Potential for dose reduction in CT emphysema densitometry with post-scan noise reduction: a phantom study

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.

Facilitating standardized COVID-19 suspicion prediction based on computed tomography radiomics in a multi-demographic setting

Objective

To develop an automatic COVID-19 Reporting and Data System (CO-RADS)–based classification in a multi-demographic setting.

Methods

This multi-institutional review boards–approved retrospective study included 2720 chest CT scans (mean age, 58 years [range 18–100 years]) from Italian and Russian patients. Three board-certified radiologists from three countries assessed randomly selected subcohorts from each population and provided CO-RADS–based annotations. CT radiomic features were extracted from the selected subcohorts after preprocessing steps like lung lobe segmentation and automatic noise reduction. We compared three machine learning models, logistic regression (LR), multilayer perceptron (MLP), and random forest (RF) for the automated CO-RADS classification. Model evaluation was carried out in two scenarios, first, training on a mixed multi-demographic subcohort and testing on an independent hold-out dataset. In the second scenario, training was done on a single demography and externally validated on the other demography.

Results

The overall inter-observer agreement for the CO-RADS scoring between the radiologists was substantial (k = 0.80). Irrespective of the type of validation test scenario, suspected COVID-19 CT scans were identified with an accuracy of 84%. SHapley Additive exPlanations (SHAP) interpretation showed that the “wavelet_(LH)_GLCM_Imc1” feature had a positive impact on COVID prediction both with and without noise reduction. The application of noise reduction improved the overall performance between the classifiers for all types.

Conclusion

Using an automated model based on the COVID-19 Reporting and Data System (CO-RADS), we achieved clinically acceptable performance in a multi-demographic setting. This approach can serve as a standardized tool for automated COVID-19 assessment.

Keypoints

• Automatic CO-RADS scoring of large-scale multi-demographic chest CTs with mean AUC of 0.93 ± 0.04.

• Validation procedure resembles TRIPOD 2b and 3 categories, enhancing the quality of experimental design to test the cross-dataset domain shift between institutions aiding clinical integration.

• Identification of COVID-19 pneumonia in the presence of community-acquired pneumonia and other comorbidities with an AUC of 0.92.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-022-08730-6.

Impact of pixel value truncation on image quality of low dose chest CT

PURPOSE

In some noisy low-dose CT lung cancer screening images, we noticed that the CT density values of air were increased and the visibility of emphysema was distinctly decreased. By examining histograms of these images, we found that the CT density values were truncated at -1,024 HU. The purpose of this study was to investigate the effect of pixel value truncation on the visibility of emphysema using mathematical models.

METHODS AND MATERIALS

Assuming CT noise follows a normal distribution, we derived the relationship between the mean CT density value and the standard deviation (SD) when the pixel values below -1,024 HU are truncated and replaced by -1,024 HU. To validate our mathematical model, 20 untruncated phantom CT images were truncated by simulation, and the mean CT density values and SD of air in the images were measured and compared with the theoretical values. In addition, the mean CT density values and SD of air were measured in 100 cases of real clinical images obtained by GE, Siemens, and Philips scanners, respectively, and the agreement with the theoretical values was examined. Next, the contrast-to-noise ratio (CNR) between air (-1,000 HU) and lung parenchyma (-850 HU) was derived from the mathematical model in the presence and absence of truncation as a measure of the visibility of emphysema. In addition, the radiation dose ratios required to obtain the same CNR in the case with and without truncation were also calculated.

RESULTS

The mathematical model revealed that when the pixel values are truncated, the mean CT density values are proportional to the noise magnitude when the magnitude exceeds a certain level. The mean CT density values and SD measured in the images with pixel values truncated by simulation and in the real clinical images acquired by GE and Philips scanners agreed well with the theoretical values from our mathematical model. In the Siemens images, the measured and theoretical values agreed well when a portion of the truncated values were replaced by random values instead of simply replacing by -1,024 HU. The CNR of air and lung parenchyma was lowered by truncating CT density values compared to that of no truncation. Furthermore, it was found that higher radiation dose was required to obtain the same CNR with truncation as without. As an example, when the noise SD was 60 HU, the radiation dose required for the GE and Philips truncation method was about 1.2 times higher than that without truncation, and that for the Siemens truncation method was about 1.4 times higher.

CONCLUSIONS

It was demonstrated mathematically that pixel value truncation causes a brightening of the mean CT density value and decreases the CNR of emphysema. Our results indicate that it is advisable to turn off truncation at -1,024 HU, especially when scanning at low and ultra-low radiation doses in the thorax. This article is protected by copyright. All rights reserved.

Improved precision of noise estimation in CT with a volume-based approach

Assessment of image noise is a relevant issue in computed tomography (CT). Noise is routinely measured by the standard deviation of density values (Hounsfield units, HU) within a circular region of interest (ROI). We explored the effect of a spherical volume of interest (VOI) on noise measurements. Forty-nine chronic obstructive pulmonary disease patients underwent CT with clinical protocol (regular dose [RD], volumetric CT dose index [CTDIvol] 3.04 mGy, 64-slice unit), and ultra-low dose (ULD) protocol (median CTDIvol 0.38 mGy, dual-source unit). Noise was measured in 27 1-cm² ROIs and 27 0.75-cm³ VOIs inside the trachea. Median true noise was 21 HU (range 17-29) for RD-CT and 33 HU (26-39) for ULD-CT. The VOI approach resulted in a lower mean distance between limits of agreement compared to ROI: 5.9 versus 10.0 HU for RD-CT (-40%); 4.7 versus 9.9 HU for ULD-CT (-53%). Mean systematic bias barely changed: -1.6 versus -0.9HU for RD-CT; 0.0 to 0.4HU for ULD-CT. The average measurement time was 6.8 s (ROI) versus 9.7 (VOI), independent of dose level. For chest CT, measuring noise with a VOI-based instead of a ROI-based approach reduces variability by 40-53%, without a relevant effect on systematic bias and measurement time.

Ultra-low-dose CT combined with noise reduction techniques for quantification of emphysema in COPD patients: An intra-individual comparison study with standard-dose CT

PURPOSE

Phantom studies in CT emphysema quantification show that iterative reconstruction and deep learning-based noise reduction (DLNR) allow lower radiation dose. We compared emphysema quantification on ultra-low-dose CT (ULDCT) with and without noise reduction, to standard-dose CT (SDCT) in chronic obstructive pulmonary disease (COPD).

METHOD

Forty-nine COPD patients underwent ULDCT (third generation dual-source CT; 70ref-mAs, Sn-filter 100kVp; median CTDIvol 0.38 mGy) and SDCT (64-multidetector CT; 40mAs, 120kVp; CTDIvol 3.04 mGy). Scans were reconstructed with filtered backprojection (FBP) and soft kernel. For ULDCT, we also applied advanced modelled iterative reconstruction (ADMIRE), levels 1/3/5, and DLNR, levels 1/3/5/9. Emphysema was quantified as Low Attenuation Value percentage (LAV%, ≤-950HU). ULDCT measures were compared to SDCT as reference standard.

RESULTS

For ULDCT, the median radiation dose was 84 % lower than for SDCT. Median extent of emphysema was 18.6 % for ULD-FBP and 15.4 % for SDCT (inter-quartile range: 11.8-28.4 % and 9.2 %-28.7 %, p = 0.002). Compared to SDCT, the range in limits of agreement of emphysema quantification as measure of variability was 14.4 for ULD-FBP, 11.0-13.1 for ULD-ADMIRE levels and 10.1-13.9 for ULD-DLNR levels. Optimal settings were ADMIRE 3 and DLNR 3, reducing variability of emphysema quantification by 24 % and 27 %, at slight underestimation of emphysema extent (-1.5 % and -2.9 %, respectively).

CONCLUSIONS

Ultra-low-dose CT in COPD patients allows dose reduction by 84 %. State-of-the-art noise reduction methods in ULDCT resulted in slight underestimation of emphysema compared to SDCT. Noise reduction methods (especially ADMIRE 3 and DLNR 3) reduced variability of emphysema quantification in ULDCT by up to 27 % compared to FBP.

Influence of a novel deep-learning based reconstruction software on the objective and subjective image quality in low-dose abdominal computed tomography

OBJECTIVES

Modern reconstruction and post-processing software aims at reducing image noise in CT images, potentially allowing for a reduction of the employed radiation exposure. This study aimed at assessing the influence of a novel deep-learning based software on the subjective and objective image quality compared to two traditional methods [filtered back-projection (FBP), iterative reconstruction (IR)].

METHODS

In this institutional review board-approved retrospective study, abdominal low-dose CT images of 27 patients (mean age 38 ± 12 years, volumetric CT dose index 2.9 ± 1.8 mGy) were reconstructed with IR, FBP and, furthermore, post-processed using a novel software. For the three reconstructions, qualitative and quantitative image quality was evaluated by means of CT numbers, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in six different ROIs. Additionally, the reconstructions were compared using SNR, peak SNR, root mean square error and mean absolute error to assess structural differences.

RESULTS

On average, CT numbers varied within 1 Hounsfield unit (HU) for the three assessed methods in the assessed ROIs. In soft tissue, image noise was up to 42% lower compared to FBP and up to 27% lower to IR when applying the novel software. Consequently, SNR and CNR were highest with the novel software. For both IR and the novel software, subjective image quality was equal but higher than the image quality of FBP-images.

CONCLUSION

The assessed software reduces image noise while maintaining image information, even in comparison to IR, allowing for a potential dose reduction of approximately 20% in abdominal CT imaging.

ADVANCES IN KNOWLEDGE

The assessed software reduces image noise by up to 27% compared to IR and 48% compared to FBP while maintaining the image information.The reduced image noise allows for a potential dose reduction of approximately 20% in abdominal imaging.