No abstract

Background Grayscale image attributes of computed tomography (CT) of pulmonary scans contain valuable information relating to patients with respiratory ailments. These attributes are used to evaluate the severity of lung conditions of patients confirmed to be with and without COVID‐19. Method Five hundred thirteen CT images relating to 57 patients (49 with COVID‐19; 8 free of COVID‐19) were collected at Namazi Medical Centre (Shiraz, Iran) in 2020 and 2021. Five visual scores (VS: 0, 1, 2, 3, or 4) are clinically assigned to these images with the score increasing with the severity of COVID‐19‐related lung conditions. Eleven deep learning and machine learning techniques (DL/ML) are used to distinguish the VS class based on 12 grayscale image attributes. Results The convolutional neural network achieves 96.49% VS accuracy (18 errors from 513 images) successfully distinguishing VS Classes 0 and 1, outperforming clinicians’ visual inspections. An algorithmic score (AS), involving just five grayscale image attributes, is developed independently of clinicians’ assessments (99.81% AS accuracy; 1 error from 513 images). Conclusion Grayscale CT image attributes can be successfully used to distinguish the severity of COVID‐19 lung damage. The AS technique developed provides a suitable basis for an automated system using ML/DL methods and 12 image attributes.

Background. Rhinoplasty is one of the most common types of cosmetic surgery undertaken. In most rhinoplasty patients, an osteotomy is used to reshape the nasal pyramid. The most common complications following osteotomy are edema and ecchymosis. Edema and ecchymosis have a significant effect on a patients’ satisfaction with surgery and their return to social activities. For this purpose, various methods have been used to reduce edema and ecchymosis, including intravenous injection of corticosteroids, cold compresses, and tranexamic acid. Objective. To reduce edema and ecchymosis in rhinoplasty patients by administering a subcutaneous injection of dexamethasone and thereby prevent unwanted systemic side effects of corticosteroid treatments. Method. We conduct a hospital-based nonrandomised study of rhinoplasty patients, with their informed consent treated over the course of one year. Dexamethasone was injected on one side of consenting patient’s face immediately before surgery and the results were compared with the opposite side that was not injected. The face images of patients were taken on the front view on the first, third, seventh, and fourteenth days following the treatment. The grade of edema and ecchymosis encountered in each patient was determined by three ENT specialists. The degree of edema and ecchymosis was compared on the injected and noninjected sides and the findings were statistically analysed. The nonrandomised study considered 42 rhinoplasty patients. The mean age of patients was 27.9 years and their age ranged between 17 and 52 years. For 20 patients (47.6%), injection was performed on the right side, and for 22 patients (52.3%), injection was performed on the left side. Findings. The statistical analysis of patient outcomes reveals that a supraperiosteal injection of dexamethasone was not effective in reducing edema and ecchymosis after rhinoplasty.