Biomedical Applications of Wavelet Transform Algorithm on Deep Learning Ultrasonic Image Optimization as a Prognosis Model for Acute Myocarditis

We aimed to investigate the biomedical methods of wavelet transform algorithm on ultrasonic image denoising algorithm and the risk factors for the adverse prognostic events of patients with myocarditis and analyse its correlation with free triiodothyronine (FT3) level. A retrospective study was performed to include 68 patients diagnosed with acute myocarditis (AM). The included patients were enrolled into adverse event (AE) group ( n = 7) and non-adverse event (NAE) group ( n = 61). The clinical data, laboratory examination indicators, echocardiographic parameters, and thyroid functions between the patients in the two groups at admission were compared. Besides, wavelet transform (WT) algorithm was employed to process ultrasonic images containing noises. Univariate and multivariate analysis were performed using Logistic regression model. It was demonstrated that peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) (35.279, 0.847) of wavelet transform algorithm were higher than those of denoising convolutional neural network (DnCNN) algorithm (30.673, 0.582) and Red-Net algorithm (28.489, 0.638). In the AE group, the QRS interval was longer (102 (93, 135) ms versus 86 (79, 102) ms), the proportion of prolonged QRS period was higher (28.57%, 9.83%), and the creatine kinase isoenzyme, a marker of myocardial injury, was higher 32.87 (13.64, 78.62) U/L versus 12.02 (9.89, 27.65) U/L], and the level of FT3 was lower 1.87 (1.23, 2.36) pg/mL versus 2.83 (1.83, 3.45) pg/mL compared to the NAE group. The left ventricular ejection fraction (LVEF) in the adverse event group was lower than that in the non-adverse event group 45.78 (36.18, 54.32) % versus 63.72 (54.82, 64.68). Multivariate Logistic regression analysis showed that the risk factors for adverse events in patients with acute myocarditis included QRS interval > 120 ms (OR = 1.021), creatine kinase isoenzyme > 24 U/L (OR = 1.024), FT3 (OR = 0.067), and LVEF < 50% (OR = 0.973). This work confirmed that the wavelet transform algorithm can optimize the image quality of echocardiography, improve the clarity, and provide a feasible idea for improving the prognosis of patients with acute myocarditis.