Analysis of the perivascular fat attenuation index and quantitative plaque parameters in relation to haemodynamically impaired myocardial ischaemia.

To investigate the correlation between quantitative plaque parameters, the perivascular fat attenuation index, and myocardial ischaemia caused by haemodynamic impairment. Patients with stable angina who had invasive flow reserve fraction (FFR) assessment and coronary artery computed tomography (CT) angiography were retrospectively enrolled. A total of 138 patients were included in this study, which were categorized into the FFR < 0.75 group (n = 43), 0.75 ≤ FFR ≤ 0.8 group (n = 37), and FFR > 0.8 group (n = 58), depending on the range of FFR values. The perivascular FAI and CTA-derived parameters, including plaque length (PL), total plaque volume (TPV), minimum lumen area (MLA), and narrowest degree (ND), were recorded for the lesions. An FFR < 0.75 was defined as myocardial-specific ischaemia. The relationships between myocardial ischaemia and parameters such as the PL, TPV, MLA, ND, and FAI were analysed using a logistic regression model and receiver operating characteristic (ROC) curves to compare the diagnostic accuracy of various indicators for myocardial ischaemia. The PL, TPV, ND, and FAI were greater in the FFR < 0.75 group than in the grey area group and the FFR > 0.80 group (all p < 0.05). The MLA in the FFR < 0.75 group was lower than that in the grey area group and the FFR > 0.80 group (both P < 0.05). There were no significant differences in the PL, TPV, or ND between the grey area and the FFR > 0.80 group, but there was a significant difference in the FAI. The coronary artery lesions with FFRs ≤ 0.75 had the greatest FAI values. Multivariate analysis revealed that the perivascular FAI and PL density are significant predictors of myocardial ischaemia. The FAI has some predictive value for myocardial ischaemia (AUC = 0.781). After building a combination model using the FAI and plaque length, the predictive power increased (AUC, 0.781 vs. 0.918), and the change was statistically significant (P < 0.001). The combined model of PL + FAI demonstrated great diagnostic efficacy in identifying myocardial ischaemia caused by haemodynamic impairment; the lower the FFR was, the greater the FAI. Thus, the PL + FAI could be a combined measure to securely rule out myocardial ischaemia.

Preclinical validation of a novel deep learning-based metal artifact correction algorithm for orthopedic CT imaging.

PURPOSE: To validate a novel deep learning-based metal artifact correction (MAC) algorithm for CT, namely, AI-MAC, in preclinical setting with comparison to conventional MAC and virtual monochromatic imaging (VMI) technique. MATERIALS AND METHODS: An experimental phantom was designed by consecutively inserting two sets of pedicle screws (size Φ 6.5 × 30-mm and Φ 7.5 × 40-mm) into a vertebral specimen to simulate the clinical scenario of metal implantation. The resulting MAC, VMI, and AI-MAC images were compared with respect to the metal-free reference image by subjective scoring, as well as by CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and correction accuracy via adaptive segmentation of the paraspinal muscle and vertebral body. RESULTS: The AI-MAC and VMI images showed significantly higher subjective scores than the MAC image (all p < 0.05). The SNRs and CNRs on the AI-MAC image were comparable to the reference (all p > 0.05), whereas those on the VMI were significantly lower (all p < 0.05). The paraspinal muscle segmented on the AI-MAC image was 4.6% and 5.1% more complete to the VMI and MAC images for the Φ 6.5 × 30-mm screws, and 5.0% and 5.1% for the Φ 7.5 × 40-mm screws, respectively. The vertebral body segmented on the VMI was closest to the reference, with only 3.2% and 7.4% overestimation for Φ 6.5 × 30-mm and Φ 7.5 × 40-mm screws, respectively. CONCLUSIONS: Using metal-free reference as the ground truth for comparison, the AI-MAC outperforms VMI in characterizing soft tissue, while VMI is useful in skeletal depiction.