Real-time detection of acromegaly from facial images with artificial intelligence.

OBJECTIVE: Despite improvements in diagnostic methods, acromegaly is still a late-diagnosed disease. In this study, it was aimed to automatically recognize acromegaly disease from facial images by using deep learning methods and to facilitate the detection of the disease. DESIGN: Cross-sectional, single-centre study. METHODS: The study included 77 acromegaly (52.56 ± 11.74, 34 males/43 females) patients and 71 healthy controls (48.47 ± 8.91, 39 males/32 females), considering gender and age compatibility. At the time of the photography, 56/77 (73%) of the acromegaly patients were in remission. Normalized images were obtained by scaling, aligning, and cropping video frames. Three architectures named ResNet50, DenseNet121, and InceptionV3 were used for the transfer learning-based convolutional neural network (CNN) model developed to classify face images as "Healthy" or "Acromegaly". Additionally, we trained and integrated these CNN machine learning methods to create an Ensemble Method (EM) for facial detection of acromegaly. RESULTS: The positive predictive values obtained for acromegaly with the ResNet50, DenseNet121, InceptionV3, and EM were calculated as 0.958, 0.965, 0.962, and 0.997, respectively. The average sensitivity, specificity, precision, and correlation coefficient values calculated for each of the ResNet50, DenseNet121, and InceptionV3 models are quite close. On the other hand, EM outperformed these three CNN architectures and provided the best overall performance in terms of sensitivity, specificity, accuracy, and precision as 0.997, 0.997, 0.997, and 0.998, respectively. CONCLUSIONS: The present study provided evidence that the proposed AcroEnsemble Model might detect acromegaly from facial images with high performance. This highlights that artificial intelligence programs are promising methods for detecting acromegaly in the future.

A practice report of bladder injuries due to gunshot wounds in Syrian refugees.

BACKGROUND: This study was intended to report our recent experience of bladder injuries due to gunshots in the Syrian conflict and review the literature regarding diagnosis and treatment. METHODS: Twenty-two cases with abdominal and inguinal firearm wounds and bladder ruptures sustained in the Syrian conflict were reported. Age, mechanism/location of damage, associated injuries, Revised Trauma Score (RTS), Injury Severity Score (ISS), Trauma Injury Severity Score (TRISS), and complications were analyzed. The severity of the bladder injuries was classified according to the American Association for the Surgery of Trauma Organ Injury Scaling (AAST-OIS grade ?II database).The type of the bladder rupture was defined according to the classification System for Bladder Injury Based on Findings at CT Cystography. RESULTS: The mean age was 26 years (range, 18-36). The mean ISS was 22 (10-57), mean TRISS was 0.64 (0.004-0.95), and mean RTS was 6.97 (3.30-7.84). In the mortality group, the mean ISS, TRISS, and RTS were 48 (36-57), 0.016 (0.004-0.090), and 4.10 (3.30-4.92), respectively; whereas, the mean ISS, TRISS, and RTS were found as 21 (10-26), 0.64 (0.49-0.95), and 7.24 (5.65-7.84), respectively in the survival group (P=0.06). CT-cystography showed seventeen type 2, three type 4, and two type 5 bladder injuries. According to AAST-OIS, there were nine grade IV, six grade III, five grade II, and two grade V injuries. CONCLUSION: In war settings, when injuries are often severe and multiple surgical exploration and closure are mandatory, mortality risk is associated with high ISS and low TRISS and RTS values.