Effective Blind Image Deblurring Using Matrix-Variable Optimization

Luminosity rectified blind Richardson-Lucy deconvolution for single retinal image restoration

BACKGROUND AND OBJECTIVE

Due to imperfect imaging conditions, retinal images can be degraded by uneven/insufficient illumination, blurriness caused by optical aberrations and unintentional motions. Degraded images reduce the effectiveness of diagnosis by an ophthalmologist. To restore the image quality, in this research we propose the luminosity rectified Richardson-Lucy (LRRL) blind deconvolution framework for single retinal image restoration.

METHODS

We established an image formation model based on the double-pass fundus reflection feature and developed a differentiable non-convex cost function that jointly achieves illumination correction and blind deconvolution. To solve this non-convex optimization problem, we derived the closed-form expression of the gradients and used gradient descent with Nesterov-accelerated adaptive momentum estimation to accelerate the optimization, which is more efficient than the traditional half quadratic splitting method.

RESULTS

The LRRL was tested on 1719 images from three public databases. Four image quality matrixes including image definition, image sharpness, image entropy, and image multiscale contrast were used for objective assessments. The LRRL was compared against the state-of-the-art retinal image blind deconvolution methods.

CONCLUSIONS

Our LRRL corrects the problematic illumination and improves the clarity of the retinal image simultaneously, showing its superiority in terms of restoration quality and implementation efficiency. The MATLAB code is available on Github.

Intelligent Algorithm-Based Ultrasound for Evaluating the Anesthesia and Nursing Intervention for Elderly Patients with Femoral Intertrochanteric Fractures

This study was aimed to explore the anesthesia, analgesia, and nursing intervention scheme for elderly patients undergoing the operation of intertrochanteric fracture of femur under the guidance of ultrasound optimized by blind deblurring algorithm. Fifty elderly patients undergoing intertrochanteric femoral surgery were randomly enrolled into control group (tracheal intubation intravenous anesthesia + routine nursing) and experimental group (ultrasound-guided nerve block anesthesia + comprehensive nursing based on blind deblurring algorithm), with 25 patients in each group. The effects of anesthesia and recovery were evaluated in the two groups. The results showed that the image evaluation index of blind deblurring algorithm was superior to other algorithms (BM3D, DnCNN, and Red-Net), which improved the quality of ultrasound imaging and was more conducive to intraoperative anesthesia guidance. At the beginning and end of intubation and operation, the fluctuation range of mean arterial pressure (MAP) and heart rate (HR) in the experimental group was lower than that in the control group. The maintenance time of sensory and motor anesthesia block (7.53 ± 1.47 h, 5.45 ± 1.36 h) was longer than that of control group (3.38 ± 1.26 h, 3.02 ± 1.31 h). Visual Analogue Scale/Score (VAS) scores at 6 h, 12 h, and 24 h after surgery were lower than those in the control group. The effective rate of nursing and the incidence of complications (92% and 8%) were better than the control group (80% and 16%), and the difference was statistically significant (P < 0.05). In summary, the optimization effect of blind deblurring algorithm was good, which can improve the quality of ultrasound-guided surgery and help in the smooth implementation of surgery. Moreover, nerve block anesthesia and comprehensive nursing were of great value in postoperative analgesia and recovery of patients.