Use of radiomics to differentiate left atrial appendage thrombi and mixing artifacts on single-phase CT angiography.

To assess if radiomics can differentiate left atrial appendage (LAA) contrast-mixing artifacts and thrombi on early-phase CT angiography without the need for late-phase images. Our study included 111 patients who underwent early- and late-phase, contrast-enhanced cardiac CT. Of these, 79 patients had LAA filling defects from thrombus (n = 46, mean age: 72  ±  12 years, M:F 26:20) or contrast-mixing artifact (n = 33, mean age: 71  ±  13 years, M:F 21:12) on early-contrast-enhanced phase. The remaining 32 patients (mean age: 66  ±  10 years, M:F 19:13) had homogeneous LAA opacification without filling defects. The entire LAA volume on early-phase CT images was manually segmented to obtain radiomic features (Frontier, Siemens). A radiologist assessed for the presence of LAA filling defects and recorded the size and mean CT attenuation (HU) of filling defects and normal LAA. The data were analyzed using multiple logistic regression with receiver operating characteristics area under the curve (AUC) as an output. The radiologist correctly identified all 32 patients without LAA filling defects, 42/46 LAA with thrombi, and 23/33 contrast mixing artifacts. Although HU of LAA thrombi and contrast mixing artifacts was significantly different, with the lowest AUC (0.66), it was inferior to both radiologist assessment and radiomics (p = 0.05). Combination of radiologist assessment and radiomics (AUC 0.92) was superior to HU (0.66), radiomics (0.85), and radiologist (0.80) alone (p < 0.008). Radiomics can differentiate between LAA filling defects from thrombi and contrast mixing artifacts on early-phase contrast-enhanced CT images without the need for late-phase CT.

Differentiation of deep venous thrombosis from femoral vein mixing artifact on routine abdominopelvic CT.

PURPOSE: The objective of this study is to assess the performance of qualitative and quantitative imaging features for the differentiation of deep venous thrombosis (DVT) from mixing artifact on routine portal venous phase abdominopelvic CT. METHODS: This retrospective study included 40 adult patients with a femoral vein filling defect on portal venous phase CT and a Duplex ultrasound (n = 36) or catheter venogram (n = 4) to confirm presence or absence of DVT. Two radiologists (R1, R2) assessed the femoral veins for various qualitative and quantitative features. RESULTS: 60% of patients were confirmed to have DVT and 40% had mixing artifact. Features with significantly greater frequency in DVT than mixing artifact (all p ≤ 0.006) were central location (R1 90% vs. 28%; R2 96% vs. 31%), sharp margin (R1 83% vs. 28%; R2 96% vs. 31%), venous expansion (R1 48% vs. 6%, R2 56% vs. 6%), and venous wall enhancement (R1 62% vs. 0%; R2 48% vs. 0%). DVT exhibited significantly lower mean attenuation than mixing artifact (R1 42.1 ± 20.2 vs. 57.1 ± 23.6 HU; R2 43.6 ± 19.4 vs. 58.8 ± 23.4 HU, p ≤ 0.031) and a significantly larger difference in vein diameter compared to the contralateral vein (R1 0.4 ± 0.4 vs. 0.1 ± 0.2 cm; R2 0.3 ± 0.4 vs. 0.0 ± 0.1 cm, p ≤ 0.026). At multivariable analysis, central location and sharp margin were significant independent predictors of DVT for both readers (p ≤ 0.013). CONCLUSION: Awareness of these qualitative and quantitative imaging features may improve radiologists' confidence for differentiating femoral vein DVT and mixing artifact on routine portal venous phase CT. However, given overlap with mixing artifact, larger studies remain warranted.