Three-dimensional maxillary virtual patient creation by convolutional neural network-based segmentation on cone-beam computed tomography images.

OBJECTIVE: To qualitatively and quantitatively assess integrated segmentation of three convolutional neural network (CNN) models for the creation of a maxillary virtual patient (MVP) from cone-beam computed tomography (CBCT) images. MATERIALS AND METHODS: A dataset of 40 CBCT scans acquired with different scanning parameters was selected. Three previously validated individual CNN models were integrated to achieve a combined segmentation of maxillary complex, maxillary sinuses, and upper dentition. Two experts performed a qualitative assessment, scoring-integrated segmentations from 0 to 10 based on the number of required refinements. Furthermore, experts executed refinements, allowing performance comparison between integrated automated segmentation (AS) and refined segmentation (RS) models. Inter-observer consistency of the refinements and the time needed to create a full-resolution automatic segmentation were calculated. RESULTS: From the dataset, 85% scored 7-10, and 15% were within 3-6. The average time required for automated segmentation was 1.7 min. Performance metrics indicated an excellent overlap between automatic and refined segmentation with a dice similarity coefficient (DSC) of 99.3%. High inter-observer consistency of refinements was observed, with a 95% Hausdorff distance (HD) of 0.045 mm. CONCLUSION: The integrated CNN models proved to be fast, accurate, and consistent along with a strong interobserver consistency in creating the MVP. CLINICAL RELEVANCE: The automated segmentation of these structures simultaneously could act as a valuable tool in clinical orthodontics, implant rehabilitation, and any oral or maxillofacial surgical procedures, where visualization of MVP and its relationship with surrounding structures is a necessity for reaching an accurate diagnosis and patient-specific treatment planning.

Diagnosing autism spectrum disorder in children using conventional MRI and apparent diffusion coefficient based deep learning algorithms.

OBJECTIVE: To develop and validate deep learning (DL) methods for diagnosing autism spectrum disorder (ASD) based on conventional MRI (cMRI) and apparent diffusion coefficient (ADC) images. METHODS: A total of 151 ASD children and 151 age-matched typically developing (TD) controls were included in this study. The data from these subjects were assigned to training and validation datasets. An additional 20 ASD children and 25 TD controls were acquired, whose data were utilized in an independent test set. All subjects underwent cMRI and diffusion-weighted imaging examination of the brain. We developed a series of DL models to separate ASD from TD based on the cMRI and ADC data. The seven models used include five single-sequence models (SSMs), one dominant-sequence model (DSM), and one all-sequence model (ASM). To enhance the feature detection of the models, we embed an attention mechanism module. RESULTS: The highest AUC (0.824 ~ 0.850) was achieved when applying the SSM based on either FLAIR or ADC to the validation and independent test sets. A DSM using the combination of FLAIR and ADC showed an improved AUC in the validation (0.873) and independent test sets (0.876). The ASM also showed better diagnostic value in the validation (AUC = 0.838) and independent test sets (AUC = 0.836) compared to the SSMs. Among the models with attention mechanism, the DSM achieved the highest diagnostic performance with an AUC, accuracy, sensitivity, and specificity of 0.898, 84.4%, 85.0%, and 84.0% respectively. CONCLUSIONS: This study established the potential of DL models to distinguish ASD cases from TD controls based on cMRI and ADC images. KEY POINTS: • Deep learning models based on conventional MRI and ADC can be used to diagnose ASD. • The model (DSM) based on the FLAIR and ADC sequence achieved the best diagnostic performance with an AUC of 0.836 in the independent test sets. • The attention mechanism further improved the diagnostic performance of the models.

Automated Stanford classification of aortic dissection using a 2-step hierarchical neural network at computed tomography angiography.

OBJECTIVES: This study aimed to evaluate the feasibility of automatic Stanford classification of classic aortic dissection (AD) using a 2-step hierarchical neural network. METHODS: Between 2015 and 2019, 130 arterial phase series (57 type A, 43 type B, and 30 negative cases) in aortic CTA were collected for the training and validation. A 2-step hierarchical model was built including the first step detecting AD and the second step predicting the probability (0-1) of Stanford types. The model's performance was evaluated with an off-line prospective test in 2020. The sensitivity and specificity for Stanford type A, type B, and no AD (Sens A, B, N and Spec A, B, N, respectively) and Cohen's kappa were reported. RESULTS: Of 298 cases (22 with type A, 29 with type B, and 247 without AD) in the off-line prospective test, the Sens A, Sens B, and Sens N were 95.45% (95% confidence interval [CI], 77.16-99.88%), 79.31% (95% CI, 60.28-92.01%), and 93.52% (95% CI, 89.69-96.25%), respectively. The Spec A, Spec B, and Spec N were 98.55% (95% CI, 96.33-99.60%), 94.05% (95% CI, 90.52-96.56%), and 94.12% (95% CI, 83.76-98.77%), respectively. The classification rate achieved 92.28% (95% CI, 88.64-95.04%). The Cohen's kappa was 0.766 (95% CI, 0.68-0.85; p < 0.001). CONCLUSIONS: Stanford classification of classic AD can be determined by a 2-step hierarchical neural network with high sensitivity and specificity of type A and high specificity in type B and no AD. KEY POINTS: • The Stanford classification for aortic dissection is widely adopted and divides it into Stanford type A and type B based on the ascending thoracic aorta dissected or not. • The 2-step hierarchical neural network for Stanford classification of classic aortic dissection achieved high sensitivity (95.45%) and specificity (98.55%) of type A and high specificity in type B and no aortic dissection (94.05% and 94.12%, respectively) in 298 test cases. • The 2-step hierarchical neural network demonstrated moderate agreement (Cohen's kappa: 0.766, p < 0.001) with cardiovascular radiologists in detection and Stanford classification of classic aortic dissection in 298 test cases.

Application of a computational neural network to optimize the fluorescence signal from a receptor-ligand interaction on a microfluidic chip.

We describe the use of a computational neural network platform to optimize the fluorescence upon binding 5-carboxyfluorescein-d-Ala-d-Ala-d-Ala (5-FAM(DA)3 ) (1) to the antibiotic teicoplanin covalently attached to a glass slide. A three-level response surface experimental design was used as the first stage of investigation. Subsequently, three defined experimental parameters were examined by the neural network approach: (i) the concentration of teicoplanin used to derivatize a glass platform on the microfluidic device, (ii) the time required for the immobilization of teicoplanin on the platform, and (iii) the length of time 1 is allowed to equilibrate with teicoplanin in the microfluidic channel. Optimal neural structure provided a best fit model, both for the training set (r(2) = 0.961) and test set (r(2) = 0.934) data. Model simulated results were experimentally validated with excellent agreement (% difference) between experimental and predicted fluorescence shown, thus demonstrating efficiency of the neural network approach.

[Significance of natural language processing and chat-based generative language models]. / Stellenwert von Natural Language Processing und chatbasierten Generative Language Models.

BACKGROUND: Natural language processing (NLP) has experienced significant growth in recent years and shows potential for broad impacts in scientific research and clinical practice. OBJECTIVE: This study comprises an exploration of the role of NLP in scientific research and its subsequent effects on traditional publication practices, as well as an evaluation of the opportunities and challenges offered by large language models (LLM) and a reflection on necessary paradigm shifts in research culture. MATERIALS AND METHODS: Current LLMs, such as ChatGPT, and their potential applications were compared and assessed. An analysis of the literature and case studies on the integration of LLMs into scientific and clinical practice was conducted. RESULTS AND CONCLUSION: LLMs provide enhanced access to and processing capabilities of text-based information and represent a vast potential for (medical) research as well as daily clinical practice. Chat-based LLMs enable efficient completion of often time-consuming tasks, but due to their tendency for hallucinations, have a significant limitation. Current developments require critical examination and a paradigm shift to fully exploit the benefits of LLMs and minimize potential risks.

A two-step neural network-based guiding system for obtaining reliable radiographs for critical shoulder angle measurement.

Background: The critical shoulder angle (CSA) has been reported to be highly associated with rotator cuff tears (RCTs) and an increased risk of RCT re-tears. However, the measurement of the CSA is greatly affected by the malpositioning of the shoulder. To address this issue, a two-step neural network-based guiding system was developed to obtain reliable CSA radiographs, and its feasibility and accuracy was evaluated. Methods: A total of 1,754 shoulder anteroposterior (AP) radiographs were retrospectively acquired to train and validate a two-step neural network-based guiding system to obtain reliable CSA radiographs. The study included patients aged 18 years or older who underwent X-rays and/or computed tomography (CT) scans of the shoulder. Patients who had undergone shoulder surgery, had a confirmed fracture, or were diagnosed with a musculoskeletal tumor or glenoid defect were excluded from the study. The system consisted of a two-step neural network that in the first step, localized the region of interest of the shoulder, and in the second step, classified the radiography according to type [i.e., 'forward' when the non-overlapping coracoid process is above the glenoid rim, 'backward' when the non-overlapping coracoid process is below or aligned with the glenoid rim, a ratio of the transverse to longitudinal diameter of the glenoid projection (RTL) ≤0.25, or a RTL >0.25]. The performance of the model was assessed in an offline, prospective manner, focusing on the sensitivity and specificity for the forward, backward, RTL ≤0.25, or RTL >0.25 types (denoted as SensF, B, -, + and SpecF, B, -, +, respectively), and Cohen's kappa was also reported. Results: Of 273 cases in the offline prospective test, the SensF, SensB, Sens-, and Sens+ were 88.88% [95% confidence interval (CI): 50.67-99.41%], 94.11% (95% CI: 82.77-98.47%), 96.96% (95% CI: 91.94-99.02%), and 95.06% (95% CI: 87.15-98.40%), respectively. The SpecF, SpecB, Spec-, and Spec+ were 98.48% (95% CI: 95.90-99.51%), 99.55% (95% CI: 97.12-99.97%), 95.04% (95% CI: 89.65-97.81%), and 97.39% (93.69-99.03%), respectively. A high classification rate (93.41%; 95% CI: 89.14-96.24%) and almost perfect agreement (Cohen's kappa: 0.903, 95% CI: 0.86-0.95) were achieved. Conclusions: The guiding system can rapidly and accurately classify the types of AP shoulder radiography, thereby guiding the adjustment of patient positioning. This will facilitate the rapid obtainment of reliable CSA radiography to measure the CSA on proper AP radiographs.

Artificial neural networks for the detection of odontoid fractures using the Konstanz Information Miner Analytics Platform.

STUDY DESIGN: An experimental study. PURPOSE: This study aimed to investigate the potential use of artificial neural networks (ANNs) in the detection of odontoid fractures using the Konstanz Information Miner (KNIME) Analytics Platform that provides a technique for computer-assisted diagnosis using radiographic X-ray imaging. OVERVIEW OF LITERATURE: In medical image processing, computer-assisted diagnosis with ANNs from radiographic X-ray imaging is becoming increasingly popular. Odontoid fractures are a common fracture of the axis and account for 10%-15% of all cervical fractures. However, a literature review of computer-assisted diagnosis with ANNs has not been made. METHODS: This study analyzed 432 open-mouth (odontoid) radiographic views of cervical spine X-ray images obtained from dataset repositories, which were used in developing ANN models based on the convolutional neural network theory. All the images contained diagnostic information, including 216 radiographic images of individuals with normal odontoid processes and 216 images of patients with acute odontoid fractures. The model classified each image as either showing an odontoid fracture or not. Specifically, 70% of the images were training datasets used for model training, and 30% were used for testing. KNIME's graphic user interface-based programming enabled class label annotation, data preprocessing, model training, and performance evaluation. RESULTS: The graphic user interface program by KNIME was used to report all radiographic X-ray imaging features. The ANN model performed 50 epochs of training. The performance indices in detecting odontoid fractures included sensitivity, specificity, F-measure, and prediction error of 100%, 95.4%, 97.77%, and 2.3%, respectively. The model's accuracy accounted for 97% of the area under the receiver operating characteristic curve for the diagnosis of odontoid fractures. CONCLUSIONS: The ANN models with the KNIME Analytics Platform were successfully used in the computer-assisted diagnosis of odontoid fractures using radiographic X-ray images. This approach can help radiologists in the screening, detection, and diagnosis of acute odontoid fractures.

Unsupervised classification of multi-contrast magnetic resonance histology of peripheral arterial disease lesions using a convolutional variational autoencoder with a Gaussian mixture model in latent space: A technical feasibility study.

PURPOSE: To investigate the feasibility of a deep learning algorithm combining variational autoencoder (VAE) and two-dimensional (2D) convolutional neural networks (CNN) for automatically quantifying hard tissue presence and morphology in multi-contrast magnetic resonance (MR) images of peripheral arterial disease (PAD) occlusive lesions. METHODS: Multi-contrast MR images (T2-weighted and ultrashort echo time) were acquired from lesions harvested from six amputated legs with high isotropic spatial resolution (0.078 mm and 0.156 mm, respectively) at 9.4 T. A total of 4014 pseudo-color combined images were generated, with 75% used to train a VAE employing custom 2D CNN layers. A Gaussian mixture model (GMM) was employed to classify the latent space data into four tissue classes: I) concentric calcified (c), II) eccentric calcified (e), III) occluded with hard tissue (h) and IV) occluded with soft tissue (s). Test image probabilities, encoded by the trained VAE were used to evaluate model performance. RESULTS: GMM component classification probabilities ranged from 0.92 to 0.97 for class (c), 1.00 for class (e), 0.82-0.95 for class (h) and 0.56-0.93 for the remaining class (s). Due to the complexity of soft-tissue lesions reflected in the heterogeneity of the pseudo-color images, more GMM components (n=17) were attributed to class (s), compared to the other three (c, e and h) (n=6). CONCLUSION: Combination of 2D CNN VAE and GMM achieves high classification probabilities for hard tissue-containing lesions. Automatic recognition of these classes may aid therapeutic decision-making and identifying uncrossable lesions prior to endovascular intervention.

A deep-learning approach to predict bleeding risk over time in patients on extended anticoagulation therapy.

BACKGROUND: Thus far, all the clinical models developed to predict major bleeding in patients on extended anticoagulation therapy use the baseline predictors to stratify patients into different risk groups. Therefore, these models do not account for the clinical changes and events that occur after the baseline visit, which can modify risk of bleeding. However, it is difficult to develop predictive models from the routine follow-up clinical interviews, which are irregular sequences of multivariate time series data. OBJECTIVES: To demonstrate that deep learning can incorporate patient time series follow-up data to improve prediction of major bleeding. METHODS: We used the baseline and follow-up data that were collected over 8 years in a longitudinal cohort study of 2542 patients, of whom 118 had major bleeding. Four supervised neural network-based machine-learning models were trained on the baseline, follow-up, or both datasets using 70% of the data. The performance of these models was evaluated, along with modified versions of 6 previously developed clinical models, on the remaining 30% of the data. RESULTS: An ensemble of feedforward and recurrent neural networks that used the baseline and follow-up data was the best-performing model, achieving a sensitivity and a specificity of 61% and 82%, respectively, in identifying major bleeding, and it outperformed the previously developed clinical models in terms of area under the receiver operating characteristic curve (82%) and area under the precision-recall curve (14%). CONCLUSION: Time series follow-up data can improve major bleeding prediction in patients on extended anticoagulation therapy.

Oral squamous cell carcinoma diagnosis in digitized histological images using convolutional neural network.

Background/purpose: Diagnostic methods of oral squamous cell carcinoma (SCC) using artificial intelligence (AI) and digital-histopathologic images have been developed. However, previous AI training methods have focused on the cellular atypia given by the training of high-magnification images, and little attention has been paid to structural atypia provided by low-power wide fields. Since oral SCC has histopathologic types with bland cytology, both cellular atypia and structural atypia must be considered as histopathologic features. This study aimed to investigate AI ability to judge oral SCC in a novel training method considering cellular and structural atypia and their suitability. Materials and methods: We examined digitized histological whole-slide images from 90 randomly selected patients with tongue SCC who attended a dental hospital. Image patches of 1000 × 1000 pixels were cut from whole-slide images at 0.3125-, 1.25-, 5-, and 20-fold magnification, and 90,059 image patches were used for training and evaluation. These image patches were resized into 224 × 224, 384 × 384, 512 × 512, and 768 × 768 pixels, and the differences in input size were analyzed. EfficientNet B0 was utilized as the convolutional neural network model. Gradient-weighted class activation mapping (Grad-CAM) was used to elucidate its validity. Results: The proposed method achieved a peak accuracy of 99.65% with an input size of 512 × 512 pixels. Grad-CAM suggested that AI focused on both cellular and structural atypia of SCC, and tended to focus on the region surrounding the basal layer. Conclusion: Training AI regarding both cellular and structural atypia using various magnification images simultaneously may be suitable for the diagnosis of oral SCC.

A comparative study of two automated solutions for cross-sectional skeletal muscle measurement from abdominal computed tomography images.

BACKGROUND: Measurement of cross-sectional muscle area (CSMA) at the mid third lumbar vertebra (L3) level from computed tomography (CT) images is becoming one of the reference methods for sarcopenia diagnosis. However, manual skeletal muscle segmentation is tedious and is thus restricted to research. Automated solutions are required for use in clinical practice. PURPOSE: The aim of this study was to compare the reliability of two automated solutions for the measurement of CSMA. METHODS: We conducted a retrospective analysis of CT images in our hospital database. We included consecutive individuals hospitalized at the Grenoble University Hospital in France between January and May 2018 with abdominal CT images and sagittal reconstruction. We used two types of software to automatically segment skeletal muscle: ABACS, a module of the SliceOmatic software solution "ABACS-SliceOmatic," and a deep learning-based solution called "AutoMATiCA." Manual segmentation was performed by a medical expert to generate reference data using "SliceOmatic." The Dice similarity coefficient (DSC) was used to measure overlap between the results of the manual and the automated segmentations. The DSC value for each method was compared with the Mann-Whitney U test. RESULTS: A total of 676 hospitalized individuals was retrospectively included (365 males [53.8%] and 312 females [46.2%]). The median DSC for SliceOmatic vs AutoMATiCA (0.969 [5th percentile: 0.909]) was greater than the median DSC for SliceOmatic vs. ABACS-SliceOmatic (0.949 [5th percentile: 0.836]) (p < 0.001). CONCLUSIONS: AutoMATiCA, which used artificial intelligence, was more reliable than ABACS-SliceOmatic for skeletal muscle segmentation at the L3 level in a cohort of hospitalized individuals. The next step is to develop and validate a neural network that can identify L3 slices, which is currently a fastidious process.

Automated Opportunistic Trabecular Volumetric Bone Mineral Density Extraction Outperforms Manual Measurements for the Prediction of Vertebral Fractures in Routine CT.

Opportunistic osteoporosis screening using multidetector CT-scans (MDCT) and convolutional neural network (CNN)-derived segmentations of the spine to generate volumetric bone mineral density (vBMD) bears the potential to improve incidental osteoporotic vertebral fracture (VF) prediction. However, the performance compared to the established manual opportunistic vBMD measures remains unclear. Hence, we investigated patients with a routine MDCT of the spine who had developed a new osteoporotic incidental VF and frequency matched to patients without incidental VFs as assessed on follow-up MDCT images after 1.5 years. Automated vBMD was generated using CNN-generated segmentation masks and asynchronous calibration. Additionally, manual vBMD was sampled by two radiologists. Automated vBMD measurements in patients with incidental VFs at 1.5-years follow-up (n = 53) were significantly lower compared to patients without incidental VFs (n = 104) (83.6 ± 29.4 mg/cm3 vs. 102.1 ± 27.7 mg/cm3, p < 0.001). This comparison was not significant for manually assessed vBMD (99.2 ± 37.6 mg/cm3 vs. 107.9 ± 33.9 mg/cm3, p = 0.30). When adjusting for age and sex, both automated and manual vBMD measurements were significantly associated with incidental VFs at 1.5-year follow-up, however, the associations were stronger for automated measurements (ß = -0.32; 95% confidence interval (CI): -20.10, 4.35; p < 0.001) compared to manual measurements (ß = -0.15; 95% CI: -11.16, 5.16; p < 0.03). In conclusion, automated opportunistic measurements are feasible and can be useful for bone mineral density assessment in clinical routine.

Transfer-Learning Deep Radiomics and Hand-Crafted Radiomics for Classifying Lymph Nodes from Contrast-Enhanced Computed Tomography in Lung Cancer.

OBJECTIVES: Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of this study was to predict the PET result from traditional contrast-enhanced computed tomography (CT) and to test different feature extraction strategies. METHODS: In this study, 100 lung cancer patients underwent a contrast-enhanced 18F-fluorodeoxyglucose (FDG) PET/CT scan between August 2012 and December 2019. We trained machine learning models to predict FDG uptake in the subsequent PET scan. Model inputs were composed of (i) traditional "hand-crafted" radiomics features from the segmented lymph nodes, (ii) deep features derived from a pretrained EfficientNet-CNN, and (iii) a hybrid approach combining (i) and (ii). RESULTS: In total, 2734 lymph nodes [555 (20.3%) PET-positive] from 100 patients [49% female; mean age 65, SD: 14] with lung cancer (60% adenocarcinoma, 21% plate epithelial carcinoma, 8% small-cell lung cancer) were included in this study. The area under the receiver operating characteristic curve (AUC) ranged from 0.79 to 0.87, and the scaled Brier score (SBS) ranged from 16 to 36%. The random forest model (iii) yielded the best results [AUC 0.871 (0.865-0.878), SBS 35.8 (34.2-37.2)] and had significantly higher model performance than both approaches alone (AUC: p < 0.001, z = 8.8 and z = 22.4; SBS: p < 0.001, z = 11.4 and z = 26.6, against (i) and (ii), respectively). CONCLUSION: Both traditional radiomics features and transfer-learning deep radiomics features provide relevant and complementary information for non-invasive N-staging in lung cancer.

Deep Learning Neural Networks to Predict Serious Complications After Bariatric Surgery: Analysis of Scandinavian Obesity Surgery Registry Data.

BACKGROUND: Obesity is one of today's most visible public health problems worldwide. Although modern bariatric surgery is ostensibly considered safe, serious complications and mortality still occur in some patients. OBJECTIVE: This study aimed to explore whether serious postoperative complications of bariatric surgery recorded in a national quality registry can be predicted preoperatively using deep learning methods. METHODS: Patients who were registered in the Scandinavian Obesity Surgery Registry (SOReg) between 2010 and 2015 were included in this study. The patients who underwent a bariatric procedure between 2010 and 2014 were used as training data, and those who underwent a bariatric procedure in 2015 were used as test data. Postoperative complications were graded according to the Clavien-Dindo classification, and complications requiring intervention under general anesthesia or resulting in organ failure or death were considered serious. Three supervised deep learning neural networks were applied and compared in our study: multilayer perceptron (MLP), convolutional neural network (CNN), and recurrent neural network (RNN). The synthetic minority oversampling technique (SMOTE) was used to artificially augment the patients with serious complications. The performances of the neural networks were evaluated using accuracy, sensitivity, specificity, Matthews correlation coefficient, and area under the receiver operating characteristic curve. RESULTS: In total, 37,811 and 6250 patients were used as the training data and test data, with incidence rates of serious complication of 3.2% (1220/37,811) and 3.0% (188/6250), respectively. When trained using the SMOTE data, the MLP appeared to have a desirable performance, with an area under curve (AUC) of 0.84 (95% CI 0.83-0.85). However, its performance was low for the test data, with an AUC of 0.54 (95% CI 0.53-0.55). The performance of CNN was similar to that of MLP. It generated AUCs of 0.79 (95% CI 0.78-0.80) and 0.57 (95% CI 0.59-0.61) for the SMOTE data and test data, respectively. Compared with the MLP and CNN, the RNN showed worse performance, with AUCs of 0.65 (95% CI 0.64-0.66) and 0.55 (95% CI 0.53-0.57) for the SMOTE data and test data, respectively. CONCLUSIONS: MLP and CNN showed improved, but limited, ability for predicting the postoperative serious complications after bariatric surgery in the Scandinavian Obesity Surgery Registry data. However, the overfitting issue is still apparent and needs to be overcome by incorporating intra- and perioperative information.

Superstitious Perception: Comparing Perceptual Prediction by Humans and Neural Networks.

Recent developments in convolutional neural networks (CNNs) have introduced new ways to model the complex processes of human vision. To date, the comparison of human vision and CNNs has focused on internal representations (i.e., receptive fields), with behavioral comparisons left largely unexplored. Here, we probe the influence of cognitive strategy on the similarity between CNN output and human behavior. We gave study participants a superstitious perception task (i.e., we asked them to detect an assigned target in white noise) while asking them to engage in either an active or passive attentional strategy. Previous research has shown that an active attentional strategy tends to engage central executive functions, whereas a passive strategy allows perceptual processes to unfold with limited central control. The results showed that the pattern of human responses in the superstitious perception task depended significantly on task strategy. Specifically, detecting targets superstitiously (i.e., false alarms) was correlated with evidence of a target's presence in the passive condition, but not in the active condition.Human data were compared to the performance of a CNN performing the same task, with the decision criterion of the CNN set to match the false alarm rates observed in the two strategy conditions of the human participants. CNN responses resembled those of human participants in the passive condition more closely than those in the active condition. This observation suggests that the CNN does a better job of mimicking human behavior when central executive functions are not engaged than when they are engaged. This, in turn, has important implications for what human participants are doing in the superstitious perception task. Namely, it implies that superstitious perception may have two important ingredients that are somewhat dissociable. First, there is the ability to detect weak signals in noise that correspond to the target image. This appears to be what participants are doing under passive strategy conditions; they allow externally generated signals to dominate their perceptual experience. Second, there is the ability to ignore the noise in favor of basing responses solely on internally generated signals. This seems to correspond more closely to what participants are doing under active strategy conditions, when attention is controlled by representations in memory. This research emphasizes the importance of modeling the full range of human responsiveness in even a simple noisy detection task.

Ai based motion analysis software for sport and physical therapy assessment / Software de análisis de movimiento basado en ia para la evaluación del deporte y la fisioterapia / Software de análise de movimento baseado em ia para avaliação de esporte e fisioterapia

ABSTRACT Introduction: As the World Health Organization declared the novel coronavirus as a pandemic in March 2020, physical therapy is more difficult to execute, and social distancing is mandatory in the healthcare sector. Objective: In physical therapy, an online video analysis software that provides real-time graphic and numerical information about the patient's movement executions without direct personal contact would mean a significant improvement in eHealth treatment. Methods: We have developed a software layer on top of OpenPose human body position estimation software that can extract the time series of angles of arbitrary body parts using the output coordinates from OpenPose processing the data recorded by two cameras simultaneously. To validate the procedure of determining the joint angles using the Openpose software we have used the Kinovea software. Results: The comparison of the determined maximal knee angle in our and the Kinovea software, which is widely used in biomechanical measurements, was not significantly different (2.03±1.06°, p<0.05) Conclusion: This indicates, that the developed software can calculate the appropriate joint angles with the accuracy that physiotherapy treatments require. As, to our knowledge no such software yet exists, with the help of this software development, therapists could control and correct the exercises in real-time, and also from a distance, and physical therapy effectiveness could be increased. Level of Evidence II; Experimental, comparative.

RESUMEN Introducción: Como la Organización Mundial de la Salud declaró el nuevo coronavirus como una pandemia en marzo de 2020, la fisioterapia es más difícil de ejecutar, el distanciamiento social es obligatorio en el sector de la salud. Objetivo: En la práctica de fisioterapia un software de análisis de vídeo online que proporcione información gráfica y numérica en tiempo real sobre las ejecuciones de movimiento del paciente sin contacto personal directo supondría una mejora significativa en el tratamiento de la eSalud. Métodos: Fue desarrollado una capa de software sobre el software de estimación de posición del cuerpo humano OpenPose que puede extraer la serie temporal de ángulos de partes arbitrarias del cuerpo utilizando las coordenadas de salida de OpenPose procesando los datos registrados por dos cámaras simultáneamente. Para validar el procedimiento de determinación de los ángulos articulares mediante el software Openpose fue utilizado el software Kinovea. Resultados: La comparación del ángulo máximo de rodilla determinado en nuestro software y Kinovea, que es ampliamente utilizado en mediciones biomecánicas, no fue significativamente diferente (2,03±1,06°, p<0,05). Conclusión: Esto indica que el software desarrollado puede calcular los ángulos articulares adecuados con la precisión que requieren los tratamientos de fisioterapia. Dado que aún no existe dicho software, con la ayuda de este desarrollo de software, los terapeutas podrían controlar y corregir los ejercicios en tiempo real, y también a distancia, y se podría aumentar la eficacia de la fisioterapia. Nivel de Evidencia II; Experimental, comparativo.

RESUMO Introdução: Como a Organização Mundial da Saúde declarou o novo coronavírus como pandemia em março de 2020, a fisioterapia é mais difícil de executar, o distanciamento social é obrigatório no setor de saúde. Objetivo: Na prática da fisioterapia, um software de análise de vídeo online que fornece informações gráficas e numéricas em tempo real sobre as execuções de movimento do paciente sem contato pessoal direto significaria uma melhora significativa no tratamento eHealth. Métodos: Desenvolveu-se uma camada de software em cima do software de estimativa de posição do corpo humano OpenPose que pode extrair as séries temporais de ângulos de partes do corpo arbitrárias usando as coordenadas de saída do OpenPose processando os dados gravados por duas câmeras simultaneamente. Para validar o procedimento de determinação dos ângulos articulares utilizando o software Openpose utilizou-se o software Kinovea. Resultados: A comparação do ângulo máximo do joelho determinado em nosso e no software Kinovea, amplamente utilizado em medidas biomecânicas, não foi significativamente diferente (2,03±1,06°, p<0,05) Conclusão: Isso indica que o software desenvolvido pode calcular os ângulos articulares adequados com a precisão que os tratamentos de fisioterapia exigem. Como esse software ainda não existe, com a ajuda do desenvolvimento desse software, os terapeutas puderam controlar e corrigir os exercícios em tempo real, e também à distância, aumentando a eficácia da fisioterapia. Nível de Evidência II; Experimental, comparativo.

Uso de redes neurais para a predição de diagnóstico de AVE: uma revisão sistemática / Use of neural networks for stroke diagnosis prediction: a systematic review neural networks and stroke prediction

Fundamentos: O Acidente Vascular Encefálico (AVE) é uma síndrome de déficit neurológico agudo atribuído à lesão vascular do Sistema Nervoso (SN). As técnicas de Inteligência Artificial (IA) na Medicina ­ como algoritmos de Redes Neurais Artificiais (RNAs) ­ têm ajudado na tomada de decisões clínicas voltadas para essa condição. Objetivo: o objetivo desta revisão será avaliar como as redes neurais artificiais estão sendo utilizadas para a predição de diagnóstico de AVE. Métodos: Trata-se de uma revisão sistemática de artigos indexados nas bases de dados PubMed, BVS, SciELO, Cochrane e SpringerLink, entre janeiro e fevereiro de 2022. Os critérios de inclusão e filtros para esse trabalho foram: artigos relacionados ao tema, estudos randomizados, coorte e ensaios clínicos, trabalhos em humanos, realizados nos últimos 5 anos, apenas nos idiomas Português, Inglês e Espanhol e com texto completo disponível gratuitamente. Os parâmetros de exclusão foram: artigos duplicados, fuga ao tema, artigos de revisão e trabalhos que não preenchiam todos os critérios de inclusão. Resultados: As RNAs estão sendo utilizadas, principalmente, para avaliação de áreas de lesões isquêmicas e hemorrágicas por métodos de segmentação e os exames mais utilizados para a modelagem dos programas têm sido Ressonância Magnética (RM) e Tomografia Computadorizada (TC). Além da TC e RM, a angiorressonância e angiotomografia também estão sendo utilizadas para o modelamento do algoritmo e são úteis por apresentarem maior sensibilidade para detecção de infartos. Conclusão: Algoritmos de segmentação e classificação aplicados nas RNAs fazem parte da medicina personalizada e servem de base para médicos na prática clínica.

Background: Stroke is an acute neurological deficit syndrome attributed to vascular injury to the Nervous System (NS). Artificial Intelligence (AI) techniques in Medicine ­ such as Artificial Neural Networks (ANNs) algorithms ­ have helped in making clinical decisions aimed at this condition. Objective: the objective of this review will be to evaluate how artificial neural networks are being used to predict the diagnosis of stroke. Methods: This is a systematic review of articles indexed in PubMed, VHL, SciELO, Cochrane and SpringerLink databases, between January and February 2022. The inclusion criteria and filters for this work were: articles related to the topic, studies randomized, cohort and clinical trials, studies in humans, carried out in the last 5 years, only in Portuguese, English and Spanish and with full text available free of charge. The exclusion parameters were: duplicate articles, escape from the topic, review articles and works that did not meet all the inclusion criteria. Results: ANNs are being used mainly for the evaluation of areas of ischemic and hemorrhagic lesions by segmentation methods and the most used exams for modeling the programs have been Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). In addition to CT and MRI, magnetic resonance angiography and tomography angiography are also being used to model the algorithm and are useful because they have greater sensitivity for detecting infarctions. Conclusion: Segmentation and classification algorithms applied in ANNs are part of personalized medicine and serve as a basis for physicians in clinical practice.