Facial Diagnosis Research Articles

A Comparative Study Recognizing the Expression of Information Between Elderly Individuals and Young Individuals.

Studies have shown that elderly individuals have significantly worse facial expression recognition scores than young adults. Some have suggested that this difference is due to perceptual degradation, while others suggest it is due to decreased attention of elderly individuals to the most informative regions of the face. To resolve this controversy, this study recruited 85 participants and used a behavioral task and eye-tracking techniques (EyeLink 1000 Plus eye tracker). It adopted the "study-recognition" paradigm, and a mixed experimental design of 3 (facial expressions: positive, neutral, negative) × 2 (subjects' age: young, old) × 3 (facial areas of interest: eyes, nose, and mouth) was used to explore whether there was perceptual degradation in older people's attention to facial expressions and investigate the differences in diagnostic areas between young and older people. The behavioral results revealed that young participants had significantly higher facial expression recognition scores than older participants did; moreover, the eye-tracking results revealed that younger people generally fixated on faces significantly more than elderly people, demonstrating the perceptual degradation in elderly people. Young people primarily look at the eyes, followed by the nose and, finally, the mouth when examining facial expressions. The elderly participants primarily focus on the eyes, followed by the mouth and then the nose. The findings confirmed that young participants have better facial expression recognition performance than elderly participants, which may be related more to perceptual degradation than to decreased attention to informative areas of the face. For elderly people, the duration of gaze toward the facial diagnosis area (such as the eyes) should be increased when recognizing faces to compensate for the disadvantage of decreased facial recognition performance caused by perceptual aging.

The correlation between meridians and face diagnosis —two case reports

This study aimed to investigate the correlation between facial diagnosis and the twelve meridians in traditional Chinese medicine (TCM) for potential clinical diagnostic applications. Using a stationary camera, facial images were captured and compiled into a comprehensive database, along with participants' medical histories obtained through questionnaires. The results indicated that irregular patterns on participants' faces corresponded to specific meridians, revealing potential organ-related conditions. These findings suggest a correlation between facial reflex zones and the twelve meridians, highlighting the diagnostic potential of this method for identifying early signs of clinical conditions.

Simulated multimodal deep facial diagnosis

Facial phenotypes are extensively studied in medical and biological research, serving as critical markers that potentially indicate underlying genetic traits or medical conditions. With the recent advancements in big data, algorithms, and hardware, deep facial diagnosis, which employs deep learning techniques to systematically examine facial phenotypes and identify signs of certain diseases or medical conditions, has attracted significant attention and research, gradually emerging as a promising tool in precision medicine. Primarily limited by the scarcity of data for training facial diagnosis models, the accuracy of facial diagnosis for various conditions remains low up to now. In the past decade, RGB-D cameras, measuring depth information along with standard RGB capabilities, have proven superior in processing spatial details with more stability and accuracy. Motivated by the facts mentioned above, in this paper, we propose a Simulated Multimodal Framework, which effectively improves the computer-aided facial diagnosis performance of state-of-the-art models in experiments under different conditions. The underlying principle is to leverage the simulated depth by generative models to improve the performance of RGB image recognition. Furthermore, as a rapid and non-invasive tool for disease screening and detection, our proposal demonstrated an average accuracy improvement of over 20% compared to practicing physicians in the study.

Image-Based Face Recognition Techniques Used in Disease Detection Approaches: A Survey

Facial diseases lead to noticeable changes on the human face, and some of them extend beyond internal effects or organ-based disorders. Indeed, certain types of facial diseases result in visually noticeable abnormalities on the human face. These alterations in facial patterns can serve as potential indicators for corresponding diseases, particularly in the fields of endocrinology and metabolism, Muscles-Nervous disorders, Chromosomes, and Genetic disorders, among others. Technologies used in Face Recognition (FR) have been developed over the past few decades; however, only a limited amount of research has been applied in recent years to FR-based disease detection for clinical purposes. FR applications relying on Artificial Neural Network (ANN) techniques have recorded higher accuracy rates in diagnosing facial diseases. This field of recognition holds promising potential for optimizing facial diagnosis approaches and supporting medical staff in evaluating detections. In practice, only a few research ideas have been translated into medical products, emphasizing the need to identify and integrate future applications. As a primary focus, this paper centers on the key applications and technologies for detecting various types of facial diseases, along with a discussion of prospects.

Cold sensitivity classification using facial image based on convolutional neural network

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, we proposed a model to quantitatively classify cold sensitivity using a fully automated facial image analysis system.Methods: We investigated cold sensitivity in 452 subjects. Cold sensitivity was determined using a questionnaire and the Cold Pattern Score (CPS) was used for analysis. Subjects with a CPS score below the first quartile (low CPS group) belonged to the cold non-sensitivity group, and subjects with a CPS score above the third quartile (high CPS group) belonged to the cold sensitivity group. After splitting the facial images into train/validation/test sets, the train and validation set were input into a convolutional neural network to learn the model, and then the classification accuracy was calculated for the test set.Results: The classification accuracy of the low CPS group and high CPS group using facial images in all subjects was 76.17%. The classification accuracy by sex was 69.91% for female and 62.86% for male. It is presumed that the deep learning model used facial color or facial shape to classify the low CPS group and the high CPS group, but it is difficult to specifically determine which feature was more important.Conclusions: The experimental results of this study showed that the low CPS group and the high CPS group can be classified with a modest level of accuracy using only facial images. There was a need to develop more advanced models to increase classification accuracy.

Evaluation of facial temperature distribution changes during meditation using infrared thermal imaging: An experimental, cross-over study

To investigate the differences between meditation and resting states using infrared thermal imaging (IRTI) to determine facial temperature distribution features during meditation. This study also annotated the patterns of facial temperature changes during meditation from the perspective of traditional Chinese medicine facial diagnosis. Each participant performed 10 minutes meditation and 10 minutes resting but in different sequences. A concentration test was set as the task load, followed by a meditation/resting or resting/meditation session, during which the participants’ facial temperatures were observed using IRTI. Participants were scored on the Big Five Inventory (BFI) and Mindful Attention Awareness Scale (MAAS). Forehead temperatures decreased more during meditation than during the resting state. The chin temperature increased only during meditation (P < .0001). For the subjects with meditation experience, there were significant differences in the temperatures of the left forehead (P < .01), right forehead (P < .01) and chin (P < .05) between the meditation and resting state at the 10th minute. In the non-task state, the BFI-Extraversion showed a negative correlation with the temperature of the left forehead (R =﹣0.41, P = .03). In the post-task state, the temperature of the left forehead was negatively correlated with scores on the MAAS (R =﹣0.42, P = .02). Using IRTI to study meditation offers a practical solution to the challenges in meditation research. The results indicate that an increase in chin temperature may be a representative feature of a meditation state, and forehead temperature is also a potential indicator.

Deep Facial Diagnosis: Deep Transfer Learning from Face Recognition to Facial Diagnosis

One of the most crucial uses for facial analysis is facial diagnosis. Practitioners of traditional medicine have used their expertise to assess a person's health state for tens of thousands of years. Since then, a lot has changed, and this long-standing tradition has been supplanted by computerised face diagnosis. The proposed method of utilizing deep transfer learning from face recognition for face illness diagnosis with computer assistance is an interesting approach that can potentially provide a low-cost and non-invasive way for disease screening and detection. The objective of this research endeavor is to investigate whether techniques based on deep learning may be employed to detect malignancies through uncontrolled 2D face images. By leveraging the pre-trained face recognition models, the system can effectively learn relevant features from the face images and use them to diagnose different diseases. The proposed system will be using data augmentation to handle the imbalance of data in the system and reduce over-fitting. By artificially generating new data from the existing dataset, the system can increase the amount of data and diversity of the samples, leading to better generalization and improved accuracies.

Automatic part segmentation of facial anatomies using geometric deep learning toward a computer-aided facial rehabilitation

Detection, identification, and segmentation of facial landmarks and anatomies play an essential role in the automatic reconstruction of patient specific model of the human head for facial diagnosis, monitoring, and rehabilitation. The objective of the present study was to apply geometric deep learning to perform part segmentation on the human face to automatically segment facial anatomies from a 3D point set.A database of Computed Tomography images of 333 subjects was reconstructed. Labels of facial anatomies (eyes, nose, and mouth) were manually performed. Two state-of-the-art geometric deep learning models (PointNet++ and PointCNN) were implemented and evaluated. Then, the best model was applied to perform part segmentation on new Kinect-driven face data of healthy subjects and facial palsy patients. Accuracy and Intersection over Union (IoU) were used as evaluation metrics.An accuracy level of 99.19% and an IoU of 89.09% are obtained for the CT database using the PointNet++ model. Regarding the use of the PointCNN model, an accuracy level of 98.43 and an IoU of 78.33 were obtained. An accuracy range of [81.45%–92.09%] and [81.05%–84.08%] was obtained by using PointNet++ model on Kinect data for healthy subjects and facial palsy patients respectively.This study suggested that geometric deep learning can be used for automatic segmentation of facial anatomies from a 3D data set. The obtained outcomes confirmed the accuracy of PointNet++ and PointCNN architectures. As perspectives, the proposed method will be implemented into an available computer vision system for facial monitoring and rehabilitation.

Concordance of the facial biotype between Bjork-Jarabak cephalometrics and photographic analysis of the facial opening angle.

Analysis of the facial biotype can provide useful information for orthodontic diagnosis and can determine the type of growth of a patient to guide orthodontic treatment. The objective of this study was to determine the concordance of the facial biotype according to Bjork-Jarabak cephalometric analysis and photographic analysis of the angle of facial opening in Peruvian individuals. This retrospective study included 244 cephalometric radiographs and frontal photographs of the same patients obtained from a database. The facial biotype (mesofacial, brachyfacial, or dolichofacial) was determined with the Björk-Jarabak polygon (cephalometric) and the angle of facial opening (photographic). Two trained investigators performed all the measurements. The concordance of the facial diagnosis was determined using correlations of the interclass coefficient and the kappa test. p<0.05. In cases with a mesofacial biotype, both analyses coincided in 60 individuals (68.2%), while in those diagnosed with a dolichofacial biotype, the analyses only coincided in 17 individuals (10.4%). There was no concordance between the two methods regarding the brachyfacial biotype since according to the angle of facial opening none of the individuals presented a brachyfacial biotype (kappa weighted test= 0.020, p=0.586). Cephalometric and photographic analyses should be complementary and one should not substitute the other. Attention should be focused on dolichofacial and brachyfacial biotypes, which showed less concordance between evaluations. So, more studies are needed to follow this line of research. Key words:Facial biotype, cephalometry, photography, facial type, radiography.

Role of "facial diagnosis" objectification in tumor diagnosis and treatment

&lt;p&gt;As an important part of Traditional Chinese Medicine (TCM)&amp;nbsp;inspection, face diagnosis is significant&amp;nbsp;in judging the rise and fall of viscera and essence and diagnosing and treating diseases. Cancer is a serious disease that endangers&amp;nbsp;human life and health. Face diagnosis can play&amp;nbsp;a great role in diagnosing and treating&amp;nbsp;tumors, but this approach has not achieved the expected effects due to the lack of research. Herein, we summarized&amp;nbsp;the research regarding&amp;nbsp;facial expression, color, shape,&amp;nbsp;and state, demonstrating that facial diagnosis is significant in diagnosing and treating&amp;nbsp;tumors. We also&amp;nbsp;propose&amp;nbsp;that facial diagnosis must be combined with computer technology to realize the objectification of facial diagnosis as soon as possible to play a greater role in diagnosing and treating&amp;nbsp;tumors.&lt;/p&gt;

Private Facial Prediagnosis as an Edge Service for Parkinson's DBS Treatment Valuation.

Facial phenotyping for medical prediagnosis has recently been successfully exploited as a novel way for the preclinical assessment of a range of rare genetic diseases, where facial biometrics is revealed to have rich links to underlying genetic or medical causes. In this paper, we aim to extend this facial prediagnosis technology for a more general disease, Parkinson's Diseases (PD), and proposed an Artificial-Intelligence-of-Things (AIoT) edge-oriented privacy-preserving facial prediagnosis framework to analyze the treatment of Deep Brain Stimulation (DBS) on PD patients. In the proposed framework, a novel edge-based privacy-preserving framework is proposed to implement private deep facial diagnosis as a service over an AIoT-oriented information theoretically secure multi-party communication scheme, while data privacy has been a primary concern toward a wider exploitation of Electronic Health and Medical Records (EHR/EMR) over cloud-based medical services. In our experiments with a collected facial dataset from PD patients, for the first time, we proved that facial patterns could be used to evaluate the facial difference of PD patients undergoing DBS treatment. We further implemented a privacy-preserving information theoretical secure deep facial prediagnosis framework that can achieve the same accuracy as the non-encrypted one, showing the potential of our facial prediagnosis as a trustworthy edge service for grading the severity of PD in patients.

Detection of diseases using facial features with Deep transfer learning

There is always a relation between face and diseases that leads the idea of facial diagnosis. The aim of this project is to predict the diseases using 2 Dimensional facial images. In this study, we are dealing with diagnosis of single and multiple illnesses such as Beta-thalassemia, hyperthyroidism, Down syndrome, leprosy and vitiligo. Accuracy for face recognition is over 90%. In practical collecting disease specific images are complex, expensive and time taking process. Therefore, collecting data sets for face recognition is hard and complicated. So, in deep transfer learning applications we can do facial diagnosis with a small dataset which will be easy process where we can train the pre trained model.

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes.

Background: In medical genetics, one application of neural networks is the diagnosis of genetic diseases based on images of patient faces. While these applications have been validated in the literature with primarily pediatric subjects, it is not known whether these applications can accurately diagnose patients across a lifespan. We aimed to extend previous works to determine whether age plays a factor in facial diagnosis as well as to explore other factors that may contribute to the overall diagnostic accuracy. Methods: To investigate this, we chose two relatively common conditions, Williams syndrome and 22q11.2 deletion syndrome. We built a neural network classifier trained on images of affected and unaffected individuals of different ages and compared classifier accuracy to clinical geneticists. We analyzed the results of saliency maps and the use of generative adversarial networks to boost accuracy. Results: Our classifier outperformed clinical geneticists at recognizing face images of these two conditions within each of the age groups (the performance varied between the age groups): 1) under 2 years old, 2) 2–9 years old, 3) 10–19 years old, 4) 20–34 years old, and 5) ≥35 years old. The overall accuracy improvement by our classifier over the clinical geneticists was 15.5 and 22.7% for Williams syndrome and 22q11.2 deletion syndrome, respectively. Additionally, comparison of saliency maps revealed that key facial features learned by the neural network differed with respect to age. Finally, joint training real images with multiple different types of fake images created by a generative adversarial network showed up to 3.25% accuracy gain in classification accuracy. Conclusion: The ability of clinical geneticists to diagnose these conditions is influenced by the age of the patient. Deep learning technologies such as our classifier can more accurately identify patients across the lifespan based on facial features. Saliency maps of computer vision reveal that the syndromic facial feature attributes change with the age of the patient. Modest improvements in the classifier accuracy were observed when joint training was carried out with both real and fake images. Our findings highlight the need for a greater focus on age as a confounder in facial diagnosis.

Prediction of Diseases Based on Facial Diagnosis Using Deep Learning

Practitioners can diagnose diseases by looking at a patient's facial features, a process known as facial diagnosis. Doctors need to have a lot of real-world experience to diagnose facial conditions with high accuracy. Modern medical studies show that many diseases do, in fact, manifest matching unique traits on human faces. Due to the scarcity of medical resources, it is challenging to get a check-up today in many rural and undeveloped areas, which frequently causes treatment to be delayed. Limitations still exist, such as high expenses, lengthy hospital waiting-times, and conflicts between doctor and consulted patient that result in medical disputes, even in major cities. We can rapidly and easily do non-invasive screening and disease detection thanks to computer-aided face diagnosis.To perform CA facial-diagnosis of various diseases and test DTL methods for both single and multiple disease spotting on a short data-set, we therefore propose adopting deep transfer learning from face recognition.© 2022 STAIQC. All rights reserved

Palda: Public Dataset and Algorithms for Facial Imaging and Diagnosis of Neurological Disorders

Palda: Public Dataset and Algorithms for Facial Imaging and Diagnosis of Neurological Disorders

A deep learning-based diagnostic tool for identifying various diseases via facial images.

With the current health crisis caused by the COVID-19 pandemic, patients have become more anxious about infection, so they prefer not to have direct contact with doctors or clinicians. Lately, medical scientists have confirmed that several diseases exhibit corresponding specific features on the face the face. Recent studies have indicated that computer-aided facial diagnosis can be a promising tool for the automatic diagnosis and screening of diseases from facial images. However, few of these studies used deep learning (DL) techniques. Most of them focused on detecting a single disease, using handcrafted feature extraction methods and conventional machine learning techniques based on individual classifiers trained on small and private datasets using images taken from a controlled environment. This study proposes a novel computer-aided facial diagnosis system called FaceDisNet that uses a new public dataset based on images taken from an unconstrained environment and could be employed for forthcoming comparisons. It detects single and multiple diseases. FaceDisNet is constructed by integrating several spatial deep features from convolutional neural networks of various architectures. It does not depend only on spatial features but also extracts spatial-spectral features. FaceDisNet searches for the fused spatial-spectral feature set that has the greatest impact on the classification. It employs two feature selection techniques to reduce the large dimension of features resulting from feature fusion. Finally, it builds an ensemble classifier based on stacking to perform classification. The performance of FaceDisNet verifies its ability to diagnose single and multiple diseases. FaceDisNet achieved a maximum accuracy of 98.57% and 98% after the ensemble classification and feature selection steps for binary and multiclass classification categories. These results prove that FaceDisNet is a reliable tool and could be employed to avoid the difficulties and complications of manual diagnosis. Also, it can help physicians achieve accurate diagnoses without the need for physical contact with the patients.

The Association between Facial Morphology and Cold Pattern

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, using a fully automated facial shape analysis system, we show that facial morphological features are associated with cold pattern.Methods: The facial morphological features calculated from 68 facial landmarks included the angles, areas, and distances between the landmark points of each part of the face. Cold pattern severity was determined using a questionnaire and the cold pattern scores (CPS) were used for analysis. The association between facial features and CPS was calculated using Pearson's correlation coefficient and partial correlation coefficients.Results: The upper chin width and the lower chin width were negatively associated with CPS. The distance from the center point to the middle jaw and the distance from the center point to the lower jaw were negatively associated with CPS. The angle of the face outline near the ear and the angle of the chin line were positively associated with CPS. The area of the upper part of the face and the area of the face except the sensory organs were negatively associated with CPS. The number of facial morphological features that exhibited a statistically significant correlation with CPS was 37 (unadjusted).Conclusions: In this study of a Korean population, subjects with a high CPS had a more pointed chin, longer face, more angular jaw, higher eyes, and more upward corners of the mouth, and their facial sensory organs were relatively widespread.

Image-based non-contact monitoring of changes in facial skin texture induced by the contact needle technique of acupuncture

In this study, we verified whether or not feature values of the facial skin texture can be used for facial complexion diagnosis. A total of 10 patients with fatigue were recruited and categorized under two groups: acupuncture group and blank control group. In the acupuncture group, the contact needle technique was used, while in the blank control group, the patients rested for 30 min in the supine position. We captured images of the facial skin using a digital camera before and after the intervention and then analyzed feature values from the images. The standard deviation (SD) of short-line inclination angles significantly decreased with acupuncture treatment. There was a significant difference in the SD of short-line inclination angles between the two groups. This study was approved by the Clinical Research Ethics Committee of Kanazawa University Hospital in Japan [for human study: approval no. 2018-154 (2912)] in December 2018.

Deep Facial Diagnosis: Deep Transfer Learning From Face Recognition to Facial Diagnosis

The relationship between face and disease has been discussed from thousands years ago, which leads to the occurrence of facial diagnosis. The objective here is to explore the possibility of identifying diseases from uncontrolled 2D face images by deep learning techniques. In this paper, we propose using deep transfer learning from face recognition to perform the computer-aided facial diagnosis on various diseases. In the experiments, we perform the computer-aided facial diagnosis on single (beta-thalassemia) and multiple diseases (beta-thalassemia, hyperthyroidism, Down syndrome, and leprosy) with a relatively small dataset. The overall top-1 accuracy by deep transfer learning from face recognition can reach over 90% which outperforms the performance of both traditional machine learning methods and clinicians in the experiments. In practical, collecting disease-specific face images is complex, expensive and time consuming, and imposes ethical limitations due to personal data treatment. Therefore, the datasets of facial diagnosis related researches are private and generally small comparing with the ones of other machine learning application areas. The success of deep transfer learning applications in the facial diagnosis with a small dataset could provide a low-cost and noninvasive way for disease screening and detection.

Differentiation between maxillary and malar midface position within the facial profile.

AimsTo define midfacial position differentiating maxillary and zygomatic regions and to evaluate the corresponding cephalometric characteristics discerning midfacial flatness and fullness.Material and MethodsA total of 183 pretreatment lateral cephalometric radiographs of non-growing orthodontic patients (age 25.98 ± 8.43 years) screened at our university orthodontic clinic. The lateral cephalographs of the orthodontic patients were stratified in four groups: flat, normal toward flat, normal toward full, full,according to distances from nasion and sella to points J and G (NJ, SJ, NG and SG). J is the midpoint of the distance connecting orbitale to point A, and G the center of the triangle connecting orbit, key ridge and pterygomaxillary fissure. Statistics included the Kendall tau-b test for best associations among measurements.ResultsAll measurements were statistically significantly different between flat and full groups. The highest associations were between NJ and SJ (τb = 0.71; p < 0.001) and NG and SG (τb = 0.70; p < 0.001). Flat midfaces were characterized by canting of the cranial base and palatal plane, hyperdivergent pattern and maxillary retrognathism. The opposite was true for fuller midfaces.ConclusionMidface skeletal location was assessed differentially in the naso-maxillary and malo-zygomatic structures differentially. Craniofacial characteristics were identified according to this stratification, indicating the potential for application in facial diagnosis and need for testing on 3D cone-beam computed tomography images.