Deep Learning Reconstruction Algorithm-Based MRI Image Evaluation of Edaravone in the Treatment of Lower Limb Ischemia-Reperfusion Injury

Abstract

This research aimed to evaluate the therapeutic effect of edaravone on lower limb ischemia-reperfusion injury by MRI images of graph patch-based directional curvelet transform (GPBDCT), compression reconstruction algorithm. 200 patients with lower limb ischemia-reperfusion injury after replantation of severed limb were randomly divided into the observation group (edaravone treatment) and control group (Mailuoning injection treatment), with 100 cases in each group. MRI scanning and image processing using the GPBDCT algorithm were used to evaluate the therapeutic effect of the two groups of patients. The results showed that the signal noise ratio (SNR) (22.01), relative l 2 norm error (RLNE) (0.0792), and matching degree γ (0.9997) of the compression and reconstruction algorithm based on GPBDCT were superior to those of the conventional compression and reconstruction algorithm ( P < 0.05 ). MRI examination showed that the decrease of bleeding signal after treatment in the observation group was superior to that in the control group. The levels of superoxide dismutase (SOD) (15 ± 2.02), malondialdehyde (MDA) (2.27 ± 1.02), B cell lymphoma-2 (Bcl-2) (8.5 ± 1.02), Bcl-2-associated X (Bax) (3.7 ± 0.42), and Caspase-3 protein (35.9 ± 5.42) in the observation group before and after treatment were significantly higher than those in the control group ( P < 0.05 ). In conclusion, the GPBDCT-based compression reconstruction algorithm has a better effect on MRI image processing, and edaravone can better remove free radicals and alleviate apoptosis.