Opportunistic Screening at Abdominal CT: Use of Automated Body Composition Biomarkers for Added Cardiometabolic Value

Primary care provider perspectives on the value of opportunistic CT screening

BACKGROUND

Clinical adoption of AI applications requires stakeholders see value in their use. AI-enabled opportunistic-CT-screening (OS) capitalizes on incidentally-detected findings within CTs for potential health benefit. This study evaluates primary care providers' (PCP) perspectives on OS.

METHODS

A survey was distributed to US Internal and Family Medicine residencies. Assessed were familiarity with AI and OS, perspectives on potential value/costs, communication of results, and technology implementation.

RESULTS

62 % of respondents (n = 71) were in Family Medicine, 64.8 % practiced in community hospitals. Although 74.6 % of respondents had heard of AI/machine learning, 95.8 % had little-to-no familiarity with OS. The majority reported little-to-no trust in AI. Reported concerns included AI accuracy (74.6 %) and unknown liability (73.2 %). 78.9 % of respondents reported that OS applications would require radiologist oversight. 53.5 % preferred OS results be included in a separate "screening" section within the Radiology report, accompanied by condition risks and management recommendations. The majority of respondents reported results would likely affect clinical management for all queried applications, and that atherosclerotic cardiovascular disease risk, abdominal aortic aneurysm, and liver fibrosis should be included within every CT report regardless of reason for examination. 70.5 % felt that PCP practices are unlikely to pay for OS. Added costs to the patient (91.5 %), the healthcare provider (77.5 %), and unknown liability (74.6 %) were the most frequently reported concerns.

CONCLUSION

PCP preferences and concerns around AI-enabled OS offer insights into clinical value and costs. As AI applications grow, feedback from end-users should be considered in the development of such technology to optimize implementation and adoption. Increasing stakeholder familiarity with AI may be a critical prerequisite first step before stakeholders consider implementation.

Development and validation of a reliable method for automated measurements of psoas muscle volume in CT scans using deep learning-based segmentation: a cross-sectional study

OBJECTIVES

We aimed to develop an automated method for measuring the volume of the psoas muscle using CT to aid sarcopenia research efficiently.

METHODS

We used a data set comprising the CT scans of 520 participants who underwent health check-ups at a health promotion centre. We developed a psoas muscle segmentation model using deep learning in a three-step process based on the nnU-Net method. The automated segmentation method was evaluated for accuracy, reliability, and time required for the measurement.

RESULTS

The Dice similarity coefficient was used to compare the manual segmentation with automated segmentation; an average Dice score of 0.927 ± 0.019 was obtained, with no critical outliers. Our automated segmentation system had an average measurement time of 2 min 20 s ± 20 s, which was 48 times shorter than that of the manual measurement method (111 min 6 s ± 25 min 25 s).

CONCLUSION

We have successfully developed an automated segmentation method to measure the psoas muscle volume that ensures consistent and unbiased estimates across a wide range of CT images.

Effect of fully automatic classification model from different tube voltage images on bone density screening: A self-controlled study

PURPOSE

To develop two bone status prediction models combining deep learning and radiomics based on standard-dose chest computed tomography (SDCT) and low-dose chest computed tomography (LDCT), and to evaluate the effect of tube voltage on reproducibility of radiomics features and predictive efficacy of these models.

METHODS

A total of 1508 patients were enrolled in this retrospective study. LDCT was conducted using 80 kVp, tube current ranging from 100 to 475 mA. On the other hand, SDCT was performed using 120 kVp, tube current ranging from 100 to 520 mA. We developed an automatic thoracic vertebral cancellous bone (TVCB) segmentation model. Subsequently, 1184 features were extracted and two classifiers were developed based on LDCT and SDCT images. Based on the diagnostic results of quantitative computed tomography examination, the first-level classifier was initially developed to distinguish normal or abnormal BMD (including osteoporosis and osteopenia), while the second-level classifier was employed to identify osteoporosis or osteopenia. The Dice coefficient was used to evaluate the performance of the automated segmentation model. The Concordance Correlation Coefficients (CCC) of radiomics features were calculated between LDCT and SDCT, and the performance of these models was evaluated.

RESULTS

Our automated segmentation model achieved a Dice coefficient of 0.98 ± 0.01 and 0.97 ± 0.02 in LDCT and SDCT, respectively. Alterations in tube voltage decreased the reproducibility of the extracted radiomic features, with 85.05 % of the radiomic features exhibiting low reproducibility (CCC < 0.75). The area under the curve (AUC) using LDCT-based and SDCT-based models was 0.97 ± 0.01 and 0.94 ± 0.02, respectively. Nonetheless, cross-validation with independent test sets of different tube voltage scans suggests that variations in tube voltage can impair the diagnostic efficacy of the model. Consequently, radiomics models are not universally applicable to images of varying tube voltages. In clinical settings, ensuring consistency between the tube voltage of the image used for model development and that of the acquired patient image is critical.

CONCLUSIONS

Automatic bone status prediction models, utilizing either LDCT or SDCT images, enable accurate assessment of bone status. Tube voltage impacts reproducibility of features and predictive efficacy of models. It is necessary to account for tube voltage variation during the image acquisition.

Adjusting for the effect of IV contrast on automated CT body composition measures during the portal venous phase

OBJECTIVE

Fully-automated CT-based algorithms for quantifying numerous biomarkers have been validated for unenhanced abdominal scans. There is great interest in optimizing the documentation and reporting of biophysical measures present on all CT scans for the purposes of opportunistic screening and risk profiling. The purpose of this study was to determine and adjust the effect of intravenous (IV) contrast on these automated body composition measures at routine portal venous phase post-contrast imaging.

METHODS

Final study cohort consisted of 1,612 older adults (mean age, 68.0 years; 594 women) all imaged utilizing a uniform CT urothelial protocol consisting of pre-contrast, portal venous, and delayed excretory phases. Fully-automated CT-based algorithms for quantifying numerous biomarkers, including muscle and fat area and density, bone mineral density, and solid organ volume were applied to pre-contrast and portal venous phases. The effect of IV contrast upon these body composition measures was analyzed. Regression analyses, including square of the Pearson correlation coefficient (r2), were performed for each comparison.

RESULTS

We found that simple, linear relationships can be derived to determine non-contrast equivalent values from the post-contrast CT biomeasures. Excellent positive linear correlation (r2 = 0.91-0.99) between pre- and post-contrast values was observed for all automated soft tissue measures, whereas moderate positive linear correlation was observed for bone attenuation (r2 = 0.58-0.76). In general, the area- and volume-based measurement require less adjustment than attenuation-based measures, as expected.

CONCLUSION

Fully-automated quantitative CT-biomarker measures at portal venous phase abdominal CT can be adjusted to a non-contrast equivalent using simple, linear relationships.

Estimating Body Weight From Measurements From Different Single-Slice Computed Tomography Levels: An Evaluation of Total Cross-Sectional Body Area Measurements and Deep Learning

OBJECTIVE

This study aimed to evaluate the correlation between the estimated body weight obtained from 2 easy-to-perform methods and the actual body weight at different computed tomography (CT) levels and determine the best reference site for estimating body weight.

METHODS

A total of 862 patients from a public database of whole-body positron emission tomography/CT studies were retrospectively analyzed. Two methods for estimating body weight at 10 single-slice CT levels were evaluated: a linear regression model using total cross-sectional body area and a deep learning-based model. The accuracy of body weight estimation was evaluated using the mean absolute error (MAE), root mean square error (RMSE), and Spearman rank correlation coefficient ( ρ ).

RESULTS

In the linear regression models, the estimated body weight at the T5 level correlated best with the actual body weight (MAE, 5.39 kg; RMSE, 7.01 kg; ρ = 0.912). The deep learning-based models showed the best accuracy at the L5 level (MAE, 6.72 kg; RMSE, 8.82 kg; ρ = 0.865).

CONCLUSIONS

Although both methods were feasible for estimating body weight at different single-slice CT levels, the linear regression model using total cross-sectional body area at the T5 level as an input variable was the most favorable method for single-slice CT analysis for estimating body weight.

Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults

BACKGROUND

Computed tomography (CT) body compositions reflect age-related metabolic derangements. We aimed to develop a multi-outcome deep learning model using CT multi-level body composition parameters to detect metabolic syndrome (MS), osteoporosis and sarcopenia by identifying metabolic clusters simultaneously. We also investigated the prognostic value of metabolic phenotyping by CT model for long-term mortality.

METHODS

The derivation set (n = 516; 75% train set, 25% internal test set) was constructed using age- and sex-stratified random sampling from two community-based cohorts. Data from participants in the individual health assessment programme (n = 380) were used as the external test set 1. Semi-automatic quantification of body compositions at multiple levels of abdominal CT scans was performed to train a multi-layer perceptron (MLP)-based multi-label classification model. External test set 2 to test the prognostic value of the model output for mortality was built using data from individuals who underwent abdominal CT in a tertiary-level institution (n = 10 141).

RESULTS

The mean ages of the derivation and external sets were 62.8 and 59.7 years, respectively, without difference in sex distribution (women 50%) or body mass index (BMI; 23.9 kg/m2). Skeletal muscle density (SMD) and bone density (BD) showed a more linear decrement across age than skeletal muscle area. Alternatively, an increase in visceral fat area (VFA) was observed in both men and women. Hierarchical clustering based on multi-level CT body composition parameters revealed three distinctive phenotype clusters: normal, MS and osteosarcopenia clusters. The L3 CT-parameter-based model, with or without clinical variables (age, sex and BMI), outperformed clinical model predictions of all outcomes (area under the receiver operating characteristic curve: MS, 0.76 vs. 0.55; osteoporosis, 0.90 vs. 0.79; sarcopenia, 0.85 vs. 0.81 in external test set 1; P < 0.05 for all). VFA contributed the most to the MS predictions, whereas SMD, BD and subcutaneous fat area were features of high importance for detecting osteoporosis and sarcopenia. In external test set 2 (mean age 63.5 years, women 79%; median follow-up 4.9 years), a total of 907 individuals (8.9%) died during follow-up. Among model-predicted metabolic phenotypes, sarcopenia alone (adjusted hazard ratio [aHR] 1.55), MS + sarcopenia (aHR 1.65), osteoporosis + sarcopenia (aHR 1.83) and all three combined (aHR 1.87) remained robust predictors of mortality after adjustment for age, sex and comorbidities.

CONCLUSIONS

A CT body composition-based MLP model detected MS, osteoporosis and sarcopenia simultaneously in community-dwelling and hospitalized adults. Metabolic phenotypes predicted by the CT MLP model were associated with long-term mortality, independent of covariates.

Body composition analysis by radiological imaging - methods, applications, and prospects

BACKGROUND

 This review discusses the quantitative assessment of tissue composition in the human body (body composition, BC) using radiological methods. Such analyses are gaining importance, in particular, for oncological and metabolic problems. The aim is to present the different methods and definitions in this field to a radiological readership in order to facilitate application and dissemination of BC methods. The main focus is on radiological cross-sectional imaging.

METHODS

 The review is based on a recent literature search in the US National Library of Medicine catalog (pubmed.gov) using appropriate search terms (body composition, obesity, sarcopenia, osteopenia in conjunction with imaging and radiology, respectively), as well as our own work and experience, particularly with MRI- and CT-based analyses of abdominal fat compartments and muscle groups.

RESULTS AND CONCLUSION

 Key post-processing methods such as segmentation of tomographic datasets are now well established and used in numerous clinical disciplines, including bariatric surgery. Validated reference values are required for a reliable assessment of radiological measures, such as fatty liver or muscle. Artificial intelligence approaches (deep learning) already enable the automated segmentation of different tissues and compartments so that the extensive datasets can be processed in a time-efficient manner - in the case of so-called opportunistic screening, even retrospectively from diagnostic examinations. The availability of analysis tools and suitable datasets for AI training is considered a limitation.

KEY POINTS

  · Radiological imaging methods are increasingly used to determine body composition (BC).. · BC parameters are usually quantitative and well reproducible.. · CT image data from routine clinical examinations can be used retrospectively for BC analysis.. · Prospectively, MRI examinations can be used to determine organ-specific BC parameters.. · Automated and in-depth analysis methods (deep learning or radiomics) appear to become important in the future..

CITATION FORMAT

· Linder N, Denecke T, Busse H. Body composition analysis by radiological imaging - methods, applications, and prospects. Fortschr Röntgenstr 2024; DOI: 10.1055/a-2263-1501.

Myosteatosis and aortic calcium score on abdominal CT as prognostic markers in non-dialysis chronic kidney disease patients

We aimed to examine the relationship between abdominal computed tomography (CT)-based body composition data and both renal function decline and all-cause mortality in patients with non-dialysis chronic kidney disease (CKD). This retrospective study comprised non-dialysis CKD patients who underwent consecutive unenhanced abdominal CT between January 2010 and December 2011. CT-based body composition was measured using semiautomated method that included visceral fat, subcutaneous fat, skeletal muscle area and density, and abdominal aortic calcium score (AAS). Sarcopenia and myosteatosis were defined by decreased skeletal muscle index (SMI) and decreased skeletal muscle density, respectively, each with specific cutoffs. Risk factors for CKD progression and survival were identified using logistic regression and Cox proportional hazard regression models. Survival between groups based on myosteatosis and AAS was compared using the Kaplan-Meier curve. 149 patients (median age: 70 years) were included; 79 (53.0%) patients had sarcopenia and 112 (75.2%) had myosteatosis. The median AAS was 560.9 (interquartile range: 55.7-1478.3)/m2. The prognostic factors for CKD progression were myosteatosis [odds ratio (OR) = 4.31, p = 0.013] and high AAS (OR = 1.03, p = 0.001). Skeletal muscle density [hazard ratio (HR) = 0.93, p = 0.004] or myosteatosis (HR = 4.87, p = 0.032) and high AAS (HR = 1.02, p = 0.001) were independent factors for poor survival outcomes. The presence of myosteatosis and the high burden of aortic calcium were significant factors for CKD progression and survival in patients with non-dialysis CKD.

AI-generated CT body composition biomarkers associated with increased mortality risk in socioeconomically disadvantaged individuals

PURPOSE

To evaluate the relationship between socioeconomic disadvantage using national area deprivation index (ADI) and CT-based body composition measures derived from fully automated artificial intelligence (AI) tools to identify body composition measures associated with increased risk for all-cause mortality and adverse cardiovascular events.

METHODS

Fully automated AI body composition tools quantifying abdominal aortic calcium, abdominal fat (visceral [VAT], visceral-to-subcutaneous ratio [VSR]), and muscle attenuation (muscle HU) were applied to non-contrast CT examinations in adults undergoing screening CT colonography (CTC). Patients were partitioned into 5 socioeconomic groups based on the national ADI rank at the census block group level. Pearson correlation analysis was performed to determine the association between national ADI and body composition measures. One-way analysis of variance was used to compare means across groups. Odds ratios (ORs) were generated using high-risk, high specificity (90% specificity) body composition thresholds with the most disadvantaged groups being compared to the least disadvantaged group (ADI < 20).

RESULTS

7785 asymptomatic adults (mean age, 57 years; 4361:3424 F:M) underwent screening CTC from April 2004-December 2016. ADI rank data were available in 7644 patients. Median ADI was 31 (IQR 22-43). Aortic calcium, VAT, and VSR had positive correlation with ADI and muscle attenuation had a negative correlation with ADI (all p < .001). Compared with the least disadvantaged group, mean differences for the most disadvantaged group (ADI > 80) were: Aortic calcium (Agatston) = 567, VAT = 27 cm2, VSR = 0.1, and muscle HU = -6 HU (all p < .05). Compared with the least disadvantaged group, the most disadvantaged group had significantly higher odds of having high-risk body composition measures: Aortic calcium OR = 3.8, VAT OR = 2.5, VSR OR = 2.0, and muscle HU OR = 3.1(all p < .001).

CONCLUSION

Fully automated CT body composition tools show that socioeconomic disadvantage is associated with high-risk body composition measures and can be used to identify individuals at increased risk for all-cause mortality and adverse cardiovascular events.

Detection of moderate hepatic steatosis on contrast-enhanced dual-source dual-energy CT: Role and accuracy of virtual non-contrast CT

PURPOSE

To investigate diagnostic accuracy of virtual non contrast (VNC) images, based on dual-source dual-energy CT (dsDECT), for detection of at least moderate steatosis and to define a threshold value to make this diagnosis on VNC.

METHODS

This single-institution retrospective study included patients who had multi-phasic protocol dsDECT. Regions of interests were placed in different segments of the liver and spleen on true non-contrast (TNC), VNC, and portal-venous phase (PVP) images. At least moderate steatosis was defined as liver attenuation (LHU) < 40 HU on TNC. Diagnostic performance of VNC to detect steatosis was determined and the new threshold was tested in a validation cohort.

RESULTS

236 patients were included in training cohort. Mean liver attenuation values were 51.3 ± 10.8 HU and 58.1 ± 11.5 HU for TNC and VNC (p < 0.001), with a mean difference (VNC - TNC) of 6.8 ± 6.9 HU. Correlation between TNC and VNC was strong (r = 0.81, p < 0.001). The AUCs of LHU on VNC for detection of hepatic steatosis were 0.92 (95 % Cl: 0.86-0.98), 0.92 (95 % Cl: 0.87-0.97), 0.92 (95 % Cl: 0.86-0.99), 0.91 (95 % Cl: 0.84-0.97), and 0.87 (95 % Cl: 0.80-0.95) for entire liver, left lateral, left medial, right anterior, and right posterior segments, respectively. VNC had sensitivity/specificity of 100 % /42 % when using a threshold of 40 HU; they were 69 % and 95 %, respectively, when using optimized threshold of 46 HU. This threshold showed similar performance in validation cohort (n = 80).

CONCLUSIONS

Hepatic attenuation on VNC has promising performance for detection of at least moderate steatosis. Proposed threshold of 46 HU provides high specificity and moderate sensitivity to detect steatosis.

Comparing fully automated AI body composition measures derived from thin and thick slice CT image data

PURPOSE

To compare fully automated artificial intelligence body composition measures derived from thin (1.25 mm) and thick (5 mm) slice abdominal CT data.

METHODS

In this retrospective study, fully automated CT-based body composition algorithms for quantifying bone attenuation, muscle attenuation, muscle area, liver attenuation, liver volume, spleen volume, visceral-to-subcutaneous fat ratio (VSR) and aortic calcium were applied to both thin (1.25 × 0.625 mm) and thick (5 × 3 mm) abdominal CT series from two patient cohorts: unenhanced scans in asymptomatic adults undergoing colorectal cancer screening, and post-contrast scans in patients with colorectal cancer. Body composition measures derived from thin and thick slice data were compared, including correlation coefficients and Bland-Altman analysis.

RESULTS

A total of 9882 CT scans (mean age, 57.0 years; 4527 women, 5355 men) were evaluated, including 8947 non-contrast and 935 contrast-enhanced CT exams. Very strong positive correlation was observed for all soft tissue measures: muscle attenuation (r2 = 0.97), muscle area (r2 = 0.98), liver attenuation (r2 = 0.99), liver volume (r2 = 0.98) and spleen volume (r2 = 0.99), VSR (r2 = 0.98), and aortic calcium (r2 = 0.92); (p < 0.001 for all). Moderate positive correlation was observed for bone attenuation (r2 = 0.35). Bland-Altman analysis showed strong agreement for muscle attenuation, muscle area, liver attenuation, liver volume and spleen volume. Mean percentage differences amongst body composition measures were less than 5% for VSR (4.6%), muscle area (- 0.5%), liver attenuation (0.4%) and liver volume (2.7%) and less than 10% for muscle attenuation (- 5.5%) and spleen volume (5.1%). For aortic calcium, thick slice overestimated for Agatston scores between 0 and 100 and > 400 burden in 3.1% and 0.3% relative to thin slice, respectively, but underestimated scores between 100 and 400.

CONCLUSION

Automated body composition measures derived from thin and thick abdominal CT data are strongly correlated and show agreement, particularly for soft tissue applications, making it feasible to use either series for these CT-based body composition algorithms.

Association of CT-Derived Skeletal Muscle and Adipose Tissue Metrics with Frailty in Older Adults

RATIONALE AND OBJECTIVES

Tools are needed for frailty screening of older adults. Opportunistic analysis of body composition could play a role. We aim to determine whether computed tomography (CT)-derived measurements of muscle and adipose tissue are associated with frailty.

MATERIALS AND METHODS

Outpatients aged ≥ 55 years consecutively imaged with contrast-enhanced abdominopelvic CT over a 3-month interval were included. Frailty was determined from the electronic health record using a previously validated electronic frailty index (eFI). CT images at the level of the L3 vertebra were automatically segmented to derive muscle metrics (skeletal muscle area [SMA], skeletal muscle density [SMD], intermuscular adipose tissue [IMAT]) and adipose tissue metrics (visceral adipose tissue [VAT], subcutaneous adipose tissue [SAT]). Distributions of demographic and CT-derived variables were compared between sexes. Sex-specific associations of muscle and adipose tissue metrics with eFI were characterized by linear regressions adjusted for age, race, ethnicity, duration between imaging and eFI measurements, and imaging parameters.

RESULTS

The cohort comprised 886 patients (449 women, 437 men, mean age 67.9 years), of whom 382 (43%) met the criteria for pre-frailty (ie, 0.10 < eFI ≤ 0.21) and 138 (16%) for frailty (eFI > 0.21). In men, 1 standard deviation changes in SMD (β = -0.01, 95% confidence interval [CI], -0.02 to -0.001, P = .02) and VAT area (β = 0.008, 95% CI, 0.0005-0.02, P = .04), but not SMA, IMAT, or SAT, were associated with higher frailty. In women, none of the CT-derived muscle or adipose tissue metrics were associated with frailty.

CONCLUSION

We observed a positive association between frailty and CT-derived biomarkers of myosteatosis and visceral adiposity in a sex-dependent manner.

Environmental Sustainability and AI in Radiology: A Double-Edged Sword

According to the World Health Organization, climate change is the single biggest health threat facing humanity. The global health care system, including medical imaging, must manage the health effects of climate change while at the same time addressing the large amount of greenhouse gas (GHG) emissions generated in the delivery of care. Data centers and computational efforts are increasingly large contributors to GHG emissions in radiology. This is due to the explosive increase in big data and artificial intelligence (AI) applications that have resulted in large energy requirements for developing and deploying AI models. However, AI also has the potential to improve environmental sustainability in medical imaging. For example, use of AI can shorten MRI scan times with accelerated acquisition times, improve the scheduling efficiency of scanners, and optimize the use of decision-support tools to reduce low-value imaging. The purpose of this Radiology in Focus article is to discuss this duality at the intersection of environmental sustainability and AI in radiology. Further discussed are strategies and opportunities to decrease AI-related emissions and to leverage AI to improve sustainability in radiology, with a focus on health equity. Co-benefits of these strategies are explored, including lower cost and improved patient outcomes. Finally, knowledge gaps and areas for future research are highlighted.

Detection of Moderate Hepatic Steatosis on Portal Venous Phase Contrast-Enhanced CT: Evaluation Using an Automated Artificial Intelligence Tool

BACKGROUND. Precontrast CT is an established means of evaluating for hepatic steatosis; postcontrast CT has historically been limited for this purpose. OBJECTIVE. The purpose of this study was to evaluate the diagnostic performance of portal venous phase postcontrast CT in detecting at least moderate hepatic steatosis using liver and spleen attenuation measurements determined by an automated artificial intelligence (AI) tool. METHODS. This retrospective study included 2917 patients (1381 men, 1536 women; mean age, 56.8 years) who underwent a CT examination that included at least two series through the liver. Examinations were obtained from an AI vendor's data lake of data from 24 centers in one U.S. health care network and 29 centers in one Israeli health care network. An automated deep learning tool extracted liver and spleen attenuation measurements. The reference for at least moderate steatosis was precontrast liver attenuation of less than 40 HU (i.e., estimated liver fat > 15%). A radiologist manually reviewed examinations with outlier AI results to confirm portal venous timing and identify issues impacting attenuation measurements. RESULTS. After outlier review, analysis included 2777 patients with portal venous phase images. Prevalence of at least moderate steatosis was 13.9% (387/2777). Patients without and with at least moderate steatosis, respectively, had mean postcontrast liver attenuation of 104.5 ± 18.1 (SD) HU and 67.1 ± 18.6 HU (p < .001); a mean difference in postcontrast attenuation between the liver and the spleen (hereafter, postcontrast liver-spleen attenuation difference) of -7.6 ± 16.4 (SD) HU and -31.8 ± 20.3 HU (p < .001); and mean liver enhancement of 49.3 ± 15.9 (SD) HU versus 38.6 ± 13.6 HU (p < .001). Diagnostic performance for the detection of at least moderate steatosis was higher for postcontrast liver attenuation (AUC = 0.938) than for the postcontrast liver-spleen attenuation difference (AUC = 0.832) (p < .001). For detection of at least moderate steatosis, postcontrast liver attenuation had sensitivity and specificity of 77.8% and 93.2%, respectively, at less than 80 HU and 90.5% and 78.4%, respectively, at less than 90 HU; the postcontrast liver-spleen attenuation difference had sensitivity and specificity of 71.4% and 79.3%, respectively, at less than -20 HU and 87.0% and 62.1%, respectively, at less than -10 HU. CONCLUSION. Postcontrast liver attenuation outperformed the postcontrast liver-spleen attenuation difference for detecting at least moderate steatosis in a heterogeneous patient sample, as evaluated using an automated AI tool. Splenic attenuation likely is not needed to assess for at least moderate steatosis on postcontrast images. CLINICAL IMPACT. The technique could promote early detection of clinically significant nonalcoholic fatty liver disease through individualized or large-scale opportunistic evaluation.

CT-based body composition in diffuse large B cell lymphoma patients: changes after treatment and association with survival

PURPOSE

Primary purpose was to assess changes of bone mineral density (BMD) in diffuse large B cell lymphoma (DLBCL) patients treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone R-CHOP (like) chemotherapy regimen. Secondary purposes were to assess other body composition features changes and to assess the association of pre-therapy values and their changes over time with survival.

MATERIAL AND METHODS

Patients selected underwent R-CHOP(like) regimen for DLBCL, and underwent PET-CT before and after treatment. Main clinical data collected included body mass index, date of last follow-up, date of progression, and date of death. From the low-dose CT images, BMD was assessed at the L1 level; the other body composition values, including muscle and fat distribution, were assessed at the L3 level by using a dedicated software. Descriptive statistics were reported as median and interquartile range, or frequencies and percentages. Statistical comparisons of body composition variables between pre- and post-treatment assessments were performed using the Wilcoxon matched pairs signed rank test. Non-normal distribution of variables was tested with the Shapiro-Wilk test. For qualitative variables, the Fisher exact test was used. Log rank test was used to compare survival between different subgroups of the study population defined by specific body composition cutoffs. The significance level was set at p < 0.05.

RESULTS

Eighty-two patients were included. The mean follow-up was 37.5 ± 21.4 months. A significant difference was found in mean BMD before and after R-CHOP(like) treatment (p < 0.0001). The same trend was observed for mean skeletal muscle area (SMA) (p = 0.004) and mean skeletal muscle index (SMI) (p = 0.006). No significant association was demonstrated between body composition variables, PFS and OS.

CONCLUSION

R-CHOP(like) treatment in DLBCL patients was associated with significant reduction of BMD, SMA and SMI.

Harnessing artificial intelligence in radiology to augment population health

This review article serves to highlight radiological services as a major cost driver for the healthcare sector, and the potential improvements in productivity and cost savings that can be generated by incorporating artificial intelligence (AI) into the radiology workflow, referencing Singapore healthcare as an example. More specifically, we will discuss the opportunities for AI in lowering healthcare costs and supporting transformational shifts in our care model in the following domains: predictive analytics for optimising throughput and appropriate referrals, computer vision for image enhancement (to increase scanner efficiency and decrease radiation exposure) and pattern recognition (to aid human interpretation and worklist prioritisation), natural language processing and large language models for optimising reports and text data-mining. In the context of preventive health, we will discuss how AI can support population level screening for major disease burdens through opportunistic screening and democratise expertise to increase access to radiological services in primary and community care.

Automated Deep Learning Artificial Intelligence Tool for Spleen Segmentation on CT: Defining Volume-Based Thresholds for Splenomegaly

BACKGROUND. Splenomegaly historically has been assessed on imaging by use of potentially inaccurate linear measurements. Prior work tested a deep learning artificial intelligence (AI) tool that automatically segments the spleen to determine splenic volume. OBJECTIVE. The purpose of this study is to apply the deep learning AI tool in a large screening population to establish volume-based splenomegaly thresholds. METHODS. This retrospective study included a primary (screening) sample of 8901 patients (4235 men, 4666 women; mean age, 56 ± 10 [SD] years) who underwent CT colonoscopy (n = 7736) or renal donor CT (n = 1165) from April 2004 to January 2017 and a secondary sample of 104 patients (62 men, 42 women; mean age, 56 ± 8 years) with end-stage liver disease who underwent contrast-enhanced CT performed as part of evaluation for potential liver transplant from January 2011 to May 2013. The automated deep learning AI tool was used for spleen segmentation, to determine splenic volumes. Two radiologists independently reviewed a subset of segmentations. Weight-based volume thresholds for splenomegaly were derived using regression analysis. Performance of linear measurements was assessed. Frequency of splenomegaly in the secondary sample was determined using weight-based volumetric thresholds. RESULTS. In the primary sample, both observers confirmed splenectomy in 20 patients with an automated splenic volume of 0 mL; confirmed incomplete splenic coverage in 28 patients with a tool output error; and confirmed adequate segmentation in 21 patients with low volume (< 50 mL), 49 patients with high volume (> 600 mL), and 200 additional randomly selected patients. In 8853 patients included in analysis of splenic volumes (i.e., excluding a value of 0 mL or error values), the mean automated splenic volume was 216 ± 100 [SD] mL. The weight-based volumetric threshold (expressed in milliliters) for splenomegaly was calculated as (3.01 × weight [expressed as kilograms]) + 127; for weight greater than 125 kg, the splenomegaly threshold was constant (503 mL). Sensitivity and specificity for volume-defined splenomegaly were 13% and 100%, respectively, at a true craniocaudal length of 13 cm, and 78% and 88% for a maximum 3D length of 13 cm. In the secondary sample, both observers identified segmentation failure in one patient. The mean automated splenic volume in the 103 remaining patients was 796 ± 457 mL; 84% (87/103) of patients met the weight-based volume-defined splenomegaly threshold. CONCLUSION. We derived a weight-based volumetric threshold for splenomegaly using an automated AI-based tool. CLINICAL IMPACT. The AI tool could facilitate large-scale opportunistic screening for splenomegaly.

Chest CT opportunistic biomarkers for phenotyping high-risk COVID-19 patients: a retrospective multicentre study

OBJECTIVE

To assess the value of opportunistic biomarkers derived from chest CT performed at hospital admission of COVID-19 patients for the phenotypization of high-risk patients.

METHODS

In this multicentre retrospective study, 1845 consecutive COVID-19 patients with chest CT performed within 72 h from hospital admission were analysed. Clinical and outcome data were collected by each center 30 and 80 days after hospital admission. Patients with unknown outcomes were excluded. Chest CT was analysed in a single core lab and behind pneumonia CT scores were extracted opportunistic data about atherosclerotic profile (calcium score according to Agatston method), liver steatosis (≤ 40 HU), myosteatosis (paraspinal muscle F < 31.3 HU, M < 37.5 HU), and osteoporosis (D12 bone attenuation < 134 HU). Differences according to treatment and outcome were assessed with ANOVA. Prediction models were obtained using multivariate binary logistic regression and their AUCs were compared with the DeLong test.

RESULTS

The final cohort included 1669 patients (age 67.5 [58.5-77.4] yo) mainly men 1105/1669, 66.2%) and with reduced oxygen saturation (92% [88-95%]). Pneumonia severity, high Agatston score, myosteatosis, liver steatosis, and osteoporosis derived from CT were more prevalent in patients with more aggressive treatment, access to ICU, and in-hospital death (always p < 0.05). A multivariable model including clinical and CT variables improved the capability to predict non-critical pneumonia compared to a model including only clinical variables (AUC 0.801 vs 0.789; p = 0.0198) to predict patient death (AUC 0.815 vs 0.800; p = 0.001).

CONCLUSION

Opportunistic biomarkers derived from chest CT can improve the characterization of COVID-19 high-risk patients.

CLINICAL RELEVANCE STATEMENT

In COVID-19 patients, opportunistic biomarkers of cardiometabolic risk extracted from chest CT improve patient risk stratification.

KEY POINTS

• In COVID-19 patients, several information about patient comorbidities can be quantitatively extracted from chest CT, resulting associated with the severity of oxygen treatment, access to ICU, and death. • A prediction model based on multiparametric opportunistic biomarkers derived from chest CT resulted superior to a model including only clinical variables in a large cohort of 1669 patients suffering from SARS- CoV2 infection. • Opportunistic biomarkers of cardiometabolic comorbidities derived from chest CT may improve COVID-19 patients' risk stratification also in absence of detailed clinical data and laboratory tests identifying subclinical and previously unknown conditions.

Artificial intelligence tool detection of intravenous contrast enhancement using spleen attenuation

PURPOSE

To assess the ability of an automated AI tool to detect intravenous contrast material (IVCM) in abdominal CT examinations using spleen attenuation.

METHODS

A previously validated automated AI tool measuring the attenuation of the spleen was deployed on a sample of 32,994 adult (age ≥ 18) patients (mean age, 61.9 ± 14.7 years; 13,869 men, 19,125 women) undergoing 65,449 supine position CT examinations (41,020 with and 24,429 without IVCM by DICOM header) from January 1, 2000 to December 31, 2021. After exclusions, receiver operating characteristic (ROC) curve analysis was performed to determine the optimal threshold for binary classification of IVCM status (non-contrast vs IVCM enhanced), which was then applied to the sample. Discordant examinations (i.e., IVCM status determined by AI tool did not match DICOM header) were manually reviewed to establish ground truth. Repeat ROC curve and contingency table analysis were performed to assess AI tool performance.

RESULTS

ROC analysis of the initial study sample of 61,783 CT examinations yielded AUC of 0.970 with Youden index suggesting an optimal spleen attenuation threshold of 65 Hounsfield units (HU). Manual review of 2094 discordant CT examinations revealed discordance due to DICOM header error in 1278 (61.0%) and AI tool misclassification in 410 (19.6%), with 406 (9.4%) meeting exclusion criteria. Analysis of 61,377 CT examinations in the final study sample yielded AUC of 0.999 with accuracy of 99.3% at the 65 HU threshold. Error rate for DICOM header information was 2.1% (1278/61,377) versus 0.7% (410/61,377) for the AI tool.

CONCLUSION

The automated spleen attenuation AI tool was highly accurate for detection of IVCM at a threshold of 65 HU.

A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow

Background

Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation.

Purpose

In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow.

Methods

Our end-to-end automated pipeline has two major components- 1. A router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Since nnU-net has emerged as a widely-used out-of-the-box method for training segmentation models with state-of-the-art performance, feasibility of our pipleine is demonstrated by recording clock times for a traumatic pelvic hematoma nnU-net model.

Results

Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 min 32 s (± SD of 1 min 26 s). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 min, and illustrates feasibility in the clinical setting where quantitative results would be expected prior to report sign-off. Inference times accounted for most of the total clock time, ranging from 2 min 41 s to 8 min 27 s. All other virtual and on-premises host steps combined ranged from a minimum of 34 s to a maximum of 48 s.

Conclusion

The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/," and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.

CT Number Accuracy and Association With Object Size: A Phantom Study Comparing Energy-Integrating Detector CT and Deep Silicon Photon-Counting Detector CT

BACKGROUND. Variable beam hardening based on patient size causes variation in CT numbers for energy-integrating detector (EID) CT. Photon-counting detector (PCD) CT more accurately determines effective beam energy, potentially improving CT number reliability. OBJECTIVE. The purpose of the present study was to compare EID CT and deep silicon PCD CT in terms of both the effect of changes in object size on CT number and the overall accuracy of CT numbers. METHODS. A phantom with polyethylene rings of varying sizes (mimicking patient sizes) as well as inserts of different materials was scanned on an EID CT scanner in single-energy (SE) mode (120-kV images) and in rapid-kilovoltage-switching dual-energy (DE) mode (70-keV images) and on a prototype deep silicon PCD CT scanner (70-keV images). ROIs were placed to measure the CT numbers of the materials. Slopes of CT number as a function of object size were computed. Materials' ideal CT number at 70 keV was computed using the National Institute of Standards and Technology XCOM Photon Cross Sections Database. The root mean square error (RMSE) between measured and ideal numbers was calculated across object sizes. RESULTS. Slope (expressed as Hounsfield units per centimeter) was significantly closer to zero (i.e., less variation in CT number as a function of size) for PCD CT than for SE EID CT for air (1.2 vs 2.4 HU/cm), water (-0.3 vs -1.0 HU/cm), iodine (-1.1 vs -4.5 HU/cm), and bone (-2.5 vs -10.1 HU/cm) and for PCD CT than for DE EID CT for air (1.2 vs 2.8 HU/cm), water (-0.3 vs -1.0 HU/cm), polystyrene (-0.2 vs -0.9 HU/cm), iodine (-1.1 vs -1.9 HU/cm), and bone (-2.5 vs -6.2 HU/cm) (p < .05). For all tested materials, PCD CT had the smallest RMSE, indicating CT numbers closest to ideal numbers; specifically, RMSE (expressed as Hounsfield units) for SE EID CT, DE EID CT, and PCD CT was 32, 44, and 17 HU for air; 7, 8, and 3 HU for water; 9, 10, and 4 HU for polystyrene; 31, 37, and 13 HU for iodine; and 69, 81, and 20 HU for bone, respectively. CONCLUSION. For numerous materials, deep silicon PCD CT, in comparison with SE EID CT and DE EID CT, showed lower CT number variability as a function of size and CT numbers closer to ideal numbers. CLINICAL IMPACT. Greater reliability of CT numbers for PCD CT is important given the dependence of diagnostic pathways on CT numbers.

Transforming radiology to support population health

This commentary highlights key areas in which diagnostic radiological services in Singapore will need to evolve in order to address the needs of Healthier SG and population health. Policymakers should focus on “doing the right thing” by improving access to radiological expertise and services to support community and primary care and “doing the thing right” by establishing robust frameworks to support value-based care.

Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Deep learning (DL) models can harness electronic health records (EHRs) to predict diseases and extract radiologic findings for diagnosis. With ambulatory chest radiographs (CXRs) frequently ordered, we investigated detecting type 2 diabetes (T2D) by combining radiographic and EHR data using a DL model. Our model, developed from 271,065 CXRs and 160,244 patients, was tested on a prospective dataset of 9,943 CXRs. Here we show the model effectively detected T2D with a ROC AUC of 0.84 and a 16% prevalence. The algorithm flagged 1,381 cases (14%) as suspicious for T2D. External validation at a distinct institution yielded a ROC AUC of 0.77, with 5% of patients subsequently diagnosed with T2D. Explainable AI techniques revealed correlations between specific adiposity measures and high predictivity, suggesting CXRs' potential for enhanced T2D screening.

US Quantification of Liver Fat: Past, Present, and Future

Fatty liver disease has a high and increasing prevalence worldwide, is associated with adverse cardiovascular events and higher long-term medical costs, and may lead to liver-related morbidity and mortality. There is an urgent need for accurate, reproducible, accessible, and noninvasive techniques appropriate for detecting and quantifying liver fat in the general population and for monitoring treatment response in at-risk patients. CT may play a potential role in opportunistic screening, and MRI proton-density fat fraction provides high accuracy for liver fat quantification; however, these imaging modalities may not be suited for widespread screening and surveillance, given the high global prevalence. US, a safe and widely available modality, is well positioned as a screening and surveillance tool. Although well-established qualitative signs of liver fat perform well in moderate and severe steatosis, these signs are less reliable for grading mild steatosis and are likely unreliable for detecting subtle changes over time. New and emerging quantitative biomarkers of liver fat, such as those based on standardized measurements of attenuation, backscatter, and speed of sound, hold promise. Evolving techniques such as multiparametric modeling, radiofrequency envelope analysis, and artificial intelligence-based tools are also on the horizon. The authors discuss the societal impact of fatty liver disease, summarize the current state of liver fat quantification with CT and MRI, and describe past, currently available, and potential future US-based techniques for evaluating liver fat. For each US-based technique, they describe the concept, measurement method, advantages, and limitations. © RSNA, 2023 Online supplemental material is available for this article. Quiz questions for this article are available through the Online Learning Center.

Opportunistic Screening: Radiology Scientific Expert Panel

Radiologic tests often contain rich imaging data not relevant to the clinical indication. Opportunistic screening refers to the practice of systematically leveraging these incidental imaging findings. Although opportunistic screening can apply to imaging modalities such as conventional radiography, US, and MRI, most attention to date has focused on body CT by using artificial intelligence (AI)-assisted methods. Body CT represents an ideal high-volume modality whereby a quantitative assessment of tissue composition (eg, bone, muscle, fat, and vascular calcium) can provide valuable risk stratification and help detect unsuspected presymptomatic disease. The emergence of "explainable" AI algorithms that fully automate these measurements could eventually lead to their routine clinical use. Potential barriers to widespread implementation of opportunistic CT screening include the need for buy-in from radiologists, referring providers, and patients. Standardization of acquiring and reporting measures is needed, in addition to expanded normative data according to age, sex, and race and ethnicity. Regulatory and reimbursement hurdles are not insurmountable but pose substantial challenges to commercialization and clinical use. Through demonstration of improved population health outcomes and cost-effectiveness, these opportunistic CT-based measures should be attractive to both payers and health care systems as value-based reimbursement models mature. If highly successful, opportunistic screening could eventually justify a practice of standalone "intended" CT screening.

A vendor-agnostic, PACS integrated, and DICOMcompatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow

Background

Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation.

Purpose

In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow.

Methods

Our end-to-end automated pipeline has two major components-1. a router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Feasibility is demonstrated by recording clock times for a traumatic pelvic hematoma cascaded nnU-net model.

Results

Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 minutes 32 seconds (+/- SD of 1 min 26 sec). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 minutes. Inference times accounted for most of the total clock time, ranging from 2 minutes 41 seconds to 8 minutes 27 seconds. All other virtual and on-premises host steps combined ranged from a minimum of 34 seconds to a maximum of 48 seconds.

Conclusion

The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/", and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.

Role of Machine Learning-Based CT Body Composition in Risk Prediction and Prognostication: Current State and Future Directions

CT body composition analysis has been shown to play an important role in predicting health and has the potential to improve patient outcomes if implemented clinically. Recent advances in artificial intelligence and machine learning have led to high speed and accuracy for extracting body composition metrics from CT scans. These may inform preoperative interventions and guide treatment planning. This review aims to discuss the clinical applications of CT body composition in clinical practice, as it moves towards widespread clinical implementation.

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.

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.

Artificial intelligence and body composition

AIMS

Although obesity is associated with chronic disease, a large section of the population with high BMI does not have an increased risk of metabolic disease. Increased visceral adiposity and sarcopenia are also risk factors for metabolic disease in people with normal BMI. Artificial Intelligence (AI) techniques can help assess and analyze body composition parameters for predicting cardiometabolic health. The purpose of the study was to systematically explore literature involving AI techniques for body composition assessment and observe general trends.

METHODS

We searched the following databases: Embase, Web of Science, and PubMed. There was a total of 354 search results. After removing duplicates, irrelevant studies, and reviews(a total of 303), 51 studies were included in the systematic review.

RESULTS

AI techniques have been studied for body composition analysis in the context of diabetes mellitus, hypertension, cancer and many specialized diseases. Imaging techniques employed for AI methods include CT (Computerized Tomography), MRI (Magnetic Resonance Imaging), ultrasonography, plethysmography, and EKG(Electrocardiogram). Automatic segmentation of body composition by deep learning with convolutional networks has helped determine and quantify muscle mass. Limitations include heterogeneity of study populations, inherent bias in sampling, and lack of generalizability. Different bias mitigation strategies should be evaluated to address these problems and improve the applicability of AI to body composition analysis.

CONCLUSIONS

AI assisted measurement of body composition might assist in improved cardiovascular risk stratification when applied in the appropriate clinical context.

Incidental Coronary Artery Calcium: Opportunistic Screening of Previous Nongated Chest Computed Tomography Scans to Improve Statin Rates (NOTIFY-1 Project)

BACKGROUND

Coronary artery calcium (CAC) can be identified on nongated chest computed tomography (CT) scans, but this finding is not consistently incorporated into care. A deep learning algorithm enables opportunistic CAC screening of nongated chest CT scans. Our objective was to evaluate the effect of notifying clinicians and patients of incidental CAC on statin initiation.

METHODS

NOTIFY-1 (Incidental Coronary Calcification Quality Improvement Project) was a randomized quality improvement project in the Stanford Health Care System. Patients without known atherosclerotic cardiovascular disease or a previous statin prescription were screened for CAC on a previous nongated chest CT scan from 2014 to 2019 using a validated deep learning algorithm with radiologist confirmation. Patients with incidental CAC were randomly assigned to notification of the primary care clinician and patient versus usual care. Notification included a patient-specific image of CAC and guideline recommendations regarding statin use. The primary outcome was statin prescription within 6 months.

RESULTS

Among 2113 patients who met initial clinical inclusion criteria, CAC was identified by the algorithm in 424 patients. After chart review and additional exclusions were made, a radiologist confirmed CAC among 173 of 194 patients (89.2%) who were randomly assigned to notification or usual care. At 6 months, the statin prescription rate was 51.2% (44/86) in the notification arm versus 6.9% (6/87) with usual care (P<0.001). There was also more coronary artery disease testing in the notification arm (15.1% [13/86] versus 2.3% [2/87]; P=0.008).

CONCLUSIONS

Opportunistic CAC screening of previous nongated chest CT scans followed by clinician and patient notification led to a significant increase in statin prescriptions. Further research is needed to determine whether this approach can reduce atherosclerotic cardiovascular disease events.

REGISTRATION

URL: https://www.

CLINICALTRIALS

gov; Unique identifier: NCT04789278.

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.

Incidentalomas at abdominal imaging

As all radiologists are well aware, cross-sectional abdominal imaging tests such as CT, MR, and ultrasound generally include organs and structures that are not directly related to the clinical indication for obtaining the examination. As a result, unsuspected additional findings or "incidentalomas" must be handled in a responsible manner that balances any need for reporting and management against the potential harms that may result from such actions. The majority of abdominal incidentalomas detected at imaging will not cause downstream harm to the patient, unless perhaps the radiologist unleashes an unnecessary work-up cascade that results in patient anxiety, inconvenience, added costs, or complications. Applying the principle of primum non-nocere, an argument can be made for not even reporting incidental imaging findings that have an exceedingly low likelihood of clinical relevance, such as small, simple-appearing sporadic cysts that are commonly seen in many abdominal organs. The situation becomes more challenging, however, when "likely benign" yet indeterminate lesions are encountered. At some threshold, which is difficult to precisely define for all cases, further action may be indicated, be it imaging follow-up to confirm resolution or stability, more definitive imaging characterization, or even tissue sampling. For more concerning or ominous incidentalomas, the need for further work-up will be more clear cut.

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 bone mineral density is a prognostic factor for elderly patients with HCC undergoing TACE: results from a multicenter study

OBJECTIVES

Low bone mineral density (BMD) was recently identified as a novel risk factor for patients with hepatocellular carcinoma (HCC). In this multicenter study, we aimed to validate the role of BMD as a prognostic factor for patients with HCC undergoing transarterial chemoembolization (TACE).

METHODS

This retrospective multicenter trial included 908 treatment-naïve patients with HCC who were undergoing TACE as a first-line treatment, at six tertiary care centers, between 2010 and 2020. BMD was assessed by measuring the mean Hounsfield units (HUs) in the midvertebral core of the 11^th thoracic vertebra, on contrast-enhanced computer tomography performed before treatment. We assessed the influence of BMD on median overall survival (OS) and performed multivariate analysis including established estimates for survival.

RESULTS

The median BMD was 145 HU (IQR, 115-175 HU). Patients with a high BMD (≥ 114 HU) had a median OS of 22.2 months, while patients with a low BMD (< 114 HU) had a lower median OS of only 16.2 months (p < .001). Besides albumin, bilirubin, tumor number, and tumor diameter, BMD remained an independent prognostic factor in multivariate analysis.

CONCLUSIONS

BMD is an independent predictive factor for survival in elderly patients with HCC undergoing TACE. The integration of BMD into novel scoring systems could potentially improve survival prediction and clinical decision-making.

KEY POINTS

• Bone mineral density can be easily assessed in routinely acquired pre-interventional computed tomography scans. • Bone mineral density is an independent predictive factor for survival in elderly patients with HCC undergoing TACE. • Thus, bone mineral density is a novel imaging biomarker for prognosis prediction in elderly patients with HCC undergoing TACE.

Body composition as a predictor of chemotherapy-related toxicity in ovarian cancer patients: A systematic review

OBJECTIVES

The main objective of this systematic review was to examine the literature evaluating association of image-based body composition with chemotherapy-related toxicity in ovarian cancer patients. A secondary objective was to evaluate the different definitions of sarcopenia across studies.

METHODS

This systematic review was conducted according to the PRISMA-DTA statement and the protocol was registered on Prospero. A comprehensive literature search of 3 electronic databases was performed by two authors. For each eligible article, information was collected concerning the clinical setting; basic study data; population characteristics; technical aspects; body composition features; chemotherapy drugs administered; association of body composition values and toxicities. The overall quality of the included studies was critically evaluated.

RESULTS

After the initial retrieval of 812 articles, the systematic review included 6 articles (5/6 studies were retrospective; one was prospective). The number of patients ranged between 69 and 239; mean/median age ranged between 55 and 65 years; the percentage of sarcopenic patients ranged between 25% and 54%. The cut-off values to define sarcopenia and the vertebral levels for evaluation of body composition were different. Five studies included chemotherapy based on carboplatin and paclitaxel, 1 included chemotherapy based on pegylated liposomal doxorubicin. Among the studies including carboplatin and paclitaxel, 3/5 demonstrated an association with toxicity, whereas 2/5 did not. Altogether, 4/6 papers demonstrated an association between the body composition values and the development of chemotherapy-related toxicities.

CONCLUSIONS

There is a wide variability of results about the association of body composition and chemotherapy-related toxicity in ovarian cancer patients. Therefore further studies, possibly including a comprehensive assessment of body compartments and where the definition of body composition cut-offs is constant, are warranted to better understand this association.

SYSTEMATIC REVIEW REGISTRATION

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022337753, identifier (CRD42022337753).

Pulse-Echo Quantitative US Biomarkers for Liver Steatosis: Toward Technical Standardization

Excessive liver fat (steatosis) is now the most common cause of chronic liver disease worldwide and is an independent risk factor for cirrhosis and associated complications. Accurate and clinically useful diagnosis, risk stratification, prognostication, and therapy monitoring require accurate and reliable biomarker measurement at acceptable cost. This article describes a joint effort by the American Institute of Ultrasound in Medicine (AIUM) and the RSNA Quantitative Imaging Biomarkers Alliance (QIBA) to develop standards for clinical and technical validation of quantitative biomarkers for liver steatosis. The AIUM Liver Fat Quantification Task Force provides clinical guidance, while the RSNA QIBA Pulse-Echo Quantitative Ultrasound Biomarker Committee develops methods to measure biomarkers and reduce biomarker variability. In this article, the authors present the clinical need for quantitative imaging biomarkers of liver steatosis, review the current state of various imaging modalities, and describe the technical state of the art for three key liver steatosis pulse-echo quantitative US biomarkers: attenuation coefficient, backscatter coefficient, and speed of sound. Lastly, a perspective on current challenges and recommendations for clinical translation for each biomarker is offered.

AI-Supported Comprehensive Detection and Quantification of Biomarkers of Subclinical Widespread Diseases at Chest CT for Preventive Medicine

Automated image analysis plays an increasing role in radiology in detecting and quantifying image features outside of the perception of human eyes. Common AI-based approaches address a single medical problem, although patients often present with multiple interacting, frequently subclinical medical conditions. A holistic imaging diagnostics tool based on artificial intelligence (AI) has the potential of providing an overview of multi-system comorbidities within a single workflow. An interdisciplinary, multicentric team of medical experts and computer scientists designed a pipeline, comprising AI-based tools for the automated detection, quantification and characterization of the most common pulmonary, metabolic, cardiovascular and musculoskeletal comorbidities in chest computed tomography (CT). To provide a comprehensive evaluation of each patient, a multidimensional workflow was established with algorithms operating synchronously on a decentralized Joined Imaging Platform (JIP). The results of each patient are transferred to a dedicated database and summarized as a structured report with reference to available reference values and annotated sample images of detected pathologies. Hence, this tool allows for the comprehensive, large-scale analysis of imaging-biomarkers of comorbidities in chest CT, first in science and then in clinical routine. Moreover, this tool accommodates the quantitative analysis and classification of each pathology, providing integral diagnostic and prognostic value, and subsequently leading to improved preventive patient care and further possibilities for future studies.

The Cases for and against Artificial Intelligence in the Medical School Curriculum

Although artificial intelligence (AI) has immense potential to shape the future of medicine, its place in undergraduate medical education currently is unclear. Numerous arguments exist both for and against including AI in the medical school curriculum. AI likely will affect all medical specialties, perhaps radiology more so than any other. The purpose of this article is to present a balanced perspective on whether AI should be included officially in the medical school curriculum. After presenting the balanced point-counterpoint arguments, the authors provide a compromise. Keywords: Artificial Intelligence, Medical Education, Medical School Curriculum, Medical Students, Radiology, Use of AI in Education © RSNA, 2022.

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.

Proceedings from the Society of Interventional Radiology Foundation Research Consensus Panel on Artificial Intelligence in Interventional Radiology: From Code to Bedside

Artificial intelligence (AI)-based technologies are the most rapidly growing field of innovation in healthcare with the promise to achieve substantial improvements in delivery of patient care across all disciplines of medicine. Recent advances in imaging technology along with marked expansion of readily available advanced health information, data offer a unique opportunity for interventional radiology (IR) to reinvent itself as a data-driven specialty. Additionally, the growth of AI-based applications in diagnostic imaging is expected to have downstream effects on all image-guidance modalities. Therefore, the Society of Interventional Radiology Foundation has called upon 13 key opinion leaders in the field of IR to develop research priorities for clinical applications of AI in IR. The objectives of the assembled research consensus panel were to assess the availability and understand the applicability of AI for IR, estimate current needs and clinical use cases, and assemble a list of research priorities for the development of AI in IR. Individual panel members proposed and all participants voted upon consensus statements to rank them according to their overall impact for IR. The results identified the top priorities for the IR research community and provide organizing principles for innovative academic-industrial research collaborations that will leverage both clinical expertise and cutting-edge technology to benefit patient care in IR.

The Usefulness of Radiomics Methodology for Developing Descriptive and Prognostic Image-Based Phenotyping in the Aging Population: Results From a Small Feasibility Study

Background: Radiomics is an emerging field that translates medical images into quantitative data to enable phenotypic profiling of human disease. In this retrospective study, we asked whether it is possible to use image-based phenotyping to describe and determine prognostic factors in the aging population.

Methods: A radiomic frailty cohort with 101 patients was included in the analysis (65 ± 15 years, 55 men). A total of 44 texture features were extracted from the segmented muscle area of the ultrasound images of the anterior thigh. Univariate and multivariate analyses were performed to assess the image data sets and clinical data.

Results: Our results showed that the heterogeneity of muscle was associated with an increased incidence of hearing impairment, stroke, myocardial infarction, dementia/memory loss, and falls in the following two years. Regression analysis revealed a muscle radiomic model with 87.1% correct predictive value with good sensitivity and moderate specificity (p = 0.001).

Conclusion: It is possible to develop and identify image-based phenotypes in the elderly population. The muscle radiomic model needs to further be validated. Future studies correlated with biological data (genomics, transcriptomics, metabolomics, etc.) will give further insights into the biological basis and molecular processes of the developed radiomic model.

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.

Value-added Opportunistic CT Screening: State of the Art

Opportunistic CT screening leverages robust imaging data embedded within abdominal and thoracic scans that are generally unrelated to the specific clinical indication and have heretofore gone largely unused. This incidental imaging information may prove beneficial to patients in terms of wellness, prevention, risk profiling, and presymptomatic detection of relevant disease. The growing interest in CT-based opportunistic screening relates to a confluence of factors: the objective and generalizable nature of CT-based body composition measures, the emergence of fully automated explainable AI solutions, the sheer volume of body CT scans performed, and the increasing emphasis on precision medicine and value-added initiatives. With a systematic approach to body composition and other useful CT markers, initial evidence suggests that their ability to help radiologists assess biologic age and predict future adverse cardiometabolic events rivals even the best available clinical reference standards. Emerging data suggest that standalone "intended" CT screening over an unorganized opportunistic approach may be justified, especially when combined with established cancer screening. This review will discuss the current status of opportunistic CT screening, including specific body composition markers and the various disease processes that may be impacted. The remaining hurdles to widespread clinical adoption include generalization to more diverse patient populations, disparate technical settings, and reimbursement.

Fully Automated Abdominal CT Biomarkers for Type 2 Diabetes Using Deep Learning

Background CT biomarkers both inside and outside the pancreas can potentially be used to diagnose type 2 diabetes mellitus. Previous studies on this topic have shown significant results but were limited by manual methods and small study samples. Purpose To investigate abdominal CT biomarkers for type 2 diabetes mellitus in a large clinical data set using fully automated deep learning. Materials and Methods For external validation, noncontrast abdominal CT images were retrospectively collected from consecutive patients who underwent routine colorectal cancer screening with CT colonography from 2004 to 2016. The pancreas was segmented using a deep learning method that outputs measurements of interest, including CT attenuation, volume, fat content, and pancreas fractal dimension. Additional biomarkers assessed included visceral fat, atherosclerotic plaque, liver and muscle CT attenuation, and muscle volume. Univariable and multivariable analyses were performed, separating patients into groups based on time between type 2 diabetes diagnosis and CT date and including clinical factors such as sex, age, body mass index (BMI), BMI greater than 30 kg/m², and height. The best set of predictors for type 2 diabetes were determined using multinomial logistic regression. Results A total of 8992 patients (mean age, 57 years ± 8 [SD]; 5009 women) were evaluated in the test set, of whom 572 had type 2 diabetes mellitus. The deep learning model had a mean Dice similarity coefficient for the pancreas of 0.69 ± 0.17, similar to the interobserver Dice similarity coefficient of 0.69 ± 0.09 (P = .92). The univariable analysis showed that patients with diabetes had, on average, lower pancreatic CT attenuation (mean, 18.74 HU ± 16.54 vs 29.99 HU ± 13.41; P < .0001) and greater visceral fat volume (mean, 235.0 mL ± 108.6 vs 130.9 mL ± 96.3; P < .0001) than those without diabetes. Patients with diabetes also showed a progressive decrease in pancreatic attenuation with greater duration of disease. The final multivariable model showed pairwise areas under the receiver operating characteristic curve (AUCs) of 0.81 and 0.85 between patients without and patients with diabetes who were diagnosed 0-2499 days before and after undergoing CT, respectively. In the multivariable analysis, adding clinical data did not improve upon CT-based AUC performance (AUC = 0.67 for the CT-only model vs 0.68 for the CT and clinical model). The best predictors of type 2 diabetes mellitus included intrapancreatic fat percentage, pancreatic fractal dimension, plaque severity between the L1 and L4 vertebra levels, average liver CT attenuation, and BMI. Conclusion The diagnosis of type 2 diabetes mellitus was associated with abdominal CT biomarkers, especially measures of pancreatic CT attenuation and visceral fat. © RSNA, 2022 Online supplemental material is available for this article.