Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network.

Neovascular age-related macular degeneration (nAMD) can result in blindness if left untreated, and patients often require repeated anti-vascular endothelial growth factor injections. Although, the treat-and-extend method is becoming popular to reduce vision loss attributed to recurrence, it may pose a risk of overtreatment. This study aimed to develop a deep learning model based on DenseNet201 to predict nAMD recurrence within 3 months after confirming dry-up 1 month following three loading injections in treatment-naïve patients. A dataset of 1076 spectral domain optical coherence tomography (OCT) images from 269 patients diagnosed with nAMD was used. The performance of the model was compared with that of 6 ophthalmologists, using 100 randomly selected samples. The DenseNet201-based model achieved 53.0% accuracy in predicting nAMD recurrence using a single pre-injection image and 60.2% accuracy after viewing all the images immediately after the 1st, 2nd, and 3rd injections. The model outperformed experienced ophthalmologists, with an average accuracy of 52.17% using a single pre-injection image and 53.3% after examining four images before and after three loading injections. In conclusion, the artificial intelligence model demonstrated a promising ability to predict nAMD recurrence using OCT images and outperformed experienced ophthalmologists. These findings suggest that deep learning models can assist in nAMD recurrence prediction, thus improving patient outcomes and optimizing treatment strategies.

Effect of Transcranial Direct Current Stimulation with Balance Training in a Middle-Aged Population: Randomized Double-Blind Sham-Controlled Trial.

Introduction: The first signs of deteriorated balance impairment begin during middle age. Early intervention could delay the fall risk in older populations; hence, addressing balance deficits during this age is crucial. The authors aimed to determine the effects of transcranial direct current stimulation (tDCS) combined with balance training (BT) on the improvement of static and dynamic balance in a middle-aged population, along with the participants' safety and satisfaction. Methods: Participants (n = 28) were randomized into two groups: active tDCS (active tDCS + BT) and sham tDCS (sham tDCS + BT). Both groups received the intervention thrice a week for 6 weeks. Dynamic and static balance were assessed by sway rate changes with eyes open and closed, and the functional reach test and a postintervention survey were conducted to assess participants' safety and satisfaction. Results: The active tDCS group showed significantly greater static and dynamic balance improvements in sway scores. The surveys demonstrated the safety of the program and satisfaction of 80% of the participants with the combined intervention. Conclusion: tDCS could be used in a middle-aged population as part of regular BT to improve balance and minimize the risk of balance deficits in older populations while ensuring patient safety and satisfaction. This study is a subanalysis of a larger clinical trial that included young adults as well (Clinical trial number: KCT0007414).

Effect of tDCS Combined With Physical Training on Physical Performance in a Healthy Population.

Purpose: The effectiveness of transcranial direct current stimulation (tDCS) combined with physical training has shown inconsistent results through research. Hence, a study utilizing a long-term tDCS application over the primary motor cortex and a large sample size is required to determine whether tDCS combined with physical training can increase physical performance (muscular strength, endurance, and explosive strength) in healthy adults. Material and methods: Fifty-six healthy adults were randomly distributed into two groups: active (active tDCS+ physical training) and sham (sham tDCS + physical training) and received the intervention three times per week for six weeks. Muscle strength was assessed using maximal isometric muscle strength (MIMS) by a digital dynamometer. Muscular endurance and lower limb explosive strength were assessed by using muscle fitness testing (MFT), and the Sargent jump test. Results: The active and sham groups exhibited significant improvement in all measured parameters in intragroup analyses. However, intergroup analyses revealed no significant difference between the groups. Conclusion: Our findings suggest that only physical training improved MIMS in the upper and lower extremities, MFT endurance scores, and lower limb explosive power. Thus, tDCS failed to demonstrate its effectiveness in a healthy population according to the protocol used in this study.

Detecting medial patellar luxation with ensemble deep convolutional neural network based on a single rear view image of the hindlimb.

Medial patellar luxation (MPL) is a common orthopedic disease in dogs, which predisposes elderly and small-breed dogs. Unlike in humans, diagnosis in the early course of the disease is challenging because symptoms and joint-pain expression in canines are vague. Herein, we introduced a deep-learning system to diagnose MPL using a single rear-view hindlimb image. We believe that this is the first attempt to build a deep-learning system to diagnose MPL based on image analysis. Notably, 7689 images were collected from 2653 dogs in 30 private animal clinics between July 2021 and July 2022. Model performance was compared with ResNet50, VGG16, VGG19, Inception-V3, and veterinarian performance. For performance comparison, a professional veterinarian with > 10 years of experience selected images of 25 normal dogs and 25 dogs with MPL. The proposed model showed the highest performance, with 92.5% accuracy, whereas human experts showed an average accuracy of 55.2%. Therefore, our model can diagnose MPL using only a single rear-view hindlimb image. Furthermore, to solve the image uncertainty caused by the input image noise, we used a one-class SVM and ensemble learning methods to ensure model robustness. Our study will help diagnose MPL in clinical settings using a single rear-view hindlimb image.

Inhibitory Effects of ECQ on Indomethacin-Induced Gastric Damage in Rats.

We investigated inhibitory effects of extract containing quercetin-3-O-ß-D-glucuronopyranoside (ECQ) extracted from Rumex Aquaticus Herba on indomethacin-induced gastric damage in Rats. Gastritis was induced in male Sprague-Dawley rats (200~220 g) by oral administration of indomethacin at a dose of 40 mg/kg. One hour before administration of indomethacin, animals were orally pretreated with ECQ at doses of 0.3, 1, 3 or 10 mg/kg. Six hours after indomethacin administration, the rats were sacrificed and the stomach was excised and opened along the greater curvature, and the surface area of gastric lesion was measured using optical microscope. Superoxide dismutase (SOD), catalase (CAT), myeloperoxidase (MPO) activities and malondialdehyde (MDA) levels were measured by ELISA. Western blot analysis was performed to detect protein expression of SOD-2. Linear hemorrhagic mucosal lesions were observed in the stomach 6 hours after oral administration of indomethacin. Pretreatment with ECQ significantly reduced the severity of the lesions in a dose-dependent manner. It also inhibited the reductions in SOD and CAT activities and SOD expression by the indomethacin-induced gastric damage. In addition, the pretreatment with ECQ significantly suppressed the elevation of the MPO activity and the MDA levels induced by indomethacin. These results suggest that ECQ has the inhibitory effects via antioxidative action against indomethacin-induced gastritis in rats.