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.

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.

Comprehensive comparison of dual-energy computed tomography and magnetic resonance imaging for the assessment of bone marrow edema and fracture lines in acute vertebral fractures.

OBJECTIVES: To compare dual-energy CT (DECT) and MRI for assessing presence and extent of traumatic bone marrow edema (BME) and fracture line depiction in acute vertebral fractures. METHODS: Eighty-eight consecutive patients who underwent dual-source DECT and 3-T MRI of the spine were retrospectively analyzed. Five radiologists assessed all vertebrae for presence and extent of BME and for identification of acute fracture lines on MRI and, after 12 weeks, on DECT series. Additionally, image quality, image noise, and diagnostic confidence for overall diagnosis of acute vertebral fracture were assessed. Quantitative analysis of CT numbers was performed by a sixth radiologist. Two radiologists analyzed MRI and grayscale DECT series to define the reference standard. RESULTS: For assessing BME presence and extent, DECT showed high sensitivity (89% and 84%, respectively) and specificity (98% in both), and similarly high diagnostic confidence compared to MRI (2.30 vs. 2.32; range 0-3) for the detection of BME (p = .72). For evaluating acute fracture lines, MRI achieved high specificity (95%), moderate sensitivity (76%), and a significantly lower diagnostic confidence compared to DECT (2.42 vs. 2.62, range 0-3) (p < .001). A cutoff value of - 0.43 HU provided a sensitivity of 89% and a specificity of 90% for diagnosing BME, with an overall AUC of 0.96. CONCLUSIONS: DECT and MRI provide high diagnostic confidence and image quality for assessing acute vertebral fractures. While DECT achieved high overall diagnostic accuracy in the analysis of BME presence and extent, MRI provided moderate sensitivity and lower confidence for evaluating fracture lines. KEY POINTS: • In the setting of spinal trauma, dual-energy CT (DECT) is highly accurate in the evaluation of acute vertebral fractures and bone marrow edema presence and extent. • MRI provides moderate sensitivity and lower diagnostic confidence for the depiction of acute fracture lines, when compared to DECT, which might result in potentially inaccurate and underestimated severity assessment of injuries in certain cases when no fracture lines are visible on MRI. • DECT may represent a valid imaging alternative to MRI in specific settings of acute spinal trauma and in follow-up examinations, especially in elderly or unstable patients and in cases of subtle or complex orientated fracture lines.

Diagnostic accuracy of quantitative dual-energy CT-based volumetric bone mineral density assessment for the prediction of osteoporosis-associated fractures.

OBJECTIVES: To evaluate the predictive value of volumetric bone mineral density (BMD) assessment of the lumbar spine derived from phantomless dual-energy CT (DECT)-based volumetric material decomposition as an indicator for the 2-year occurrence risk of osteoporosis-associated fractures. METHODS: L1 of 92 patients (46 men, 46 women; mean age, 64 years, range, 19-103 years) who had undergone third-generation dual-source DECT between 01/2016 and 12/2018 was retrospectively analyzed. For phantomless BMD assessment, dedicated DECT postprocessing software using material decomposition was applied. Digital files of all patients were sighted for 2 years following DECT to obtain the incidence of osteoporotic fractures. Receiver operating characteristic (ROC) analysis was used to calculate cut-off values and logistic regression models were used to determine associations of BMD, sex, and age with the occurrence of osteoporotic fractures. RESULTS: A DECT-derived BMD cut-off of 93.70 mg/cm3 yielded 85.45% sensitivity and 89.19% specificity for the prediction to sustain one or more osteoporosis-associated fractures within 2 years after BMD measurement. DECT-derived BMD was significantly associated with the occurrence of new fractures (odds ratio of 0.8710, 95% CI, 0.091-0.9375, p < .001), indicating a protective effect of increased DECT-derived BMD values. Overall AUC was 0.9373 (CI, 0.867-0.977, p < .001) for the differentiation of patients who sustained osteoporosis-associated fractures within 2 years of BMD assessment. CONCLUSIONS: Retrospective DECT-based volumetric BMD assessment can accurately predict the 2-year risk to sustain an osteoporosis-associated fracture in at-risk patients without requiring a calibration phantom. Lower DECT-based BMD values are strongly associated with an increased risk to sustain fragility fractures. KEY POINTS: •Dual-energy CT-derived assessment of bone mineral density can identify patients at risk to sustain osteoporosis-associated fractures with a sensitivity of 85.45% and a specificity of 89.19%. •The DECT-derived BMD threshold for identification of at-risk patients lies above the American College of Radiology (ACR) QCT guidelines for the identification of osteoporosis (93.70 mg/cm3 vs 80 mg/cm3).

Diagnostic accuracy of color-coded virtual noncalcium reconstructions derived from portal venous phase dual-energy CT in the assessment of lumbar disk herniation.

OBJECTIVES: To investigate the diagnostic accuracy of color-coded contrast-enhanced dual-energy CT virtual noncalcium (VNCa) reconstructions for the assessment of lumbar disk herniation compared to unenhanced VNCa imaging. METHODS: A total of 91 patients were retrospectively evaluated (65 years ± 16; 43 women) who had undergone third-generation dual-source dual-energy CT and 3.0-T MRI within an examination interval up to 3 weeks between November 2019 and December 2020. Eight weeks after assessing unenhanced color-coded VNCa reconstructions for the presence and degree of lumbar disk herniation, corresponding contrast-enhanced portal venous phase color-coded VNCa reconstructions were independently analyzed by the same five radiologists. MRI series were additionally analyzed by one highly experienced musculoskeletal radiologist and served as reference standard. RESULTS: MRI depicted 210 herniated lumbar disks in 91 patients. VNCa reconstructions derived from contrast-enhanced CT scans showed similar high overall sensitivity (93% vs 95%), specificity (94% vs 95%), and accuracy (94% vs 95%) for the assessment of lumbar disk herniation compared to unenhanced VNCa images (all p > .05). Interrater agreement in VNCa imaging was excellent for both, unenhanced and contrast-enhanced CT (κ = 0.84 vs κ = 0.86; p > .05). Moreover, ratings for diagnostic confidence, image quality, and noise differed not significantly between unenhanced and contrast-enhanced VNCa series (all p > .05). CONCLUSIONS: Color-coded VNCa reconstructions derived from contrast-enhanced dual-energy CT yield similar diagnostic accuracy for the depiction of lumbar disk herniation compared to unenhanced VNCa imaging and therefore may improve opportunistic retrospective lumbar disk herniation assessment, particularly in case of staging CT examinations. KEY POINTS: • Color-coded dual-source dual-energy CT virtual noncalcium (VNCa) reconstructions derived from portal venous phase yield similar high diagnostic accuracy for the assessment of lumbar disk herniation compared to unenhanced VNCa CT series (94% vs 95%) with MRI serving as a standard of reference. • Diagnostic confidence, image quality, and noise levels differ not significantly between unenhanced and contrast-enhanced portal venous phase VNCa dual-energy CT series. • Dual-source dual-energy CT might have the potential to improve opportunistic retrospective lumbar disk herniation assessment in CT examinations performed for other indications through reconstruction of VNCa images.

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.

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.

Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study.

OBJECTIVES: To evaluate the performance of radiomic features extracted from high-resolution computed tomography (HRCT) for the differentiation between cholesteatoma and middle ear inflammation (MEI), and to investigate the impact of post-reconstruction harmonization and data resampling. METHODS: One hundred patients were included in this retrospective dual-center study: 48 with histology-proven cholesteatoma (center A: 23; center B: 25) and 52 with MEI (A: 27; B: 25). Radiomic features (co-occurrence and run-length matrix, absolute gradient, autoregressive model, Haar wavelet transform) were extracted from manually defined 2D-ROIs. The ten best features for lesion differentiation were selected using probability of error and average correlation coefficients. A multi-layer perceptron feed-forward artificial neural network (MLP-ANN) was used for radiomics-based classification, with histopathology serving as the reference standard (70% of cases for training, 30% for validation). The analysis was performed five times each on (a) unmodified data and on data that were (b) resampled to the same matrix size, and (c) corrected for acquisition protocol differences using ComBat harmonization. RESULTS: Using unmodified data, the MLP-ANN classification yielded an overall median area under the receiver operating characteristic curve (AUC) of 0.78 (0.72-0.84). Using original data from center A and resampled data from center B, an overall median AUC of 0.88 (0.82-0.99) was yielded, while using ComBat harmonized data, an overall median AUC of 0.89 (0.79-0.92) was revealed. CONCLUSION: Radiomic features extracted from HRCT differentiate between cholesteatoma and MEI. When using multi-centric data obtained with differences in CT acquisition parameters, data resampling and ComBat post-reconstruction harmonization clearly improve radiomics-based lesion classification. KEY POINTS: • Unenhanced high-resolution CT coupled with radiomics analysis may be useful for the differentiation between cholesteatoma and middle ear inflammation. • Pooling of data extracted from inhomogeneous CT datasets does not appear meaningful without further post-processing. • When using multi-centric CT data obtained with differences in acquisition parameters, post-reconstruction harmonization and data resampling clearly improve radiomics-based soft-tissue differentiation.

Incremental diagnostic value of color-coded virtual non-calcium dual-energy CT for the assessment of traumatic bone marrow edema of the scaphoid.

OBJECTIVES: To investigate the diagnostic accuracy of color-coded dual-energy CT virtual non-calcium (VNCa) reconstructions for the assessment of bone marrow edema (BME) of the scaphoid in patients with acute wrist trauma. METHODS: Our retrospective study included data from 141 patients (67 women, 74 men; mean age 43 years, range 19-80 years) with acute wrist trauma who had undergone third-generation dual-source dual-energy CT and 3-T MRI within 7 days. Eight weeks after assessment of conventional grayscale dual-energy CT scans for the presence of fractures, corresponding color-coded VNCa reconstructions were independently analyzed by the same six radiologists for the presence of BME. CT numbers on VNCa reconstructions were evaluated by a seventh radiologist. Consensus reading of MRI series by two additional radiologists served as the reference standard. RESULTS: MRI depicted 103 scaphoideal zones with BME in 76 patients. On qualitative analysis, VNCa images yielded high overall sensitivity (580/618 [94%]), specificity (1880/1920 [98%]), and accuracy (2460/2538 [97%]) for assessing BME as compared with MRI as reference standard. The interobserver agreement was excellent (κ = 0.98). CT numbers derived from VNCa images were significantly different in zones with and without edema (p < 0.001). A cutoff value of - 46 Hounsfield units provided a sensitivity of 91% and specificity of 97% for differentiating edematous scaphoid lesions. Receiver operating characteristic curve analysis revealed an overall area under the curve of 0.98. CONCLUSIONS: Qualitative and quantitative analyses showed excellent diagnostic accuracy of color-coded VNCa reconstructions for assessing traumatic BME of the scaphoid compared to MRI. KEY POINTS: • Color-coded virtual non-calcium (VNCa) reconstructions yield excellent diagnostic accuracy in assessing bone marrow edema of the scaphoid. • VNCa imaging enables detection of non-displaced fractures that are occult on standard grayscale CT. • Diagnostic confidence is comparable between VNCa imaging and MRI.

Assessment of thoracic disk herniation by using virtual noncalcium dual-energy CT in comparison with standard grayscale CT.

OBJECTIVES: To determine the diagnostic accuracy of dual-energy CT (DECT) virtual noncalcium (VNCa) reconstructions for assessing thoracic disk herniation compared to standard grayscale CT. METHODS: In this retrospective study, 87 patients (1131 intervertebral disks; mean age, 66 years; 47 women) who underwent third-generation dual-source DECT and 3.0-T MRI within 3 weeks between November 2016 and April 2020 were included. Five blinded radiologists analyzed standard DECT and color-coded VNCa images after a time interval of 8 weeks for the presence and degree of thoracic disk herniation and spinal nerve root impingement. Consensus reading of independently evaluated MRI series served as the reference standard, assessed by two separate experienced readers. Additionally, image ratings were carried out by using 5-point Likert scales. RESULTS: MRI revealed a total of 133 herniated thoracic disks. Color-coded VNCa images yielded higher overall sensitivity (624/665 [94%; 95% CI, 0.89-0.96] vs 485/665 [73%; 95% CI, 0.67-0.80]), specificity (4775/4990 [96%; 95% CI, 0.90-0.98] vs 4066/4990 [82%; 95% CI, 0.79-0.84]), and accuracy (5399/5655 [96%; 95% CI, 0.93-0.98] vs 4551/5655 [81%; 95% CI, 0.74-0.86]) for the assessment of thoracic disk herniation compared to standard CT (all p < .001). Interrater agreement was excellent for VNCa and fair for standard CT (ϰ = 0.82 vs 0.37; p < .001). In addition, VNCa imaging achieved higher scores regarding diagnostic confidence, image quality, and noise compared to standard CT (all p < .001). CONCLUSIONS: Color-coded VNCa imaging yielded substantially higher diagnostic accuracy and confidence for assessing thoracic disk herniation compared to standard CT. KEY POINTS: • Color-coded VNCa reconstructions derived from third-generation dual-source dual-energy CT yielded significantly higher diagnostic accuracy for the assessment of thoracic disk herniation and spinal nerve root impingement compared to standard grayscale CT. • VNCa imaging provided higher diagnostic confidence and image quality at lower noise levels compared to standard grayscale CT. • Color-coded VNCa images may potentially serve as a viable imaging alternative to MRI under circumstances where MRI is unavailable or contraindicated.

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.

Color-coded virtual non-calcium dual-energy CT for the depiction of bone marrow edema in patients with acute knee trauma: a multireader diagnostic accuracy study.

OBJECTIVES: To evaluate the diagnostic accuracy of dual-energy computed tomography (CT) virtual non-calcium (VNCa) reconstructions for the depiction of traumatic knee bone marrow edema. METHODS: Fifty-seven patients (mean age, 50 years; range, 20-82 years) with acute knee trauma further divided into 30 women and 27 men, who had undergone third-generation dual-source dual-energy CT and 3-T magnetic resonance imaging (MRI) within 7 days between January 2017 and May 2018, were retrospectively analyzed. Six radiologists, blinded to clinical and MRI information, independently analyzed conventional grayscale dual-energy CT series for fractures; after 8 weeks, readers evaluated color-coded VNCa reconstructions for the presence of bone marrow edema in six femoral and six tibial regions. Quantitative analysis of CT numbers on VNCa reconstructions was performed by a seventh radiologist. Two additional radiologists, blinded to clinical and CT information, analyzed MRI series in consensus to define the reference standard. Sensitivity, specificity, and the area under the curve (AUC) were the primary metrics of diagnostic accuracy. RESULTS: MRI revealed 197 areas with bone marrow edema (91/342 femoral, 106/342 tibial). In the qualitative analysis, VNCa showed high overall sensitivity (1108/1182 [94%]) and specificity (2789/2922 [95%]) for depicting bone marrow edema. The AUC was 0.96 (femur) and 0.97 (tibia). A cutoff value of - 51 Hounsfield units (HU) provided high sensitivity (102/106 [96%]) and specificity (229/236 [97%]) for differentiating tibial bone marrow edema. CONCLUSIONS: In both quantitative and qualitative analyses, dual-energy CT VNCa reconstructions yielded excellent diagnostic accuracy for depicting traumatic knee bone marrow edema compared with MRI. KEY POINTS: • Dual-energy CT (DECT) virtual non-calcium (VNCa) reconstructions are highly accurate in depicting bone marrow edema of the femur and tibia. • Diagnostic confidence, image noise, and image quality were rated as equivalent in VNCa reconstructions and MRI (magnetic resonance imaging) series. • VNCa images may serve as an alternative imaging approach to MRI.

Virtual Noncalcium Dual-Energy CT: Detection of Lumbar Disk Herniation in Comparison with Standard Gray-scale CT.

Purpose To assess the diagnostic performance of dual-energy CT with reconstruction of virtual noncalcium (VNCa) images for the detection of lumbar disk herniation compared with standard CT image reconstruction. Materials and Methods For this retrospective study, 41 patients (243 intervertebral disks; overall mean age, 68 years; 24 women [mean age, 68 years] and 17 men [mean age, 68 years]) underwent clinically indicated third-generation, dual-source, dual-energy CT and 3.0-T MRI within 2 weeks between March 2017 and January 2018. Six radiologists, blinded to clinical and MRI information, independently evaluated conventional gray-scale dual-energy CT series for the presence and degree of lumbar disk herniation and spinal nerve root impingement. After 8 weeks, readers reevaluated examinations by using color-coded VNCa reconstructions. MRI evaluated by two separate experienced readers, blinded to clinical and dual-energy CT information, served as the standard of reference. Sensitivity and specificity were the primary metrics of diagnostic performance. Results A total of 112 herniated lumbar disks were depicted at MRI. VNCa showed higher overall sensitivity (612 of 672 [91%] vs 534 of 672 [80%]) and specificity (723 of 786 [92%] vs 665 of 786 [85%]) for detecting lumbar disk herniation compared with standard CT (all comparisons, P < .001). Interreader agreement was excellent for VNCa and substantial for standard CT (κ = 0.82 vs 0.67; P < .001). VNCa achieved superior diagnostic confidence, image quality, and noise scores compared with standard CT (all comparisons, P < .001). Conclusion Color-coded dual-energy CT virtual noncalcium reconstructions show substantially higher diagnostic performance and confidence for depicting lumbar disk herniation compared with standard CT. © RSNA, 2018.

Dual-energy CT in early acute pancreatitis: improved detection using iodine quantification.

OBJECTIVES: To evaluate the diagnostic performance of a dual-energy computed tomography (DECT)-based technique using iodine quantification and fat fraction analysis for the diagnosis of early acute pancreatitis METHODS: In this retrospective study, 45 patients (35 men and 10 women; mean age, 54.9 ± 14.0 years) with early acute pancreatitis were included. Serum lipase levels and follow-up examinations served as the reference standard. A matched control group (n = 45) was assembled for evaluation of material decomposition values of normal pancreatic parenchyma. Three blinded radiologists independently interpreted all cases on conventional grayscale DECT series. In addition, readers re-evaluated all cases by manually performing region-of-interest (ROI) measurements on pancreatic-phase DECT material density images of the head, body, and tail of each patient's pancreas. Receiver operating characteristic (ROC) curve analysis was performed to estimate the optimal threshold for discriminating between inflammatory and normal pancreas parenchyma. RESULTS: DECT-based iodine density values showed significant differences between inflammatory (1.8 ± 0.3 mg/mL) and normal pancreatic parenchyma (2.7 ± 0.7 mg/mL) (p ≤ 0.01). Fat fraction measurements showed no significant differences (p = 0.08). The optimal iodine density threshold for the diagnosis of acute pancreatitis was 2.1 mg/mL with a sensitivity of 96% and specificity of 77%. Iodine quantification revealed an area under the curve (AUC) of 0.86, significantly higher compared to standard image evaluation of the radiologists (AUC, 0.80; sensitivity, 78%; specificity, 82%) (p < 0.01). CONCLUSION: DECT using iodine quantification allows for diagnosis of early acute pancreatitis with higher sensitivity compared to standard image evaluation. KEY POINTS: • Iodine density values showed significant differences between inflammatory and normal pancreatic parenchyma. • DECT using iodine quantification allows for diagnosis of early acute pancreatitis. • An iodine density of ≤ 2.1 mg/mL optimizes the diagnosis of acute pancreatitis.

Single- and dual-energy CT pulmonary angiography using second- and third-generation dual-source CT systems: comparison of radiation dose and image quality.

OBJECTIVES: To evaluate radiation exposure and image quality in matched patient cohorts for CT pulmonary angiography (CTPA) acquired in single- and dual-energy mode using second- and third-generation dual-source CT (DSCT) systems. METHODS: We retrospectively included 200 patients (mean age, 65.5 years ± 15.7 years) with suspected pulmonary embolism-equally divided into four study groups (n = 50) and matched by gender and body mass index. CTPA was performed with vendor-predefined second-generation (group A, 100-kV single-energy computed tomography (SECT); group B, 80/Sn140-kV dual-energy computed tomography (DECT)) or third-generation DSCT (group C, 100-kV SECT; group D, 90/Sn150-kV DECT) devices. Radiation metrics were assessed using a normalized scan range of 27.5 cm. For objective image quality evaluation, dose-independent figure-of-merit (FOM) contrast-to-noise ratios (CNRs) were calculated. Subjective image analysis included ratings for overall image quality, reader confidence, and image artifacts using five-point Likert scales. RESULTS: Calculations of the effective dose (ED) of radiation for a normalized scan range of 27.5 cm showed nonsignificant differences between SECT and DECT acquisitions for each scanner generation (p ≥ 0.253). The mean effective radiation dose was lower for third-generation groups C (1.5 mSv ± 0.8 mSv) and D (1.4 mSv ± 0.7 mSv) compared to second-generation groups A (2.5 mSv ± 0.9 mSv) and B (2.3 mSv ± 0.6 mSv) (both p ≤ 0.013). FOM-CNR measurements were highest for group D. Qualitative image parameters of overall image quality, reader confidence, and image artifacts showed nonsignificant differences among the four groups (p ≥ 0.162). CONCLUSIONS: Third-generation DSCT systems show lower radiation dose parameters for CTPA compared to second-generation DSCT. DECT can be performed with both scanner generations without radiation dose penalty or detrimental effects on image quality compared to SECT. KEY POINTS: • Radiation exposure showed nonsignificant differences between SECT and DECT for both DSCT scanner devices. • Dual-energy CTPA provides equivalent image quality compared to standard image acquisition. • Subjective image quality assessment was similar among the four study groups.

Comparison of Radiation Dose and Image Quality of Contrast-Enhanced Dual-Source CT of the Chest: Single-Versus Dual-Energy and Second-Versus Third-Generation Technology.

OBJECTIVE: The purpose of this study was to compare radiation dose and image quality of single- and dual-energy CT (SECT, DECT) examinations of the chest in matched cohorts for second and third-generation dual-source CT (DSCT) systems. MATERIALS AND METHODS: We analyzed 200 patients (100 men; mean age, 61.7 ± 14.8 years old; 100 women, mean age, 59.4 ± 15.1 years old), matched by sex and body mass index, who had undergone clinically indicated contrast-enhanced chest CT. Four study groups, each consisting of 50 patients, were evaluated. Contrast-enhanced chest CT was performed using vendor-preset second-generation DSCT (group A, 120-kV SECT; group C, 80/Sn140-kV DECT) or third-generation DSCT (group B, 90-kV SECT; group D, 90/Sn150-kV DECT) protocols. Radiation dose assessment was normalized to a scan range of 27.5 cm. Image quality was objectively analyzed using dose-independent figure-of-merit (FOM) contrast-to-noise ratio (CNR) calculations and subjectively evaluated by three independent radiologists. RESULTS: Direct comparison of effective radiation dose for second-generation DSCT groups A and C showed statistically significant lower radiation dose values for DECT compared with SECT acquisition (3.2 ± 1.2 mSv vs 2.3 ± 0.6 mSv, p ≤ 0.004), but differences between third-generation SECT and DECT were not significant (1.2 ± 0.9 mSv vs 1.3 ± 0.6 mSv, p = 0.412). FOM CNR analysis revealed highest values for third-generation DECT (p ≤ 0.043). Differences in subjective image quality between the four groups were not statistically significant (p ≥ 0.179). CONCLUSION: Contrast-enhanced DECT examinations of the chest can be performed routinely with second- and third-generation DSCT systems without either increased radiation exposure or decreased image quality compared with SECT acquisition.

Evaluation of a Computer-Aided Diagnosis System for Automated Bone Age Assessment in Comparison to the Greulich-Pyle Atlas Method: A Multireader Study.

OBJECTIVE: The aim of this study was to investigate a novel version of a computer-aided diagnosis (CAD) system developed for automated bone age (BA) assessment in comparison to the Greulich and Pyle method, regarding its accuracy and the influence of carpal bones on BA assessment. METHODS: Total BA, BA of the left distal radius, and BA of carpal bones in 305 patients were determined independently by 3 blinded radiologists and assessed by the CAD system. Pearson product-moment correlation, Bland-Altman plot, root-mean-square deviation, and further agreement analyses were computed. RESULTS: Mean total BA and BA of the distal radius showed high correlation between both approaches (r = 0.985 and r = 0.963). There was significantly higher correlation between values of total BA and BA of the distal radius (r = 0.969) compared with values of total BA and BA of carpal bones (r = 0.923). The assessment of carpal bones showed significantly lower interreader agreement compared with measurements of the distal radius (κ = 0.79 vs κ = 0.98). CONCLUSION: A novel version of a CAD system enables highly accurate automated BA assessment. The assessment of carpal bones revealed lower precision and interreader agreement. Therefore, methods determining BA without analyzing carpal bones may be more precise and accurate.

Optimisation of window settings for traditional and noise-optimised virtual monoenergetic imaging in dual-energy computed tomography pulmonary angiography.

OBJECTIVES: To define optimal window settings for displaying virtual monoenergetic images (VMI) of dual-energy CT pulmonary angiography (DE-CTPA). METHODS: Forty-five patients who underwent clinically-indicated third-generation dual-source DE-CTPA were retrospectively evaluated. Standard linearly-blended (M_0.6), 70-keV traditional VMI (M70), and 40-keV noise-optimised VMI (M40+) reconstructions were analysed. For M70 and M40+ datasets, the subjectively best window setting (width and level, B-W/L) was independently determined by two observers and subsequently related with pulmonary artery attenuation to calculate separate optimised values (O-W/L) using linear regression. Subjective evaluation of image quality (IQ) between W/L settings were assessed by two additional readers. Repeated measures of variance were performed to compare W/L settings and IQ indices between M_0.6, M70, and M40+. RESULTS: B-W/L and O-W/L for M70 were 460/140 and 450/140, and were 1100/380 and 1070/380 for M40+, respectively, differing from standard DE-CTPA W/L settings (450/100). Highest subjective scores were observed for M40+ regarding vascular contrast, embolism demarcation, and overall IQ (all p<0.001). CONCLUSIONS: Application of O-W/L settings is beneficial to optimise subjective IQ of VMI reconstructions of DE-CTPA. A width slightly less than two times the pulmonary trunk attenuation and a level approximately of overall pulmonary vessel attenuation are recommended. KEY POINTS: • Application of standard window settings for VMI results in inferior image perception. • No significant differences between B-W/L and O-W/L for M70/M40+ were observed. • O-W/L for M70 were 450/140 and were 1070/380 for M40+. • Improved subjective IQ characteristics were observed for VMI displayed with O-W/L.

Noise-Optimized Virtual Monoenergetic Dual-Energy CT Improves Diagnostic Accuracy for the Detection of Active Arterial Bleeding of the Abdomen.

PURPOSE: To evaluate diagnostic accuracy of a noise-optimized virtual monoenergetic imaging (VMI+) reconstruction technique for detection of active arterial abdominal bleeding on dual-energy (DE) CT angiography compared with standard image reconstruction. MATERIALS AND METHODS: DE CT angiography data sets of 71 patients (46 men; age 63.6 y ± 13.3) with suspected arterial bleeding of the abdomen or pelvis were reconstructed with standard linearly blended (F_0.5), VMI+, and traditional virtual monoenergetic imaging (VMI) algorithms in 10-keV increments from 40 to 100 keV. Attenuation measurements were performed in the descending aorta, area of hemorrhage, and feeding artery to calculate contrast-to-noise ratios (CNRs) in patients with active arterial bleeding. Based on quantitative image quality results, the best series for each reconstruction technique were chosen to analyze the diagnostic performance of 3 blinded radiologists. RESULTS: DE CT angiography showed acute arterial bleeding in 36 patients. Mean CNR was superior in 40-keV VMI+ compared with VMI series (all P < .001), which showed highest CNRs in 70-keV VMI and F_0.5 (21.6 ± 7.9, 12.9 ± 4.7, and 10.4 ± 3.6) images. Area under the curve analysis for detection of arterial bleeding showed significantly superior (P < .001) results for 40-keV VMI+ (0.963) compared with 70-keV VMI (0.775) and F_0.5 (0.817) series. CONCLUSIONS: Diagnostic accuracy in patients with active arterial bleeding of the abdomen can be significantly improved using VMI+ reconstructions at 40 keV compared with standard linearly blended and traditional VMI series in DE CT angiography.

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.