Analysis of the sensitivity and specificity of compressed sensing magnetic resonance imaging in the diagnosis of heart failure.

Background: Magnetic resonance imaging (MRI) is a powerful tool for predicting heart failure (HF) patient prognosis (including death), but it adversely affecting clinical diagnosis and work efficiency. Compressed sensing technology reconstructs and recovers signals using sampling points that are far below the requirement of traditional sampling laws, which can shorten the signal acquisition time without affecting the image quality of MRI. This study aimed to apply compressed sensing technology to the MRI images of patients with HF to evaluate its effectiveness in the diagnosis of HF. Although compressed sensing MRI technology has not yet been widely adopted in clinical practice, it has demonstrated favorable application prospects. Through continuous updating and optimization, it is expected to become a research hotspot in medical imaging, providing more valuable information for clinical work. Methods: In this study, 66 patients with acute ischemic stroke admitted to hospital were selected for the experimental group, and 20 patients with normal cardiac function who underwent physical examinations during the same period were selected for the control group. An MRI image reconstruction algorithm based on compressed sensing was developed and used in the cardiac MRI image processing. Results: The results showed that the e' and heart rate of the experimental group were significantly higher than those of the control group, and the E/e' ratio was significantly lower than that of the control group (P<0.05). The early peak filling rate (PFR1), the PFR1/the late peak filling rate (PFR2), the early filling volume (FV1), and the FV1/the filling volume (FV) of the experimental group were significantly higher than those of the control group, and the PFR2 and the late filling volume (FV2) of the experimental group were significantly lower than those of the control group (P<0.05). The diagnostic sensitivity, specificity, and the area under the curve (AUC) for the concentration-time of the PFR2 were 0.891, 0.788, and 0.904, respectively. The diagnostic sensitivity, specificity, and AUC for the FV2 were 0.902, 0.878, and 0.925, respectively. The peak signal to noise ratio and structural similarity of the images reconstructed using the oral contraceptives algorithm were significantly higher than those determined by the sensitivity coding algorithm and the orthogonal matching pursuit algorithm (P<0.05). Conclusions: The imaging algorithm based on compressed sensing had excellent processing effect on cardiac MRI and improved the image quality. Cardiac MRI imaging had good diagnostic performance for HF and had the value of clinical popularization.