Clinical acceptance of deep learning reconstruction for abdominal CT imaging: objective and subjective image quality and low-contrast detectability assessment

Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity

BACKGROUND

The best settings of deep learning image reconstruction (DLIR) algorithm for abdominal low-kiloelectron volt (keV) virtual monoenergetic imaging (VMI) have not been determined.

PURPOSE

To determine the optimal settings of the DLIR algorithm for abdominal low-keV VMI.

MATERIAL AND METHODS

The portal-venous phase computed tomography (CT) scans of 109 participants with 152 lesions were reconstructed into four image series: VMI at 50 keV using adaptive statistical iterative reconstruction (Asir-V) at 50% blending (AV-50); and VMI at 40 keV using AV-50 and DLIR at medium (DLIR-M) and high strength (DLIR-H). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of nine anatomical sites were calculated. Noise power spectrum (NPS) using homogenous region of liver, and edge rise slope (ERS) at five edges were measured. Five radiologists rated image quality and diagnostic acceptability, and evaluated the lesion conspicuity.

RESULTS

The SNR and CNR values, and noise and noise peak in NPS measurements, were significantly lower in DLIR images than AV-50 images in all anatomical sites (all P < 0.001). The ERS values were significantly higher in 40-keV images than 50-keV images at all edges (all P < 0.001). The differences of the peak and average spatial frequency among the four reconstruction algorithms were significant but relatively small. The 40-keV images were rated higher with DLIR-M than DLIR-H for diagnostic acceptance (P < 0.001) and lesion conspicuity (P = 0.010).

CONCLUSION

DLIR provides lower noise, higher sharpness, and more natural texture to allow 40 keV to be a new standard for routine VMI reconstruction for the abdomen and DLIR-M gains higher diagnostic acceptance and lesion conspicuity rating than DLIR-H.

Post-processing of quantitative 4D-CT for initial evaluation of scapholunate Instability: Assessment of simplified approaches to data analysis

OBJECTIVES

To evaluate the diagnostic performance of simplified post-processing approaches for quantitative wrist 4D-CT in the assessment of scapholunate instability (SLI).

METHODS

A prospective monocentric case-control study included 60 patients with suspected post-traumatic scapholunate ligament (SLL) tears and persistent pain. Of these, 40 patients exhibited SLL tears, subdivided into two groups of 20 each: one group with completely torn ligaments and the other with partially torn ligaments. The remaining 20 patients, whose SLLs were intact, served as controls. 4D-CT and CT arthrography were performed, and post-processed by two readers using three approaches: the standard method with full data assessment and dedicated software, partial data assessment with post-processing software (bone locking), and partial data assessment without post-processing software (no bone locking). The scapholunate gap (SLG) parameter was measured in millimeters to evaluate scapholunate diastasis during radioulnar deviation (RUD). The scapholunate ligament status on CT arthrography was considered the gold standard.

RESULTS

The SLG-derived parameters (range, mean, and maximal values) were significantly increased in patients with both intact and torn scapholunate ligaments across all post-processing approaches (P values ranging from 0.001 to 0.004). SLG range was the best parameter for diagnosing SLL tears, with ROC AUC values ranging from 0.7 to 0.88 across the three post-processing methods. The interobserver reproducibility was better with the alternative approaches (ICC values 0.93-0.96) compared to the standard approach (ICC values 0.65-0.72). Additionally, post-processing time was shorter with the alternative approaches, especially when specific software was not used (reduced from 10 to three minutes).

CONCLUSION

Simpler approaches to wrist 4D-CT data analysis yielded acceptable diagnostic performances and improved interobserver reproducibility compared to the standard approach.

Low-contrast lesion detection in neck CT: a multireader study comparing deep learning, iterative, and filtered back projection reconstructions using realistic phantoms

BACKGROUND

Computed tomography (CT) reconstruction algorithms can improve image quality, especially deep learning reconstruction (DLR). We compared DLR, iterative reconstruction (IR), and filtered back projection (FBP) for lesion detection in neck CT.

METHODS

Nine patient-mimicking neck phantoms were examined with a 320-slice scanner at six doses: 0.5, 1, 1.6, 2.1, 3.1, and 5.2 mGy. Each of eight phantoms contained one circular lesion (diameter 1 cm; contrast -30 HU to the background) in the parapharyngeal space; one phantom had no lesions. Reconstruction was made using FBP, IR, and DLR. Thirteen readers were tasked with identifying and localizing lesions in 32 images with a lesion and 20 without lesions for each dose and reconstruction algorithm. Receiver operating characteristic (ROC) and localization ROC (LROC) analysis were performed.

RESULTS

DLR improved lesion detection with ROC area under the curve (AUC) 0.724 ± 0.023 (mean ± standard error of the mean) using DLR versus 0.696 ± 0.021 using IR (p = 0.037) and 0.671 ± 0.023 using FBP (p < 0.001). Likewise, DLR improved lesion localization, with LROC AUC 0.407 ± 0.039 versus 0.338 ± 0.041 using IR (p = 0.002) and 0.313 ± 0.044 using FBP (p < 0.001). Dose reduction to 0.5 mGy compromised lesion detection in FBP-reconstructed images compared to doses ≥ 2.1 mGy (p ≤ 0.024), while no effect was observed with DLR or IR (p ≥ 0.058).

CONCLUSION

DLR improved the detectability of lesions in neck CT imaging. Dose reduction to 0.5 mGy maintained lesion detectability when denoising reconstruction was used.

RELEVANCE STATEMENT

Deep learning enhances lesion detection in neck CT imaging compared to iterative reconstruction and filtered back projection, offering improved diagnostic performance and potential for x-ray dose reduction.

KEY POINTS

Low-contrast lesion detectability was assessed in anatomically realistic neck CT phantoms. Deep learning reconstruction (DLR) outperformed filtered back projection and iterative reconstruction. Dose has little impact on lesion detectability against anatomical background structures.

Submillisievert Abdominal Photon-Counting CT versus Energy-integrating Detector CT for Urinary Calculi Detection: Impact on Diagnostic Confidence

Background Contrast-unenhanced abdominal CT is the imaging standard for urinary calculi detection; however, studies comparing photon-counting detector (PCD) CT and energy-integrating detector (EID) CT dose-reduction potentials are lacking. Purpose To compare the radiation dose and image quality of optimized EID CT with those of an experimental PCD CT scan protocol including tin prefiltration in patients suspected of having urinary calculi. Materials and Methods This retrospective single-center study included patients who underwent unenhanced abdominal PCD CT or EID CT for suspected urinary caliculi between February 2022 and March 2023. Signal and noise measurements were performed at three anatomic levels (kidney, psoas, and obturator muscle). Nephrolithiasis and/or urolithiasis presence was independently assessed by three radiologists, and diagnostic confidence was recorded on a five-point scale (1, little to no confidence; 5, complete confidence). Reader agreement was determined by calculating Krippendorff α. Results A total of 507 patients (mean age, 51.7 years ± 17.4 [SD]; 317 male patients) were included (PCD CT group, 229 patients; EID CT group, 278 patients). Readers 1, 2, and 3 detected nephrolithiasis in 129, 127, and 129 patients and 94, 94, and 94 patients, whereas the readers detected urolithiasis in 113, 114, and 114 patients and 152, 153, and 152 patients in the PCD CT and EID CT groups, respectively. Regardless of protocol (PCD CT or EID CT) or calculus localization, near perfect interreader agreement was found (α ≥ 0.99; 95% CI: 0.99, 1). There was no evidence of a difference in reader confidence between PCD CT and EID CT (median confidence, 5; IQR, 5-5; P ≥ .57). The effective doses were 0.79 mSv (IQR, 0.63-0.99 mSv) and 1.39 mSv (IQR, 1.01-1.87 mSv) for PCD CT and EID CT, respectively. Despite the lower radiation exposure, the signal-to-noise ratios at the kidney, psoas, and obturator levels were 30%, 23%, and 17% higher, respectively, in the PCD CT group (P < .001). Conclusion Submillisievert abdominal PCD CT provided high-quality images for the diagnosis of urinary calculi; radiation exposure was reduced by 44% with a higher signal-to-noise ratio than with EID CT and with no evidence of a difference in reader confidence. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Nezami and Malayeri in this issue.

A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction

Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.

Computed Tomography 2.0: New Detector Technology, AI, and Other Developments

ABSTRACT

Computed tomography (CT) dramatically improved the capabilities of diagnostic and interventional radiology. Starting in the early 1970s, this imaging modality is still evolving, although tremendous improvements in scan speed, volume coverage, spatial and soft tissue resolution, as well as dose reduction have been achieved. Tube current modulation, automated exposure control, anatomy-based tube voltage (kV) selection, advanced x-ray beam filtration, and iterative image reconstruction techniques improved image quality and decreased radiation exposure. Cardiac imaging triggered the demand for high temporal resolution, volume acquisition, and high pitch modes with electrocardiogram synchronization. Plaque imaging in cardiac CT as well as lung and bone imaging demand for high spatial resolution. Today, we see a transition of photon-counting detectors from experimental and research prototype setups into commercially available systems integrated in patient care. Moreover, with respect to CT technology and CT image formation, artificial intelligence is increasingly used in patient positioning, protocol adjustment, and image reconstruction, but also in image preprocessing or postprocessing. The aim of this article is to give an overview of the technical specifications of up-to-date available whole-body and dedicated CT systems, as well as hardware and software innovations for CT systems in the near future.

Evaluation of Image Quality and Detectability of Deep Learning Image Reconstruction (DLIR) Algorithm in Single- and Dual-energy CT

This study is aimed to evaluate effects of deep learning image reconstruction (DLIR) on image quality in single-energy CT (SECT) and dual-energy CT (DECT), in reference to adaptive statistical iterative reconstruction-V (ASIR-V). The Gammex 464 phantom was scanned in SECT and DECT modes at three dose levels (5, 10, and 20 mGy). Raw data were reconstructed using six algorithms: filtered back-projection (FBP), ASIR-V at 40% (AV-40) and 100% (AV-100) strength, and DLIR at low (DLIR-L), medium (DLIR-M), and high strength (DLIR-H), to generate SECT 120kVp images and DECT 120kVp-like images. Objective image quality metrics were computed, including noise power spectrum (NPS), task transfer function (TTF), and detectability index (d'). Subjective image quality evaluation, including image noise, texture, sharpness, overall quality, and low- and high-contrast detectability, was performed by six readers. DLIR-H reduced overall noise magnitudes from FBP by 55.2% in a more balanced way of low and high frequency ranges comparing to AV-40, and improved the TTF values at 50% for acrylic inserts by average percentages of 18.32%. Comparing to SECT 20 mGy AV-40 images, the DECT 10 mGy DLIR-H images showed 20.90% and 7.75% improvement in d' for the small-object high-contrast and large-object low-contrast tasks, respectively. Subjective evaluation showed higher image quality and better detectability. At 50% of the radiation dose level, DECT with DLIR-H yields a gain in objective detectability index compared to full-dose AV-40 SECT images used in daily practice.

Abdominopelvic CT Image Quality: Evaluation of Thin (0.5-mm) Slices Using Deep Learning Reconstruction

BACKGROUND. Because thick-section images (typically 3-5 mm) have low image noise, radiologists typically use them to perform clinical interpretation, although they may additionally refer to thin-section images (typically 0.5-0.625 mm) for problem solving. Deep learning reconstruction (DLR) can yield thin-section images with low noise. OBJECTIVE. The purpose of this study is to compare abdominopelvic CT image quality between thin-section DLR images and thin- and thick-section hybrid iterative reconstruction (HIR) images. METHODS. This retrospective study included 50 patients (31 men and 19 women; median age, 64 years) who underwent abdominopelvic CT between June 15, 2020, and July 29, 2020. Images were reconstructed at 0.5-mm section using DLR and at 0.5-mm and 3.0-mm sections using HIR. Five radiologists independently performed pairwise comparisons (0.5-mm DLR and either 0.5-mm or 3.0-mm HIR) and recorded the preferred image for subjective image quality measures (scale, -2 to 2). The pooled scores of readers were compared with a score of 0 (denoting no preference). Image noise was quantified using the SD of ROIs on regions of homogeneous liver. RESULTS. For comparison of 0.5-mm DLR images and 0.5-mm HIR images, the median pooled score was 2 (indicating a definite preference for DLR) for noise and overall image quality and 1 (denoting a slight preference for DLR) for sharpness and natural appearance. For comparison of 0.5-mm DLR and 3.0-mm HIR, the median pooled score was 1 for the four previously mentioned measures. These assessments were all significantly different (p < .001) from 0. For artifacts, the median pooled score for both comparisons was 0, which was not significant for comparison with 3.0-mm HIR (p = .03) but was significant for comparison with 0.5-mm HIR (p < .001) due to imbalance in scores of 1 (n = 28) and -1 (slight preference for HIR, n = 1). Noise for 0.5-mm DLR was lower by mean differences of 12.8 HU compared with 0.5-mm HIR and 4.4 HU compared with 3.0-mm HIR (both p < .001). CONCLUSION. Thin-section DLR improves subjective image quality and reduces image noise compared with currently used thin- and thick-section HIR, without causing additional artifacts. CLINICAL IMPACT. Although further diagnostic performance studies are warranted, the findings suggest the possibility of replacing current use of both thin- and thick-section HIR with the use of thin-section DLR only during clinical interpretations.

Is it possible to use low-dose deep learning reconstruction for the detection of liver metastases on CT routinely?

OBJECTIVES

To compare the image quality and hepatic metastasis detection of low-dose deep learning image reconstruction (DLIR) with full-dose filtered back projection (FBP)/iterative reconstruction (IR).

METHODS

A contrast-detail phantom consisting of low-contrast objects was scanned at five CT dose index levels (10, 6, 3, 2, and 1 mGy). A total of 154 participants with 305 hepatic lesions who underwent abdominal CT were enrolled in a prospective non-inferiority trial with a three-arm design based on phantom results. Data sets with full dosage (13.6 mGy) and low dosages (9.5, 6.8, or 4.1 mGy) were acquired from two consecutive portal venous acquisitions, respectively. All images were reconstructed with FBP (reference), IR (control), and DLIR (test). Eleven readers evaluated phantom data sets for object detectability using a two-alternative forced-choice approach. Non-inferiority analyses were performed to interpret the differences in image quality and metastasis detection of low-dose DLIR relative to full-dose FBP/IR.

RESULTS

The phantom experiment showed the dose reduction potential from DLIR was up to 57% based on the reference FBP dose index. Radiation decreases of 30% and 50% resulted in non-inferior image quality and hepatic metastasis detection with DLIR compared to full-dose FBP/IR. Radiation reduction of 70% by DLIR performed inferiorly in detecting small metastases (< 1 cm) compared to full-dose FBP (difference: -0.112; 95% confidence interval [CI]: -0.178 to 0.047) and full-dose IR (difference: -0.123; 95% CI: -0.182 to 0.053) (p < 0.001).

CONCLUSION

DLIR enables a 50% dose reduction for detecting low-contrast hepatic metastases while maintaining comparable image quality to full-dose FBP and IR.

KEY POINTS

• Non-inferiority study showed that deep learning image reconstruction (DLIR) can reduce the dose to oncological patients with low-contrast lesions without compromising the diagnostic information. • Radiation dose levels for DLIR can be reduced to 50% of full-dose FBP and IR for detecting low-contrast hepatic metastases, while maintaining comparable image quality. • The reduction of radiation by 70% by DLIR is clinically acceptable but insufficient for detecting small low-contrast hepatic metastases (< 1 cm).

Image quality comparison of lower extremity CTA between CT routine reconstruction algorithms and deep learning reconstruction

BACKGROUND

To evaluate the image quality of lower extremity computed tomography angiography (CTA) with deep learning-based reconstruction (DLR) compared to model-based iterative reconstruction (MBIR), hybrid-iterative reconstruction (HIR), and filtered back projection (FBP).

METHODS

Fifty patients (38 males, average age 59.8 ± 19.2 years) who underwent lower extremity CTA between January and May 2021 were included. Images were reconstructed with DLR, MBIR, HIR, and FBP. The standard deviation (SD), contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), noise power spectrum (NPS) curves, and the blur effect, were calculated. The subjective image quality was independently evaluated by two radiologists. The diagnostic accuracy of DLR, MBIR, HIR, and FBP reconstruction algorithms was calculated.

RESULTS

The CNR and SNR were significantly higher in DLR images than in the other three reconstruction algorithms, and the SD was significantly lower in DLR images of the soft tissues. The noise magnitude was the lowest with DLR. The NPS average spatial frequency (f_av) values were higher using DLR than HIR. For blur effect evaluation, DLR and FBP were similar for soft tissues and the popliteal artery, which was better than HIR and worse than MBIR. In the aorta and femoral arteries, the blur effect of DLR was worse than MBIR and FBP and better than HIR. The subjective image quality score of DLR was the highest. The sensitivity and specificity of the lower extremity CTA with DLR were the highest in the four reconstruction algorithms with 98.4% and 97.2%, respectively.

CONCLUSIONS

Compared to the other three reconstruction algorithms, DLR showed better objective and subjective image quality. The blur effect of the DLR was better than that of the HIR. The diagnostic accuracy of lower extremity CTA with DLR was the best among the four reconstruction algorithms.

Understanding CT imaging findings based on the underlying pathophysiology in patients with small bowel ischemia

Because acute small bowel ischemia has a high mortality rate, it requires rapid intervention to avoid unfavorable outcomes. Computed tomography (CT) examination is important for the diagnosis of bowel ischemia. Acute small bowel ischemia can be the result of small bowel obstruction or mesenteric ischemia, including mesenteric arterial occlusion, mesenteric venous thrombosis, and non-occlusive mesenteric ischemia. The clinical significance of each CT finding is unique and depends on the underlying pathophysiology. This review describes the definition and mechanism(s) of bowel ischemia, reviews CT findings suggesting bowel ischemia, details factors involved in the development of small bowel ischemia, and presents CT findings with respect to the different factors based on the underlying pathophysiology. Such knowledge is needed for accurate treatment decisions.

Initial Characterization of Focal Bone Lesions with Conventional Radiographs or Computed Tomography: Diagnostic Performance and Interobserver Agreement Assessment

Objectives: To ascertain the role of CT and conventional radiographs for the initial characterization of focal bone lesions.Methods: Images from 184 patients with confirmed bone tumors included in an ethics committee-approved study were retrospectively evaluated. The reference for benign-malignant distribution was based on histological analysis and long-term follow-up. Radiographs and CT features were analyzed by 2 independent musculoskeletal radiologists blinded to the final diagnosis. Lesion margins, periosteal reaction, cortical lysis, endosteal scalloping, presence of pathologic fracture, and lesion mineralization were evaluated. Results: The benign-malignant distribution in the study population was 68.5-31.5% (126 benign and 58 malignant). In the lesions that could be seen in both radiographs and CT, the performance of these methods for the benign-malignant differentiation was similar (accuracy varying from 72.8% to 76.5%). The interobserver agreement for the overall evaluation of lesion aggressiveness was considerably increased on CT compared to radiographs (Kappa of .63 vs .22). With conventional radiographs, 18 (9.7%) and 20 (10.8%) of the lesions evaluated were not seen respectively by readers 1 and 2. Among these unseen lesions, 50%-61.1% were located in the axial skeleton. Compared to radiographs, the number of lesions with cortical lysis and endosteal scalloping was 26-34% higher with CT. Conclusion: Although radiographs remain the primary imaging tool for lesions in the peripheral skeleton, CT should be performed for axial lesions. CT imaging can assess the extent of perilesional bone lysis more precisely than radiographs with a better evaluation of lesion fracture risk.

Unenhanced abdominal low-dose CT reconstructed with deep learning-based image reconstruction: image quality and anatomical structure depiction

Purpose

To evaluate the utility of deep learning-based image reconstruction (DLIR) algorithm in unenhanced abdominal low-dose CT (LDCT).

Materials and methods

Two patient groups were included in this prospective study: 58 consecutive patients who underwent unenhanced abdominal standard-dose CT reconstructed with hybrid iterative reconstruction (SDCT group) and 48 consecutive patients who underwent unenhanced abdominal LDCT reconstructed with high strength level of DLIR (LDCT group). The background noise and signal-to-noise ratio (SNR) of the liver, pancreas, spleen, kidney, abdominal aorta, inferior vena cava, and portal vein were calculated. Two radiologists qualitatively assessed the overall image noise, overall image quality, and abdominal anatomical structures depiction. Quantitative and qualitative parameters and size-specific dose estimates (SSDE) were compared between SDCT and LDCT groups.

Results

The background noise was lower in LDCT group than in SDCT group (P = 0.02). SNRs were higher in LDCT group than in SDCT group (P < 0.001–0.004) except for the liver. Overall image noise was superior in LDCT group than in SDCT group (P < 0.001). Overall image quality was not different between SDCT and LDCT groups (P = 0.25–0.26). Depiction of almost all abdominal anatomical structures was equal to or better in LDCT group than in SDCT group (P < 0.001–0.88). The SSDE was lower in LDCT group (4.0 mGy) than in SDCT group (20.6 mGy) (P < 0.001).

Conclusions

DLIR facilitates substantial radiation dose reduction of > 75% and significantly reduces background noise. DLIR can maintain image quality and anatomical structure depiction in unenhanced abdominal LDCT.