Search

While Facial Expression Recognition (FER) has become a broadly applied technology in tracking individual people's emotions, its application in estimating emotion in a human-to-human dyadic interaction is still relatively sparse. This paper describes a study where FER is applied to a dyadic video-mediated interaction to collect facial interaction data that will be used to predict the emotions of one of the interlocutors. To realize this, we utilized the histogram of oriented gradients algorithm to detect human faces from videos by analyzing every frame. Then, we used a Deep Neural Networks (DNN) model to detect the facial expressions of two people who are having a conversation on videos. We measured the facial patterns as indicators of emotions of both interlocutors during the whole interaction. Afterward, we trained a Long Short-Term Memory (LSTM) model to estimate one person's emotions from the video. We performed the analysis on videos of a specific psychiatrist and his patients; then, we performed the patients' emotion estimation. This work shows how our multi-stage DNN (Mini-Xception) and LSTM models can predict the reaction emotions using the patient's facial expressions during the interaction. We believe that the proposed method can be applied to the future generation of facial expressions of virtual characters or social robots when they interact with humans. [ABSTRACT FROM AUTHOR]

Facial expression recognition using deep neural networks has become very popular due to their successful performances. However, the datasets used during the development and testing of these methods lack a balanced distribution of races among the sample images. This leaves a possibility of the methods being biased toward certain races. Therefore, a concern about fairness arises, and the lack of research aimed at investigating racial bias only increases the concern. On the other hand, such bias in the method would decrease the real-world performance due to the wrong generalization. For these reasons, in this study, we investigated the racial bias within popular state-of-the-art facial expression recognition methods such as Deep Emotion, Self-Cure Network, ResNet50, InceptionV3, and DenseNet121. We compiled an elaborated dataset with images of different races, cross-checked the bias for methods trained, and tested on images of people of other races. We observed that the methods are inclined towards the races included in the training data. Moreover, an increase in the performance increases the bias as well if the training dataset is imbalanced. Some methods can make up for the bias if enough variance is provided in the training set. However, this does not mitigate the bias completely. Our findings suggest that an unbiased performance can be obtained by adding the missing races into the training data equally. [ABSTRACT FROM AUTHOR]

Background: The role of preoperative upper gastrointestinal endoscopy before bariatric surgery is still debated, and a consensus among the international scientific community is lacking. The aims of this study, conducted in three different geographic areas, were to analyze data regarding the pathological endoscopic findings and report their impact on the decision-making process and surgical management, in terms of delay in surgical operation, modification of the intended bariatric procedure, or contraindication to surgery. Methods: This is a multicenter cross-sectional study using data obtained from three prospective databases. The preoperative endoscopic reports, patient demographics, Body Mass Index, type of surgery, and Helicobacter pylori status were collected. Endoscopic findings were categorized into four groups: (1) normal endoscopy, (2) abnormal findings not requiring a change in the surgical approach, (3) clinically important lesions that required a change in surgical management or further investigations or therapy prior to surgery, and (4) findings that contraindicated surgery. Results: Between 2006 and 2020, data on 643 patients were analyzed. In all of the enrolled bariatric institutions, preoperative endoscopy was performed routinely. A total of 76.2% patients had normal and/or abnormal findings that did not required a change in surgical management; in 23.8% cases a change or a delay in surgical approach occurred. Helicobacter pylori infection was detected in 15.2% patients. No patient had an endoscopic finding contraindicating surgery. Conclusions: The role of preoperative UGE is to identify a wide range of pathological findings in patients with obesity that could influence the therapeutic approach, including the choice of the proper bariatric procedure. Considering the anatomical modifications, the incidence of asymptomatic pathologies, and the risk of malignancy, we support the decision of performing preoperative endoscopy for all patients eligible for bariatric operation. [ABSTRACT FROM AUTHOR]

Purpose: Meningiomas arising from the confluence of the falx and tentorium (CFT) are a rare and challenging subset of meningiomas. Gamma Knife radiosurgery (GKRS) is well-established as a safe and effective management strategy for intracranial meningiomas, but its role in treating CFT meningiomas is not well-described. This paper reports the largest series focused exclusively on the outcomes of GKRS for CFT meningiomas. Methods: We retrospectively identified 20 CFT meningiomas out of 2031 meningioma patients who underwent GKRS at our institution between 1987 and 2021. Tumor control, overall survival (OS), and complications were recorded and analyzed. The median tumor margin dose was 13 Gy at the 50% isodose line. The median tumor volume treated was 4.4 cc (IQR 3.5–7.7). The median patient age was 58 years (range 33–83), the median MRI surveillance duration was 59 months (IQR 34–92), and the median overall follow-up duration was 92 months (IQR 42–201). Results: The local tumor control rate (PFS) at 5 and 10-years were 100% (N=10) and 83% (N=4), respectively. Eight patients had stable tumor volumes and 11 patients had regression. One patient with a twice-operated tumor had delayed progression at 7.5 years and was retreated with GKRS. No patient had adverse radiation effects during the period of MRI surveillance. The 5 and 10-year OS were 100% (N=13) and 100% (N=7), respectively. Conclusions: GKRS is a valuable therapeutic strategy for patients with newly diagnosed CFT meningiomas or progressive residual tumors after surgical resection. [ABSTRACT FROM AUTHOR]

This study aims to evaluate experimentally the potential of expansive soil stabilization using different additives: zeolitic tuff (ZT), lime, and a combination of lime and ZT. Four different percentages of ZT (10%, 20%, 25%, and 30%), three percentages of lime (2%, 4%, and 6%), and variable percentages of their combinations were used to stabilize the soil for pavement subbase application. Atterberg limits, pH, compaction, linear shrinkage, swelling, unconfined compressive strength (UCS), and California bearing ratio (CBR) tests were performed on treated and untreated soil specimens at different curing times. Results showed that ZT additives effectively reduced the plasticity, linear shrinkage, and swell potential in addition to increase the maximum dry unit weight, UCS, and CBR. The results of this study were supported by a microstructural analysis using scanning electron microscopy (SEM) associated with the energy-dispersive X-ray spectroscopy (SEM/EDX) technique. It was determined that the UCS and CBR values for the 4% lime stabilized soil increased by 22% and 70%, respectively, after the addition of 25% ZT. Based on evaluation of the results, an optimum mixture of 25% ZT and 4% lime stabilized soil can be used in pavement subbase applications as it achieved the minimum strength target. [ABSTRACT FROM AUTHOR]