Imaging-based risk stratification of patients with pulmonary embolism based on dual-energy CT-derived radiomics

BACKGROUND

Technological progress in the acquisition of medical images and the extraction of underlying quantitative imaging data has introduced exciting prospects for the diagnostic assessment of a wide range of conditions. This study aims to investigate the diagnostic utility of a machine learning classifier based on dual-energy computed tomography (DECT) radiomics for classifying pulmonary embolism (PE) severity and assessing the risk for early death.

METHODS

Patients who underwent CT pulmonary angiogram (CTPA) between January 2015 and March 2022 were considered for inclusion in this study. Based on DECT imaging, 107 radiomic features were extracted for each patient using standardized image processing. After dividing the dataset into training and test sets, stepwise feature reduction based on reproducibility, variable importance and correlation analyses were performed to select the most relevant features; these were used to train and validate the gradient-boosted tree models.

RESULTS

The trained machine learning classifier achieved a classification accuracy of .90 for identifying high-risk PE patients with an area under the receiver operating characteristic curve of .59. This CT-based radiomics signature showed good diagnostic accuracy for risk stratification in individuals presenting with central PE, particularly within higher risk groups.

CONCLUSION

Models utilizing DECT-derived radiomics features can accurately stratify patients with pulmonary embolism into established clinical risk scores. This approach holds the potential to enhance patient management and optimize patient flow by assisting in the clinical decision-making process. It also offers the advantage of saving time and resources by leveraging existing imaging to eliminate the necessity for manual clinical scoring.

Coronary Artery Disease Assessment via On-Site CT Fractional Flow Reserve in Patients Undergoing Transcatheter Aortic Valve Replacement

Purpose To examine the clinical feasibility of workstation-based CT fractional flow reserve (CT-FFR) for coronary artery disease (CAD) evaluation during preprocedural planning in patients undergoing transcatheter aortic valve replacement (TAVR). Materials and Methods In this retrospective single-center study, 434 patients scheduled for TAVR between 2018 and 2020 were screened for study inclusion; a relevant proportion of patients (35.0% [152 of 434]) was not suitable for evaluation due to insufficient imaging properties. A total of 112 patients (mean age, 82.1 years ± 6.7 [SD]; 58 [52%] men) were included in the study. Invasive angiography findings, coronary CT angiography results, and Agatston score were acquired and compared with on-site CT-FFR computation for evaluation of CAD and prediction of major adverse cardiovascular events (MACE) within a 24-month follow-up. Results Hemodynamic relevant CAD, as suggested by CT-FFR of 0.80 or less, was found in 41 of 70 (59%) patients with stenosis of 50% or more. MACE occurred in 23 of 112 (20.5%) patients, from which 14 of 23 had stenoses with CT-FFR of 0.80 or less (hazard ratio [HR], 3.33; 95% CI: 1.56, 7.10; P = .002). CT-FFR remained a significant predictor of MACE after inclusion in a multivariable model with relevant covariables (HR, 2.89; 95% CI: 1.22, 6.86; P = .02). An Agatston score of 1000 Agatston units or more (HR, 2.25; 95% CI: 0.98, 5.21; P = .06) and stenoses of 50% or more determined via invasive angiography (HR, 0.94; 95% CI: 0.41, 2.17; P = .88) were not significant predictors of MACE. Conclusion Compared with conventional CAD markers, CT-FFR better predicted adverse outcomes after TAVR. A relevant portion of the screened cohort, however, was not suitable for CT-based CAD evaluation. Keywords: CT, Transcatheter Aortic Valve Implantation/Replacement (TAVI/TAVR), Cardiac, Coronary Arteries, Outcomes Analysis © RSNA, 2024 See also the commentary by Weir-McCall and Pugliese in this issue.

Predictive Value of Dual-Energy CT-Derived Metrics for the Use of Bone Substitutes in Distal Radius Fracture Surgery

(1) Background: Low bone mineral density (BMD) is a significant risk factor for complicated surgery and leads to the increased use of bone substitutes in patients with distal radius fractures (DRFs). No accepted model has yet been established to predict the use of bone substitutes to facilitate preoperative planning. (2) Methods: Unenhanced dual-energy CT (DECT) images of DRFs were retrospectively acquired between March 2016 and September 2020 using the internal PACS system. Available follow-up imaging and medical health records were reviewed to determine the use of bone substitutes. DECT-based BMD, trabecular Hounsfield units (HU), cortical HU, and cortical thickness ratio were measured in non-fractured segments of the distal radius. Diagnostic accuracy parameters were calculated for all metrics using receiver-operating characteristic (ROC) curves and associations of all metrics with the use of bone substitutes were evaluated using logistic regression models. (3) The final study population comprised 262 patients (median age 55 years [IQR 43-67 years]; 159 females, 103 males). According to logistic regression analysis, DECT-based BMD was the only metric significantly associated with the use of bone substitutes (odds ratio 0.96, p = 0.003). However, no significant associations were found for cortical HU (p = 0.06), trabecular HU (p = 0.33), or cortical thickness ratio (p = 0.21). ROC-curve analysis revealed that a combined model of all four metrics had the highest diagnostic accuracy with an area under the curve (AUC) of 0.76. (4) Conclusions: DECT-based BMD measurements performed better than HU-based measurements and cortical thickness ratio. The diagnostic performance of all four metrics combined was superior to that of the individual parameters.

From pixels to prognosis: Imaging biomarkers for discrimination and outcome prediction of pulmonary embolism : Original Research Article

PURPOSE

Recent advancements in medical imaging have transformed diagnostic assessments, offering exciting possibilities for extracting biomarker-based information. This study aims to investigate the capabilities of a machine learning classifier that incorporates dual-energy computed tomography (DECT) radiomics. The primary focus is on discerning and predicting outcomes related to pulmonary embolism (PE).

METHODS

The study included 131 participants who underwent pulmonary artery DECT angiography between January 2015 and March 2022. Among them, 104 patients received the final diagnosis of PE and 27 patients served as a control group. A total of 107 radiomic features were extracted for every case based on DECT imaging. The dataset was divided into training and test sets for model development and validation. Stepwise feature reduction identified the most relevant features, which were used to train a gradient-boosted tree model. Receiver operating characteristics analysis and Cox regression tests assessed the association of texture features with overall survival.

RESULTS

The trained machine learning classifier achieved a classification accuracy of 0.94 for identifying patients with acute PE with an area under the receiver operating characteristic curve of 0.91. Radiomics features could be valuable for predicting outcomes in patients with PE, demonstrating strong prognostic capabilities in survival prediction (c-index, 0.991 [0.979-1.00], p = 0.0001) with a median follow-up of 130 days (IQR, 38-720). Notably, the inclusion of clinical or DECT parameters did not enhance predictive performance.

CONCLUSION

In conclusion, our study underscores the promising potential of leveraging radiomics on DECT imaging for the identification of patients with acute PE and predicting their outcomes. This approach has the potential to improve clinical decision-making and patient management, offering efficiencies in time and resources by utilizing existing DECT imaging without the need for an additional scoring system.

Potential of Dual-Energy CT-Based Collagen Maps for the Assessment of Disk Degeneration in the Lumbar Spine

RATIONALE AND OBJECTIVES

Lumbar disk degeneration is a common condition contributing significantly to back pain. The objective of the study was to evaluate the potential of dual-energy CT (DECT)-derived collagen maps for the assessment of lumbar disk degeneration.

PATIENTS AND METHODS

We conducted a retrospective analysis of 127 patients who underwent dual-source DECT and MRI of the lumbar spine between 07/2019 and 10/2022. The level of lumbar disk degeneration was categorized by three radiologists as follows: no/mild (Pfirrmann 1&2), moderate (Pfirrmann 3&4), and severe (Pfirrmann 5). Recall (sensitivity) and accuracy of DECT collagen maps were calculated. Intraclass correlation coefficient (ICC) was used to evaluate inter-reader reliability. Subjective evaluations were performed using 5-point Likert scales for diagnostic confidence and image quality.

RESULTS

We evaluated a total of 762 intervertebral disks from 127 patients (median age, 69.7 (range, 23.0-93.7), female, 56). MRI identified 230 non/mildly degenerated disks (30.2%), 484 moderately degenerated disks (63.5%), and 48 severely degenerated disks (6.3%). DECT collagen maps yielded an overall accuracy of 85.5% (1955/2286). Recall (sensitivity) was 79.3% (547/690) for the detection of no/mild lumbar disk degeneration, 88.7% (1288/1452) for the detection of moderate disk degeneration, and 83.3% (120/144) for the detection of severe disk degeneration (ICC=0.9). Subjective evaluations of DECT collagen maps showed high diagnostic confidence (median 4) and good image quality (median 4).

CONCLUSION

The use of DECT collagen maps to distinguish different stages of lumbar disk degeneration may have clinical significance in the early diagnosis of disk-related pathologies in patients with contraindications for MRI or in cases of unavailability of MRI.

Value of Dual-Energy CT-Derived Metrics for the Prediction of Bone Non-union in Distal Radius Fractures

RATIONALE AND OBJECTIVES

Bone non-union is a serious complication of distal radius fractures (DRF) that can result in functional limitations and persistent pain. However, no accepted method has been established to identify patients at risk of developing bone non-union yet. This study aimed to compare various CT-derived metrics for bone mineral density (BMD) assessment to identify predictive values for the development of bone non-union.

MATERIALS AND METHODS

CT images of 192 patients with DRFs who underwent unenhanced dual-energy CT (DECT) of the distal radius between 03/2016 and 12/2020 were retrospectively identified. Available follow-up imaging and medical health records were evaluated to determine the occurrence of bone non-union. DECT-based BMD, trabecular Hounsfield unit (HU), cortical HU and cortical thickness ratio were measured in normalized non-fractured segments of the distal radius.

RESULTS

Patients who developed bone non-union were significantly older (median age 72 years vs. 54 years) and had a significantly lower DECT-based BMD (median 68.1 mg/cm3 vs. 94.6 mg/cm3, p < 0.001). Other metrics (cortical thickness ratio, cortical HU, trabecular HU) showed no significant differences. ROC and PR curve analyses confirmed the highest diagnostic accuracy for DECT-based BMD with an area under the curve (AUC) of 0.83 for the ROC curve and an AUC of 0.46 for the PR curve. In logistic regression models, DECT-based BMD was the sole metric significantly associated with bone non-union.

CONCLUSION

DECT-derived metrics can accurately predict bone non-union in patients who sustained DRF. The diagnostic performance of DECT-based BMD is superior to that of HU-based metrics and cortical thickness ratio.

Does Dual-Energy Computed Tomography Material Decomposition Improve Radiomics Capability to Predict Survival in Head and Neck Squamous Cell Carcinoma Patients? A Preliminary Investigation

OBJECTIVE

Our study objective was to explore the additional value of dual-energy CT (DECT) material decomposition for squamous cell carcinoma of the head and neck (SCCHN) survival prognostication.

METHODS

A group of 50 SCCHN patients (male, 37; female, 13; mean age, 63.6 ± 10.82 years) with baseline head and neck DECT between September 2014 and August 2020 were retrospectively included. Primary tumors were segmented, radiomics features were extracted, and DECT material decomposition was performed. We used independent train and validation datasets with cross-validation and 100 independent iterations to identify prognostic signatures applying elastic net (EN) and random survival forest (RSF). Features were ranked and intercorrelated according to their prognostic importance. We benchmarked the models against clinical parameters. Intraclass correlation coefficients were used to analyze the interreader variation.

RESULTS

The exclusively radiomics-trained models achieved similar ( P = 0.947) prognostic performance of area under the curve (AUC) = 0.784 (95% confidence interval [CI], 0.775-0.812) (EN) and AUC = 0.785 (95% CI, 0.759-0.812) (RSF). The additional application of DECT material decomposition did not improve the model's performance (EN, P = 0.594; RSF, P = 0.198). In the clinical benchmark, the top averaged AUC value of 0.643 (95% CI, 0.611-0.675) was inferior to the quantitative imaging-biomarker models ( P < 0.001). A combined imaging and clinical model did not improve the imaging-based models ( P > 0.101). Shape features revealed high prognostic importance.

CONCLUSIONS

Radiomics AI applications may be used for SCCHN survival prognostication, but the spectral information of DECT material decomposition did not improve the model's performance in our preliminary investigation.

Incident fractures of the distal radius: Dual-energy CT-derived metrics for opportunistic risk stratification

BACKGROUND

Dual-energy CT (DECT)-derived bone mineral density (BMD) of the distal radius and other CT-derived metrics related to bone health have been suggested for opportunistic osteoporosis screening and risk evaluation for sustaining distal radius fractures (DRFs).

METHODS

The distal radius of patients who underwent DECT between 01/2016 and 08/2021 was retrospectively analyzed. Cortical Hounsfield Unit (HU), trabecular HU, cortical thickness, and DECT-based BMD were acquired from a non-fractured, metaphyseal area in all examinations. Receiver-operating characteristic (ROC) analysis was conducted to determine the area under the curve (AUC) values for predicting DRFs based on DECT-derived BMD, HU values, and cortical thickness. Logistic regression models were then employed to assess the associations of these parameters with the occurrence of DRFs.

RESULTS

In this study, 263 patients (median age: 52 years; interquartile range: 36-64; 132 women; 192 fractures) were included. ROC curve analysis revealed a higher area under the curve (AUC) value for DECT-derived BMD compared to cortical HU, trabecular HU, and cortical thickness (0.91 vs. 0.61, 0.64, and 0.69, respectively; p <.001). Logistic regression models confirmed the association between lower DECT-derived BMD and the occurrence of DRFs (Odds Ratio, 0.83; p <.001); however, no influence was observed for cortical HU, trabecular HU, or cortical thickness.

CONCLUSIONS

DECT can be used to assess the BMD of the distal radius without dedicated equipment such as calibration phantoms to increase the detection rates of osteoporosis and stratify the individual risk to sustain DRFs. In contrast, assessing HU-based values and cortical thickness does not provide clinical benefit.

Indicators for Hospitalization in Acute Pulmonary Embolism: Uncover the Association Between D-dimer Levels, Thrombus Volume and Radiomics

BACKGROUND

The advent of advanced computed tomography (CT) technology and the field of radiomics has opened up new avenues in diagnostic assessments. Increasingly, there is substantial evidence advocating for the incorporation of quantitative imaging biomarkers in the clinical decision-making process. This study aimed to examine the correlation between D-dimer levels and thrombus size in acute pulmonary embolism (PE) combining dual-energy CT (DECT) and radiomics and to investigate the diagnostic utility of a machine learning classifier based on dual-energy computed tomography (DECT) radiomics for identifying patients with a complicated course, defined as at least hospitalization at IMC.

METHODS

The study was conducted including 136 participants who underwent pulmonary artery CT angiography from January 2015 to March 2022. Based on DECT imaging, 107 radiomic features were extracted for each patient using standardized image processing. After dividing the dataset into training and test sets, stepwise feature reduction based on reproducibility, variable importance and correlation analyses were performed to select the most relevant features; these were used to train and validate the gradient-boosted tree models.Receiver operating characteristics (ROC) analysis was utilized to evaluate the association between volumetric, laboratory data and adverse outcomes.

RESULTS

In the central PE group, we observed a significant correlation between thrombus volumetrics and D-dimer levels (p = 0.0037), as well as between thrombus volumetrics and hospitalization at the Intermediate Care Unit (IMC) (p = 0.0001). In contrast, no statistically significant differences were identified in thrombus sizes between patients who experienced complications and those who had a favorable course (p = 0.3162). The trained machine learning classifier achieved an accuracy of 61% and 55% in identifying patients with a complicated course, as indicated by an area under the ROC curve of 0.63 and 0.58.

CONCLUSION

In conclusion, our findings indicate a positive correlation between D-dimer levels and central PE's pulmonary embolic burden. Thrombus volumetrics may serve as an indicator for complications and outcomes in acute PE patients. Thus, thrombus volumetrics, as opposed to D-dimers, could be an additional marker for evaluating embolic disease severity. Moreover, DECT-derived radiomic feature models show promise in identifying patients with a complicated course, such as hospitalization at IMC.

Diagnostic performance of modern computed tomography in cruciate ligament injury detection: A comprehensive study

BACKGROUND

This study aimed to evaluate the clinical utility of modern single and dual-energy computed tomography (CT) for assessing the integrity of the cruciate ligaments in patients that sustained acute trauma.

METHODS

Patients who underwent single- or dual-energy CT followed by 3 Tesla magnetic resonance imaging (MRI) or knee joint arthroscopy between 01/2016 and 12/2022 were included in this retrospective, monocentric study. Three radiologists specialized in musculoskeletal imaging independently evaluated all CT images for the presence of injury to the cruciate ligaments. An MRI consensus reading of two experienced readers and arthroscopy provided the reference standard. Diagnostic accuracy parameters and area under the receiver operator characteristic curve (AUC) were the primary metrics for diagnostic performance.

RESULTS

CT images of 204 patients (median age, 49 years; IQR 36 - 64; 113 males) were evaluated. Dual-energy CT yielded significantly higher diagnostic accuracy and AUC for the detection of injury to the anterior (94% [240/255] vs 75% [266/357] and 0.89 vs 0.66) and posterior cruciate ligaments (95% [243/255] vs 87% [311/357] and 0.90 vs 0.61) compared to single-energy CT (all parameters, p <.005). Diagnostic confidence and image quality were significantly higher in dual-energy CT compared to single-energy CT (all parameters, p <.005).

CONCLUSIONS

Modern dual-energy CT is readily available and can serve as a screening tool for detecting or excluding cruciate ligament injuries in patients with acute trauma. Accurate diagnosis of cruciate ligament injuries is crucial to prevent adverse outcomes, including delayed treatment, chronic instability, or long-term functional limitations.

Value of Post-/Pre-Procedural Aortic Regurgitation Ratio vs. Pre-Procedural Aortic Valve Calcium Score to Predict Moderate to Severe Paravalvular Leak Requiring Post-Dilation after Transcatheter Aortic Valve Implantation

BACKGROUND AND AIM

Tools that assist interventionists in selecting patients for post-dilation (PD) are needed. We aimed to assess whether pre-interventional aortic valve calcium (AVC) or the peri-interventional aortic regurgitation (ARI) ratio is a better predictor for a more than mild paravalvular leak (PVL) requiring PD after TAVI.

METHODS

Patients undergoing TAVI with available data on AVC derived from MSCTs and the ARI ratio derived from peri-interventional hemodynamic curves were studied. The main outcome was moderate-to-severe PVL requiring PD.

RESULTS

In 237 patients, more than mild PVL after valve deployment was present in 25.7%. PD was performed in 65 patients. The median (IQR) total AVC was 390.5 (211.5-665.4) mm3. All calcification values were significantly higher in patients who underwent PD. The median (IQR) individual threshold was 600 (550-685) Hus. The overall ARI ratio was 0.78 (0.61-0.96), with values being significantly lower in patients who underwent PD: 0.61 (0.49-0.80) vs. 0.82 (0.69-0.99) (p < 0.001). Both the ARI ratio (OR [95%CI] 0.053 [0.014-0.203]; p < 0.001) and AVC (1.01 [1.000-1.002]; p = 0.015) predicted PD need. ROC curves showed higher discrimination for the ARI ratio (AUC 0.73) than for any calcification parameter (all AUCs ≤ 0.62).

CONCLUSIONS

The ARI ratio provides interventionists with a powerful predictive tool for PVL requiring PD after TAVI that is beyond the predictive value of pre-procedural valve calcification derived from MSCT.

Multiparametric Evaluation of Radiomics Features and Dual-Energy CT Iodine Maps for Discrimination and Outcome Prediction of Thymic Masses

RATIONALE AND OBJECTIVES

To investigate the diagnostic value of radiomics features and dual-source dual-energy CT (DECT) based material decomposition in differentiating low-risk thymomas, high-risk thymomas, and thymic carcinomas.

MATERIALS AND METHODS

This retrospective study included 32 patients (16 males, mean age 66 ± 14 years) with pathologically confirmed thymic masses who underwent contrast-enhanced DECT between 10/2014 and 01/2023. Two experienced readers evaluated all patients regarding conventional radiomics features, as well as DECT-based features, including attenuation (HU), iodine density (mg/mL), and fat fraction (%). Data comparisons were performed using analysis of variance and chi-square statistic tests. Receiver operating characteristic curve analysis and Cox-regression tests were used to discriminate between low-risk/high-risk thymomas and thymic carcinomas.

RESULTS

Of the 32 thymic tumors, 12 (38%) were low-risk thymomas, 11 (34%) were high-risk thymomas, and 9 (28%) were thymic carcinomas. Values differed significantly between low-risk thymoma, high-risk thymoma, and thymic carcinoma regarding DECT-based features (p ≤ 0.023) and 30 radiomics features (p ≤ 0.037). The area under the curve to differentiate between low-risk/high-risk thymomas and thymic cancer was 0.998 (95% CI, 0.915-1.000; p < 0.001) for the combination of DECT imaging parameters and radiomics features, yielding a sensitivity of 100% and specificity of 96%. During a follow-up of 60 months (IQR, 35-60 months), the multiparametric approach including radiomics features, DECT parameters, and clinical parameters showed an excellent prognostic power to predict all-cause mortality (c-index = 0.978 [95% CI, 0.958-0.998], p = 0.003).

CONCLUSION

A multiparametric approach including conventional radiomics features and DECT-based features facilitates accurate, non-invasive discrimination between low-risk/high-risk thymomas and thymic carcinomas.

Advanced biomedical imaging for accurate discrimination and prognostication of mediastinal masses

BACKGROUND

To investigate the potential of radiomic features and dual-source dual-energy CT (DECT) parameters in differentiating between benign and malignant mediastinal masses and predicting patient outcomes.

METHODS

In this retrospective study, we analysed data from 90 patients (38 females, mean age 51 ± 25 years) with confirmed mediastinal masses who underwent contrast-enhanced DECT. Attenuation, radiomic features and DECT-derived imaging parameters were evaluated by two experienced readers. We performed analysis of variance (ANOVA) and Chi-square statistic tests for data comparison. Receiver operating characteristic curve analysis and Cox regression tests were used to differentiate between mediastinal masses.

RESULTS

Of the 90 mediastinal masses, 49 (54%) were benign, including cases of thymic hyperplasia/thymic rebound (n = 10), mediastinitis (n = 16) and thymoma (n = 23). The remaining 41 (46%) lesions were classified as malignant, consisting of lymphoma (n = 28), mediastinal tumour (n = 4) and thymic carcinoma (n = 9). Significant differences were observed between benign and malignant mediastinal masses in all DECT-derived parameters (p ≤ .001) and 38 radiomic features (p ≤ .044) obtained from contrast-enhanced DECT. The combination of these methods achieved an area under the curve of .98 (95% CI, .893-1.000; p < .001) to differentiate between benign and malignant masses, with 100% sensitivity and 91% specificity. Throughout a follow-up of 1800 days, a multiparametric model incorporating radiomic features, DECT parameters and gender showed promising prognostic power in predicting all-cause mortality (c-index = .8 [95% CI, .702-.890], p < .001).

CONCLUSIONS

A multiparametric approach combining radiomic features and DECT-derived imaging biomarkers allows for accurate and noninvasive differentiation between benign and malignant masses in the anterior mediastinum.

Unveiling the diagnostic enigma of D-dimer testing in cancer patients: Current evidence and areas of application

BACKGROUND

Cancer is a well-known risk factor for venous thromboembolism (VTE). A combined strategy of D-dimer testing and clinical pre-test probability is usually used to exclude VTE. However, its effectiveness is diminished in cancer patients due to reduced specificity, ultimately leading to a decreased clinical utility. This review article seeks to provide a comprehensive summary of how to interpret D-dimer testing in cancer patients.

METHODS

In accordance with PRISMA standards, literature pertaining to the diagnostic and prognostic significance of D-dimer testing in cancer patients was carefully chosen from reputable sources such as PubMed and the Cochrane databases.

RESULTS

D-dimers have not only a diagnostic value in ruling out VTE but can also serve as an aid for rule-in if their values exceed 10-times the upper limit of normal. This threshold allows a diagnosis of VTE in cancer patients with a positive predictive value of more than 80%. Moreover, elevated D-dimers carry important prognostic information and are associated with VTE reoccurrence. A gradual increase in risk for all-cause death suggests that VTE is also an indicator of biologically more aggressive cancer types and advanced cancer stages. Considering the lack of standardization for D-dimer assays, it is essential for clinicians to carefully consider the variations in assay performance and the specific test characteristics of their institution.

CONCLUSIONS

Standardizing D-dimer assays and developing modified pretest probability models specifically for cancer patients, along with adjusted cut-off values for D-dimer testing, could significantly enhance the accuracy and effectiveness of VTE diagnosis in this population.

Comparison of radiomics models and dual-energy material decomposition to decipher abdominal lymphoma in contrast-enhanced CT

PURPOSE

The radiologists' workload is increasing, and computational imaging techniques may have the potential to identify visually unequivocal lesions, so that the radiologist can focus on equivocal and critical cases. The purpose of this study was to assess radiomics versus dual-energy CT (DECT) material decomposition to objectively distinguish visually unequivocal abdominal lymphoma and benign lymph nodes.

METHODS

Retrospectively, 72 patients [m, 47; age, 63.5 (27-87) years] with nodal lymphoma (n = 27) or benign abdominal lymph nodes (n = 45) who had contrast-enhanced abdominal DECT between 06/2015 and 07/2019 were included. Three lymph nodes per patient were manually segmented to extract radiomics features and DECT material decomposition values. We used intra-class correlation analysis, Pearson correlation and LASSO to stratify a robust and non-redundant feature subset. Independent train and test data were applied on a pool of four machine learning models. Performance and permutation-based feature importance was assessed to increase the interpretability and allow for comparison of the models. Top performing models were compared by the DeLong test.

RESULTS

About 38% (19/50) and 36% (8/22) of the train and test set patients had abdominal lymphoma. Clearer entity clusters were seen in t-SNE plots using a combination of DECT and radiomics features compared to DECT features only. Top model performances of AUC = 0.763 (CI = 0.435-0.923) were achieved for the DECT cohort and AUC = 1.000 (CI = 1.000-1.000) for the radiomics feature cohort to stratify visually unequivocal lymphomatous lymph nodes. The performance of the radiomics model was significantly (p = 0.011, DeLong) superior to the DECT model.

CONCLUSIONS

Radiomics may have the potential to objectively stratify visually unequivocal nodal lymphoma versus benign lymph nodes. Radiomics seems superior to spectral DECT material decomposition in this use case. Therefore, artificial intelligence methodologies may not be restricted to centers with DECT equipment.

Diagnostic value of DECT-based colored collagen maps for the assessment of cruciate ligaments in patients with acute trauma

OBJECTIVES

The purpose of this study was to evaluate the diagnostic accuracy of third-generation dual-source dual-energy CT (DECT) color-coded collagen reconstructions for the assessment of the cruciate ligaments compared to standard grayscale image reconstruction.

METHODS

Patients who underwent third-generation dual-source DECT followed by either 3-T MRI or arthroscopy of the knee joint within 14 days between January 2016 and December 2021 were included in this retrospective study. Five radiologists independently evaluated conventional grayscale DECT for the presence of injury to the cruciate ligaments; after 4 weeks, readers re-evaluated the examinations using grayscale images and color-coded collagen reconstructions. A reference standard for MRI was provided by a consensus reading of two experienced readers and arthroscopy. Sensitivity and specificity were the primary metrics of diagnostic performance.

RESULTS

Eighty-five patients (mean age, 44 years ± 16; 50 male) with injury to the ACL or PCL (n = 31) were ultimately included. Color-coded collagen reconstructions significantly increased overall sensitivity (94/105 [90%] vs. 67/105 [64%]), specificity (248/320 [78%] vs. 215/320 [67%]), PPV (94/166 [57%] vs. 67/162 [39%]), NPV (248/259 [96%] vs. 215/253 [85%]), and accuracy (342/425 [81%] vs. 282/425 [66%]) for the detection of injury to the anterior cruciate ligament (all parameters, p < .001). For injury to the posterior cruciate ligament, diagnostic accuracy increased for complete tears (p < .001). Color-coded collagen reconstructions achieved superior diagnostic confidence, image quality, and noise scores compared to grayscale CT (all parameters, p < .001) and showed good agreement with MRI examinations.

CONCLUSIONS

DECT-derived color-coded collagen reconstructions yield substantially higher diagnostic accuracy and confidence for assessing the integrity of the cruciate ligaments compared to standard grayscale CT in patients with acute trauma.

KEY POINTS

• Color-coded collagen reconstructions derived from dual-energy CT yield substantially higher diagnostic accuracy and confidence for the assessment of the cruciate ligaments compared to standard grayscale CT in patients with acute trauma. • Color-coded collagen reconstructions demonstrate good agreement with MRI for the assessment cruciate ligament injury. • Dual-energy CT may serve as a readily available screening approach for patients with acute trauma to the knee when injury to the cruciate ligaments is suspected.

Coil embolization of a fistula from the right inferior phrenic artery to the right pulmonary artery with involvement of further arteries: A rare case report

A 51-year-old female patient was presenting dyspnea for more than a year with no previous lung infections or surgery. Initially, a diagnostic computed tomography was made, showing a rare arterio-arterial malformation between the right inferior phrenic and right pulmonary artery leading into a vascular bundle in the middle lung lobe. Due to the patients' dyspnea and massive extent of malformation, the indication for transcatheter arterial embolization was made. The first transcatheter arterial embolization procedure involved the inferior phrenic and a selective branch of the internal thoracic artery. Interventional angiography as well as computed tomography revealed further extend of the malformation showing a connection of right lateral thoracic, hepatic, and inferior epigastric artery to the fistula. After one month, a second transcatheter arterial embolization of these arteries as well as a second approach of the proximal internal thoracic artery was performed. In the follow-up the patient described a substantial improvement of her dyspnea and showed no signs of infections. A phrenic artery to pulmonary artery fistula is an extremely rare case occurring congenital or acquired. Patients may be asymptomatic or present, among others, dyspnea, hemoptysis, pulmonary infections and congestive heart failure. Symptomatic patients require treatment using transcatheter arterial embolization or surgical resection. The patient had dyspnea and a substantial extent of malformation with possibly complicated clinical course. The recommended less invasive treatment using transcatheter arterial embolization was successfully performed. In conclusion, our patient represented a rare congenital case of systemic and pulmonary artery communication, which we were able to treat sufficiently with coil embolization.

Dual-Energy CT-based Opportunistic Volumetric Bone Mineral Density Assessment of the Distal Radius

Background In patients with distal radius fractures (DRFs), low bone mineral density (BMD) is associated with bone substitute use during surgery and bone nonunion, but BMD information is not regularly available. Purpose To evaluate the feasibility of dual-energy CT (DECT)-based BMD assessment from routine examinations in the distal radius and the relationship between the obtained BMD values, the occurrence of DRFs, bone nonunion, and use of surgical bone substitute. Materials and Methods Scans in patients who underwent routine dual-source DECT in the distal radius between January 2016 and December 2021 were retrospectively acquired. Phantomless BMD assessment was performed using the delineated trabecular bone of a nonfractured segment of the distal radius and both DECT image series. CT images and health records were examined to determine fracture severity, surgical management, and the occurrence of bone nonunion. Associations of BMD with the occurrence of DRFs, bone nonunion, and bone substitute use at surgical treatment were examined with generalized additive models and receiver operating characteristic analysis. Results This study included 263 patients (median age, 52 years; IQR, 36-64 years; 132 female patients), of whom 192 were diagnosed with fractures. Mean volumetric BMD was lower in patients who sustained a DRF (93.9 mg/cm3 vs 135.4 mg/cm3; P < .001), required bone substitutes (79.6 mg/cm3 vs 95.5 mg/cm3; P < .001), and developed bone nonunion (71.1 mg/cm3 vs 96.5 mg/cm3; P < .001). Receiver operating characteristic curve analysis identified these patients with an area under the curve of 0.71-0.91 (P < .001). Lower BMD increased the risk to sustain DRFs, develop bone nonunion, and receive bone substitutes at surgery (P < .001). Conclusion DECT-based BMD assessment at routine examinations is feasible and could help predict surgical bone substitute use and the occurrence of bone nonunion in patients with DRFs. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Carrino in this issue.

Dual-Energy CT in Cardiothoracic Imaging: Current Developments

This article describes the technical principles and clinical applications of dual-energy computed tomography (DECT) in the context of cardiothoracic imaging with a focus on current developments and techniques. Since the introduction of DECT, different vendors developed distinct hard and software approaches for generating multi-energy datasets and multiple DECT applications that were developed and clinically investigated for different fields of interest. Benefits for various clinical settings, such as oncology, trauma and emergency radiology, as well as musculoskeletal and cardiovascular imaging, were recently reported in the literature. State-of-the-art applications, such as virtual monoenergetic imaging (VMI), material decomposition, perfused blood volume imaging, virtual non-contrast imaging (VNC), plaque removal, and virtual non-calcium (VNCa) imaging, can significantly improve cardiothoracic CT image workflows and have a high potential for improvement of diagnostic accuracy and patient safety.

Radiomics for therapy-specific head and neck squamous cell carcinoma survival prognostication (part I)

BACKGROUND

Treatment plans for squamous cell carcinoma of the head and neck (SCCHN) are individually decided in tumor board meetings but some treatment decision-steps lack objective prognostic estimates. Our purpose was to explore the potential of radiomics for SCCHN therapy-specific survival prognostication and to increase the models' interpretability by ranking the features based on their predictive importance.

METHODS

We included 157 SCCHN patients (male, 119; female, 38; mean age, 64.39 ± 10.71 years) with baseline head and neck CT between 09/2014 and 08/2020 in this retrospective study. Patients were stratified according to their treatment. Using independent training and test datasets with cross-validation and 100 iterations, we identified, ranked and inter-correlated prognostic signatures using elastic net (EN) and random survival forest (RSF). We benchmarked the models against clinical parameters. Inter-reader variation was analyzed using intraclass-correlation coefficients (ICC).

RESULTS

EN and RSF achieved top prognostication performances of AUC = 0.795 (95% CI 0.767-0.822) and AUC = 0.811 (95% CI 0.782-0.839). RSF prognostication slightly outperformed the EN for the complete (ΔAUC 0.035, p = 0.002) and radiochemotherapy (ΔAUC 0.092, p < 0.001) cohort. RSF was superior to most clinical benchmarking (p ≤ 0.006). The inter-reader correlation was moderate or high for all features classes (ICC ≥ 0.77 (± 0.19)). Shape features had the highest prognostic importance, followed by texture features.

CONCLUSIONS

EN and RSF built on radiomics features may be used for survival prognostication. The prognostically leading features may vary between treatment subgroups. This warrants further validation to potentially aid clinical treatment decision making in the future.

Computed tomography-based pericoronary adipose tissue attenuation in patients undergoing TAVR: a novel method for risk assessment

Objectives

This study aims to assess the attenuation of pericoronary adipose tissue (PCAT) surrounding the proximal right coronary artery (RCA) in patients with aortic stenosis (AS) and undergoing transcatheter aortic valve replacement (TAVR). RCA PCAT attenuation is a novel computed tomography (CT)-based marker for evaluating coronary inflammation. Coronary artery disease (CAD) in TAVR patients is common and usually evaluated prior to intervention. The most sensible screening method and consequential treatment approach are unclear and remain a matter of ceaseless discussion. Thus, interest remains for safe and low-demand predictive markers to identify patients at risk for adverse outcomes postaortic valve replacement.

Methods

This single-center retrospective study included patients receiving a standard planning CT scan prior to TAVR. Conventional CAD diagnostic tools, such as coronary artery calcium score and significant stenosis via invasive coronary angiography and coronary computed tomography angiography, were determined in addition to RCA PCAT attenuation using semiautomated software. These were assessed for their relationship with major adverse cardiovascular events (MACE) during a 24-month follow-up period.

Results

From a total of 62 patients (mean age: 82 ± 6.7 years), 15 (24.2%) patients experienced an event within the observation period, 10 of which were attributed to cardiovascular death. The mean RCA PCAT attenuation was higher in patients enduring MACE than that in those without an endpoint (-69.8 ± 7.5 vs. -74.6 ± 6.2, P = 0.02). Using a predefined cutoff of >-70.5 HU, 20 patients (32.3%) with high RCA PCAT attenuation were identified, nine (45%) of which met the endpoint within 2 years after TAVR. In a multivariate Cox regression model including conventional CAD diagnostic tools, RCA PCAT attenuation prevailed as the only marker with significant association with MACE (P = 0.02). After dichotomization of patients into high- and low-RCA PCAT attenuation groups, high attenuation was related to greater risk of MACE (hazard ration: 3.82, P = 0.011).

Conclusion

RCA PCAT attenuation appears to have predictive value also in a setting of concomitant AS in patients receiving TAVR. RCA PCAT attenuation was more reliable than conventional CAD diagnostic tools in identifying patients at risk for MACE .

Virtual Monoenergetic Imaging of Lower Extremities Using Dual-Energy CT Angiography in Patients with Diabetes Mellitus

BACKGROUND

Type 2 diabetes mellitus (DM) is the most common metabolic disorder in the world and an important risk factor for peripheral arterial disease (PAD). CT angiography represents the method of choice for the diagnosis, pre-operative planning, and follow-up of vascular disease. Low-energy dual-energy CT (DECT) virtual mono-energetic imaging (VMI) has been shown to improve image contrast, iodine signal, and may also lead to a reduction in contrast medium dose. In recent years, VMI has been improved with the use of a new algorithm called VMI+, able to obtain the best image contrast with the least possible image noise in low-keV reconstructions.

PURPOSE

To evaluate the impact of VMI+ DECT reconstructions on quantitative and qualitative image quality in the evaluation of the lower extremity runoff.

MATERIALS AND METHODS

We evaluated DECT angiography of lower extremities in patients suffering from diabetes who had undergone clinically indicated DECT examinations between January 2018 and January 2023. Images were reconstructed with standard linear blending (F_0.5) and low VMI+ series were generated from 40 to 100 keV, in an interval of 15 keV. Vascular attenuation, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were calculated for objective analysis. Subjective analysis was performed using five-point scales to evaluate image quality, image noise, and diagnostic assessability of vessel contrast.

RESULTS

Our final study cohort consisted of 77 patients (41 males). Attenuation values, CNR, and SNR were higher in 40-keV VMI+ reconstructions compared to the remaining VMI+ and standard F_0.5 series (HU: 1180.41 ± 45.09; SNR: 29.91 ± 0.99; CNR: 28.60 ± 1.03 vs. HU 251.32 ± 7.13; SNR: 13.22 ± 0.44; CNR: 10.57 ± 0.39 in standard F_0.5 series) (p < 0.0001). Subjective image rating was significantly higher in 55-keV VMI+ images compared to the other VMI+ and standard F_0.5 series in terms of image quality (mean score: 4.77), image noise (mean score: 4.39), and assessability of vessel contrast (mean value: 4.57) (p < 0.001).

CONCLUSIONS

DECT 40-keV and 55-keV VMI+ showed the highest objective and subjective parameters of image quality, respectively. These specific energy levels for VMI+ reconstructions could be recommended in clinical practice, providing high-quality images with greater diagnostic suitability for the evaluation of lower extremity runoff, and potentially needing a lower amount of contrast medium, which is particularly advantageous for diabetic patients.

Multiparametric detection and outcome prediction of pancreatic cancer involving dual-energy CT, diffusion-weighted MRI, and radiomics

BACKGROUND

The advent of next-generation computed tomography (CT)- and magnetic resonance imaging (MRI) opened many new perspectives in the evaluation of tumor characteristics. An increasing body of evidence suggests the incorporation of quantitative imaging biomarkers into clinical decision-making to provide mineable tissue information. The present study sought to evaluate the diagnostic and predictive value of a multiparametric approach involving radiomics texture analysis, dual-energy CT-derived iodine concentration (DECT-IC), and diffusion-weighted MRI (DWI) in participants with histologically proven pancreatic cancer.

METHODS

In this study, a total of 143 participants (63 years ± 13, 48 females) who underwent third-generation dual-source DECT and DWI between November 2014 and October 2022 were included. Among these, 83 received a final diagnosis of pancreatic cancer, 20 had pancreatitis, and 40 had no evidence of pancreatic pathologies. Data comparisons were performed using chi-square statistic tests, one-way ANOVA, or two-tailed Student's t-test. For the assessment of the association of texture features with overall survival, receiver operating characteristics analysis and Cox regression tests were used.

RESULTS

Malignant pancreatic tissue differed significantly from normal or inflamed tissue regarding radiomics features (overall P < .001, respectively) and iodine uptake (overall P < .001, respectively). The performance for the distinction of malignant from normal or inflamed pancreatic tissue ranged between an AUC of ≥ 0.995 (95% CI, 0.955-1.0; P < .001) for radiomics features, ≥ 0.852 (95% CI, 0.767-0.914; P < .001) for DECT-IC, and ≥ 0.690 (95% CI, 0.587-0.780; P = .01) for DWI, respectively. During a follow-up of 14 ± 12 months (range, 10-44 months), the multiparametric approach showed a moderate prognostic power to predict all-cause mortality (c-index = 0.778 [95% CI, 0.697-0.864], P = .01).

CONCLUSIONS

Our reported multiparametric approach allowed for accurate discrimination of pancreatic cancer and revealed great potential to provide independent prognostic information on all-cause mortality.

Cancer patients with venous thromboembolism: Diagnostic and prognostic value of elevated D-dimers

BACKGROUND

D-dimer testing is known to have a high sensitivity at simultaneously low specificity, resulting in nonspecific elevations in a variety of conditions.

METHODS

This retrospective study sought to assess diagnostic and prognostic features of D-dimers in cancer patients referred to the emergency department for suspected pulmonary embolism (PE) and deep vein thrombosis (DVT). In total, 526 patients with a final adjudicated diagnosis of PE (n = 83) and DVT (n = 69) were enrolled, whereas 374 patients served as the comparative group, in which venous thromboembolism (VTE) has been excluded.

RESULTS

For the identification of VTE, D-dimers yielded the highest positive predictive value of 96% (95% confidence interval (CI), 85-99) at concentrations of 9.9 mg/L and a negative predictive value of 100% at .6 mg/L (95% CI, 97-100). At the established rule-out cut-off level of .5 mg/L, D-dimers were found to be very sensitive (100%) at a moderate specificity of nearly 65%. Using an optimised cut-off value of 4.9 mg/L increased the specificity to 95% for the detection of life-threatening VTE at the cost of moderate sensitivities (64%). During a median follow-up of 30 months, D-dimers positively correlated with the reoccurrence of VTE (p = .0299) and mortality in both cancer patients with VTE (p < .0001) and without VTE (p = .0008).

CONCLUSIONS

Although D-dimer testing in cancer patients is discouraged by current guidelines, very high concentrations above the 10-fold upper reference limit contain diagnostic and prognostic information and might be helpful in risk assessment, while low concentrations remain useful for ruling out VTE.

Multi-Contrast Differentiation by Dual-Energy Spectral CT Angiography in a Patient with Pulmonary Barium Granulomas

Barium inhalation usually relates to accidental aspiration during radiological procedures with an oral contrast agent. When present, barium lung deposits are visible as high-density opacities on chest X-ray or CT scan due to high atomic number, and they may be indistinguishable from calcifications. Dual-layer spectral CT has shown good material differentiation capabilities, due to its increased high-Z element range and smaller spectral separation between low- and high-energy spectral data. We present the case of a 17-year-old female with a history of tracheoesophageal fistula, who underwent chest CT angiography on a dual-layer spectral platform. Despite the close Z numbers and K-edge energy levels of the two different contrast materials, spectral CT was able to identify barium lung deposits from a previous swallowing study and to clearly distinguish them from calcium and the surrounding iodine-containing structures.

Diagnosis of Uric Acid-Based Urine Sedimentation in the Bladder Using Dual-Energy CT

Urine sedimentation in the bladder can occur in various circumstances and can lead to urinary obstruction/stasis with associated pain. It is usually diagnosed with an ultrasound; however, CT is also used to assess the amount and to further check for urinary stones. Depending on the composition, urine sedimentation and stones can be treated medically by alkalinisation of the urine with potassium sodium hydrogen citrate in the case of uric acid-based sedimentation/stones. Due to technical developments and improved material differentiation and characterisation in CT imaging, dual-energy CT allows for differentiation of uric acid from calcium, which can be used for sedimentation/stone composition analysis. Subsequently, treatment decisions can be made based on the findings in dual-energy CT.

Free-breathing accelerated whole-body MRI using an automated workflow: Comparison with conventional breath-hold sequences

Whole-body magnetic resonance imaging (MRI) has become increasingly popular in oncology. However, the long acquisition time might hamper its widespread application. We sought to assess and compare free-breathing sequences with conventional breath-hold examinations in whole-body MRI using an automated workflow process. This prospective study consisted of 20 volunteers and six patients with a variety of pathologies who had undergone whole-body 1.5-T MRI that included T1-weighted radial and Dixon volumetric interpolated breath-hold examination sequences. Free-breathing sequences were operated by using an automated user interface. Image quality, diagnostic confidence, and image noise were evaluated by two experienced radiologists. Additionally, signal-to-noise ratio was measured. Diagnostic performance for the overall detection of pathologies was assessed using the area under the receiver operating characteristics curve (AUC). Study participants were asked to rate their examination experiences in a satisfaction survey. MR free-breathing scans were rated as at least equivalent to conventional MR scans in more than 92% of cases, showing high overall diagnostic accuracy (95% [95% CI 92-100]) and performance (AUC 0.971, 95% CI 0.942-0.988; p < 0.0001) for the assessment of pathologies at simultaneously reduced examination times (25 ± 2 vs. 32 ± 3 min; p < 0.0001). Interrater agreement was excellent for both free-breathing (ϰ = 0.96 [95% CI 0.88-1.00]) and conventional scans (ϰ = 0.93 [95% CI 0.84-1.00]). Qualitative and quantitative assessment for image quality, image noise, and diagnostic confidence did not differ between the two types of MR image acquisition (all p > 0.05). Scores for patient satisfaction were significantly better for free-breathing compared with breath-hold examinations (p = 0.0145), including significant correlations for the grade of noise (r = 0.79, p < 0.0001), tightness (r = 0.71, p < 0.0001), and physical fatigue (r = 0.52, p = 0.0065). In summary, free-breathing whole-body MRI in tandem with an automated user interface yielded similar diagnostic performance at equivalent image quality and shorter acquisition times compared to conventional breath-hold sequences.

Computed Tomography Radiomics to Differentiate Intrahepatic Cholangiocarcinoma and Hepatocellular Carcinoma

AIMS

Intrahepatic cholangiocarcinoma (iCCA) and hepatocellular carcinoma (HCC) differ in prognosis and treatment. We aimed to non-invasively differentiate iCCA and HCC by means of radiomics extracted from contrast-enhanced standard-of-care computed tomography (CT).

MATERIALS AND METHODS

In total, 94 patients (male, n = 68, mean age 63.3 ± 12.4 years) with histologically confirmed iCCA (n = 47) or HCC (n = 47) who underwent contrast-enhanced abdominal CT between August 2014 and November 2021 were retrospectively included. The enhancing tumour border was manually segmented in a clinically feasible way by defining three three-dimensional volumes of interest per tumour. Radiomics features were extracted. Intraclass correlation analysis and Pearson metrics were used to stratify robust and non-redundant features with further feature reduction by LASSO (least absolute shrinkage and selection operator). Independent training and testing datasets were used to build four different machine learning models. Performance metrics and feature importance values were computed to increase the models' interpretability.

RESULTS

The patient population was split into 65 patients for training (iCCA, n = 32) and 29 patients for testing (iCCA, n = 15). A final combined feature set of three radiomics features and the clinical features age and sex revealed a top test model performance of receiver operating characteristic (ROC) area under the curve (AUC) = 0.82 (95% confidence interval =0.66-0.98; train ROC AUC = 0.82) using a logistic regression classifier. The model was well calibrated, and the Youden J Index suggested an optimal cut-off of 0.501 to discriminate between iCCA and HCC with a sensitivity of 0.733 and a specificity of 0.857.

CONCLUSIONS

Radiomics-based imaging biomarkers can potentially help to non-invasively discriminate between iCCA and HCC.

CT-radiomics and clinical risk scores for response and overall survival prognostication in TACE HCC patients

We aimed to identify hepatocellular carcinoma (HCC) patients who will respond to repetitive transarterial chemoembolization (TACE) to improve the treatment algorithm. Retrospectively, 61 patients (mean age, 65.3 years ± 10.0 [SD]; 49 men) with 94 HCC mRECIST target-lesions who had three consecutive TACE between 01/2012 and 01/2020 were included. Robust and non-redundant radiomics features were extracted from the 24 h post-embolization CT. Five different clinical TACE-scores were assessed. Seven different feature selection methods and machine learning models were used. Radiomics, clinical and combined models were built to predict response to TACE on a lesion-wise and patient-wise level as well as its impact on overall-survival prognostication. 29 target-lesions of 19 patients were evaluated in the test set. Response rates were 37.9% (11/29) on the lesion-level and 42.1% (8/19) on the patient-level. Radiomics top lesion-wise response prognostications was AUC 0.55-0.67. Clinical scores revealed top AUCs of 0.65-0.69. The best working model combined the radiomic feature LargeDependenceHighGrayLevelEmphasis and the clinical score mHAP_II_score_group with AUC = 0.70, accuracy = 0.72. We transferred this model on a patient-level to achieve AUC = 0.62, CI = 0.41-0.83. The two radiomics-clinical features revealed overall-survival prognostication of C-index = 0.67. In conclusion, a random forest model using the radiomic feature LargeDependenceHighGrayLevelEmphasis and the clinical mHAP-II-score-group seems promising for TACE response prognostication.

Reduction of radiation dose using real-time visual feedback dosimetry during angiographic interventions

This prospective study sought to evaluate potential savings of radiation dose to medical staff using real-time dosimetry coupled with visual radiation dose feedback during angiographic interventions. For this purpose, we analyzed a total of 214 angiographic examinations that consisted of chemoembolizations and several other types of therapeutic interventions. The Unfors RaySafe i2 dosimeter was worn by the interventionalist at chest height over the lead protection. A total of 110 interventions were performed with real-time radiation dosimetry allowing the interventionalist to react upon higher x-ray exposure and 104 examinations served as the comparative group without real-time radiation monitoring. By using the real-time display during interventions, the overall mean operator radiation dose decreased from 3.67 (IQR, 0.95-23.01) to 2.36 μSv (IQR, 0.52-12.66) (-36%; p = 0.032) at simultaneously reduced operator exposure time by 4.5 min (p = 0.071). Dividing interventions into chemoembolizations and other types of therapeutic interventions, radiation dose decreased from 1.31 (IQR, 0.46-3.62) to 0.95 μSv (IQR, 0.53-3.11) and from 24.39 (IQR, 12.14-63.0) to 10.37 μSv (IQR, 0.85-36.84), respectively, using live-screen dosimetry (p ≤ 0.005). Radiation dose reductions were also observed for the participating assistants, indicating that they could also benefit from real-time visual feedback dosimetry during interventions (-30%; p = 0.039). Integration of real-time dosimetry into clinical processes might be useful in reducing occupational radiation exposure time during angiographic interventions. The real-time visual feedback raised the awareness of interventionalists and their assistants to the potential danger of prolonged radiation exposure leading to the adoption of radiation-sparing practices. Therefore, it might create a safer environment for the medical staff by keeping the applied radiation exposure as low as possible.

Homoarginine in the cardiovascular system: Pathophysiology and recent developments

Upcoming experimental and epidemiological data have identified the endogenous non-proteinogenic amino acid L-homoarginine (L-hArg) not only as a novel biomarker for cardiovascular disease but also as being directly involved in the pathogenesis of cardiac dysfunction. The association of low L-hArg levels with adverse cardiovascular events and mortality has proposed the idea of nutritional supplementation to rescue pathways inversely associated with cardiovascular health. Subsequent clinical and experimental studies contributed significantly to our knowledge of potential effects on the cardiorenal axis, acting either as a biomarker or a cardiovascular active agent. In this review article, we provide a comprehensive summary of the L-hArg metabolism, pathophysiological aspects, and current developments in the field of experimental and clinical evidence in favor of protective cardiovascular effects. Establishing a reliable biomarker to identify patients at high risk to die of cardiovascular disease represents one of the main goals for tackling this disease and providing individual therapeutic guidance.

Imaging biomarkers to stratify lymph node metastases in abdominal CT - Is radiomics superior to dual-energy material decomposition?

Purpose

To assess the potential of radiomic features in comparison to dual-energy CT (DECT) material decomposition to objectively stratify abdominal lymph node metastases.

Materials and methods

In this retrospective study, we included 81 patients (m, 57; median age, 65 (interquartile range, 58.7-73.3) years) with either lymph node metastases (n = 36) or benign lymph nodes (n = 45) who underwent contrast-enhanced abdominal DECT between 06/2015-07/2019. All malignant lymph nodes were classified as unequivocal according to RECIST criteria and confirmed by histopathology, PET-CT or follow-up imaging. Three investigators segmented lymph nodes to extract DECT and radiomics features. Intra-class correlation analysis was applied to stratify a robust feature subset with further feature reduction by Pearson correlation analysis and LASSO. Independent training and testing datasets were applied on four different machine learning models. We calculated the performance metrics and permutation-based feature importance values to increase interpretability of the models. DeLong test was used to compare the top performing models.

Results

Distance matrices and t-SNE plots revealed clearer clusters using a combination of DECT and radiomic features compared to DECT features only. Feature reduction by LASSO excluded all DECT features of the combined feature cohort. The top performing radiomic features model (AUC = 1.000; F1 = 1.000; precision = 1.000; Random Forest) was significantly superior to the top performing DECT features model (AUC = 0.942; F1 = 0.762; precision = 0.800; Stochastic Gradient Boosting) (DeLong < 0.001).

Conclusion

Imaging biomarkers have the potential to stratify unequivocal lymph node metastases. Radiomics models were superior to DECT material decomposition and may serve as a support tool to facilitate stratification of abdominal lymph node metastases.

Artificial intelligence, machine learning and deep learning in musculoskeletal imaging: Current applications

Artificial intelligence is rapidly expanding in all technological fields. The medical field, and especially diagnostic imaging, has been showing the highest developmental potential. Artificial intelligence aims at human intelligence simulation through the management of complex problems. This review describes the technical background of artificial intelligence, machine learning, and deep learning. The first section illustrates the general potential of artificial intelligence applications in the context of request management, data acquisition, image reconstruction, archiving, and communication systems. In the second section, the prospective of dedicated tools for segmentation, lesion detection, automatic diagnosis, and classification of musculoskeletal disorders is discussed.

Systematic evaluation of imaging techniques and baseline characteristics in patients with suspected vasculitis

Purpose

To assess the diagnostic value of different imaging modalities in distinguishing systemic vasculitis from other internal and immunological diseases.

Methods

This retrospective study included 134 patients with suspected vasculitis who underwent ultrasound, magnetic resonance imaging (MRI), or ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) between 01/2010 and 01/2019, finally consisting of 70 individuals with vasculitis. The main study parameter was the confirmation of the diagnosis using one of the three different imaging modalities, with the adjudicated clinical and histopathological diagnosis as the gold standard. A secondary parameter was the morphological appearance of the vessel affected by vasculitis.

Results

Patients with systemic vasculitis had myriad clinical manifestations with joint pain as the most common symptom. We found significant correlations between different imaging findings suggestive of vasculitis and the final adjudicated clinical diagnosis. In this context, on MRI, vessel wall thickening, edema, and diameter differed significantly between vasculitis and non-vasculitis groups (p < 0.05). Ultrasound revealed different findings that may serve as red flags in identifying patients with vasculitis, such as vascular occlusion or halo sign (p = 0.02 vs. non-vasculitis group). Interestingly, comparing maximal standardized uptake values from PET/CT examinations with vessel wall thickening or vessel diameter did not result in significant differences (p > 0.05).

Conclusions

We observed significant correlations between different imaging findings suggestive of vasculitis on ultrasound or MRI and the final adjudicated diagnosis. While ultrasound and MRI were considered suitable imaging methods for detecting and discriminating typical vascular changes, ¹⁸F-FDG PET/CT requires careful timing and patient selection given its moderate diagnostic accuracy.

Dual-Energy CT for the Detection of Portal Vein Thrombosis: Improved Diagnostic Performance Using Virtual Monoenergetic Reconstructions

Purpose: To investigate the diagnostic performance of noise-optimized virtual monoenergetic images (VMI+) in dual-energy CT (DECT) of portal vein thrombosis (PVT) compared to standard reconstructions. Method: This retrospective, single-center study included 107 patients (68 men; mean age, 60.1 ± 10.7 years) with malignant or cirrhotic liver disease and suspected PVT who had undergone contrast-enhanced portal-phase DECT of the abdomen. Linearly blended (M_0.6) and virtual monoenergetic images were calculated using both standard VMI and noise-optimized VMI+ algorithms in 20 keV increments from 40 to 100 keV. Quantitative measurements were performed in the portal vein for objective contrast-to-noise ratio (CNR) calculation. The image series showing the greatest CNR were further assessed for subjective image quality and diagnostic accuracy of PVT detection by two blinded radiologists. Results: PVT was present in 38 subjects. VMI+ reconstructions at 40 keV revealed the best objective image quality (CNR, 9.6 ± 4.3) compared to all other image reconstructions (p < 0.01). In the standard VMI series, CNR peaked at 60 keV (CNR, 4.7 ± 2.1). Qualitative image parameters showed the highest image quality rating scores for the 60 keV VMI+ series (median, 4) (p ≤ 0.03). The greatest diagnostic accuracy for the diagnosis of PVT was found for the 40 keV VMI+ series (sensitivity, 96%; specificity, 96%) compared to M_0.6 images (sensitivity, 87%; specificity, 92%), 60 keV VMI (sensitivity, 87%; specificity, 97%), and 60 keV VMI+ reconstructions (sensitivity, 92%; specificity, 97%) (p ≤ 0.01). Conclusions: Low-keV VMI+ reconstructions resulted in significantly improved diagnostic performance for the detection of PVT compared to other DECT reconstruction algorithms.

Comprehensive comparison of three different workstations for accurate planning of endovascular stent implantation in patients with thoracic aortic aneurysms

Purpose

To assess the diagnostic precision of three different workstations for measuring thoracic aortic aneurysms (TAAs) in vivo and ex vivo using either pre-interventional computed tomography angiography scans (CTA) or a specifically designed phantom model.

Methods

This retrospective study included 23 patients with confirmed TAA on routinely performed CTAs. In addition to phantom tube diameters, one experienced blinded radiologist evaluated the dimensions of TAAs on three different workstations in two separate rounds. Precision was assessed by calculating measurement errors. In addition, correlation analysis was performed using Pearson correlation.

Results

Measurements acquired at the Siemens workstation deviated by 3.54% (range, 2.78–4.03%; p = 0.14) from the true size, those at General Electric by 4.05% (range, 1.46–7.09%; p < 0.0001), and at TeraRecon by 4.86% (range, 3.22–6.45%; p < 0.0001). Accordingly, Siemens provided the most precise workstation at simultaneously most fluctuating values (scattering of 4.46%). TeraRecon had the smallest fluctuation (scattering of 2.83%), but the largest deviation from the true size of the phantom. The workstation from General Electric showed a scattering of 2.94%. The highest overall correlation between the 1st and 2nd rounds was observed with measurements from Siemens (r = 0.898), followed by TeraRecon (r = 0.799), and General Electric (r = 0.703). Repetition of measurements reduced processing times by 40% when using General Electric, by 20% with Siemens, and by 18% with TeraRecon.

Conclusions

In conclusion, all three workstations facilitated precise assessment of dimensions in the majority of cases at simultaneously high reproducibility, ensuring accurate pre-interventional planning of thoracic endovascular aortic repair.

•

Pre-interventional planning of TEVAR in patients with TAAs using CTA is feasible.

•

All three workstations facilitated accurate measurements in vivo and ex vivo.

•

Repetition of measurements resulted in faster processing due to learning effects.

Impact of Intravenously Injected Contrast Agent on Bone Mineral Density Measurement in Dual-Source Dual-Energy CT

PURPOSE

To assess the influence of intravenously injected contrast agent on bone mineral density (BMD) assessment in dual-source dual-energy CT.

METHODS

This retrospective study included 1,031 patients (mean age, 53 ± 7 years; 519 women) who had undergone third-generation dual-source dual-energy CT in context of tumor staging between January 2019 and December 2019. Dedicated postprocessing software based on material decomposition was used for phantomless volumetric BMD assessment of trabecular bone of the lumbar spine. Volumetric trabecular BMD values derived from unenhanced and contrast-enhanced portal venous phase were compared by calculating correlation and agreement analyses using Pearson product-moment correlation, linear regression, and Bland-Altman plots.

RESULTS

Mean BMD values were 115.53 ± 37.23 and 116.10 ± 37.78 mg/cm³ in unenhanced and contrast-enhanced dual-energy CT series, respectively. Values from contrast-enhanced portal venous phase differed not significantly from those of the unenhanced phase (p = 0.44) and showed high correlation (r = 0.971 [95% CI, 0.969-0.973]) with excellent agreement in Bland-Altman plots. Mean difference of the two phases was 0.61 mg/cm³ (95% limits of agreement, -17.14 and 18.36 mg/cm³).

CONCLUSION

Portal venous phase dual-source dual-energy CT allows for accurate opportunistic BMD assessment of trabecular bone of the lumbar spine compared to unenhanced imaging. Therefore, dual-source CT may provide greater flexibility regarding BMD assessment in clinical routine and reduce radiation exposure by avoiding additional osteodensitometry examinations, as contrast-enhanced CT scans in context of tumor staging are increasingly performed in dual-energy mode.

Lung Opacity and Coronary Artery Calcium Score: A Combined Tool for Risk Stratification and Outcome Prediction in COVID-19 Patients

PURPOSE

To assess and correlate pulmonary involvement and outcome of SARS-CoV-2 pneumonia with the degree of coronary plaque burden based on the CAC-DRS classification (Coronary Artery Calcium Data and Reporting System).

METHODS

This retrospective study included 142 patients with confirmed SARS-CoV-2 pneumonia (58 ± 16 years; 57 women) who underwent non-contrast CT between January 2020 and August 2021 and were followed up for 129 ± 72 days. One experienced blinded radiologist analyzed CT series for the presence and extent of calcified plaque burden according to the visual and quantitative HU-based CAC-DRS Score. Pulmonary involvement was automatically evaluated with a dedicated software prototype by another two experienced radiologists and expressed as Opacity Score.

RESULTS

CAC-DRS Scores derived from visual and quantitative image evaluation correlated well with the Opacity Score (r=0.81, 95% CI 0.76-0.86, and r=0.83, 95% CI 0.77-0.89, respectively; p<0.0001) with higher correlation in severe than in mild stage SARS-CoV-2 pneumonia (p<0.0001). Combined, CAC-DRS and Opacity Scores revealed great potential to discriminate fatal outcomes from a mild course of disease (AUC 0.938, 95% CI 0.89-0.97), and the need for intensive care treatment (AUC 0.801, 95% CI 0.77-0.83). Visual and quantitative CAC-DRS Scores provided independent prognostic information on all-cause mortality (p=0.0016 and p<0.0001, respectively), both in univariate and multivariate analysis.

CONCLUSIONS

Coronary plaque burden is strongly correlated to pulmonary involvement, adverse outcome, and death due to respiratory failure in patients with SARS-CoV-2 pneumonia, offering great potential to identify individuals at high risk.

Optimization of contrast material administration for coronary CT angiography using a software-based test-bolus evaluation algorithm

OBJECTIVES

To evaluate the benefit of a prototype circulation time-based test bolus evaluation algorithm for the individualized optimal timing of contrast media (CM) delivery in patients undergoing coronary CT angiography (CCTA).

METHODS

Thirty-two patients (62 ± 16 years) underwent CCTA using a prototype bolus evaluation tool to determine the optimal time-delay for CM administration. Contrast attenuation, signal-to-noise ratio (SNR), objective, and subjective image quality were evaluated by two independent radiologists. Results were compared to a control cohort (matched for age, sex, body mass index, and tube voltage) of patients who underwent CCTA using the generic test bolus peak attenuation +4 s protocol as scan delay.

RESULTS

In the study group, the mean time delay to CCTA acquisition was significantly longer (26.0 ± 2.9 s) compared to the control group (23.1 ± 3.5 s; p < 0.01). In the study group, SNR improvement was seen in the right coronary artery (17.5 vs 13; p = 0.028), the left main (15.3 vs 12.3; p = 0.027), and the left anterior descending artery (18.5 vs 14.1; p = 0.048). Subjective image quality was rated higher in the study group (4.75 ± 0.7 vs 3.64 ± 0.5; p < 0.001).

CONCLUSIONS

The prototype test bolus evaluation algorithm provided a reliable patient-specific scan delay for CCTA that ensured homogenous vascular attenuation, improvement in objective and subjective image quality, and avoidance of beam hardening artifacts.

ADVANCES IN KNOWLEDGE

The prototype contrast bolus evaluation and optimization tool estimated circulation time-based time-delay improves the overall quality of CCTA.

Development and evaluation of a computer-based decision support system for diffuse lung diseases at high-resolution computed tomography

BACKGROUND

High-resolution computed tomography (HRCT) is essential in narrowing the possible differential diagnoses of diffuse and interstitial lung diseases.

PURPOSE

To investigate the value of a novel computer-based decision support system (CDSS) for facilitating diagnosis of diffuse lung diseases at HRCT.

MATERIAL AND METHODS

A CDSS was developed that includes about 100 different illustrations of the most common HRCT signs and patterns and describes the corresponding pathologies in detail. The logical set-up of the software facilitates a structured evaluation. By selecting one or more CT patterns, the program generates a ranked list of the most likely differential diagnoses. Three independent and blinded radiology residents initially evaluated 40 cases with different lung diseases alone; after at least 12 weeks, observers re-evaluated all cases using the CDSS.

RESULTS

In 40 patients, a total of 113 HRCT patterns were evaluated. The percentage of correctly classified patterns was higher with CDSS (96.8%) compared to assessment without CDSS (90.3%; P < 0.01). Moreover, the percentage of correct diagnosis (81.7% vs. 64.2%) and differential diagnoses (89.2% vs. 38.3%) were superior with CDSS compared to evaluation without CDSS (both P < 0.01).

CONCLUSION

Addition of a CDSS using a structured approach providing explanations of typical HRCT patterns and graphical illustrations significantly improved the performance of trainees in characterizing and correctly identifying diffuse lung diseases.

Diagnostic performance and predictive value of D-dimer testing in patients referred to the emergency department for suspected myocardial infarction

PURPOSE

The study sought to assess the performance of D-dimer testing for the diagnosis of acute coronary syndrome (ACS) and prediction of outcomes in patients admitted for suspected myocardial infarction (MI).

RESULTS

A total of 3,557 patients with suspected ACS presenting to a single center with a broad range of symptoms including atypical chest pain were retrospectively recruited between 02/2012-01/2019. Of the study cohort, 435 patients had unstable angina (UA), 420 non-ST-segment elevation myocardial infarction (NSTEMI), 22 ST-segment elevation myocardial infarction (STEMI), and 2,680 non-coronary chest pain. Plasma D-dimer concentrations in patients with hs-cTnT >14 ng/L differed significantly from those with hs-cTnT <14 ng/L (1.5 ± 3.6 mg/L vs. 0.5 ± 0.8 mg/L; p<0.0001). Positive predictive value for a final diagnosis of ACS increased proportionally to rising D-dimer concentrations. The area under the curve (AUC) to discriminate STEMI from non-coronary chest pain (AUC 0.729, 95% confidence interval [CI] 0.71-0.75) was moderate and differed not significantly to UA (AUC 0.595, 95% CI 0.58-0.61; p=0.0653). During a median follow-up of 29 months, higher D-dimer was associated with a significantly increased risk of recurrent MI (quartile 4 vs. 1: hazard ratio [HR], 6.9 [95% CI 1.2-39.9]; p<0.0001) and higher all-cause mortality (HR, 17.4 [95% CI 4.3-69.9]; p<0.0001). D-dimer was an independent predictor of all-cause mortality (p<0.0001) and subsequent MI events (p=0.0333).

CONCLUSIONS

D-dimer testing revealed great potential to provide independent prognostic information on recurrent MI and all-cause mortality. However, D-dimers do not improve the diagnostic performance except if values exceed the 95^th percentile.

A prospective randomized trial comparing microwave and radiofrequency ablation for the treatment of liver metastases using a dual ablation system ─ The Mira study

Purpose

The aim of this study was to prospectively compare the therapy response and safety of microwave (MWA) and radiofrequency ablation (RFA) for the treatment of liver metastases using a dual ablation system.

Methods

Fifty patients with liver metastases (23 men, mean age: 62.8 ± 11.8 years) were randomly assigned to MWA or RFA for thermal ablation using a one generator dual ablation system. Magnetic resonance imaging (MRI) was acquired before treatment and 24 h post ablation. The morphologic responses to treatment regarding size, volume, necrotic areas, and diffusion characteristics were evaluated by MRI. Imaging follow-up was obtained for one year in three months intervals, whereas clinical follow-up was obtained for two years in all patients.

Results

Twenty-six patients received MWA and 24 patients received RFA (mean diameter: 1.6 cm, MWA: 1.7 cm, RFA: 1.5 cm). The mean volume 24 h after ablation was 37.0 cm³ (MWA: 50.5 cm³, RFA: 22.9 cm³, P < 0.01). The local recurrence rate was 0% (0/26) in the MWA-group and 8.3% (2/24) in the RFA-group (P = 0.09). The rate of newly developed malignant formations was 38.0% (19/50) for both groups (MWA: 38.4%, RFA: 37.5%, P = 0.07). The overall survival rate was 70.0% (35/50) after two years (MWA: 76.9%, RFA: 62.5%, P = 0.60). No major complications were reported.

Conclusion

In conclusion, MWA and RFA are both safe and effective methods for the treatment of liver metastases with MWA generating greater volumes of ablation. No significant differences were found for overall survival, rate of neoplasm, or major complications between both groups.

•

A dual ablation system allows for MWA and RFA treatment using the same hardware.

•

Both methods are safe and effective for the treatment of liver metastases.

•

MWA generates greater volumes of ablation and larger ablative margins compared to RFA.

Tumorous tissue characterization using integrated 18F-FDG PET/dual-energy CT in lung cancer: Combining iodine enhancement and glycolytic activity

Positron emission tomography/computed tomography (PET/CT) with 18F-fluorodeoxyglucose (18F-FDG) has become the method of choice for tumor staging in lung cancer patients with improved diagnostic accuracy for the evaluation of lymph node involvement and distant metastasis. Due to its spectral capabilities, dual-energy CT (DECT) employs a material decomposition algorithm enabling precise quantification of iodine concentrations in distinct tissues. This technique enhances the characterization of tumor blood supply and has demonstrated promising results for the assessment of therapy response in patients with lung cancer. Several studies have demonstrated that DECT provides additional value to the PET-based evaluation of glycolytic activity, especially for the evaluation of therapy response and follow-up of patients with lung cancer. The combination of PET and DECT in a single scanner system enables the simultaneous assessment of glycolytic activity and iodine enhancement, offering further insight to the characterization of tumorous tissues. Recently a new approach of a novel integrated PET/DECT was investigated in a pilot study on patients with non-small cell lung cancer (NSCLC). The study showed a moderate correlation between PET-based standard uptake values (SUV) and DECT-based iodine densities in the evaluation of lung tumorous tissue but with limited assessment of lymph nodes. The following review on tumorous tissue characterization using PET and DECT imaging describes the strengths and limitations of this novel technique.

Prospective Evaluation of the First Integrated Positron Emission Tomography/Dual-Energy Computed Tomography System in Patients With Lung Cancer

PURPOSE

The aim of this pilot study was to prospectively evaluate the first integrated positron emission tomography (PET)/dual-energy computed tomography (DECT) system performance in patients with non-small cell lung cancer (NSCLC).

MATERIALS AND METHODS

In this single-center, prospective trial, consecutive patients with NSCLC referred for a PET study between May 2017 and June 2018 were enrolled. All patients received contrast-enhanced imaging on a clinical PET/DECT system. Data analysis included PET-based standard uptake values (SUVmax) and DECT-based iodine densities of tumor masses, lymph nodes, and distant metastases. Results were analyzed using correlation tests and receiver operating characteristics curves.

RESULTS

The study population was composed of 21 patients (median age 62 y, 14 male patients). A moderate positive correlation was found between iodine density values (2.2 mg/mL) and SUVmax (10.5) in tumor masses (ρ=0.53, P<0.01). Iodine density values (2.3 mg/mL) and SUVmax (5.4) of lymph node metastases showed a weak positive correlation (ρ=0.23, P=0.14). In addition, iodine quantification analysis provided no added value in differentiating between pathologic and nonpathologic lymph nodes with an area under the curve (AUC) of 0.55 using PET-based SUVmax as the reference standard. A weak positive correlation was observed between iodine density (2.2 mg/mL) and SUVmax in distant metastases (14.9, ρ=0.23, P=0.52).

CONCLUSIONS

The application of an integrated PET/DECT system in lung cancer might provide additional insights in the assessment of tumor masses. However, the added value of iodine density quantification for the evaluation of lymph nodes and distant metastases seems limited.

Accuracy and precision of volumetric bone mineral density assessment using dual-source dual-energy versus quantitative CT: a phantom study

Background

Dual-source dual-energy computed tomography (DECT) offers the potential for opportunistic osteoporosis screening by enabling phantomless bone mineral density (BMD) quantification. This study sought to assess the accuracy and precision of volumetric BMD measurement using dual-source DECT in comparison to quantitative CT (QCT).

Methods

A validated spine phantom consisting of three lumbar vertebra equivalents with 50 (L1), 100 (L2), and 200 mg/cm³ (L3) calcium hydroxyapatite (HA) concentrations was scanned employing third-generation dual-source DECT and QCT. While BMD assessment based on QCT required an additional standardised bone density calibration phantom, the DECT technique operated by using a dedicated postprocessing software based on material decomposition without requiring calibration phantoms. Accuracy and precision of both modalities were compared by calculating measurement errors. In addition, correlation and agreement analyses were performed using Pearson correlation, linear regression, and Bland-Altman plots.

Results

DECT-derived BMD values differed significantly from those obtained by QCT (p < 0.001) and were found to be closer to true HA concentrations. Relative measurement errors were significantly smaller for DECT in comparison to QCT (L1, 0.94% versus 9.68%; L2, 0.28% versus 5.74%; L3, 0.24% versus 3.67%, respectively). DECT demonstrated better BMD measurement repeatability compared to QCT (coefficient of variance < 4.29% for DECT, < 6.74% for QCT). Both methods correlated well to each other (r = 0.9993; 95% confidence interval 0.9984–0.9997; p < 0.001) and revealed substantial agreement in Bland-Altman plots.

Conclusions

Phantomless dual-source DECT-based BMD assessment of lumbar vertebra equivalents using material decomposition showed higher diagnostic accuracy compared to QCT.

Potential of high dimensional radiomic features to assess blood components in intraaortic vessels in non-contrast CT scans

Background

To assess the potential of radiomic features to quantify components of blood in intraaortic vessels to non-invasively predict moderate-to-severe anemia in non-contrast enhanced CT scans.

Methods

One hundred patients (median age, 69 years; range, 19–94 years) who received CT scans of the thoracolumbar spine and blood-testing for hemoglobin and hematocrit levels ± 24 h between 08/2018 and 11/2019 were retrospectively included. Intraaortic blood was segmented using a spherical volume of interest of 1 cm diameter with consecutive radiomic analysis applying PyRadiomics software. Feature selection was performed applying analysis of correlation and collinearity. The final feature set was obtained to differentiate moderate-to-severe anemia. Random forest machine learning was applied and predictive performance was assessed. A decision-tree was obtained to propose a cut-off value of CT Hounsfield units (HU).

Results

High correlation with hemoglobin and hematocrit levels was shown for first-order radiomic features (p < 0.001 to p = 0.032). The top 3 features showed high correlation to hemoglobin values (p) and minimal collinearity (r) to the top ranked feature Median (p < 0.001), Energy (p = 0.002, r = 0.387), Minimum (p = 0.032, r = 0.437). Median (p < 0.001) and Minimum (p = 0.003) differed in moderate-to-severe anemia compared to non-anemic state. Median yielded superiority to the combination of Median and Minimum (p(AUC) = 0.015, p(precision) = 0.017, p(accuracy) = 0.612) in the predictive performance employing random forest analysis. A Median HU value ≤ 36.5 indicated moderate-to-severe anemia (accuracy = 0.90, precision = 0.80).

Conclusions

First-order radiomic features correlate with hemoglobin levels and may be feasible for the prediction of moderate-to-severe anemia. High dimensional radiomic features did not aid augmenting the data in our exemplary use case of intraluminal blood component assessment.

Trial registration Retrospectively registered.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-021-00654-9.

Quantification of COVID-19 Opacities on Chest CT - Evaluation of a Fully Automatic AI-approach to Noninvasively Differentiate Critical Versus Noncritical Patients

Objectives

To evaluate the potential of a fully automatic artificial intelligence (AI)-driven computed tomography (CT) software prototype to quantify severity of COVID-19 infection on chest CT in relationship with clinical and laboratory data.

Methods

We retrospectively analyzed 50 patients with laboratory confirmed COVID-19 infection who had received chest CT between March and July 2020. Pulmonary opacifications were automatically evaluated by an AI-driven software and correlated with clinical and laboratory parameters using Spearman-Rho and linear regression analysis. We divided the patients into sub cohorts with or without necessity of intensive care unit (ICU) treatment. Sub cohort differences were evaluated employing Wilcoxon-Mann-Whitney-Test.

Results

We included 50 CT examinations (mean age, 57.24 years), of whom 24 (48%) had an ICU stay. Extent of COVID-19 like opacities on chest CT showed correlations (all p < 0.001 if not otherwise stated) with occurrence of ICU stay (R = 0.74), length of ICU stay (R = 0.81), lethal outcome (R = 0.56) and length of hospital stay (R = 0.33, p < 0.05). The opacities extent was correlated with laboratory parameters: neutrophil count (NEU) (R = 0.60), lactate dehydrogenase (LDH) (R = 0.60), troponin (TNTHS) (R = 0.55) and c-reactive protein (CRP) (R = 0.51). Differences (p < 0.001) between ICU group and non-ICU group concerned longer length of hospital stay (24.04 vs. 10.92 days), higher opacity score (12.50 vs. 4.96) and severity of laboratory data changes such as c-reactive protein (11.64 vs. 5.07 mg/dl, p < 0.01).

Conclusions

Automatically AI-driven quantification of opacities on chest CT correlates with laboratory and clinical data in patients with confirmed COVID-19 infection and may serve as non-invasive predictive marker for clinical course of COVID-19.