Value-added Opportunistic CT Screening: State of the Art

CT image-based biomarkers acquired by AI-based algorithms for the opportunistic prediction of falls

Objective

Evaluate whether biomarkers measured by automated artificial intelligence (AI)-based algorithms are suggestive of future fall risk.

Methods

In this retrospective age- and sex-matched case-control study, 9029 total patients underwent initial abdominal CT for a variety of indications over a 20-year interval at one institution. 3535 case patients (mean age at initial CT, 66.5 ± 9.6 years; 63.4% female) who went on to fall (mean interval to fall, 6.5 years) and 5494 controls (mean age at initial CT, 66.7 ± 9.8 years; 63.4% females; mean follow-up interval, 6.6 years) were included. Falls were identified by electronic health record review. Validated and fully automated quantitative CT algorithms for skeletal muscle, adipose tissue, and trabecular bone attenuation at the level of L1 were applied to all scans. Uni- and multivariate assessment included hazard ratios (HRs) and area under the receiver operating characteristic (AUROC) curve.

Results

Fall HRs (with 95% CI) for low muscle Hounsfield unit, high total adipose area, and low bone Hounsfield unit were 1.82 (1.65-2.00), 1.31 (1.19-1.44) and 1.91 (1.74-2.11), respectively, and the 10-year AUROC values for predicting falls were 0.619, 0.556, and 0.639, respectively. Combining all these CT biomarkers further improved the predictive value, including 10-year AUROC of 0.657.

Conclusion

Automated abdominal CT-based opportunistic measures of muscle, fat, and bone offer a novel approach to risk stratification for future falls, potentially by identifying patients with osteosarcopenic obesity.

Advances in knowledge

There are few well-established clinical tools to predict falls. We use novel AI-based body composition algorithms to leverage incidental CT data to help determine a patient's future fall risk.

Segment aorta and localize landmarks simultaneously on noncontrast CT using a multitask learning framework for patients without severe vascular disease

BACKGROUND

Non-contrast chest CT is widely used for lung cancer screening, and its images carry potential information of the thoracic aorta. The morphological assessment of the thoracic aorta may have potential value in the presymptomatic detection of thoracic aortic-related diseases and the risk prediction of future adverse events. However, due to low vasculature contrast in such images, visual assessment of aortic morphology is challenging and highly depends on physicians' experience.

PURPOSE

The main objective of this study is to propose a novel multi-task framework based on deep learning for simultaneous aortic segmentation and localization of key landmarks on unenhanced chest CT. The secondary objective is to use the algorithm to measure quantitative features of thoracic aorta morphology.

METHODS

The proposed network is composed of two subnets to carry out segmentation and landmark detection, respectively. The segmentation subnet aims to demarcate the aortic sinuses of the Valsalva, aortic trunk and aortic branches, whereas the detection subnet is devised to locate five landmarks on the aorta to facilitate morphology measures. The networks share a common encoder and run decoders in parallel, taking full advantage of the synergy of the segmentation and landmark detection tasks. Furthermore, the volume of interest (VOI) module and the squeeze-and-excitation (SE) block with attention mechanisms are incorporated to further boost the capability of feature learning.

RESULTS

Benefiting from the multitask framework, we achieved a mean Dice score of 0.95, average symmetric surface distance of 0.53 mm, Hausdorff distance of 2.13 mm for aortic segmentation, and mean square error (MSE) of 3.23 mm for landmark localization in 40 testing cases.

CONCLUSION

We proposed a multitask learning framework which can perform segmentation of the thoracic aorta and localization of landmarks simultaneously and achieved good results. It can support quantitative measurement of aortic morphology for further analysis of aortic diseases, such as hypertension.

AI-based opportunistic CT screening of incidental cardiovascular disease, osteoporosis, and sarcopenia: cost-effectiveness analysis

PURPOSE

To assess the cost-effectiveness and clinical efficacy of AI-assisted abdominal CT-based opportunistic screening for atherosclerotic cardiovascular (CV) disease, osteoporosis, and sarcopenia using artificial intelligence (AI) body composition algorithms.

METHODS

Markov models were constructed and 10-year simulations were performed on hypothetical age- and sex-specific cohorts of 10,000 U.S. adults (base case: 55 year olds) undergoing abdominal CT. Using expected disease prevalence, transition probabilities between health states, associated healthcare costs, and treatment effectiveness related to relevant conditions (CV disease/osteoporosis/sarcopenia) were modified by three mutually exclusive screening models: (1) usual care ("treat none"; no intervention regardless of opportunistic CT findings), (2) universal statin therapy ("treat all" for CV prevention; again, no consideration of CT findings), and (3) AI-assisted abdominal CT-based opportunistic screening for CV disease, osteoporosis, and sarcopenia using automated quantitative algorithms for abdominal aortic calcification, bone mineral density, and skeletal muscle, respectively. Model validity was assessed against published clinical cohorts.

RESULTS

For the base-case scenarios of 55-year-old men and women modeled over 10 years, AI-assisted CT-based opportunistic screening was a cost-saving and more effective clinical strategy, unlike the "treat none" and "treat all" strategies that ignored incidental CT body composition data. Over a wide range of input assumptions beyond the base case, the CT-based opportunistic strategy was dominant over the other two scenarios, as it was both more clinically efficacious and more cost-effective. Cost savings and clinical improvement for opportunistic CT remained for AI tool costs up to $227/patient in men ($65 in women) from the $10/patient base-case scenario.

CONCLUSION

AI-assisted CT-based opportunistic screening appears to be a highly cost-effective and clinically efficacious strategy across a broad array of input assumptions, and was cost saving in most scenarios.

Utility of Fully Automated Body Composition Measures on Pretreatment Abdominal CT for Predicting Survival in Patients With Colorectal Cancer

BACKGROUND. CT examinations contain opportunistic body composition data with potential prognostic utility. Previous studies have primarily used manual or semiautomated tools to evaluate body composition in patients with colorectal cancer (CRC). OBJECTIVE. The purpose of this article is to assess the utility of fully automated body composition measures derived from pretreatment CT examinations in predicting survival in patients with CRC. METHODS. This retrospective study included 1766 patients (mean age, 63.7 ± 14.4 [SD] years; 862 men, 904 women) diagnosed with CRC between January 2001 and September 2020 who underwent pretreatment abdominal CT. A panel of fully automated artificial intelligence-based algorithms was applied to portal venous phase images to quantify skeletal muscle attenuation at the L3 lumbar level, visceral adipose tissue (VAT) area and subcutaneous adipose tissue (SAT) area at L3, and abdominal aorta Agatston score (aortic calcium). The electronic health record was reviewed to identify patients who died of any cause (n = 848). ROC analyses and logistic regression analyses were used to identify predictors of survival, with attention to highest- and lowest-risk quartiles. RESULTS. Patients who died, compared with patients who survived, had lower median muscle attenuation (19.2 vs 26.2 HU, p < .001), SAT area (168.4 cm² vs 197.6 cm², p < .001), and aortic calcium (620 vs 182, p < .001). Measures with highest 5-year AUCs for predicting survival in patients without (n = 1303) and with (n = 463) metastatic disease were muscle attenuation (0.666 and 0.701, respectively) and aortic calcium (0.677 and 0.689, respectively). A combination of muscle attenuation, SAT area, and aortic calcium yielded 5-year AUCs of 0.758 and 0.732 in patients without and with metastases, respectively. Risk of death was increased (p < .05) in patients in the lowest quartile for muscle attenuation (hazard ratio [HR] = 1.55) and SAT area (HR = 1.81) and in the highest quartile for aortic calcium (HR = 1.37) and decreased (p < .05) in patients in the highest quartile for VAT area (HR = 0.79) and SAT area (HR = 0.76). In 423 patients with available BMI, BMI did not significantly predict death (p = .75). CONCLUSION. Fully automated CT-based body composition measures including muscle attenuation, SAT area, and aortic calcium predict survival in patients with CRC. CLINICAL IMPACT. Routine pretreatment body composition evaluation could improve initial risk stratification of patients with CRC.

CT required to perform robotic-assisted total hip arthroplasty can identify previously undiagnosed osteoporosis and guide femoral fixation strategy

Osteoporosis can determine surgical strategy for total hip arthroplasty (THA), and perioperative fracture risk. The aims of this study were to use hip CT to measure femoral bone mineral density (BMD) using CT X-ray absorptiometry (CTXA), determine if systematic evaluation of preoperative femoral BMD with CTXA would improve identification of osteopenia and osteoporosis compared with available preoperative dual-energy X-ray absorptiometry (DXA) analysis, and determine if improved recognition of low BMD would affect the use of cemented stem fixation. Retrospective chart review of a single-surgeon database identified 78 patients with CTXA performed prior to robotic-assisted THA (raTHA) (Group 1). Group 1 was age- and sex-matched to 78 raTHAs that had a preoperative hip CT but did not have CTXA analysis (Group 2). Clinical demographics, femoral fixation method, CTXA, and DXA data were recorded. Demographic data were similar for both groups. Preoperative femoral BMD was available for 100% of Group 1 patients (CTXA) and 43.6% of Group 2 patients (DXA). CTXA analysis for all Group 1 patients preoperatively identified 13 osteopenic and eight osteoporotic patients for whom there were no available preoperative DXA data. Cemented stem fixation was used with higher frequency in Group 1 versus Group 2 (28.2% vs 14.3%, respectively; p = 0.030), and in all cases where osteoporosis was diagnosed, irrespective of technique (DXA or CTXA). Preoperative hip CT scans which are routinely obtained prior to raTHA can determine bone health, and thus guide femoral fixation strategy. Systematic preoperative evaluation with CTXA resulted in increased recognition of osteopenia and osteoporosis, and contributed to increased use of cemented femoral fixation compared with routine clinical care; in this small study, however, it did not impact short-term periprosthetic fracture risk.

Computed tomography-based measurements of normative liver and spleen volumes in children

BACKGROUND

Quantification of organ size has utility in clinical care and research for diagnostics, prognostics and surgical planning. Volumetry is regarded as the best measure of organ size and change in size over time. Scarce reference values exist for liver and spleen volumes in healthy children.

OBJECTIVE

To report liver and spleen volumes for a sample of children defined by manual segmentation of contrast-enhanced CT images with the goal of defining normal values and thresholds that might indicate disease.

MATERIALS AND METHODS

This retrospective study included clinically acquired contrast-enhanced CTs of the abdomen/pelvis for children and adolescents imaged between January 2018 and July 2021. Liver and spleen volumes were derived through manual segmentation of CTs reconstructed at 2.5-, 3- or 5-mm slice thickness. A subset of images (5%, n=16) was also segmented using 0.5-mm slice thickness reconstructions to define agreement based on image slice thickness. We used Pearson correlation and multivariable regression to assess associations between organ volumes and patient characteristics. We generated reference intervals for the 5th, 25th, 50th (median), 75th and 95th percentiles for organ volumes as a function of age and weight using quantile regression models. Finally, we calculated Bland-Altman plots and intraclass correlation coefficients (ICC) to quantify agreement.

RESULTS

We included a total of 320 children (mean age ± standard deviation [SD] = 9±4.6 years; mean weight 38.1±18.8 kg; 160 female). Liver volume ranged from 340-2,002 mL, and spleen volume ranged from 28-480 mL. Patient weight (kg) (β=12.5), age (months) (β=1.7) and sex (female) (β = -35.3) were independent predictors of liver volume, whereas patient weight (kg) (β=2.4) and age (months) (β=0.3) were independent predictors of spleen volume. There was excellent absolute agreement (ICC=0.99) and minimal absolute difference (4 mL) in organ volumes based on reconstructed slice thickness.

CONCLUSION

We report reference liver and spleen volumes for children without liver or spleen disease. These results provide reference ranges and potential thresholds to identify liver and spleen size abnormalities that might reflect disease in children.

Technical Adequacy of Fully Automated Artificial Intelligence Body Composition Tools: Assessment in a Heterogeneous Sample of External CT Examinations

Please see the Editorial Comment by Robert D. Boutin discussing this article. Chinese (audio/PDF) and Spanish (audio/PDF) translations are available for this article's abstract. Background: Clinically usable artificial intelligence (AI) tools analyzing imaging studies should be robust to expected variations in study parameters. Objective: To assess the technical adequacy of a set of automated AI abdominal CT body composition tools on a heterogeneous sample of external CT examinations performed outside of the authors' hospital system, as well as to explore possible reasons for tool failure. Methods: This retrospective study included 8949 patients (mean age, 55.5±15.9 years; 4256 men, 4693 women) who underwent 11,699 abdominal CT examinations performed at 777 different external institutions using 82 different scanner models from 6 different manufacturers, and subsequently transferred to the local PACS for clinical purposes. Three independent automated AI tools assessing body composition (bone attenuation, muscle amount and attenuation, visceral and subcutaneous fat amounts) were deployed, evaluating one axial series per examination. Technical adequacy was defined as tool output values within empirically derived reference ranges. Failures (i.e., tool output outside of reference range) were reviewed to identify possible causes. Results: All three tools were technically adequate in 11,431/11,699 (97.7%) examinations, with at least one tool failing in 268/11,699 (2.3%). Individual adequacy rates were 97.8%, 99.1%, and 98.0% for bone, muscle, and fat tools, respectively. A single type of image processing error (anisometry error, due to incorrect DICOM header voxel dimension information) accounted for 81/92 (88%) examinations for which all three tools failed, and all three tools failed whenever this error occurred. Anisometry error was the most common specific cause for failure for all tools (31.6% for bone, 81.0% for muscle, and 62.8% for fat). A total of 79/81 (97.5%) anisometry errors occurred on scanners from a single manufacturer; 80/81 (98.8%) occurred on the same scanner model. No cause for failure was identified in 59.4%, 16.0%, and 34.9% of failures for the bone, muscle, and fat tools, respectively. Conclusion: The automated AI body composition tools had high technical adequacy rates in a heterogeneous sample of external CT examinations, supporting the tools' generalizability and potential for broad use. Clinical Impact: Certain reasons for AI tool failure relating to technical factors may be largely preventable through proper acquisition and reconstruction protocols.

Fully automated CT-based adiposity assessment: comparison of the L1 and L3 vertebral levels for opportunistic prediction

PURPOSE

The purpose of this study is to compare fully automated CT-based measures of adipose tissue at the L1 level versus the standard L3 level for predicting mortality, which would allow for use at both chest (L1) and abdominal (L3) CT.

METHODS

This retrospective study of 9066 asymptomatic adults (mean age, 57.1 ± 7.8 [SD] years; 4020 men, 5046 women) undergoing unenhanced low-dose abdominal CT for colorectal cancer screening. A previously validated artificial intelligence (AI) tool was used to assess cross-sectional visceral and subcutaneous adipose tissue areas (SAT and VAT), as well as their ratio (VSR) at the L1 and L3 levels. Post-CT survival prediction was compared using area under the ROC curve (ROC AUC) and hazard ratios (HRs).

RESULTS

Median clinical follow-up interval after CT was 8.8 years (interquartile range, 5.2-11.6 years), during which 5.9% died (532/9066). No significant difference (p > 0.05) for mortality was observed between L1 and L3 VAT and SAT at 10-year ROC AUC. However, L3 measures were significantly better for VSR at 10-year AUC (p < 0.001). HRs comparing worst-to-best quartiles for mortality at L1 vs. L3 were 2.12 (95% CI, 1.65-2.72) and 2.22 (1.74-2.83) for VAT; 1.20 (0.95-1.52) and 1.16 (0.92-1.46) for SAT; and 2.26 (1.7-2.93) and 3.05 (2.32-4.01) for VSR. In women, the corresponding HRs for VSR were 2.58 (1.80-3.69) (L1) and 4.49 (2.98-6.78) (L3).

CONCLUSION

Automated CT-based measures of visceral fat (VAT and VSR) at L1 are predictive of survival, although overall measures of adiposity at L1 level are somewhat inferior to the standard L3-level measures. Utilizing predictive L1-level fat measures could expand opportunistic screening to chest CT imaging.

Abdominal CT Body Composition Thresholds Using Automated AI Tools for Predicting 10-year Adverse Outcomes

Background CT-based body composition measures derived from fully automated artificial intelligence tools are promising for opportunistic screening. However, body composition thresholds associated with adverse clinical outcomes are lacking. Purpose To determine population and sex-specific thresholds for muscle, abdominal fat, and abdominal aortic calcium measures at abdominal CT for predicting risk of death, adverse cardiovascular events, and fragility fractures. Materials and Methods In this retrospective single-center study, fully automated algorithms for quantifying skeletal muscle (L3 level), abdominal fat (L3 level), and abdominal aortic calcium were applied to noncontrast abdominal CT scans from asymptomatic adults screened from 2004 to 2016. Longitudinal follow-up documented subsequent death, adverse cardiovascular events (myocardial infarction, cerebrovascular event, and heart failure), and fragility fractures. Receiver operating characteristic (ROC) curve analysis was performed to derive thresholds for body composition measures to achieve optimal ROC curve performance and high specificity (90%) for 10-year risks. Results A total of 9223 asymptomatic adults (mean age, 57 years ± 7 [SD]; 5152 women and 4071 men) were evaluated (median follow-up, 9 years). Muscle attenuation and aortic calcium had the highest diagnostic performance for predicting death, with areas under the ROC curve of 0.76 for men (95% CI: 0.72, 0.79) and 0.72 for women (95% CI: 0.69, 0.76) for muscle attenuation. Sex-specific thresholds were higher in men than women (P < .001 for muscle attenuation for all outcomes). The highest-performing markers for risk of death were muscle attenuation in men (31 HU; 71% sensitivity [164 of 232 patients]; 72% specificity [1114 of 1543 patients]) and aortic calcium in women (Agatston score, 167; 70% sensitivity [152 of 218 patients]; 70% specificity [1427 of 2034 patients]). Ninety-percent specificity thresholds for muscle attenuation for both risk of death and fragility fractures were 23 HU (men) and 13 HU (women). For aortic calcium and risk of death and adverse cardiovascular events, 90% specificity Agatston score thresholds were 1475 (men) and 735 (women). Conclusion Sex-specific thresholds for automated abdominal CT-based body composition measures can be used to predict risk of death, adverse cardiovascular events, and fragility fractures. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Ohliger in this issue.

Low skeletal muscle mass is associated with mortality in kidney transplant recipients

Muscle wasting in chronic kidney disease is associated with increased cardiovascular events, morbidity, and mortality. However, whether pretransplantation skeletal muscle mass affects kidney transplantation (KT) outcomes has not been established. We analyzed 623 patients who underwent KT between 2004 and 2019. We measured the cross-sectional area of total skeletal muscle at the third lumbar vertebra level on pretransplantation computed tomography scan. The patients were grouped into low and normal skeletal muscle mass groups based on the sex-specific skeletal muscle mass index lowest quartile. During the entire follow-up period, 45 patients (7.2%) died and 56 patients (9.0%) experienced death-censored graft loss. Pretransplantation low skeletal muscle mass was independently associated with all-cause mortality (adjusted hazard ratio, 2.269; 95% confidence interval, 1.232-4.182). Low muscle mass was also associated with an increased risk of hospital readmission within 1 year after transplantation. Death-censored graft survival rates were comparable between the 2 groups. The low muscle group showed higher creatinine-based estimated glomerular filtration rates (eGFRs) than the normal muscle group. Although cystatin C-based eGFRs were measured in only one-third of patients, cystatin C-based eGFRs were comparable between the 2 groups. Pretransplantation low skeletal muscle mass index is associated with an increased risk of mortality and hospital readmission after KT.

Evaluation of emphysema on thoracic low-dose CTs through attention-based multiple instance deep learning

In addition to lung cancer, other thoracic abnormalities, such as emphysema, can be visualized within low-dose CT scans that were initially obtained in cancer screening programs, and thus, opportunistic evaluation of these diseases may be highly valuable. However, manual assessment for each scan is tedious and often subjective, thus we have developed an automatic, rapid computer-aided diagnosis system for emphysema using attention-based multiple instance deep learning and 865 LDCTs. In the task of determining if a CT scan presented with emphysema or not, our novel Transfer AMIL approach yielded an area under the ROC curve of 0.94 ± 0.04, which was a statistically significant improvement compared to other methods evaluated in our study following the Delong Test with correction for multiple comparisons. Further, from our novel attention weight curves, we found that the upper lung demonstrated a stronger influence in all scan classes, indicating that the model prioritized upper lobe information. Overall, our novel Transfer AMIL method yielded high performance and provided interpretable information by identifying slices that were most influential to the classification decision, thus demonstrating strong potential for clinical implementation.

Identification of Bone Mineral Density Deficit Using L1 Trabecular Attenuation by Opportunistic Multidetector CT Scan in Adult Patients

BACKGROUND

Multidetector computer tomography (CT) has been used to diagnose pathologies such as osteoporosis via opportunistic screening, where the assessment of the bone structure and the measurement of bone mineral density (BMD) are of great relevance.

PURPOSE

To construct reference BMD values based on the measurement of the attenuation of the L1 vertebral body by multidetector CT scan (in the soft tissue and bone windows) in adult patients and to establish normative ranges by sex and age of BMD values.

MATERIALS AND METHODS

A retrospective cross-sectional study of 5080 patients who underwent multidetector CT scan between January and December 2021. Adult patients (≥18 years) with non-contrast multidetector CT scan of the abdomen or thorax-abdomen at a voltage 120 kV. The attenuation of the L1 vertebral body in Hounsfield units (HU) in both windows were compared using the Mann-Whitney U-test with α = 0.05. Additionally, the quartiles of the BMD were constructed (in both windows) grouped by sex and age.

RESULTS

Only 454 (51.30 ± 15.89 years, 243 women) patients met the inclusion criteria. There is no difference in BMD values between windows (soft tissue: 163.90 ± 57.13, bone: 161.86 ± 55.80, p = 0.625), mean L1 attenuation decreased linearly with age at a rate of 2 HU per year, and the presence of BMD deficit among patients was high; 152 of 454 (33.48%) patients presented BMD values suggestive of osteoporosis, and of these, approximately half 70 of 454 (15.42%) corresponded to patients with BMD values suggestive of a high risk of osteoporotic fracture.

CONCLUSIONS

From clinical practice, the bone mineral density (BMD) of a patient in either window below the first quartile for age- and sex-matched peers suggests a deficit in BMD that cannot be ignored and requires clinical management that enables identification of the etiology, its evolution, and the consequences of this alteration.

Opportunistic osteoporosis screening using chest CT with artificial intelligence

Osteoporosis has a high incidence and a low detection rate. If it is not detected in time, it will cause osteoporotic fracture and other serious consequences. This study showed that the attenuation values of vertebrae on chest CT could be used for opportunistic screening of osteoporosis. This will be beneficial to improve the detection rate of osteoporosis and reduce the incidence of adverse events caused by osteoporosis.

INTRODUCTION

To explore the value of the attenuation values of all thoracic vertebrae and the first lumbar vertebra measured by artificial intelligence on non-enhanced chest CT to do osteoporosis screening.

METHODS

On base of images of chest CT, using artificial intelligence (AI) to measure the attenuation values (HU) of all thoracic and the first vertebrae of patients who underwent CT examination for lung cancer screening and dual-energy X-ray absorptiometry (DXA) examination during the same period. The patients were divided into three groups: normal group, osteopenia group, and osteoporosis group according to the results of DXA. Clinical baseline data and attenuation values were compared among the three groups. The correlation between attenuation values and BMD values was analyzed, and the predictive ability and diagnostic efficacy of attenuation values of thoracic and first lumbar vertebrae on osteopenia or osteoporosis risk were further evaluated.

RESULTS

CT values of each thoracic vertebrae and the first lumbar vertebrae decreased with age, especially in menopausal women and presented high predictive ability and diagnostic efficacy for osteopenia or osteoporosis. After clinical data correction, with every 10 HU increase of CT values, the risk of osteopenia or osteoporosis decreased by 32 ~ 44% and 61 ~ 80%, respectively. And the combined diagnostic efficacy of all thoracic vertebrae was higher than that of a single vertebra. The AUC of recognizing osteopenia or osteoporosis from normal group was 0.831and 0.972, respectively.

CONCLUSIONS

The routine chest CT with AI is of great value in opportunistic screening for osteopenia or osteoporosis, which can quickly screen the population at high risk of osteoporosis without increasing radiation dose, thus reducing the incidence of osteoporotic fracture.

Improved CT-based Osteoporosis Assessment with a Fully Automated Deep Learning Tool

Purpose

To develop, test, and validate a deep learning (DL) tool that improves upon a previous feature-based CT image processing bone mineral density (BMD) algorithm and compare it against the manual reference standard.

Materials and Methods

This single-center, retrospective, Health Insurance Portability and Accountability Act-compliant study included manual L1 trabecular Hounsfield unit measurements from abdominal CT scans in 11 035 patients (mean age, 58 years ± 12 [SD]; 6311 women) as the reference standard. Automated level selection and L1 trabecular region of interest (ROI) placement were then performed in this CT cohort with both a previously validated feature-based image processing tool and a new DL tool. Overall technical success rates and agreement with the manual reference standard were assessed.

Results

The overall success rate of the DL tool in this heterogeneous patient cohort was significantly higher than that of the older image processing BMD algorithm (99.3% vs 89.4%, P < .001). Using this DL tool, the closest median Hounsfield unit values for single-, three-, and seven-slice vertebral ROIs were within 5% of the manual reference standard Hounsfield unit values in 35.1%, 56.9%, and 85.8% of scans; within 10% in 56.6%, 75.6%, and 92.9% of scans; and within 25% in 76.5%, 89.3%, and 97.1% of scans, respectively. Trade-offs in sensitivity and specificity for osteoporosis assessment were observed from the single-slice approach (sensitivity, 39.4%; specificity, 98.3%) to the minimum value of the multislice approach (for seven contiguous slices; sensitivity, 71.3% and specificity, 94.6%).

Conclusion

The new DL BMD tool demonstrated a higher success rate than the older feature-based image processing tool, and its outputs can be targeted for higher specificity or sensitivity for osteoporosis assessment.Keywords: CT, CT-Quantitative, Abdomen/GI, Skeletal-Axial, Spine, Deep Learning, Machine Learning Supplemental material is available for this article. © RSNA, 2022.

Estimation of visceral fat area using criteria for metabolic syndrome: A cross-sectional study

BACKGROUND AND AIMS

The aim of this study was to calculate the visceral fat area (VFA) based on the criteria for metabolic syndrome (MetS).

METHODS

A multiple regression analysis was performed to determine the estimated VFA using data from Japanese participants (2315 men and 1684 women). Receiver operating characteristic curve (ROC) analyses were performed to determine the optimal estimated VFA cutoff for the diagnosis of central obesity. The cutoff was also applied to a second cohort to validate the model.

RESULTS

The estimated VFA was calculated using the MetS criteria, age, and body mass index (adjusted coefficient of determination = 0.682 for men and 0.726 for women). The area under the ROC curve for waist circumference, VFA, and estimated VFA were 0.669, 0.741, and 0.749, respectively, for men and 0.711, 0.787, and 0.803, respectively, for women. The optimal cutoffs for estimated VFA were 128.1 cm² for men and 82.2 cm² for women. Multivariate logistic regression for heart disease revealed that estimated VFA, rather than waist circumference, was associated with a high risk of heart disease.

CONCLUSION

The estimated VFA is a better index of central obesity than waist circumference and VFA for the diagnosis of MetS.

CT-Derived Body Composition Assessment as a Prognostic Tool in Oncologic Patients: From Opportunistic Research to Artificial Intelligence-Based Clinical Implementation

CT-based body composition measures are well established in research settings as prognostic markers in oncologic patients. Numerous retrospective studies have shown the role of objective measurements extracted from abdominal CT images of skeletal muscle, abdominal fat, and bone mineral density in providing more accurate assessments of frailty and cancer cachexia in comparison with traditional clinical methods. Quantitative CT-based measurements of liver fat and aortic atherosclerotic calcification have received relatively less attention in cancer care but also provide prognostic information. Patients with cancer routinely undergo serial CT scans for staging, treatment response, and surveillance, providing the opportunity for performing quantitative body composition assessment as part of routine clinical care. The emergence of fully automated artificial intelligence-based segmentation and quantification tools to replace earlier time-consuming manual and semi-automated methods for body composition analysis will allow these opportunistic measures to transition from the research realm to clinical practice. With continued investigation, the measurements may ultimately be applied to achieve more precise risk stratification as a component of personalized oncologic care.

Visual Ordinal Scoring of Coronary Artery Calcium on Contrast-Enhanced and Non-Contrast Chest CT: A Retrospective Study of Diagnostic Performance and Prognostic Utility

Background: Current guidelines recommend visual evaluation of coronary artery calcium (CAC) on all non-gated non-contrast chest CT examinations. However, chest CT examinations are often performed with contrast material administration. Objective: To evaluate diagnostic performance, prognostic utility, and interobserver agreement of visual CAC assessment on chest CT performed for other indications. Methods: This retrospective study included 260 patients (mean age, 60±11 years; 158 male, 102 female) who underwent both non-gated chest CT (contrast-enhanced in 116 patients; non-contrast in 144 patients) and cardiac calcium-score CT within a 12-month interval. A cardiothoracic radiologist visually assessed CAC on chest CT using an ordinal scale (absent, mild, moderate, or severe). Cardiac CT Agatston calcium scores were quantified according to established guidelines and categorized as absent (0), mild (1-99), moderate (100-299), or severe (≥300). Diagnostic performance of chest CT for presence of CAC was assessed using cardiac CT as reference standard. Major adverse cardiac events (MACE) were assessed as a composite of cardiovascular death and myocardial infarction and evaluated using Cox proportional hazards models. A second cardiothoracic radiologist performed visual CAC assessments in a random subset of 50 chest CT examinations to assess interobserver agreement. Results: For presence of any CAC on cardiac CT, contrast-enhanced and non-contrast chest CT had sensitivity of 83% [62/75] and 90% [85/95] (p=.20) and specificity of 100% [41/41] and 100% [49/49] (p=.99). CAC present on cardiac CT was misclassified as absent on 13 contrast-enhanced and 10 non-contrast chest CT examinations; Agatston score was less than 30 in all such patients, and none experienced MACE. Visual ordinal CAC score was associated with MACE for contrast-enhanced [hazard ratio (HR)=4.5 [95% CI 1.2, 16.4], p=.02) and non-contrast (HR=3.4 [95% CI 1.5, 7.8], p=.003) chest CT. Interobserver agreement was excellent for contrast-enhanced (κ =0.95) and non-contrast (κ =0.89) chest CT. Conclusions: Visual ordinal CAC assessment on both contrast-enhanced and non-contrast chest CT has high diagnostic performance, prognostic utility, and interobserver agreement. Clinical Impact: Routine reporting of CAC on all chest CT examinations regardless of clinical indication and contrast material administration could identify a large number of patients with previously unknown CAC who might benefit from preventive treatment.