ABSTRACT
Objective:To explore the feasibility of cardiac T 2 weighted dark blood sequence (T 2W-DB) based on artificial intelligence assisted compression-sensing(ACS) in clinical cardiac MR examination, compared with the conventional cardiac fast spin-echo T 2W-DB sequence. Methods:A total of 38 patients referred for cardiac MR examination in Tongji Hospital were enrolled prospectively from August to December 2021. The conventional T 2W-DB scan and the single-shot ACS T 2W-DB scan were acquired at continuous short-axial slices covering the whole left ventricle in all patients, and the acquisition time of each scan was recorded. The image quality of the two sequences was evaluated by the objective quantitative parameters and the subjective scoring methods, respectively. The signal to noise ratio (SNR), the contrast to noise ratio of the interventricular septum to blood pool (CNR), and the sharpness of the images were calculated. The subjective scoring was to evaluate the overall image quality, the effect of blood pool suppression, the visibility of right ventricular free wall, left ventricular free wall, and interventricular septum with a 5-point Likert scale. The intraclass correlation coefficient and Kendall W were calculated to evaluate the interobserver agreement of the objective quantitative parameters and subjective scoring. The paired t-test or Wilcoxon test was used to compare the difference in acquisition time, objective quantitative parameters and subjective scoring between the conventional T 2W-DB and the single-shot ACS T 2W-DB. Results:The inter-observer agreement between the single-shot ACS T 2W-DB and conventional T 2W-DB was good in all the objective quantitative parameters and subjective scoring of image quality ( P<0.05 for all). Compared with conventional T 2W-DB, acquisition time of single-shot ACS T 2W-DB was remarkably shortened [(85.8±14.7) s vs. (16.9±3.0) s, t=35.42, P<0.001]. Compared with SNR (66.4±29.0) and CNR(61.8±28.6) of conventional T 2W-DB, single-shot ACS T 2W-DB had significantly higher SNR(110.8±36.8, t=-8.13, P?0.001) and CNR(88.2±31.1, t=-5.89, P?0.001). Compared with conventional T 2W-DB, single-shot ACS T 2W-DB had better blood pool inhibition effect (4.6±0.6 vs. 4.7±0.5, Z=-2.64, P=0.008). There was no significant difference in overall image quality, visibility of right ventricular free wall, left ventricular free wall, and interventricular septum between the two sequences( P>0.05 for all). Conclusions:In cardiac MR examination, compared with the conventional T 2W-DB sequence, the single-shot ACS T 2W-DB sequence can significantly shorten the acquisition time and obtain better image quality.
ABSTRACT
Objective:To investigate the value of chest CT quantitative index in clinical classification and lung injury severity evaluation of COVID-19.Methods:The current study retrospectively analyzed the clinical and CT data of 438 patients with COVID-19 between January 2020 and March 2020 in Tongji Hospital, Tongji Medical College, Huazhong University of Science & Technology. The clinical types included common type ( n=146), severe type ( n=247) and critical type ( n=45). The chest CT indexes of all patients were quantitatively analyzed by artificial intelligence (AI) deep learning, including whole lung volume, CT lung opacification, ground glass opacification volume (GGO volume; CT value<-300 HU), solid opacification volume (SO volume; CT value ≥-300 HU) and the ratio of volume to the whole lung volume, the ratio of SO volume to GGO volume (SO volume/GGO volume). Kruskal-Wallis test was used to conduct statistical analysis of the differences in quantitative parameters among clinical types, and multiple ordered logistic regression was used to analyze the correlation between quantitative parameters and clinical types. Results:Among the 438 patients diagnosed with COVID-19, severe and critical patients were older ( P<0.05), and most of the critical patients were male ( P<0.05). The main clinical manifestations of all clinical types were fever, followed by cough, fatigue, chest tightness, dyspnea, gastrointestinal symptoms and so on. GGO volume was the main CT manifestation of all the three clinical subtypes. The whole-lung opacification volume, GGO volume, SO volume and their proportions in whole-lung volume significantly increased from common, severe to critical types (all P<0.05). SO volume/GGO volume increased with the severity of clinical type [common type 0.12 (0.03, 0.34), severe type 0.29 (0.11, 0.59), critical type 0.61 (0.39, 0.97)]. Multiple ordered logistic regression analysis showed that whole-lung opacification volume (OR=1.009), SO volume/GGO volume (OR=1.866), GGO volume (OR=1.008) and SO volume (OR=1.016) had a significant positive effect on the severity of clinical typing ( P<0.01). Conclusion:Quantitative indicators of chest CT based on deep learning algorithm (SO volume, GGO volume, SO volume/GGO volume) are closely related to the clinical severity of COVID-19.