Frontal Images Research Articles

Specific Binding Ratio Estimation of [123I]-FP-CIT SPECT Using Frontal Projection Image and Machine Learning.

This study aimed to develop a new convolutional neural network (CNN) method for estimating the specific binding ratio (SBR) from only frontal projection images in single-photon emission-computed tomography using [123I]ioflupane. We created five datasets to train two CNNs, LeNet and AlexNet: (1) 128FOV used a 0° projection image without preprocessing, (2) 40FOV used 0° projection images cropped to 40 × 40 pixels centered on the striatum, (3) 40FOV training data doubled by data augmentation (40FOV_DA, left-right reversal only), (4) 40FOVhalf, and (5) 40FOV_DAhalf, split into left and right (20 × 40) images of 40FOV and 40FOV_DA to separately evaluate the left and right SBR. The accuracy of the SBR estimation was assessed using the mean absolute error, root mean squared error, correlation coefficient, and slope. The 128FOV dataset had significantly larger absolute errors compared to all other datasets (p < 0. 05). The best correlation coefficient between the SBRs using SPECT images and those estimated from frontal projection images alone was 0.87. Clinical use of the new CNN method in this study was feasible for estimating the SBR with a small error rate using only the frontal projection images collected in a short time.

Predicting obstructive sleep apnea severity from craniofacial images using ensemble machine learning models.

Obstructive sleep apnea (OSA) is a prevalent disease affecting 10 to 15% of Americans and nearly one billion people worldwide. It leads to multiple symptoms including daytime sleepiness; snoring, choking, or gasping during sleep; fatigue; headaches; non-restorative sleep; and insomnia due to frequent arousals. Although polysomnography (PSG) is the gold standard for OSA diagnosis, it is expensive, not universally available, and time-consuming, so many patients go undiagnosed due to lack of access to the test. Given the incomplete access and high cost of PSG, many studies are seeking alternative diagnosis approaches based on different data modalities. Here, we propose a machine learning model to predict OSA severity from 2D frontal view craniofacial images. In a cross-validation study of 280 patients, our method achieves an average AUC of 0.780. In comparison, the craniofacial analysis model proposed by a recent study only achieves 0.638 AUC on our dataset. The proposed model also outperforms the widely used STOP-BANG OSA screening questionnaire, which achieves an AUC of 0.52 on our dataset. Our findings indicate that deep learning has the potential to significantly reduce the cost of OSA diagnosis.

Evaluating 3D human face reconstruction from a frontal 2D image, focusing on facial regions associated with foetal alcohol syndrome

Foetal alcohol syndrome (FAS) is a preventable condition caused by maternal alcohol consumption during pregnancy. The FAS facial phenotype is an important factor for diagnosis, alongside central nervous system impairments and growth abnormalities. Current methods for analysing the FAS facial phenotype rely on 3D facial image data, obtained from costly and complex surface scanning devices. An alternative is to use 2D images, which are easy to acquire with a digital camera or smart phone. However, 2D images lack the geometric accuracy required for accurate facial shape analysis. Our research offers a solution through the reconstruction of 3D human faces from single or multiple 2D images. We have developed a framework for evaluating 3D human face reconstruction from a single-input 2D image using a 3D face model for potential use in FAS assessment. We first built a generative morphable model of the face from a database of registered 3D face scans with diverse skin tones. Then we applied this model to reconstruct 3D face surfaces from single frontal images using a model-driven sampling algorithm. The accuracy of the predicted 3D face shapes was evaluated in terms of surface reconstruction error and the accuracy of FAS-relevant landmark locations and distances. Results show an average root mean square error of 2.62 mm. Our framework has the potential to estimate 3D landmark positions for parts of the face associated with the FAS facial phenotype. Future work aims to improve on the accuracy and adapt the approach for use in clinical settings. Significance: Our study presents a framework for constructing and evaluating a 3D face model from 2D face scans and evaluating the accuracy of 3D face shape predictions from single images. The results indicate low generalisation error and comparability to other studies. The reconstructions also provide insight into specific regions of the face relevant to FAS diagnosis. The proposed approach presents a potential cost-effective and easily accessible imaging tool for FAS screening, yet its clinical application needs further research.

SqueezExpNet: Dual-stage convolutional neural network for accurate facial expression recognition with attention mechanism

Facial expression recognition (FER) using a deep convolutional neural network (DCNN) is important and challenging. Although a substantial effort is made to increase FER accuracy through DCNN, previous studies are still not sufficiently generalisable for real-world applications. Traditional FER studies are mainly limited to controlled lab-posed frontal facial images, which lack the challenges of motion blur, head poses, occlusions, face deformations and lighting under uncontrolled conditions. In this work, we proposed a SqueezExpNet architecture that can take advantage of local and global facial information for a highly accurate FER system that can handle environmental variations. Our network was divided into two stages: a geometrical attention stage that possesses a SqueezeNet-like architecture to obtain local highlight information and a spatial texture stage comprising several squeezed and expanded layers to exploit high-level global features. In particular, we created a weighted mask of 3D face landmarks and used element-wise multiplication with a spatial feature in the first stage to draw attention to important local facial regions. Next, we input the face spatial image and its augmentations into the second stage of the network. Finally, like a classifier, a recurrent neural network was designed to collaborate the highlighted information from dual stages rather than simply using the SoftMax function, thereby aiding in overcoming the uncertainties. Experiments covering basic and compound FER tasks were performed using the three leading facial expression datasets. Our strategy outperformed the existing DCNN methods and achieved state-of-the-art results. The developed architecture, adopted research methodology and reported findings may find potential applications of real-time FER in surveillance, health and feedback systems.

COVID-19 chest X-ray image analysis by threshold-based segmentation

COVID-19 is a severe acute respiratory syndrome that has caused a major ongoing pandemic worldwide. Imaging systems such as conventional chest X-ray (CXR) and computed tomography (CT) were proven essential for patients due to the lack of information about the complications that could result from this disease. In this study, the aim was to develop and evaluate a method for automatic diagnosis of COVID-19 using binary segmentation of chest X-ray images. The study used frontal chest X-ray images of 27 infected and 19 uninfected individuals from Kaggle COVID-19 Radiography Database, and applied binary segmentation and quartering in MATLAB to analyze the images. The binary images of the lung were split into four quarters; Q1 = right upper quarter, Q2 = left upper quarter, Q3 = right lower, and Q4 = left lower. The results showed that COVID-19 patients had a higher percentage of attenuation in the lower lobes of the lungs (p-value < 0.00001) compared to healthy individuals, which is likely due to ground-glass opacities and consolidations caused by the infection. The ratios of white pixels in the four quarters of the X-ray images were calculated, and it was found that the left lower quarter had the highest number of white pixels but without a statistical significance compared to right lower quarter (p-value = 0.102792). This supports the theory that COVID-19 primarily affects the lower and lateral fields of the lungs, and suggests that the virus is accumulated mostly in the lower left quarter of the lungs. Overall, this study contributes to the understanding of the impact of COVID-19 on the respiratory system and can help in the development of accurate diagnostic methods.

Facial clues to the photosensitive trichothiodystrophy phenotype in childhood.

Among genodermatoses, trichothiodystrophies (TTDs) are a rare genetically heterogeneous group of syndromic conditions, presenting with skin, hair, and nail abnormalities. An extra-cutaneous involvement (craniofacial district and neurodevelopment) can be also a part of the clinical picture. The presence of photosensitivity describes three forms of TTDs: MIM#601675 (TTD1), MIM#616390 (TTD2) and MIM#616395 (TTD3), that are caused by variants afflicting some components of the DNA Nucleotide Excision Repair (NER) complex and with more marked clinical consequences. In the present research, 24 frontal images of paediatric patients with photosensitive TTDs suitable for facial analysis through the next-generation phenotyping (NGP) technology were obtained from the medical literature. The pictures were compared to age and sex-matched to unaffected controls using 2 distinct deep-learning algorithms: DeepGestalt and GestaltMatcher (Face2Gene, FDNA Inc., USA). To give further support to the observed results, a careful clinical revision was undertaken for each facial feature in paediatric patients with TTD1 or TTD2 or TTD3. Interestingly, a distinctive facial phenotype emerged by the NGP analysis delineating a specific craniofacial dysmorphic spectrum. In addition, we tabulated every single detail within the observed cohort. The novelty of the present research includes the facial characterization in children with the photosensitive types of TTDs through the 2 different algorithms. This result can become additional criteria for early diagnosis, and for subsequent targeted molecular investigations as well as a possible tailored multidisciplinary personalized management.

3D-Guided Frontal Face Generation for Pose-Invariant Recognition

Although deep learning techniques have achieved extraordinary accuracy in recognizing human faces, the pose variances of images captured in real-world scenarios still hinder reliable model appliance. To mitigate this gap, we propose to recognize faces via generation frontal face images with a 3D -Guided Deep P ose- I nvariant Face Recognition M odel (3D-PIM) consisted of a simulator and a refiner module. The simulator employs a 3D Morphable Model (3D MM) to fit the shape and appearance features and recover primary frontal images with less training data. The refiner further enhances the image realism on both global facial structure and local details with adversarial training, while keeping the discriminative identity information consistent with original images. An Adaptive Weighting (AW) metric is then adopted to leverage the complimentary information from recovered frontal faces and original profile faces and to obtain credible similarity scores for recognition. Extended experiments verify the superiority of the proposed “recognition via generation” framework over state-of-the-art.

Differences in gaze behaviors between trainees and experts during endovascular therapy for cerebral aneurysms: a preliminary study using a cerebral aneurysm model.

In the neuroendovascular field, the training of operators has become an important issue. Recently, eye-tracking technology has been introduced into various fields of medical education. This study aimed to apply eye-tracking technology to the training of neuroendovascular therapy. Six neurosurgeons, including three neuroendovascular specialists and three trainees, at our institution and related facilities participated in the study. Eye movement was recorded by the eye-tracking device during the microcatheter navigation and coil placement into the silastic aneurysm model under biplane X-ray fluoroscopy. Eye-tracking analysis during neuroendovascular therapy was feasible in all six subjects. In microcatheter navigation, specialists tended to more frequently switch their attention between frontal and lateral images than trainees. In coil embolization, the overall gaze frequency tended to increase, and the average fixation duration tended to decrease as the number of experienced cases increased. Inexperienced operators tend to fix their gaze when they are operators than when they are assistants. More experienced operators tended to look at the microcatheter longer in the coil insertion task. The eye-tracking analysis may be useful for operator training in neuroendovascular therapy. Experts may have moved their eyes more frequently than trainees to gaze at the right place. In the future, it will be necessary to collect gaze data for more operators in various tasks.

Evaluation of edge detection algorithm of frontal image of facial contour in plastic surgery

With the improvement of medical levels and the continuous improvement of people’s living standards, the demand for beauty by the general public is increasing. The plastic surgery industry has also developed by leaps and bounds. People’s dissatisfaction with their own facial appearance, facial injuries and some other reasons have prompted people to carry out facial reconstruction, and facial plastic surgery has developed rapidly. However, in the current facial plastic surgery, the edge detection effect on the contour image is general. In order to improve the edge detection effect of facial contour lines in medical images, this paper proposed a facial contour line generation algorithm. First, the detection effects of four operators were compared. After comparing the effects, the Sobel operator was used as the input data to generate an edge detection algorithm. Then, the grayscale features of the tissue in the image and the symmetry of the image were used to perform bidirectional contour tracking on the detected image to extract facial contour lines. In addition, for facial contour features, the midpoint method can be used to generate auxiliary contours. The algorithm was verified by a set of facial CT (Computed Tomography) images in the experiment. The results showed that the new generation algorithm accelerated the edge detection speed, had good denoising performance, and enhanced the edge detection effect by about 12.05% compared with the traditional edge detection algorithm. The validity and practicability of facial edge detection were verified, and it provided a theoretical basis for further realizing the design of a facial contour digital image processing system.

Comparing the esthetic impact of virtual mandibular advancement, bichectomy, jawline, and their combination

The purpose of this study was to compare the effects of mandibular advancement (MA), bichectomy, jawline, and their combination on facial attractiveness. The 3-dimensional (3D) visual sculpting is a method to perform the task. FaceBuilder software, a Blender 2.93 LTS add-on, was used to generate a 3D head and face model of a female patient with Class II Division I malocclusion. MA, bichectomy, jawline, and combination modifications were performed on the model using a 3D virtual sculpting tab, and 4 new head models were created. Five hundred thirteen participants scored lateral and frontal views of the modified and reference models. The Mann-Whitney U, Kruskal-Wallis, and Wilcoxon tests were used for statistical analysis. MA modification received the highest frontal and lateral image scores. The raters found the jawline frontal photograph to be the least attractive. Significant differences were observed between the lateral and frontal attractiveness scores in all modifications except bichectomy. The combination of 3 modifications in both frontal and lateral images received the second-lowest score. Facial esthetic modifications receive different attractiveness scores in lateral or frontal evaluations. MA outperforms bichectomy and jawline augmentation in terms of improving facial attractiveness.

Estimating Human Weight From a Single Image

Body weight, as one of the biometric traits, has been studied in both the forensic and medical domains. However, estimating weight directly from 2D images is particularly challenging since visual inspection is rather sensitive to the distance between the subject and camera, even for frontal view images. In this case, the widely used body mass index (BMI), which is associated with body height and weight, can be employed as a measure of weight to indicate health conditions. Previous works on the estimation of BMI have predominantly focused on using multiple 2D images, 3D images, or facial images; however, these cues are not always available. To address this issue, we explore the feasibility of obtaining BMI from a single 2D body image with the dual-branch regression framework proposed in this work. More specifically, the framework comprises an anthropometric feature computation branch and a deep learning-based feature extraction branch. One aggregation layer maps all the features to an estimated BMI value. In addition, a new public 2D image-to-BMI dataset, which contains 4189 images (1477 males and 2712 females) from approximately 3000 subjects with attributes including gender, age, height, and weight, was collected and released to facilitate the study. Extensive experiments confirm that the proposed framework combining anthropometric features and deep features outperforms the single-type feature approaches to BMI estimation in most cases.

Distinguishing Orthodontic Experts From Laypersons Through Gaze Analysis

Visual inspection is an important process conducted as an initial diagnostic step in medical examinations. It is assumed that the gaze movements of an orthodontist (expert) differ from those of a layperson. In this study, to examine whether the degree of proficiency in conducting a visual examination can be estimated from gaze movement, we conducted a gaze measurement experiment in which facial images (frontal and lateral images of three patients) were viewed by ten experts and ten laypersons. The performance in discriminating whether a subject was an expert or layperson exhibited a certain improvement when applying an aggregation method for the gaze data, that is, the grid gaze frequency and AOI gaze frequency. We examined whether proficiency levels could be determined using machine learning techniques. The results demonstrated that our method distinguished experts and laypersons relatively effectively using gaze frequency based on the grid and area of interest set by an expert for each face part.

Rail Joint Gap Measurement Method using Train Frontal Images Captured by a Handy Video Camcorder

Rail Joint Gap Measurement Method using Train Frontal Images Captured by a Handy Video Camcorder

Characteristics of Electroencephalogram in the Prefrontal Cortex during Deep Brain Stimulation of Subthalamic Nucleus in Parkinson's Disease under Propofol General Anesthesia.

Monitoring the depth of anesthesia by electroencephalogram (EEG) based on the prefrontal cortex is an important means to achieve accurate regulation of anesthesia for subthalamic nucleus (STN) deep brain stimulation (DBS) under general anesthesia in patients with Parkinson's disease (PD). However, no previous study has conducted an in-depth investigation into this monitoring data. Here, we aimed to analyze the characteristics of prefrontal cortex EEG during DBS with propofol general anesthesia in patients with PD and determine the reference range of parameters derived from the depth of anesthesia monitoring. Additionally, we attempted to explore whether the use of benzodiazepines in the 3 days during hospitalization before surgery impacted the interpretation of the EEG parameters. We included the data of 43 patients with PD who received STN DBS treatment and SedLine monitoring during the entire course of general anesthesia with propofol in a single center. Eighteen patients (41.86%) took benzodiazepines during hospitalization. We divided the anesthesia process into three stages: awake state before anesthesia, propofol anesthesia state, and shallow anesthesia state during microelectrode recording (MER). We analyzed the power spectral density (PSD) and derived parameters of the patients' prefrontal EEG, including the patient state index (PSI), spectral edge frequency (SEF) of the left and right sides, and the suppression ratio. The baseline characteristics, preoperative medication, preoperative frontal lobe image characteristics, preoperative motor and non-motor evaluation, intraoperative vital signs, internal environment and anesthetic information, and postoperative complications are listed. We also compared the groups according to whether they took benzodiazepines before surgery during hospitalization. The average PSI of the awake state, propofol anesthesia state, and MER state were 89.86 ± 6.89, 48.68 ± 12.65, and 62.46 ± 13.08, respectively. The preoperative administration of benzodiazepines did not significantly affect the PSI or SEF, but did reduce the total time of suppression, maximum suppression ratio, and the PSD of beta and gamma during MER. Regarding the occurrence of postoperative delirium and mini-mental state examination (MMSE) scores, there was no significant difference between the two groups (chi-square test, p = 0.48; Mann-Whitney U test, p = 0.30). For the first time, we demonstrate the reference range of the derived parameters of the depth of anesthesia monitoring and the characteristics of the prefrontal EEG of patients with PD in the awake state, propofol anesthesia state, and shallow anesthesia during MER. Taking benzodiazepines in the 3 days during hospitalization before surgery reduces suppression and the PSD of beta and gamma during MER, but does not significantly affect the observation of anesthesiologists on the depth of anesthesia, nor affect the postoperative delirium and MMSE scores.

Effect of smile esthetics on the quality of life in a Han Chinese population.

This study aimed to explore the influence of smile esthetics on the quality of life in a Han Chinese population. A total of 110 Han Chinese volunteers (52 males and 58 females, mean age 26.7 years) were recruited, and frontal images of their smiles were collected. A photoediting program was used to evaluate the following components of smile esthetics: the buccal corridor ratios, the angle between the interpupillary and commissural lines, the number of visible teeth, and width-to-length ratios of the maxillary central incisors. Oral health-related quality of life (OHRQoL) in these volunteers was evaluated using the Psychosocial Impact of Dental Aesthetics Questionnaire (PIDAQ) and Oral Health Impact Profile-14 (OHIP-14). Statistical analyses were performed by using Pearson's correlations and multiple linear regression (α=0.05). Compared to males, females scored higher on psychological impact (p=0.017). Moreover, the number of visible teeth had a significant effect on social impact, psychological impact and esthetic concern (all p < 0.05). However, the buccal corridor ratios, the angle between the interpupillary and commissural lines, and the width-to-length ratios of the maxillary central incisor did not correlate with the OHRQoL (all p > 0.05). The number of visible teeth significantly influenced the quality of life in a Han Chinese population. Smile esthetics had a significantly greater psychological impact on females than males. This study highlights the effects of smile esthetics on the quality of life in a Han Chinese population. Female patients may raise more esthetic concerns in clinical practice.

Cultural modulation effects on the self-face advantage: Do Caucasians find their own faces faster than Chinese?

The self-face advantage (SFA) is reflected through a faster recognition of a self-face compared with familiar and unfamiliar faces. Nevertheless, as Westerners and East Asians tend to present differences in self-concept styles, it is possible that the SFA is modulated by culture. The present study explored this possibility using a visual search task. British Caucasians and Malaysian Chinese participants were asked to search for frontal view images of self, friend, and unfamiliar faces among an array of unfamiliar faces. Regardless of race, participants were more accurate and faster in searching for the own face and friend's face compared with an unfamiliar face, with no differences in the search between the own and friend's face, and these findings could not be accounted by the cultural differences in self-concept (i.e., operationalised by scores from the Independent and Interdependent Self-Concept Scale and the Horizontal and Vertical Individualism and Collectivism Scale). Altogether our results suggest that culture does not modulate the SFA and that this effect is better explained by a familiar face advantage.

Modified Golden percentage for an Anterior Aesthetic -A Morphometric Analysis

Background: Golden Proportion, Preston’s Proportion, RED Proportion, and Golden Percentage are the most common theories suggested in the literature to be used for smile analysis and design. Objectives: The aim of this study was to evaluate the occurrence of these four dental aesthetic proportions in a Saudi sample and alternatively propose a modified method for anterior teeth analysis. Materials and Methods: The Standardized frontal image of the dentition of 200 selected students was taken. The proportions (Golden Proportion, Preston’s Proportion, RED Proportion, and Golden Percentage) of the maxillary anterior teeth photographs were analyzed using Adobe Photoshop software. One-sample t-test was used and the p-value was taken significantly when less than 0.05 [p&lt;0.05] and a confidence interval of 95%. Results: The assessed Golden Proportion values showed a statistically significant difference from the standard value (62%; p-value &lt; 0.05), Preston’s Proportion showed an insignificant difference from the standard values (p-value &gt; 0.05), Golden Percentage, showed that as much as 77% of 12 teeth and 77.5% of 22 teeth conformed to it. The average mathematically rounded percentages found in this study are as follows: 13%, 15%, 22%, 23%, 15%, and 12%, respectively. No complete matching to RED Proportion was found in any sample. Conclusion: All tested proportions except Golden Percentage did not conform to standard values and thus have limited application in anterior teeth analysis in the studied population. The proposed modified Golden Percentages in this study are more representative and recommended for smile design for the Saudi population.

Robust monocular 3D face reconstruction under challenging viewing conditions

Despite extensive research, 3D face reconstruction from a single image remains an open research problem due to the high degree of variability in pose, occlusions and complex lighting conditions. While deep learning-based methods have achieved great success, they are usually limited to near frontal images and images that are free of occlusions. Also, the lack of diverse training data with 3D annotations considerably limits the performance of such methods. As such, existing methods fail to recover, with high fidelity, the facial details especially when dealing with images captured under extreme conditions. To address this issue, we propose an unsupervised coarse-to-fine framework for the reconstruction of 3D faces with detailed textures. Our core idea is that multiple images of the same person but captured under different viewing conditions should provide the same 3D face. We thus propose to leverage a self-augmentation learning technique to train a model that is robust to diverse variations. In addition, instead of directly employing image pixels, we use a set of discriminative features describing the identity and attributes of the face as input to the refinement module, making the model invariant to viewing conditions. This combination of self-augmentation learning with rich face-related features allows the reconstruction of plausible facial details even under challenging viewing conditions. We train the model end-to-end and in a self-supervised manner, without any 3D annotations, landmarks or identity labels, using a combination of an image-level photometric loss and a perception-level loss that is identity and attribute-aware. We evaluate the proposed approach on CelebA and AFLW2000 datasets, and demonstrate its robustness to appearance variations despite learning from unlabeled images. The qualitative comparisons indicate that our method produces detailed 3D faces even under extreme occlusions, out of plane rotations and noise perturbations where existing state-of-the-art methods often fail. We also quantitatively show that our method outperforms SOTA with more than 30.14%, 9.87% and 11.3% in terms of PSNR, SSIM and IDentity similarity, respectively.

Chest Disease Detection and Classification

Chest diseases &amp; conditions such as Atelectasis, Cardiomegaly, Lung consolidation, Hernia, and Fibrosis becoming increasingly prevalent in the Asia-Pacific region. The Asia-Pacific Burden of Respiratory Diseases study examined the disease and economic burden of lung diseases across the Asia-Pacific and more specifically India. The objective is to use a deep learning model to diagnose pathologies from Chest X-Rays. ML approaches on CT and Xray images aided incorrectly in identifying lung diseases. Respiratory diseases range from mild and self-limiting, such as the common cold, influenza, and pharyngitis to life-threatening diseases such as bacterial pneumonia, pleural thickening, hernia, and severe acute respiratory syndromes, such as COVID-19. Authorities &amp; Doctors will be able to deal with the effects more efficiently if such illnesses can be detected speedily and accurately with little human intervention in the future. In addition, various additional elements, such as environmental influences and commonalities among the most afflicted places, should be considered to slow the spread of lung diseases and precautions should be taken. Chest X-ray exam is one of the most frequent and cost-effective medical imaging examination. However clinical diagnosis of chest X-ray can be challenging, and sometimes believed to be harder than diagnosis via chest CT imaging. Even some promising work have been reported in the past, and especially in recent deep learning work on Tuberculosis (TB) classification. To achieve clinically relevant computer-aided detection and diagnosis (CAD) in real world medical sites on all data settings of chest X-rays is still very difficult, if not impossible when only several thousands of images are employed for study. This is evident from [2] where the performance deep neural networks for thorax disease recognition is severely limited by the availability of only 4143 frontal view images [3].

Artificial Intelligence for Evaluation of Emotions behind Face Masks.

Artificial Intelligence for Evaluation of Emotions behind Face Masks.