Pain Expression Recognition Research Articles

Classification of pain expression images in elderly with hip fractures based on improved ResNet50 network.

The aim of this study is designed an improved ResNet 50 network to achieve automatic classification model for pain expressions by elderly patients with hip fractures. This study built a dataset by combining the advantages of deep learning in image recognition, using a hybrid of the Multi-Task Cascaded Convolutional Neural Networks (MTCNN). Based on ResNet50 network framework utilized transfer learning to implement model function. This study performed the hyperparameters by Bayesian optimization in the learning process. This study calculated intraclass correlation between visual analog scale scores provided by clinicians independently and those provided by pain expression evaluation assistant(PEEA). The automatic pain expression recognition model in elderly patients with hip fractures, which constructed using the algorithm. The accuracy achieved 99.6% on the training set, 98.7% on the validation set, and 98.2% on the test set. The substantial kappa coefficient of 0.683 confirmed the efficacy of PEEA in clinic. This study demonstrates that the improved ResNet50 network can be used to construct an automatic pain expression recognition model for elderly patients with hip fractures, which has higher accuracy.

Postoperative accurate pain assessment of children and artificial intelligence: A medical hypothesis and planned study.

Although the pediatric perioperative pain management has been improved in recent years, the valid and reliable pain assessment tool in perioperative period of children remains a challenging task. Pediatric perioperative pain management is intractable not only because children cannot express their emotions accurately and objectively due to their inability to describe physiological characteristics of feeling which are different from those of adults, but also because there is a lack of effective and specific assessment tool for children. In addition, exposure to repeated painful stimuli early in life is known to have short and long-term adverse sequelae. The short-term sequelae can induce a series of neurological, endocrine, cardiovascular system stress related to psychological trauma, while long-term sequelae may alter brain maturation process, which can lead to impair neurodevelopmental, behavioral, and cognitive function. Children's facial expressions largely reflect the degree of pain, which has led to the developing of a number of pain scoring tools that will help improve the quality of pain management in children if they are continually studied in depth. The artificial intelligence (AI) technology represented by machine learning has reached an unprecedented level in image processing of deep facial models through deep convolutional neural networks, which can effectively identify and systematically analyze various subtle features of children's facial expressions. Based on the construction of a large database of images of facial expressions in children with perioperative pain, this study proposes to develop and apply automatic facial pain expression recognition software using AI technology. The study aims to improve the postoperative pain management for pediatric population and the short-term and long-term quality of life for pediatric patients after operational event.

FENP: A Database of Neonatal Facial Expression for Pain Analysis

In this article, we introduce a new neonatal facial expression database for pain analysis. This database, called facial expression of neonatal pain (FENP), contains 11,000 neonatal facial expression images associated with 106 Chinese neonates from two children's hospitals, i.e., the Children's Hospital Affiliated to Nanjing Medical University and Second Affiliated Hospital Affiliated to Nanjing Medical University in China. The facial expression images cover four categories of facial expressions, i.e., severe pain expression, mild pain expression, crying expression and calmness expression, where each category contains 2750 neonatal facial expression images. Based on this database, we also investigate the pain facial expression recognition problem using several state-of-the-art facial expression features and expression recognition methods, such as Gabor+SVM, LBP+SVM, HOG+SVM, LBP+HOG+SVM, and several Convolutional Neural Network (CNN) methods (including AlexNet, VGGNet, GoogLeNet, ResNet and DenseNet). The experimental results indicate that the proposed neonatal pain facial expression database is very suitable for the study of both neonatal pain and facial expression recognition. Moreover, the FENP database is publicly available after signing a license agreement (the users can contact Jingjie Yan (yanjingjie@njupt.edu.cn), Guanming Lu (lugm@njupt.edu.cn)) or Xiaonan Li (xnli@njmu.edu.cn).

The Time Course of Facial Expression Recognition Using Spatial Frequency Information: Comparing Pain and Core Emotions

We are able to recognize others’ experience of pain from their facial expressions. However, little is known about what makes the recognition of pain possible and whether it is similar or different from core emotions. This study investigated the mechanisms underpinning the recognition of pain expressions, in terms of spatial frequency (SF) information analysis, and compared pain with 2 core emotions (ie, fear and happiness). Two experiments using a backward masking paradigm were conducted to examine the time course of low- and high-SF information processing, by manipulating the presentation duration of face stimuli and target-mask onset asynchrony. Overall, we found a temporal advantage of low-SF over high-SF information for expression recognition, including pain. This asynchrony between low- and high-SF happened at a very early stage of information extraction, which indicates that the decoding of low-SF expression information is not only faster but possibly occurs before the processing of high-SF information. Interestingly, the recognition of pain was also found to be slower and more difficult than core emotions. It is suggested that more complex decoding process may be involved in the successful recognition of pain from facial expressions, possibly due to the multidimensional nature of pain experiences. PerspectiveTwo studies explore the perceptual and temporal properties of the decoding of pain facial expressions. At very early stages of attention, the recognition of pain was found to be more difficult than fear and happiness. It suggests that pain is a complex expression, and requires additional time to detect and process.

A Hybrid Pain Detection Technique using SVM Parameter Optimization and Contourlet-Gabor Transform Feature Fusion

This paper highlights automatic pain expression recognition from facial images of pain. This technique is frequently used in healthcare applications. The research detects the pain expression by an effective recognition method. It is based on the concepts of fusion of contourlet transform with Gabor transform for feature extraction, and classification of expressions by using SVM. The ABC algorithm and GA is implemented for optimizing SVM parameters. In order to authenticate the precision and stoutness of the system, a number of experiments have been done on two databases namely UNBC shoulder pain database and IFD-CEERI database. It's provided throughout the simulation techniques. The suggested strategy is actually effective in recognition of pain expression in terms of accuracy.

Sex differences in the decoding of pain-related body postures.

Pain can be detected through nonverbal cues, including facial expressions, vocalisations, and body posture. While there are sex differences in how emotional expressions are recognized, these differences have not always been found for pain. One reason for this inconsistency may be methodological, as pain studies tend not to be designed to investigate individual differences in expression recognition. Also, few studies consider sex differences outside facial expression. This study applied an image degradation method used to examine individual differences in emotion recognition, to investigate sex differences in the decoding of pain body postures. Forty participants (20 male) were presented with a series of body posture images depicting pain at differing levels of image degradation. Happiness, anger and sadness expressions were also included for comparison. Results showed significant effects of image degradation, affect type, and actor sex. Females were rated as presenting more intense pain than males; this pattern was also found for fear, but not anger or happiness. The accuracy of pain intensity judgements was reduced as image clarity decreased. Male actors depicting pain were recognized with greater accuracy than female actors. Interestingly, similar patterns were found for anger and fear expressions. We conclude that sex has a significant influence on pain decoding under certain conditions, and while there are similarities with the way pain and core emotions are decoded, this may depend on the type of emotion presented. This also suggests that sex-related effects in the recognition of pain expressions may include body postural cues. Observer's judgements of pain displayed through body postures are driven by the sex of the person in pain.

EXAUSTÃO EMOCIONAL E RECONHECIMENTO DE EMOÇÕES NA FACE E VOZ EM MÉDICOS

This study examined the emotion recognition of pain, sadness, and happiness in the face and voice by General Practice Doctors, as a fuction of their perceived emotional exhaustion. The sample consisted of 72 physicians, and the study carried out in two stages. In the first stage, several questionnaires applied, including the Maslach Burnout Inventory to assess participant's emotional exhaustion. One week later, two tasks were presented: a facial emotion recognition (task 1) and a vocal emotion recognition in facial expressions (task 2). As expected, participants were faster and displayed a high recognition accuracy for happiness, followed by pain, in both tasks. In task 2, there was a lower accuracy, specially in the recognition of sadness, and a higher bias in the recognition of vocal pain expressions. The results from this second task were dependent on emotional exhaustion: physicians with higher emotional exhaustion were faster and showed high recognition accuracy. Overall, the results sugested a high sensitivity of

Capturing correlations of local features for image representation

Local descriptors are popular ways to characterize the local properties of images in various computer vision based tasks. To form the global descriptors for image regions, the first-order feature pooling is widely used. However, as the first-order pooling technique treats each dimension of local features separately, the pairwise correlations of local features are usually ignored.Encouraged by the success of recently developed second-order pooling techniques, in this paper we formulate a general second-order pooling framework and explore several analogues of the second-order average and max operations. We comprehensively investigate a variety of moments which are in the central positions to the second-order pooling technique. As a result, the superiority of the second-order standardized moment average pooling (2Standmap) is suggested. We successfully apply 2Standmap to four challenging tasks namely texture classification, medical image analysis, pain expression recognition, and micro-expression recognition. It illustrates the effectiveness of 2Standmap to capture multiple cues and the generalization to both static images and spatial-temporal sequences.

Three Dimensional Binary Edge Feature Representation for Pain Expression Analysis.

Automatic pain expression recognition is a challenging task for pain assessment and diagnosis. Conventional 2D-based approaches to automatic pain detection lack robustness to the moderate to large head pose variation and changes in illumination that are common in real-world settings and with few exceptions omit potentially informative temporal information. In this paper, we propose an innovative 3D binary edge feature (3D-BE) to represent high-resolution 3D dynamic facial expression. To exploit temporal information, we apply a latent-dynamic conditional random field approach with the 3D-BE. The resulting pain expression detection system proves that 3D-BE represents the pain facial features well, and illustrates the potential of noncontact pain detection from 3D facial expression data.

Pain Expression Recognition Based on Fuzzy Classification Approach

Human activity analysis and expressions recognition play a central role in pervasive health care. Expressions recognition is an active research field in computer vision. In this paper, We propose an approach for automatically recognizing the pain expression from video sequences, in which pain is categorized into four levels, including “no-pain”, “slight pain”, “moderate pain” and “severe pain”. First of all, each frame in video sequences is represented as a “word” by extracting facial velocity information, which is used to charaterize pain expression. Then boosting fuzzy classification algorithm is used for pain expression recognition. The algorithm can automatically categorize and recognize the human pain expression which is contained in the video. Finally we test our algorithm on a pain expression dataset built by ourselves. Experiment results show that the average recognition accuracy is over 91%, which validates its effectiveness. Our results are significantly better than three state-of-the-art approaches for pain expression recognition on the same data.

Pain expression recognition based on pLSA model.

We present a new approach to automatically recognize the pain expression from video sequences, which categorize pain as 4 levels: “no pain,” “slight pain,” “moderate pain,” and “ severe pain.” First of all, facial velocity information, which is used to characterize pain, is determined using optical flow technique. Then visual words based on facial velocity are used to represent pain expression using bag of words. Final pLSA model is used for pain expression recognition, in order to improve the recognition accuracy, the class label information was used for the learning of the pLSA model. Experiments were performed on a pain expression dataset built by ourselves to test and evaluate the proposed method, the experiment results show that the average recognition accuracy is over 92%, which validates its effectiveness.

A Refined Examination of the Facial Cues Contributing to Vicarious Effects on Self-Pain and Spinal Responses

Vicarious pain has been shown to enhance observers' nociceptive reactivity and pain perception. We exposed healthy participants to specific parts of facial pain expressions in order to investigate which components are required to induce this modulation. We created 2 classes of stimuli: one containing the most useful information for identification of pain expressions (diagnostic) and one containing the least useful information (antidiagnostic). Twenty-eight normal volunteers received electrical stimulation of the sural nerve immediately after they viewed these stimuli. Subjective ratings (intensity and unpleasantness) as well as the nociceptive flexion reflex (NFR) evoked by the shock were recorded. Results show that diagnostic stimuli lead to higher subjective ratings of shock pain than the antidiagnostic stimuli, but the stimuli classes had no significant impact on the NFR. A control experiment showed that our facial stimuli were given very low valence and arousal ratings compared to stimuli previously used to demonstrate the effect of emotional pictures on pain. Thus, the results are unlikely to be explained by emotions felt by the observer and suggest a vicarious facilitation of supraspinal pain processing induced by key features underlying pain expressions recognition. Results provide further support to the perception-action model of empathy. PerspectiveThis study demonstrates that visual features that are efficiently used for the recognition of pain expressions are sufficient to induce a vicarious facilitation of self-pain. Supraspinal pain responses were modulated by the informativeness of the areas of the pain expressions that participants viewed prior to the painful stimulations.

Does Vigilance to Pain Make Individuals Experts in Facial Recognition of Pain?

It is well known that individual factors are important in the facial recognition of pain. However, it is unclear whether vigilance to pain as a pain-related attentional mechanism is among these relevant factors. Vigilance to pain may have two different effects on the recognition of facial pain expressions: pain-vigilant individuals may detect pain faces better but overinclude other facial displays, misinterpreting them as expressing pain; or they may be true experts in discriminating between pain and other facial expressions. The present study aimed to test these two hypotheses. Furthermore, pain vigilance was assumed to be a distinct predictor, the impact of which on recognition cannot be completely replaced by related concepts such as pain catastrophizing and fear of pain. Photographs of neutral, happy, angry and pain facial expressions were presented to 40 healthy participants, who were asked to classify them into the appropriate emotion categories and provide a confidence rating for each classification. Additionally, potential predictors of the discrimination performance for pain and anger faces - pain vigilance, pain-related catastrophizing, fear of pain--were assessed using self-report questionnaires. Pain-vigilant participants classified pain faces more accurately and did not misclassify anger as pain faces more frequently. However, vigilance to pain was not related to the confidence of recognition ratings. Pain catastrophizing and fear of pain did not account for the recognition performance. Moderate pain vigilance, as assessed in the present study, appears to be associated with appropriate detection of pain-related cues and not necessarily with the overinclusion of other negative cues.

The painful face – Pain expression recognition using active appearance models

Pain is typically assessed by patient self-report. Self-reported pain, however, is difficult to interpret and may be impaired or in some circumstances (i.e., young children and the severely ill) not even possible. To circumvent these problems behavioral scientists have identified reliable and valid facial indicators of pain. Hitherto, these methods have required manual measurement by highly skilled human observers. In this paper we explore an approach for automatically recognizing acute pain without the need for human observers. Specifically, our study was restricted to automatically detecting pain in adult patients with rotator cuff injuries. The system employed video input of the patients as they moved their affected and unaffected shoulder. Two types of ground truth were considered. Sequence-level ground truth consisted of Likert-type ratings by skilled observers. Frame-level ground truth was calculated from presence/absence and intensity of facial actions previously associated with pain. Active appearance models (AAM) were used to decouple shape and appearance in the digitized face images. Support vector machines (SVM) were compared for several representations from the AAM and of ground truth of varying granularity. We explored two questions pertinent to the construction, design and development of automatic pain detection systems. First, at what level (i.e., sequence- or frame-level) should datasets be labeled in order to obtain satisfactory automatic pain detection performance? Second, how important is it, at both levels of labeling, that we non-rigidly register the face?