Xi, Yin

Abstract Background Cardiomegaly is a clinically significant incidental finding on chest computed tomography (CT) associated with heart failure, arrhythmias, and sudden cardiac death. Qualitative radiologist assessment is variable, and automated AI tools may enable objective opportunistic cardiac volumetry. Purpose To evaluate whether AI-enabled total cardiac volume (TCVAI) derived from non-ECG-gated, non-contrast chest CT can identify cardiomegaly as defined by echocardiography. Materials and Methods This retrospective study included 307 consecutive patients (median age, 67 years; 56% male) who underwent non-contrast chest CT at a single center on 7 scanner types (4 vendors) and clinically indicated echocardiography within 31 days. A commercially available AI tool (AI-Rad Companion, Siemens Healthineers) automatically quantified TCVAI, indexed to body surface area (TCVAI/BSA). Echocardiography reports were reviewed for chamber dilation and left ventricular hypertrophy (LVH), collectively defined as cardiomegaly. Associations between TCVAI/BSA and echocardiographic findings were assessed using correlation, ordinal regression, and receiver operating characteristic (ROC). Interscan repeatability was evaluated in 248 patients with 544 repeat CT examinations. Prespecified sex-specific thresholds were tested in a temporally independent validation cohort of 50 patients. Results Median TCVAI was higher in patients with cardiomegaly than those without (1061.9 vs 798.4 mL; P < .001). TCVAI/BSA was associated with chamber dilation and LVH severity on univariate analysis and remained associated in multivariable ordinal models, except for right ventricular dilation. Discriminatory performance was fair to good, with area under the curve (AUC) 0.81 (95% CI, 0.75-0.87) in men and 0.77 (95% CI, 0.69-0.85) in women. Interscan repeatability was excellent (intraclass correlation coefficient [ICC]: 0.93). In independent validation, performance ranged from sensitivity 89.3%/specificity 27.3% at a high-sensitivity threshold to sensitivity 28.6%/specificity 100% at a high-specificity threshold. Conclusion AI-derived cardiac volume from routine chest CT shows fair to good performance for identifying echocardiography-defined cardiomegaly with high measurement repeatability, supporting a potential role for automated cardiac volumetry as an objective, opportunistic biomarker.

Abstract Background Dual‐contrast imaging of iodine and bismuth has shown promise in previous phantom and animal studies utilizing spectral CT. However, these studies often employed Pepto‐Bismol containing bismuth subsalicylate with dosages exceeding the recommended limits for human consumption, limiting their clinical applicability. Purpose The purpose of this study was to improve iodine–bismuth dual‐contrast imaging on a clinical photon‐counting CT (PCCT) system using a noise‐optimized virtual monoenergetic imaging (VMI) approach. Methods Four bismuth samples (0.6, 1.3, 2.5, and 5.1 mg/mL) and three iodine rods (1.0, 2.0, and 5.0 mg/mL) were inserted into a multi‐energy CT phantom and scanned on a PCCT system at 140 kV. VMIs were generated from 40 to 190 keV in 10 keV increments. Iodine and bismuth maps were computed for all possible keV pairs using a generic image‐based three‐material decomposition method and compared with maps generated from the original low‐/high‐energy PCCT images. Mass concentrations, noise levels, and individual as well as joint root‐mean‐square error (RMSE) for iodine and bismuth were measured to determine the optimal keV pair. The contrast‐to‐noise ratios (CNRs) of low concentration samples (bismuth: 0.6 and 1.3 mg/mL; iodine: 1.0 mg/mL) were calculated at the optimal keV pair and compared to the values determined with the original PCCT images. In an IRB‐approved feasibility study, a research patient was administered two doses of Pepto‐Bismol prior to a routine abdomen‐pelvis CT scan. Material decomposition was performed using both the original low‐/high‐energy images and the optimal VMI pair identified in the phantom study. Bismuth signals in the stomach and proximal small bowel were assessed qualitatively and quantitatively. Results The VMI pair of 110 and 190 keV was determined to be optimal, achieving the lowest joint RMSE of 0.49 mg/mL, compared to 1.42 mg/mL for the original low‐/high‐energy pair. It also yielded the highest CNR, representing a 190–318% improvement over the original low/high‐energy decomposition. Qualitatively, both phantom and patient studies demonstrated improved iodine–bismuth separation and reduced noise using the optimized VMI pair. Conclusions These findings suggest that noise‐optimized VMI selection can enhance dual‐contrast material decomposition performance on clinical PCCT, supporting its potential for translation into gastrointestinal imaging applications.