

To compare the noise power spectrum (NPS) properties and perform a qualitative analysis of hybrid iterative reconstruction (IR), model-based IR (MBIR), and deep learning-based reconstruction (DLR) at a similar noise level in clinical study and compare these outcomes with those in phantom study.

METHODS

A Catphan phantom with an external body ring was used in the phantom study. In the clinical study, computed tomography (CT) examination data of 34 patients were reviewed. NPS was calculated from DLR, hybrid IR, and MBIR images. The noise magnitude ratio (NMR) and the central frequency ratio (CFR) were calculated from DLR, hybrid IR, and MBIR images relative to filtered back-projection images using NPS. Clinical images were independently reviewed by two radiologists.

RESULTS

In the phantom study, DLR with a mild level had a similar noise level as hybrid IR and MBIR with strong levels. In the clinical study, DLR with a mild level had a similar noise level as hybrid IR with standard and MBIR with strong levels. The NMR and CFR were 0.40 and 0.76 for DLR, 0.42 and 0.55 for hybrid IR, and 0.48 and 0.62 for MBIR. The visual inspection of the clinical DLR image was superior to that of the hybrid IR and MBIR images.

CONCLUSION

Deep learning-based reconstruction improves overall image quality with substantial noise reduction while maintaining image noise texture compared with the CT reconstruction techniques.

Deep Learning Image Reconstruction for CT: Technical Principles and Clinical Prospects

Filtered back projection (FBP) has been the standard CT image reconstruction method for 4 decades. A simple, fast, and reliable technique, FBP has delivered high-quality images in several clinical applications. However, with faster and more advanced CT scanners, FBP has become increasingly obsolete. Higher image noise and more artifacts are especially noticeable in lower-dose CT imaging using FBP. This performance gap was partly addressed by model-based iterative reconstruction (MBIR). Yet, its "plastic" image appearance and long reconstruction times have limited widespread application. Hybrid iterative reconstruction partially addressed these limitations by blending FBP with MBIR and is currently the state-of-the-art reconstruction technique. In the past 5 years, deep learning reconstruction (DLR) techniques have become increasingly popular. DLR uses artificial intelligence to reconstruct high-quality images from lower-dose CT faster than MBIR. However, the performance of DLR algorithms relies on the quality of data used for model training. Higher-quality training data will become available with photon-counting CT scanners. At the same time, spectral data would greatly benefit from the computational abilities of DLR. This review presents an overview of the principles, technical approaches, and clinical applications of DLR, including metal artifact reduction algorithms. In addition, emerging applications and prospects are discussed.

Characteristics of the deep learning-based virtual monochromatic image with fast kilovolt-switching CT: a phantom study

PURPOSE

We assessed the physical properties of virtual monochromatic images (VMIs) obtained with different energy levels in various contrast settings and radiation doses using deep learning-based spectral computed tomography (DL-Spectral CT) and compared the results with those from single-energy CT (SECT) imaging.

MATERIALS AND METHODS

A Catphan^® 600 phantom was scanned by DL-Spectral CT at various radiation doses. We reconstructed the VMIs obtained at 50, 70, and 100 keV. SECT (120 kVp) images were acquired at the same radiation doses. The standard deviations of the CT number and noise power spectrum (NPS) were calculated for noise characterization. We evaluated the spatial resolution by determining the 10% task-based transfer function (TTF) level, and we assessed the task-based detectability index (d').

RESULTS

Regardless of the radiation dose, the noise was the lowest at 70 keV VMI. The NPS showed that the noise amplitude at all spatial frequencies was the lowest among other VMI and 120 kVp images. The spatial resolution was higher for 70 keV VMI compared to the other VMIs, except for high-contrast objects. The d' of 70 keV VMI was the highest among the VMI and 120 kVp images at all radiation doses and contrast settings. The d' of the 70 keV VMIs at the minimum dose was higher than that at the maximum dose in any other image.

CONCLUSION

The physical properties of the DL-Spectral CT VMIs varied with the energy level. The 70 keV VMI had the highest detectability by far among the VMI and 120-kVp images. DL-Spectral CT may be useful to reduce radiation doses.

A Review of Deep Learning CT Reconstruction: Concepts, Limitations, and Promise in Clinical Practice

Purpose of Review

Deep Learning reconstruction (DLR) is the current state-of-the-art method for CT image formation. Comparisons to existing filter back-projection, iterative, and model-based reconstructions are now available in the literature. This review summarizes the prior reconstruction methods, introduces DLR, and then reviews recent findings from DLR from a physics and clinical perspective.

Recent Findings

DLR has been shown to allow for noise magnitude reductions relative to filtered back-projection without suffering from “plastic” or “blotchy” noise texture that was found objectionable with most iterative and model-based solutions. Clinically, early reader studies have reported increases in subjective quality scores and studies have successfully implemented DLR-enabled dose reductions.

Summary

The future of CT image reconstruction is bright; deep learning methods have only started to tackle problems in this space via addressing noise reduction. Artifact mitigation and spectral applications likely be future candidates for DLR applications.