Protocol Optimization Considerations for Implementing Deep Learning CT Reconstruction

Deep learning and iterative image reconstruction for head CT: Impact on image quality and radiation dose reduction-Comparative study

Background and purpose: This study focuses on an objective evaluation of a novel reconstruction algorithm-Deep Learning Image Reconstruction (DLIR)-ability to improve image quality and reduce radiation dose compared to the established standard of Adaptive Statistical Iterative Reconstruction-V (ASIR-V), in unenhanced head computed tomography (CT). Materials and methods: A retrospective analysis of 163 consecutive unenhanced head CTs was conducted. Image quality assessment was computed on the objective parameters of Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), derived from 5 regions of interest (ROI). The evaluation of DLIR dose reduction abilities was based on the analysis of the PACS derived parameters of dose length product and computed tomography dose index volume (CTDIvol). Results: Following the application of rigorous criteria, the study comprised 35 patients. Significant image quality improvement was achieved with the implementation of DLIR, as evidenced by up to a 145% and 160% increase in SNR in supra- and infratentorial regions, respectively. CNR measurements further confirmed the superiority of DLIR over ASIR-V, with an increase of 171.5% in the supratentorial region and a 59.3% increase in the infratentorial region. Despite the signal improvement and noise reduction DLIR facilitated radiation dose reduction of up to 44% in CTDIvol. Conclusion: Implementation of DLIR in head CT scans enables significant image quality improvement and dose reduction abilities compared to standard ASIR-V. However, the dose reduction feature was proven insufficient to counteract the lack of gantry angulation in wide-detector scanners.

Detection of Pulmonary Nodules on Ultra-low Dose Chest Computed Tomography With Deep-learning Image Reconstruction Algorithm

PURPOSE

To evaluate the accuracy of ultra-low dose (ULD) chest computed tomography (CT), with a radiation exposure equivalent to a 2-view chest x-ray, for pulmonary nodule detection using deep learning image reconstruction (DLIR).

MATERIAL AND METHODS

This prospective cross-sectional study included 60 patients referred to our institution for assessment or follow-up of solid pulmonary nodules. All patients underwent low-dose (LD) and ULD chest CT within the same examination session. LD CT data were reconstructed using Adaptive Statistical Iterative Reconstruction-V (ASIR-V), whereas ULD CT data were reconstructed using DLIR and ASIR-V. ULD CT images were reviewed by 2 readers and LD CT images were reviewed by an experienced thoracic radiologist as the reference standard. Quantitative image quality analysis was performed, and the detectability of pulmonary nodules was assessed according to their size and location.

RESULTS

The effective radiation dose for ULD CT and LD CT were 0.13±0.01 and 1.16±0.6 mSv, respectively. Over the whole population, LD CT revealed 733 nodules. At ULD, DLIR images significantly exhibited better image quality than ASIR-V images. The overall sensitivity of DLIR reconstruction for the detection of solid pulmonary nodules from the ULD CT series was 93% and 82% for the 2 readers, with a good to excellent agreement with LD CT (ICC=0.82 and 0.66, respectively). The best sensitivities were observed in the middle lobe (97% and 85%, respectively).

CONCLUSIONS

At ULD, DLIR reconstructions, with minimal radiation exposure that could facilitate large-scale screening, allow the detection of pulmonary nodules with high sensitivity in an unrestricted BMI population.

Artificial Intelligence in Computed Tomography Image Reconstruction: A Review of Recent Advances

The development of novel image reconstruction algorithms has been pivotal in enhancing image quality and reducing radiation dose in computed tomography (CT) imaging. Traditional techniques like filtered back projection perform well under ideal conditions but fail to generate high-quality images under low-dose, sparse-view, and limited-angle conditions. Iterative reconstruction methods improve upon filtered back projection by incorporating system models and assumptions about the patient, yet they can suffer from patchy image textures. The emergence of artificial intelligence (AI), particularly deep learning, has further advanced CT reconstruction. AI techniques have demonstrated great potential in reducing radiation dose while preserving image quality and noise texture. Moreover, AI has exhibited unprecedented performance in addressing challenging CT reconstruction problems, including low-dose CT, sparse-view CT, limited-angle CT, and interior tomography. This review focuses on the latest advances in AI-based CT reconstruction under these challenging conditions.

Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters

OBJECTIVES

We evaluated the noise reduction effects of deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) in brain computed tomography (CT).

METHODS

CT images of a 16 cm dosimetry phantom, a head phantom, and the brains of 11 patients were reconstructed using filtered backprojection (FBP) and various levels of DLR and HIR. The slice thickness was 5, 2.5, 1.25, and 0.625 mm. Phantom imaging was also conducted at various tube currents. The noise reduction ratio was calculated using FBP as the reference. For patient imaging, overall image quality was visually compared between DLR and HIR images that exhibited similar noise reduction ratios.

RESULTS

The noise reduction ratio increased with increasing levels of DLR and HIR in phantom and patient imaging. For DLR, noise reduction was more pronounced with decreasing slice thickness, while such thickness dependence was less evident for HIR. Although the noise reduction effects of DLR were similar between the head phantom and patients, they differed for the dosimetry phantom. Variations between imaging objects were small for HIR. The noise reduction ratio was low at low tube currents for the dosimetry phantom using DLR; otherwise, the influence of the tube current was small. In terms of visual image quality, DLR outperformed HIR in 1.25 mm thick images but not in thicker images.

CONCLUSIONS

The degree of noise reduction using DLR depends on the slice thickness, tube current, and imaging object in addition to the level of DLR, which should be considered in the clinical use of DLR. DLR may be particularly beneficial for thin-slice imaging.

Image quality of virtual monochromatic and material density iodine images for evaluation of head and neck neoplasms using deep learning-based CT image reconstruction - A retrospective observational study

PURPOSE

To compare the quality of deep learning image reconstructed (DLIR) virtual monochromatic images (VMI) and material density (MD) iodine images from dual-energy computed tomography (DECT) for the evaluation of head and neck neoplasms with CT scans from a conventional single-energy protocol.

METHOD

A total of 294 head and neck CT scans (98 VMIs operated at 60 keV, 102 MD iodine images, and 94 images from a 120 kVp single-energy CT (SECT) protocol) were retrospectively evaluated. VMIs and MD iodine images were generated using the Gemstone Spectral Imaging (GSI) mode using DLIR and metal artifact reduction (MAR) algorithms. SECT images were generated using adaptive statistical iterative reconstruction (ASIR-V). Images were scored by two independent readers on a 6-point Likert-type scale for overall image quality, vessel contrast, soft tissue contrast, noise texture, noise intensity, artifact reduction, and sharpness.

RESULTS

Subjective overall image quality was rated as superior or excellent in 98 % of DLIR-based MD iodine images and VMIs, but only in 55 % of ASIR-V-based SECT images. For each individual quality criterion, image quality of VMIs and MD iodine images was rated as better than that of SECT images (p < 0.001 in each case). Noise texture and intensity were rated better in MD iodine images than in VMIs.

CONCLUSION

DECT using both DLIR and MAR for the generation of VMIs and MD iodine images resulted in higher subjective quality of oncologic head and neck images than ASIR-V-based SECT. Noise reduction and noise texture were best achieved with DLIR-based MD iodine images.

State-of-the-Art Deep Learning CT Reconstruction Algorithms in Abdominal Imaging

The implementation of deep neural networks has spurred the creation of deep learning reconstruction (DLR) CT algorithms. DLR CT techniques encompass a spectrum of deep learning-based methodologies that operate during the different steps of the image creation, prior to or after the traditional image formation process (eg, filtered backprojection [FBP] or iterative reconstruction [IR]), or alternatively by fully replacing FBP or IR techniques. DLR algorithms effectively facilitate the reduction of image noise associated with low photon counts from reduced radiation dose protocols. DLR methods have emerged as an effective solution to ameliorate limitations observed with prior CT image reconstruction algorithms, including FBP and IR algorithms, which are not able to preserve image texture and diagnostic performance at low radiation dose levels. An additional advantage of DLR algorithms is their high reconstruction speed, hence targeting the ideal triad of features for a CT image reconstruction (ie, the ability to consistently provide diagnostic-quality images and achieve radiation dose imaging levels as low as reasonably possible, with high reconstruction speed). An accumulated body of evidence supports the clinical use of DLR algorithms in abdominal imaging across multiple CT imaging tasks. The authors explore the technical aspects of DLR CT algorithms and examine various approaches to image synthesis in DLR creation. The clinical applications of DLR algorithms are highlighted across various abdominal CT imaging domains, with emphasis on the supporting evidence for diverse clinical tasks. An overview of the current limitations of and outlook for DLR algorithms for CT is provided. ©RSNA, 2024.

[Deep Learning Reconstruction Algorithm Combined With Smart Metal Artifact Reduction Technique Improves Image Quality of Upper Abdominal CT in Critically Ill Patients]

Objective

To evaluate the effect of deep learning reconstruction algorithm combined with smart metal artifact reduction (DLMAR) on the quality of abdominal CT images in critically ill patients who are unable to raise their arms and require electrocardiographic (ECG) monitoring.

Methods

A total of 102 patients were retrospectively enrolled. All subjects were critically ill patients who were unable to raise their arms and required ECG monitoring. Images were reconstructed using 6 algorithms, including filtered back projection (FBP), iterative reconstruction (IR), deep learning (DL), FBP combined with smart metal artifact reduction (FBPMAR), adaptive statistical iterative reconstruction-V combined with smart metal artifact reduction (IRMAR), and DLMAR. A quantitative analysis of CT values, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) was conducted in regions without metal artifacts and regions with metal artifacts in the liver, as well as the tissues, including those from the liver, spleen, pancreas, and aorta, between the two arms. Qualitative analysis of electrode metal artifacts, the visualization of the structures between the two arms, and image noise was performed with a 5-point scoring system (1=worst and 5=best).

Results

In the regions of the liver with metal artifacts, there was a significant difference between the CT values of the DLMAR group ([98.5±9.8] Hounsfield units [HU]) and those of the FBP group ([73.7±5.6] HU), the IR group ([75.3±7.5] HU), and the DL group ([66.3±11.4] HU) (P<0.01). There was no significant difference between the CT values of the DLMAR group and those of the FBPMAR group ([99.8±4.8] HU) and the IRMAR group ([99.6±3.4] HU) (P>0.05). The noise of the DLMAR group was found to be significantly lower than that of the other groups (P<0.01). Furthermore, the SNR and CNR of the DLMAR group were also found to be higher than those of the other groups (P<0.01). In the tissue region between the two arms, the differences in CT values among the six groups were not statistically significant (P>0.05). The noise of the DLMAR group was lower than those of the other groups (P<0.01), and the SNR and CNR of the DLMAR group were higher than those of the other groups (P<0.01). In terms of the removal of metal artifacts, the scores of the FBPMAR, IRMAR, and DLMAR groups (4.27±0.32, 4.44±0.34, and 4.61±0.28, respectively) were higher than those of the FBP, IR, and DL groups (1.36±0.54, 1.32±0.45, and 1.24±0.46, respectively) (P<0.01). The DLMAR group also had a higher score of 4.62±0.37 in the visualization of structures between the two arms and 4.53±0.39 in the noise reduction of images, both of which were higher than those of the other groups (P<0.01).

Conclusion

DLMAR reduces artifacts, decreases noise, and improves the quality of abdominal CT imaging in critically ill patients who are unable to raise their arms and require ECG monitoring.

Improving diagnostic confidence in low-dose dual-energy CTE with low energy level and deep learning reconstruction

OBJECTIVE

To demonstrate the value of using 50 keV virtual monochromatic images with deep learning image reconstruction (DLIR) in low-dose dual-energy CT enterography (CTE).

METHODS

In this prospective study, 114 participants (62 % M; 41.9 ± 16 years) underwent dual-energy CTE. The early-enteric phase was performed using standard-dose (noise index (NI): 8) and images were reconstructed at 70 keV and 50 keV with 40 % strength ASIR-V (ASIR-V40%). The late-enteric phase used low-dose (NI: 12) and images were reconstructed at 50 keV with ASIR-V40%, and DLIR at medium (DLIR-M) and high strength (DLIR-H). Image standard deviation (SD), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), edge-rise-slope (ERS) were computed. The quantitative comb sign score was calculated for the 27 patients with Crohn's disease. The subjective noise, image contrast, display of rectus artery were scored using a 5-point scale by two radiologists blindly.

RESULTS

Effective dose was reduced by 50 % (P < 0.001) in the late-enteric phase to 3.26 mSv. The lower-dose 50 keV-DLIR-H images (SD:17.7 ± 0.5HU) had similar image noise (P = 0.97) as the standard-dose 70 keV-ASIR-V40% images (SD:17.7 ± 0.73HU), but with higher (P < 0.001) SNR, CNR, ERS and quantitative comb sign score (5.7 ± 0.17, 1.8 ± 0.12, 156.04 ± 5.21 and 5.05 ± 0.73, respectively). Furthermore, the lower-dose 50 keV-DLIR-H images obtained the highest score in the rectus artery visibility (4.27 ± 0.6).

CONCLUSIONS

The 50 keV images in dual-energy CTE with DLIR provides high-quality images, with a 50 % reduction in radiation dose. Images with high contrast and density resolutions significantly enhance the diagnostic confidence of Crohn's disease and are essential for the clinical development of individualized treatment plans.

Image Quality and Diagnostic Performance of Low-Dose Liver CT with Deep Learning Reconstruction versus Standard-Dose CT

Purpose To compare the image quality and diagnostic capability in detecting malignant liver tumors of low-dose CT (LDCT, 33% dose) with deep learning-based denoising (DLD) and standard-dose CT (SDCT, 100% dose) with model-based iterative reconstruction (MBIR). Materials and Methods In this prospective, multicenter, noninferiority study, individuals referred for liver CT scans were enrolled from three tertiary referral hospitals between February 2021 and August 2022. All liver CT scans were conducted using a dual-source scanner with the dose split into tubes A (67% dose) and B (33% dose). Blended images from tubes A and B were created using MBIR to produce SDCT images, whereas LDCT images used data from tube B and were reconstructed with DLD. The noise in liver images was measured and compared between imaging techniques. The diagnostic performance of each technique in detecting malignant liver tumors was evaluated by three independent radiologists using jackknife alternative free-response receiver operating characteristic analysis. Noninferiority of LDCT compared with SDCT was declared when the lower limit of the 95% CI for the difference in figure of merit (FOM) was greater than -0.10. Results A total of 296 participants (196 men, 100 women; mean age, 60.5 years ± 13.3 [SD]) were included. The mean noise level in the liver was significantly lower for LDCT (10.1) compared with SDCT (10.7) (P < .001). Diagnostic performance was assessed in 246 participants (108 malignant tumors in 90 participants). The reader-averaged FOM was 0.880 for SDCT and 0.875 for LDCT (P = .35). The difference fell within the noninferiority margin (difference, -0.005 [95% CI: -0.024, 0.012]). Conclusion Compared with SDCT with MBIR, LDCT using 33% of the standard radiation dose had reduced image noise and comparable diagnostic performance in detecting malignant liver tumors. Keywords: CT, Abdomen/GI, Liver, Comparative Studies, Diagnosis, Reconstruction Algorithms Clinical trial registration no. NCT05804799 © RSNA, 2024 Supplemental material is available for this article.

Accuracy of liver metastasis detection and characterization: Dual-energy CT versus single-energy CT with deep learning reconstruction

PURPOSE

To assess whether image quality differences between SECT (single-energy CT) and DECT (dual-energy CT 70 keV) with equivalent radiation doses result in altered detection and characterization accuracy of liver metastases when using deep learning image reconstruction (DLIR), and whether DECT spectral curve usage improves accuracy of indeterminate lesion characterization.

METHODS

In this prospective Health Insurance Portability and Accountability Act-compliant study (March through August 2022), adult men and non-pregnant adult women with biopsy-proven colorectal cancer and liver metastases underwent SECT (120 kVp) and a DECT (70 keV) portovenous abdominal CT scan using DLIR in the same breath-hold (Revolution CT ES; GE Healthcare). Participants were excluded if consent could not be obtained, if there were nonequivalent radiation doses between the two scans, or if the examination was cancelled/rescheduled. Three radiologists independently performed lesion detection and characterization during two separate sessions (SECT DLIRmedium and DECT DLIRhigh) as well as reported lesion confidence and overall image quality. Hounsfield units were measured. Spectral HU curves were provided for any lesions rated as indeterminate. McNemar's test was used to test the marginal homogeneity in terms of diagnostic sensitivity, accuracy and lesion detection. A generalized estimating equation method was used for categorical outcomes.

RESULTS

30 participants (mean age, 58 years ± 11, 21 men) were evaluated. Mean CTDIvol was 34 mGy for both scans. 141 lesions (124 metastases, 17 benign) with a mean size of 0.8 cm ± 0.3 cm were identified. High scores for image quality (scores of 4 or 5) were not significantly different between DECT (N = 71 out of 90 total scores from the three readers) and SECT (N = 62) (OR, 2.01; 95% CI:0.89, 4.57; P = 0.093). Equivalent image noise to SECT DLIRmed (HU SD 10 ± 2) was obtained with DECT DLIRhigh (HU SD 10 ± 3) (P = 1). There was no significant difference in lesion detection between DECT and SECT (140/141 lesions) (99.3%; 95% CI:96.1%, 100%).The mean lesion confidence scores by each reader were 4.2 ± 1.3, 3.9 ± 1.0, and 4.8 ± 0.8 for SECT and 4.1 ± 1.4, 4.0 ± 1.0, and 4.7 ± 0.8 for DECT (odds ratio [OR], 0.83; 95% CI: 0.62, 1.11; P = 0.21). Small lesion (≤5mm) characterization accuracy on SECT and DECT was 89.1% (95% CI:76.4%, 96.4%; 41/46) and 84.8% (71.1%, 93.7%; 39/46), respectively (P = 0.41). Use of spectral HU lesion curves resulted in 34 correct changes in characterizations and no mischaracterizations.

CONCLUSION

DECT required a higher strength of DLIR to obtain equivalent noise compared to SECT DLIR. At equivalent radiation doses and image noise, there was no significant difference in subjective image quality or observer lesion performance between DECT (70 keV) and SECT. However, DECT spectral HU curves of indeterminate lesions improved characterization.

Can 1.25 mm thin-section images generated with Deep Learning Image Reconstruction technique replace standard-of-care 5 mm images in abdominal CT?

BACKGROUND

CT image reconstruction has evolved from filtered back projection to hybrid- and model-based iterative reconstruction. Deep learning-based image reconstruction is a relatively new technique that uses deep convolutional neural networks to improve image quality.

OBJECTIVE

To evaluate and compare 1.25 mm thin-section abdominal CT images reconstructed with deep learning image reconstruction (DLIR) with 5 mm thick images reconstructed with adaptive statistical iterative reconstruction (ASIR-V).

METHODS

This retrospective study included 52 patients (31 F; 56.9±16.9 years) who underwent abdominal CT scans between August-October 2019. Image reconstruction was performed to generate 5 mm images at 40% ASIR-V and 1.25 mm DLIR images at three strengths (low [DLIR-L], medium [DLIR-M], and high [DLIR-H]). Qualitative assessment was performed to determine image noise, contrast, visibility of small structures, sharpness, and artifact based on a 5-point-scale. Image preference determination was based on a 3-point-scale. Quantitative assessment included measurement of attenuation, image noise, and contrast-to-noise ratios (CNR).

RESULTS

Thin-section images reconstructed with DLIR-M and DLIR-H yielded better image quality scores than 5 mm ASIR-V reconstructed images. Mean qualitative scores of DLIR-H for noise (1.77 ± 0.71), contrast (1.6 ± 0.68), small structure visibility (1.42 ± 0.66), sharpness (1.34 ± 0.55), and image preference (1.11 ± 0.34) were the best (p<0.05). DLIR-M yielded intermediate scores. All DLIR reconstructions showed superior ratings for artifacts compared to ASIR-V (p<0.05), whereas each DLIR group performed comparably (p>0.05, 0.405-0.763). In the quantitative assessment, there were no significant differences in attenuation values between all reconstructions (p>0.05). However, DLIR-H demonstrated the lowest noise (9.17 ± 3.11) and the highest CNR (CNRliver = 26.88 ± 6.54 and CNRportal vein = 7.92 ± 3.85) (all p<0.001).

CONCLUSION

DLIR allows generation of thin-section (1.25 mm) abdominal CT images, which provide improved image quality with higher inter-reader agreement compared to 5 mm thick images reconstructed with ASIR-V.

CLINICAL IMPACT

Improved image quality of thin-section CT images reconstructed with DLIR has several benefits in clinical practice, such as improved diagnostic performance without radiation dose penalties.

Capability for dose reduction while maintaining nodule detection: Comparison of silver and copper X-ray spectrum modulation filters for chest CT using a phantom study with different reconstruction methods

PURPOSE

To compare the capability of CTs obtained with a silver or copper x-ray beam spectral modulation filter (Ag filter and Cu filter) and reconstructed with FBP, hybrid-type IR and deep learning reconstruction (DLR) for radiation dose reduction for lung nodule detection using a chest phantom study.

MATERIALS AND METHODS

A chest CT phantom was scanned with a 320-detector row CT with Ag filter at 0.6, 1.6 and 2.5 mGy and Cu filters at 0.6, 1.6, 2.5 and 9.6 mGy, and reconstructed with the aforementioned methods. To compare image quality of all the CT data, SNRs and CNRs for any nodule were calculated for all protocols. To compare nodule detection capability among all protocols, the probability of detection of any nodule was assessed with a 5-point visual scoring system. Then, ROC analyses were performed to compare nodule detection capability of Ag and Cu filters for each radiation dose data with the same method and of the three methods for any radiation dose data and obtained with either filter.

RESULTS

At any of the doses, SNR, CNR and area under the curve for the Ag filter were significantly higher or larger than those for the Cu filter (p < 0.05). Moreover, with DLR, those values were significantly higher or larger than all the others for CTs obtained with any of the radiation doses and either filter (p < 0.05).

CONCLUSION

The Ag filter and DLR can significantly improve image quality and nodule detection capability compared with the Cu filter and other reconstruction methods at each of radiation doses used.

Deep-learning CT reconstruction in clinical scans of the abdomen: a systematic review and meta-analysis

OBJECTIVE

To perform a systematic literature review and meta-analysis of the two most common commercially available deep-learning algorithms for CT.

METHODS

We used PubMed, Scopus, Embase, and Web of Science to conduct systematic searches for studies assessing the most common commercially available deep-learning CT reconstruction algorithms: True Fidelity (TF) and Advanced intelligent Clear-IQ Engine (AiCE) in the abdomen of human participants since only these two algorithms currently have adequate published data for robust systematic analysis.

RESULTS

Forty-four articles fulfilled inclusion criteria. 32 studies evaluated TF and 12 studies assessed AiCE. DLR algorithms produced images with significantly less noise (22-57.3% less than IR) but preserved a desirable noise texture with increased contrast-to-noise ratios and improved lesion detectability on conventional CT. These improvements with DLR were similarly noted in dual-energy CT which was only assessed for a single vendor. Reported radiation reduction potential was 35.1-78.5%. Nine studies assessed observer performance with the two dedicated liver lesion studies being performed on the same vendor reconstruction (TF). These two studies indicate preserved low contrast liver lesion detection (> 5 mm) at CTDIvol 6.8 mGy (BMI 23.5 kg/m2) to 12.2 mGy (BMI 29 kg/m2). If smaller lesion detection and improved lesion characterization is needed, a CTDIvol of 13.6-34.9 mGy is needed in a normal weight to obese population. Mild signal loss and blurring have been reported at high DLR reconstruction strengths.

CONCLUSION

Deep learning reconstructions significantly improve image quality in CT of the abdomen. Assessment of other dose levels and clinical indications is needed. Careful choice of radiation dose levels is necessary, particularly for small liver lesion assessment.

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.

How Do Cancer-Specific Computed Tomography Protocols Compare With the American College of Radiology Dose Index Registry? An Analysis of Computed Tomography Dose at 2 Cancer Centers

BACKGROUND

Little guidance exists on how to stratify radiation dose according to diagnostic task. Changing dose for different cancer types is currently not informed by the American College of Radiology Dose Index Registry dose survey.

METHODS

A total of 9602 patient examinations were pulled from 2 National Cancer Institute designated cancer centers. Computed tomography dose (CTDI vol ) was extracted, and patient water equivalent diameter was calculated. N-way analysis of variance was used to compare the dose levels between 2 protocols used at site 1, and three protocols used at site 2.

RESULTS

Sites 1 and 2 both independently stratified their doses according to cancer indications in similar ways. For example, both sites used lower doses ( P < 0.001) for follow-up of testicular cancer, leukemia, and lymphoma. Median dose at median patient size from lowest to highest dose level for site 1 were 17.9 (17.7-18.0) mGy (mean [95% confidence interval]) and 26.8 (26.2-27.4) mGy. For site 2, they were 12.1 (10.6-13.7) mGy, 25.5 (25.2-25.7) mGy, and 34.2 (33.8-34.5) mGy. Both sites had higher doses ( P < 0.001) between their routine and high-image-quality protocols, with an increase of 48% between these doses for site 1 and 25% for site 2. High-image-quality protocols were largely applied for detection of low-contrast liver lesions or subtle pelvic pathology.

CONCLUSIONS

We demonstrated that 2 cancer centers independently choose to stratify their cancer doses in similar ways. Sites 1 and 2 dose data were higher than the American College of Radiology Dose Index Registry dose survey data. We thus propose including a cancer-specific subset for the dose registry.

CT image quality evaluation in the age of deep learning: trade-off between functionality and fidelity

OBJECTIVE

To quantitatively compare DLIR and ASiR-V with realistic anatomical images.

METHODS

CT scans of an anthropomorphic phantom were acquired using three routine protocols (brain, chest, and abdomen) at four dose levels, with images reconstructed at five levels of ASiR-V and three levels of DLIR. Noise power spectrum (NPS) was estimated using a difference image by subtracting two matching images from repeated scans. Using the max-dose FBP reconstruction as the ground truth, the structure similarity index (SSIM) and gradient magnitude (GM) of difference images were evaluated. Image noise magnitude (σ), frequency location of the NPS peak (f_peak), mean SSIM (MSSIM), and mean GM (MGM) were used as quantitative metrics to compare image quality, for each anatomical region, protocol, algorithm, dose level, and slice thickness.

RESULTS

Image noise had a strong (R² > 0.99) power law relationship with dose for all algorithms. For the abdomen and chest, f_peak shifted from 0.3 (FBP) down to 0.15 mm^-1 (ASiR-V 100%) with increasing ASiR-V strength but remained 0.3 mm^-1 for all DLIR levels. f_peak shifted down for the brain protocol with increasing DLIR levels. Three levels of DLIR produced similar image noise levels as ASiR-V 40%, 80%, and 100%, respectively. DLIR had lower MSSIM but higher MGM than ASiR-V while matching imaging noise.

CONCLUSION

Compared to ASiR-V, DLIR presents trade-offs between functionality and fidelity: it has a noise texture closer to FBP and more edge enhancement, but reduced structure similarity. These trade-offs and unique protocol-dependent behaviors of DLIR should be considered during clinical implementation and deployment.

KEY POINTS

• DLIR reconstructed images demonstrate closer noise texture and lower structure similarity to FBP while producing equivalent noise levels comparable to ASiR-V. • DLIR has additional edge enhancement as compared to ASiR-V. • DLIR has unique protocol-dependent behaviors that should be considered for clinical implementation.

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.

Spatial resolution, noise properties, and detectability index of a deep learning reconstruction algorithm for dual-energy CT of the abdomen

BACKGROUND

Iterative reconstruction (IR) has increasingly replaced traditional reconstruction methods in computed tomography (CT). The next paradigm shift in image reconstruction is likely to come from artificial intelligence, with deep learning reconstruction (DLR) solutions already entering the clinic. An enduring disadvantage to IR has been a change in noise texture, which can affect diagnostic confidence. DLR has demonstrated the potential to overcome this issue and has recently become available for dual-energy CT.

PURPOSE

To evaluate the spatial resolution, noise properties, and detectability index of a commercially available DLR algorithm for dual-energy CT of the abdomen and compare it to single-energy (SE) CT.

METHODS

An oval 25 cm x 35 cm custom-made phantom was scanned on a GE Revolution CT scanner (GE Healthcare, Waukesha, WI) at two dose levels (13 and 5 mGy) and two iodine concentrations (8 and 2 mg/mL), using three typical abdominal scan protocols: dual-energy (DE), SE 80 kV (SE-80 kV) and SE 120 kV (SE-120 kV). Reconstructions were performed with three strengths of IR (ASiR-V: AR0%, AR50%, AR100%) and three strengths of DLR (TrueFidelity: low, medium, high). The DE acquisitions were reconstructed as mono-energetic images between 40 and 80 keV. The noise power spectrum (NPS), task transfer function (TTF), and detectability index (d') were determined for the reconstructions following the recommendations of AAPM Task Group 233.

RESULTS

Noise magnitude reductions (relative to AR0%) for the SE protocols were on average (-29%, -21%) for (AR50%, TF-M), while for DE-70 keV were (-28%, -43%). There was less reduction in mean frequency (f_av ) for DLR than for IR, with similar results for SE and DE imaging. There was, however, a substantial change in the NPS shape when using DE with DLR, quantifiable by a marked reduction in the peak frequency (f_peak ) that was absent in SE mode. All protocols and reconstructions (including AR0%) exhibited slight to moderate shifts towards lower spatial frequencies at the lower dose (<12% in f_av ). Spatial resolution was consistently superior for DLR compared to IR for SE but not for DE. All protocols and reconstructions (including AR0%) showed decreased resolution with reduced dose and iodine concentration, with less decrease for DLR compared to IR. DLR displayed a higher d' than IR. The effect of energy was large: d' increased with lower keV, and SE-80 kV had higher d' than SE-120 kV. Using DE with DLR could provide higher d' than SE-80 kV at the higher dose but not at lower dose.

CONCLUSIONS

DE imaging with DLR maintained spatial resolution and reduced noise magnitude while displaying less change in noise texture than IR. The d' was also higher with DLR than IR, suggesting superiority in detectability of iodinated contrast. Despite these trends being consistent with those previously established for SE imaging, there were some noteworthy differences. For DE imaging there was no improvement in resolution compared to IR and a change in noise texture. DE imaging with low keV and DLR had superior detectability to SE DLR at the high dose but was not better than SE-80 kV at low dose.

"Image quality evaluation of the Precise image CT deep learning reconstruction algorithm compared to Filtered Back-projection and iDose4: a phantom study at different dose levels"

PURPOSE

To characterize the performance of the Precise Image (PI) deep learning reconstruction (DLR) algorithm for abdominal Computed Tomography (CT) imaging.

METHODS

CT images of the Catphan-600 phantom (equipped with an external annulus) were acquired using an abdominal protocol at four dose levels and reconstructed using FBP, iDose⁴ (levels 2,5) and PI ('Soft Tissue' definition, levels 'Sharper','Sharp','Standard','Smooth','Smoother'). Image noise, image non-uniformity, noise power spectrum (NPS), target transfer function (TTF), detectability index (d'), CT numbers accuracy and image histograms were analyzed.

RESULTS

The behavior of the PI algorithm depended strongly on the selected level of reconstruction. The phantom analysis suggested that the PI image noise decreased linearly by varying the level of reconstruction from Sharper to Smoother, expressing a noise reduction up to 80% with respect to FBP. Additionally, the non-uniformity decreased, the histograms became narrower, and d' values increased as PI reconstruction levels changed from Sharper to Smoother. PI had no significant impact on the average CT number of different contrast objects. The conventional FBP NPS was deeply altered only by Smooth and Smoother levels of reconstruction. Furthermore, spatial resolution was found to be dose- and contrast-dependent, but in each analyzed condition it was greater than or comparable to FBP and iDose⁴ TTFs.

CONCLUSIONS

The PI algorithm can reduce image noise with respect to FBP and iDose⁴; spatial resolution, CT numbers and image uniformity are generally preserved by the algorithm but changes in NPS for the Smooth and Smoother levels need to be considered in protocols implementation.

Measurement Accuracy and Repeatability of RECIST-Defined Pulmonary Lesions and Lymph Nodes in Ultra-Low-Dose CT Based on Deep Learning Image Reconstruction

BACKGROUND

Deep learning image reconstruction (DLIR) improves image quality. We aimed to compare the measured diameter of pulmonary lesions and lymph nodes between DLIR-based ultra-low-dose CT (ULDCT) and contrast-enhanced CT.

METHODS

The consecutive adult patients with noncontrast chest ULDCT (0.07-0.14 mSv) and contrast-enhanced CT (2.38 mSv) were prospectively enrolled. Patients with poor image quality and body mass index ≥ 30 kg/m2 were excluded. The diameter of pulmonary target lesions and lymph nodes defined by Response Evaluation Criteria in Solid Tumors (RECIST) was measured. The measurement variability between ULDCT and enhanced CT was evaluated by Bland-Altman analysis.

RESULTS

The 141 enrolled patients (62 ± 12 years) had 89 RECIST-defined measurable pulmonary target lesions (including 30 malignant lesions, mainly adenocarcinomas) and 45 measurable mediastinal lymph nodes (12 malignant). The measurement variation of pulmonary lesions between high-strength DLIR (DLIR-H) images of ULDCT and contrast-enhanced CT was 2.2% (95% CI: 1.7% to 2.6%) and the variation of lymph nodes was 1.4% (1.0% to 1.9%).

CONCLUSIONS

The measured diameters of pulmonary lesions and lymph nodes in DLIR-H images of ULDCT are highly close to those of contrast-enhanced CT. DLIR-based ULDCT may facilitate evaluating target lesions with greatly reduced radiation exposure in tumor evaluation and lung cancer screening.

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.

Advanced CT techniques for hepatic microwave ablation zone monitoring and follow-up

PURPOSE

To evaluate utility of advanced CT techniques including HighlY constrained back-projection and dual-energy CT for intra- and post-procedure hepatic microwave ablation zone monitoring.

METHODS

8 hepatic microwave ablations were performed in 4 adult swine (5 min/65 W). Low-dose routine CECT and dual-energy CT images were obtained every 1 min during ablation. Images were reconstructed ± HYPR. Image quality and dose metrics were collected. 21 MWA were performed in 4 adult swine. Immediate post-procedure CECT was performed in the arterial, portal venous, and delayed phases using both routine and DECT imaging with full-dose weight-based IV contrast dosing. An additional 16 MWA were subsequently performed in 2 adult swine. Immediate post-procedure CT was performed with half-dose IV contrast using routine and DECT. 12 patients (10 M/2F, mean age 62.4 yrs) with 14 hepatic tumors (4 HCC, 10 metastatic lesions) treated with MWA were prospectively imaged with DECT 1 month post-procedure. 120 kV equivalent images were compared to DECT [51 keV, iodine material density]. Image quality and dose metrics were collected.

RESULTS

Gas created during MWA led to high CNR in all intraprocedural CT datasets. Optimal CNRs were noted at 4 min with CNR 6.7, 15.5,15.9, and 21.5 on LD-CECT, LD-CECT + HYPR, DECT, and DECT + HYPR, respectively (p < 0.001). Image quality scores at 4 min were 1.8, 2.8, 2.4, and 3, respectively (p < 0.001). Mean radiation dose (CTDIvol) was eightfold higher for the DECT series. For swine, post-procedural DECT images (IMD/51 keV) showed improved CNR compared to routine CT at all time points with full and with reduced dose contrast (CNR 4.6, 3.2, and 1.5, respectively, at half-contrast dose, p < 0.001). For human subjects, the 51 keV and IMD images showed higher CNRs (5.8, 4.8 vs 4.0, p < 0.001) and SNRs (3.7, 5.9 vs 2.8). Ablation zone sharpness was improved with DECT (routine 3.0 ± 0.7, DECT 3.5 ± 0.5). Diagnostic confidence was higher with DECT (routine 2.3 ± 0.9, DECT 2.6 ± 0.8). Mean DLP for DECT was 905.7 ± 606 mGy-cm, CTDIvol 37.5 ± 21.2 mGy, and effective dose 13.6 ± 9.1 mSv, slightly higher than conventional CT series.

CONCLUSION

Advanced CT techniques can improve CT image quality in peri-procedural hepatic microwave ablation zone evaluation.

Quantitative and qualitative assessments of deep learning image reconstruction in low-keV virtual monoenergetic dual-energy CT

OBJECTIVES

To evaluate a novel deep learning image reconstruction (DLIR) technique for dual-energy CT (DECT) derived virtual monoenergetic (VM) images compared to adaptive statistical iterative reconstruction (ASIR-V) in low kiloelectron volt (keV) images.

METHODS

We analyzed 30 venous phase acute abdominal DECT (80/140 kVp) scans. Data were reconstructed to ASIR-V and DLIR-High at four different keV levels (40, 50, 74, and 100) with 1- and 3-mm slice thickness. Quantitative Hounsfield unit (HU) and noise assessment were measured within the liver, aorta, fat, and muscle. Subjective assessment of image noise, sharpness, texture, and overall quality was performed by two board-certified radiologists.

RESULTS

DLIR reduced image noise by 19.9-35.5% (p < 0.001) compared to ASIR-V in all reconstructions at identical keV levels. Contrast-to-noise ratio (CNR) increased by 49.2-53.2% (p < 0.001) in DLIR 40-keV images compared to ASIR-V 50 keV, while no significant difference in noise was identified except for 1 and 3 mm in aorta and for 1-mm liver measurements, where ASIR-V 50 keV showed 5.5-6.8% (p < 0.002) lower noise levels. Qualitative assessment demonstrated significant improvement particularly in 1-mm reconstructions (p < 0.001). Lastly, DLIR 40 keV demonstrated comparable or improved image quality ratings when compared to ASIR-V 50 keV (p < 0.001 to 0.22).

CONCLUSION

DLIR significantly reduced image noise compared to ASIR-V. Qualitative assessment showed that DLIR significantly improved image quality particularly in thin sliced images. DLIR may facilitate 40 keV as a new standard for routine low-keV VM reconstruction in contrast-enhanced abdominal DECT.

KEY POINTS

• DLIR enables 40 keV as the routine low-keV VM reconstruction. • DLIR significantly reduced image noise compared to ASIR-V, across a wide range of keV levels in VM DECT images. • In low-keV VM reconstructions, improvements in image quality using DLIR were most evident and consistent in 1-mm sliced images.

Reduced-Dose Deep Learning Reconstruction for Abdominal CT of Liver Metastases

Background Assessment of liver lesions is constrained as CT radiation doses are lowered; evidence suggests deep learning reconstructions mitigate such effects. Purpose To evaluate liver metastases and image quality between reduced-dose deep learning image reconstruction (DLIR) and standard-dose filtered back projection (FBP) contrast-enhanced abdominal CT. Materials and Methods In this prospective Health Insurance Portability and Accountability Act-compliant study (September 2019 through April 2021), participants with biopsy-proven colorectal cancer and liver metastases at baseline CT underwent standard-dose and reduced-dose portal venous abdominal CT in the same breath hold. Three radiologists detected and characterized lesions at standard-dose FBP and reduced-dose DLIR, reported confidence, and scored image quality. Contrast-to-noise ratios for liver metastases were recorded. Summary statistics were reported, and a generalized linear mixed model was used. Results Fifty-one participants (mean age ± standard deviation, 57 years ± 13; 31 men) were evaluated. The mean volume CT dose index was 65.1% lower with reduced-dose CT (12.2 mGy) than with standard-dose CT (34.9 mGy). A total of 161 lesions (127 metastases, 34 benign lesions) with a mean size of 0.7 cm ± 0.3 were identified. Subjective image quality of reduced-dose DLIR was superior to that of standard-dose FBP (P < .001). The mean contrast-to-noise ratio for liver metastases of reduced-dose DLIR (3.9 ± 1.7) was higher than that of standard-dose FBP (3.5 ± 1.4) (P < .001). Differences in detection were identified only for lesions 0.5 cm or smaller: 63 of 65 lesions detected with standard-dose FBP (96.9%; 95% CI: 89.3, 99.6) and 47 lesions with reduced-dose DLIR (72.3%; 95% CI: 59.8, 82.7). Lesion accuracy with standard-dose FBP and reduced-dose DLIR was 80.1% (95% CI: 73.1, 86.0; 129 of 161 lesions) and 67.1% (95% CI: 59.3, 74.3; 108 of 161 lesions), respectively (P = .01). Lower lesion confidence was reported with a reduced dose (P < .001). Conclusion Deep learning image reconstruction (DLIR) improved CT image quality at 65% radiation dose reduction while preserving detection of liver lesions larger than 0.5 cm. Reduced-dose DLIR demonstrated overall inferior characterization of liver lesions and reader confidence. Clinical trial registration no. NCT03151564 © RSNA, 2022 Online supplemental material is available for this article.

Impact of multidetector computed tomography scan parameters, novel reconstruction settings, and lung nodule characteristics on nodule diameter measurements: A Phantom Study

PURPOSE

Novel CT reconstruction techniques strive to maintain image quality and processing efficiency. The purpose of this study is to investigate the impact of a newer hybrid iterative reconstruction technique, Adaptive Statistical Iterative Reconstruction-V (ASIR-V) in combination with various CT scan parameters on the semi-automated quantification using various lung nodules.

METHODS

A chest phantom embedded with eight spherical objects was scanned using varying CT parameters such as tube current and ASIR-V levels. We calculated absolute percentage error (APE) and mean APE (MAPE) using differences between the semi-automated measured diameters and known dimensions. Predictive variables were assessed using a multivariable general linear model. The linear regression slope coefficients (β) were reported to demonstrate effect size and directionality.

RESULTS

The APE of the semi-automated measured diameters was higher in ground-glass than solid nodules (β = 9.000, p<0.001). APE had an inverse relationship with nodule diameter (mm; β = -3.499, p<0.001) and tube current (mA; β = -0.006, p<0.001). MAPE did not vary based on the ASIR-V level (range: 5.7-13.1%).

CONCLUSION

Error is dominated by nodule characteristics with a small effect of tube current. Regardless of phantom size, nodule size accuracy is not affected by tube voltage or ASIR-V level, maintaining accuracy while maximizing radiation dose reduction. This article is protected by copyright. All rights reserved.