Facial expressions to identify post-stroke: A pilot study.

BACKGROUND AND OBJECTIVE: Timely stroke treatment can limit brain damage and improve outcomes, which depends on early recognition of the symptoms. However, stroke cases are often missed by the first respondent paramedics. One of the earliest external symptoms of stroke is based on facial expressions. METHODS: We propose a computerized analysis of facial expressions using action units to distinguish between Post-Stroke and healthy people. Action units enable analysis of subtle and specific facial movements and are interpretable to the facial expressions. The RGB videos from the Toronto Neuroface Dataset, which were recorded during standard orofacial examinations of 14 people with post-stroke (PS) and 11 healthy controls (HC) were used in this study. Action units were computed using XGBoost which was trained using HC, and classified using regression analysis for each of the nine facial expressions. The analysis was performed without manual intervention. RESULTS: The results were evaluated using leave-one-our validation. The accuracy was 82% for Kiss and Spread, with the best sensitivity of 91% in the differentiation of PS and HC. The features corresponding to mouth muscles were most suitable. CONCLUSIONS: This pilot study has shown that our method can detect PS based on two simple facial expressions. However, this needs to be tested in real-world conditions, with people of different ethnicities and smartphone use. The method has the potential for a computerized assessment of the videos for use by the first respondents using a smartphone to perform screening tests, which can facilitate the timely start of the treatment.

Correction: A stomata classification and detection system in microscope images of maize cultivars.

[This corrects the article DOI: 10.1371/journal.pone.0258679.].

Tabular data augmentation for video-based detection of hypomimia in Parkinson's disease.

BACKGROUND AND OBJECTIVE: This paper presents a method for the computerized detection of hypomimia in people with Parkinson's disease (PD). It overcomes the difficulty of the small and unbalanced size of available datasets. METHODS: A public dataset consisting of features of the video recordings of people with PD with four facial expressions was used. Synthetic data was generated using a Conditional Generative Adversarial Network (CGAN) for training augmentation. After training the model, Test-Time Augmentation was performed. The classification was conducted using the original test set to prevent bias in the results. RESULTS: The employment of CGAN followed by Test-Time Augmentation led to an accuracy of classification of the videos of 83%, specificity of 82%, and sensitivity of 85% in the test set that the prevalence of PD was around 7% and where real data was used for testing. This is a significant improvement compared with other similar studies. The results show that while the technique was able to detect people with PD, there were a number of false positives. Hence this is suitable for applications such as population screening or assisting clinicians, but at this stage is not suitable for diagnosis. CONCLUSIONS: This work has the potential for assisting neurologists to perform online diagnose and monitoring their patients. However, it is essential to test this for different ethnicity and to test its repeatability.

Error-Correcting Mean-Teacher: Corrections instead of consistency-targets applied to semi-supervised medical image segmentation.

Semantic segmentation is an essential task in medical imaging research. Many powerful deep-learning-based approaches can be employed for this problem, but they are dependent on the availability of an expansive labeled dataset. In this work, we augment such supervised segmentation models to be suitable for learning from unlabeled data. Our semi-supervised approach, termed Error-Correcting Mean-Teacher, uses an exponential moving average model like the original Mean Teacher but introduces our new paradigm of error correction. The original segmentation network is augmented to handle this secondary correction task. Both tasks build upon the core feature extraction layers of the model. For the correction task, features detected in the input image are fused with features detected in the predicted segmentation and further processed with task-specific decoder layers. The combination of image and segmentation features allows the model to correct present mistakes in the given input pair. The correction task is trained jointly on the labeled data. On unlabeled data, the exponential moving average of the original network corrects the student's prediction. The combined outputs of the students' prediction with the teachers' correction form the basis for the semi-supervised update. We evaluate our method with the 2017 and 2018 Robotic Scene Segmentation data, the ISIC 2017 and the BraTS 2020 Challenges, a proprietary Endoscopic Submucosal Dissection dataset, Cityscapes, and Pascal VOC 2012. Additionally, we analyze the impact of the individual components and examine the behavior when the amount of labeled data varies, with experiments performed on two distinct segmentation architectures. Our method shows improvements in terms of the mean Intersection over Union over the supervised baseline and competing methods. Code is available at https://github.com/CloneRob/ECMT.

Explaining COVID-19 diagnosis with Taylor decompositions.

The COVID-19 pandemic has devastated the entire globe since its first appearance at the end of 2019. Although vaccines are now in production, the number of contaminations remains high, thus increasing the number of specialized personnel that can analyze clinical exams and points out the final diagnosis. Computed tomography and X-ray images are the primary sources for computer-aided COVID-19 diagnosis, but we still lack better interpretability of such automated decision-making mechanisms. This manuscript presents an insightful comparison of three approaches based on explainable artificial intelligence (XAI) to light up interpretability in the context of COVID-19 diagnosis using deep networks: Composite Layer-wise Propagation, Single Taylor Decomposition, and Deep Taylor Decomposition. Two deep networks have been used as the backbones to assess the explanation skills of the XAI approaches mentioned above: VGG11 and VGG16. We hope that such work can be used as a basis for further research on XAI and COVID-19 diagnosis for each approach figures its own positive and negative points.

Artificial intelligence for oral cancer diagnosis: What are the possibilities?

Oral cancer could be prevented. The primary strategy is based on prevention. Most patients with oral cancer present to the hospital network with advanced staging and a low chance of cure. This condition may be related to physicians' difficulty of making an early diagnosis. With the advancement of information technology, artificial intelligence (AI) holds great promise in terms of assisting in diagnosis. Few machine learning algorithms have been developed for this purpose to date. In this paper, we will discuss the possibilities for diagnosing oral cancer using AI as a tool, as well as the implications for the population. A set of photographic images of oral lesions has been segmented, indicating not only the area of the lesion but also the class of lesion associated with it. Different neural network architectures were trained with the goal of fine segmentation (pixel by pixel), classification of image crops, and classification of whole images based on the presence or absence of a lesion. The accuracy results are acceptable, opening up possibilities not only for identifying lesions but also for classifying the pathology associated with them.

EEG Channel Selection Based User Identification via Improved Flower Pollination Algorithm.

The electroencephalogram (EEG) introduced a massive potential for user identification. Several studies have shown that EEG provides unique features in addition to typical strength for spoofing attacks. EEG provides a graphic recording of the brain's electrical activity that electrodes can capture on the scalp at different places. However, selecting which electrodes should be used is a challenging task. Such a subject is formulated as an electrode selection task that is tackled by optimization methods. In this work, a new approach to select the most representative electrodes is introduced. The proposed algorithm is a hybrid version of the Flower Pollination Algorithm and ß-Hill Climbing optimizer called FPAß-hc. The performance of the FPAß-hc algorithm is evaluated using a standard EEG motor imagery dataset. The experimental results show that the FPAß-hc can utilize less than half of the electrode numbers, achieving more accurate results than seven other methods.

A stomata classification and detection system in microscope images of maize cultivars.

Plant stomata are essential structures (pores) that control the exchange of gases between plant leaves and the atmosphere, and also they influence plant adaptation to climate through photosynthesis and transpiration stream. Many works in literature aim for a better understanding of these structures and their role in the evolution process and the behavior of plants. Although stomata studies in dicots species have advanced considerably in the past years, even there is not much knowledge about the stomata of cereal grasses. Due to the high morphological variation of stomata traits intra- and inter-species, detecting and classifying stomata automatically becomes challenging. For this reason, in this work, we propose a new system for automatic stomata classification and detection in microscope images for maize cultivars based on transfer learning strategy of different deep convolution neural netwoks (DCNN). Our performed experiments show that our system achieves an approximated accuracy of 97.1% in identifying stomata regions using classifiers based on deep learning features, which figures out as a nearly perfect classification system. As the stomata are responsible for several plant functionalities, this work represents an important advance for maize research, providing an accurate system in replacing the current manual task of categorizing these pores on microscope images. Furthermore, this system can also be a reference for studies using images from different cereal grasses.

Convolutional Neural Networks for the evaluation of cancer in Barrett's esophagus: Explainable AI to lighten up the black-box.

Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their level of accountability and transparency must be provided in such evaluations. The reliability related to machine learning predictions must be explained and interpreted, especially if diagnosis support is addressed. For this task, the black-box nature of deep learning techniques must be lightened up to transfer its promising results into clinical practice. Hence, we aim to investigate the use of explainable artificial intelligence techniques to quantitatively highlight discriminative regions during the classification of early-cancerous tissues in Barrett's esophagus-diagnosed patients. Four Convolutional Neural Network models (AlexNet, SqueezeNet, ResNet50, and VGG16) were analyzed using five different interpretation techniques (saliency, guided backpropagation, integrated gradients, input × gradients, and DeepLIFT) to compare their agreement with experts' previous annotations of cancerous tissue. We could show that saliency attributes match best with the manual experts' delineations. Moreover, there is moderate to high correlation between the sensitivity of a model and the human-and-computer agreement. The results also lightened that the higher the model's sensitivity, the stronger the correlation of human and computational segmentation agreement. We observed a relevant relation between computational learning and experts' insights, demonstrating how human knowledge may influence the correct computational learning.

Endoscopic prediction of submucosal invasion in Barrett's cancer with the use of artificial intelligence: a pilot study.

BACKGROUND: The accurate differentiation between T1a and T1b Barrett's-related cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an artificial intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett's cancer on white-light images. METHODS: Endoscopic images from three tertiary care centers in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) were evaluated using the AI system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett's cancer. RESULTS: The sensitivity, specificity, F1 score, and accuracy of the AI system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.74, and 0.71, respectively. There was no statistically significant difference between the performance of the AI system and that of experts, who showed sensitivity, specificity, F1, and accuracy of 0.63, 0.78, 0.67, and 0.70, respectively. CONCLUSION: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett's cancer. AI scored equally to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and real-life settings. Nevertheless, the correct prediction of submucosal invasion in Barrett's cancer remains challenging for both experts and AI.

Assisting Barrett's esophagus identification using endoscopic data augmentation based on Generative Adversarial Networks.

Barrett's esophagus figured a swift rise in the number of cases in the past years. Although traditional diagnosis methods offered a vital role in early-stage treatment, they are generally time- and resource-consuming. In this context, computer-aided approaches for automatic diagnosis emerged in the literature since early detection is intrinsically related to remission probabilities. However, they still suffer from drawbacks because of the lack of available data for machine learning purposes, thus implying reduced recognition rates. This work introduces Generative Adversarial Networks to generate high-quality endoscopic images, thereby identifying Barrett's esophagus and adenocarcinoma more precisely. Further, Convolution Neural Networks are used for feature extraction and classification purposes. The proposed approach is validated over two datasets of endoscopic images, with the experiments conducted over the full and patch-split images. The application of Deep Convolutional Generative Adversarial Networks for the data augmentation step and LeNet-5 and AlexNet for the classification step allowed us to validate the proposed methodology over an extensive set of datasets (based on original and augmented sets), reaching results of 90% of accuracy for the patch-based approach and 85% for the image-based approach. Both results are based on augmented datasets and are statistically different from the ones obtained in the original datasets of the same kind. Moreover, the impact of data augmentation was evaluated in the context of image description and classification, and the results obtained using synthetic images outperformed the ones over the original datasets, as well as other recent approaches from the literature. Such results suggest promising insights related to the importance of proper data for the accurate classification concerning computer-assisted Barrett's esophagus and adenocarcinoma detection.

A technical review of artificial intelligence as applied to gastrointestinal endoscopy: clarifying the terminology.

Background and aim The growing number of publications on the application of artificial intelligence (AI) in medicine underlines the enormous importance and potential of this emerging field of research. In gastrointestinal endoscopy, AI has been applied to all segments of the gastrointestinal tract most importantly in the detection and characterization of colorectal polyps. However, AI research has been published also in the stomach and esophagus for both neoplastic and non-neoplastic disorders. The various technical as well as medical aspects of AI, however, remain confusing especially for non-expert physicians. This physician-engineer co-authored review explains the basic technical aspects of AI and provides a comprehensive overview of recent publications on AI in gastrointestinal endoscopy. Finally, a basic insight is offered into understanding publications on AI in gastrointestinal endoscopy.

Bag of Samplings for computer-assisted Parkinson's disease diagnosis based on Recurrent Neural Networks.

Parkinson's Disease (PD) is a clinical syndrome that affects millions of people worldwide. Although considered as a non-lethal disease, PD shortens the life expectancy of the patients. Many studies have been dedicated to evaluating methods for early-stage PD detection, which includes machine learning techniques that employ, in most cases, motor dysfunctions, such as tremor. This work explores the time dependency in tremor signals collected from handwriting exams. To learn such temporal information, we propose a model based on Bidirectional Gated Recurrent Units along with an attention mechanism. We also introduce the concept of "Bag of Samplings" that computes multiple compact representations of the signals. Experimental results have shown the proposed model is a promising technique with results comparable to some state-of-the-art approaches in the literature.

A survey on computer-assisted Parkinson's Disease diagnosis.

BACKGROUND AND OBJECTIVE: In this work, we present a systematic review concerning the recent enabling technologies as a tool to the diagnosis, treatment and better quality of life of patients diagnosed with Parkinson's Disease (PD), as well as an analysis of future trends on new approaches to this end. METHODS: In this review, we compile a number of works published at some well-established databases, such as Science Direct, IEEEXplore, PubMed, Plos One, Multidisciplinary Digital Publishing Institute (MDPI), Association for Computing Machinery (ACM), Springer and Hindawi Publishing Corporation. Each selected work has been carefully analyzed in order to identify its objective, methodology and results. RESULTS: The review showed the majority of works make use of signal-based data, which are often acquired by means of sensors. Also, we have observed the increasing number of works that employ virtual reality and e-health monitoring systems to increase the life quality of PD patients. Despite the different approaches found in the literature, almost all of them make use of some sort of machine learning mechanism to aid the automatic PD diagnosis. CONCLUSIONS: The main focus of this survey is to consider computer-assisted diagnosis, and how effective they can be when handling the problem of PD identification. Also, the main contribution of this review is to consider very recent works only, mainly from 2015 and 2016.

Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification.

BACKGROUND AND OBJECTIVE: Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. METHODS: In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. RESULTS: The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95%. CONCLUSIONS: The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features.

A survey on Barrett's esophagus analysis using machine learning.

This work presents a systematic review concerning recent studies and technologies of machine learning for Barrett's esophagus (BE) diagnosis and treatment. The use of artificial intelligence is a brand new and promising way to evaluate such disease. We compile some works published at some well-established databases, such as Science Direct, IEEEXplore, PubMed, Plos One, Multidisciplinary Digital Publishing Institute (MDPI), Association for Computing Machinery (ACM), Springer, and Hindawi Publishing Corporation. Each selected work has been analyzed to present its objective, methodology, and results. The BE progression to dysplasia or adenocarcinoma shows a complex pattern to be detected during endoscopic surveillance. Therefore, it is valuable to assist its diagnosis and automatic identification using computer analysis. The evaluation of the BE dysplasia can be performed through manual or automated segmentation through machine learning techniques. Finally, in this survey, we reviewed recent studies focused on the automatic detection of the neoplastic region for classification purposes using machine learning methods.

A new computer vision-based approach to aid the diagnosis of Parkinson's disease.

BACKGROUND AND OBJECTIVE: Even today, pointing out an exam that can diagnose a patient with Parkinson's disease (PD) accurately enough is not an easy task. Although a number of techniques have been used in search for a more precise method, detecting such illness and measuring its level of severity early enough to postpone its side effects are not straightforward. In this work, after reviewing a considerable number of works, we conclude that only a few techniques address the problem of PD recognition by means of micrography using computer vision techniques. Therefore, we consider the problem of aiding automatic PD diagnosis by means of spirals and meanders filled out in forms, which are then compared with the template for feature extraction. METHODS: In our work, both the template and the drawings are identified and separated automatically using image processing techniques, thus needing no user intervention. Since we have no registered images, the idea is to obtain a suitable representation of both template and drawings using the very same approach for all images in a fast and accurate approach. RESULTS: The results have shown that we can obtain very reasonable recognition rates (around ≈67%), with the most accurate class being the one represented by the patients, which outnumbered the control individuals in the proposed dataset. CONCLUSIONS: The proposed approach seemed to be suitable for aiding in automatic PD diagnosis by means of computer vision and machine learning techniques. Also, meander images play an important role, leading to higher accuracies than spiral images. We also observed that the main problem in detecting PD is the patients in the early stages, who can draw near-perfect objects, which are very similar to the ones made by control patients.

Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations.

Automatic classification of vocalization type could potentially become a useful tool for acoustic the monitoring of captive colonies of highly vocal primates. However, for classification to be useful in practice, a reliable algorithm that can be successfully trained on small datasets is necessary. In this work, we consider seven different classification algorithms with the goal of finding a robust classifier that can be successfully trained on small datasets. We found good classification performance (accuracy > 0.83 and F1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithms are made publicly available.

Computational methods for the image segmentation of pigmented skin lesions: A review.

BACKGROUND AND OBJECTIVES: Because skin cancer affects millions of people worldwide, computational methods for the segmentation of pigmented skin lesions in images have been developed in order to assist dermatologists in their diagnosis. This paper aims to present a review of the current methods, and outline a comparative analysis with regards to several of the fundamental steps of image processing, such as image acquisition, pre-processing and segmentation. METHODS: Techniques that have been proposed to achieve these tasks were identified and reviewed. As to the image segmentation task, the techniques were classified according to their principle. RESULTS: The techniques employed in each step are explained, and their strengths and weaknesses are identified. In addition, several of the reviewed techniques are applied to macroscopic and dermoscopy images in order to exemplify their results. CONCLUSIONS: The image segmentation of skin lesions has been addressed successfully in many studies; however, there is a demand for new methodologies in order to improve the efficiency.