RESUMEN

Background: Thyroid nodules are commonly identified through ultrasound imaging, which plays a crucial role in the early detection of malignancy. The diagnostic accuracy, however, is significantly influenced by the expertise of radiologists, the quality of equipment, and image acquisition techniques. This variability underscores the critical need for computational tools that support diagnosis. Methods: This retrospective study evaluates an artificial intelligence (AI)-driven system for thyroid nodule assessment, integrating clinical practices from multiple prominent Thai medical centers. We included patients who underwent thyroid ultrasonography complemented by ultrasound-guided fine needle aspiration (FNA) between January 2015 and March 2021. Participants formed a consecutive series, enhancing the study's validity. A comparative analysis was conducted between the AI model's diagnostic performance and that of both an experienced radiologist and a third-year radiology resident, using a dataset of 600 ultrasound images from three distinguished Thai medical institutions, each verified with cytological findings. Results: The AI system demonstrated superior diagnostic performance, with an overall sensitivity of 80% [95% confidence interval (CI): 59.3-93.2%] and specificity of 71.4% (95% CI: 53.7-85.4%). At Siriraj Hospital, the AI achieved a sensitivity of 90.0% (95% CI: 55.5-99.8%), specificity of 100.0% (95% CI: 69.2-100%), positive prediction value (PPV) of 100.0%, negative prediction value (NPV) of 90.9%, and an overall accuracy of 95.0%, indicating the benefits of AI's extensive training across diverse datasets. The experienced radiologist's sensitivity was 40.0% (95% CI: 21.1-61.3%), while the specificity was 80.0% (95% CIs: 63.6-91.6%), respectively, showing that the AI significantly outperformed the radiologist in terms of sensitivity (P=0.043) while maintaining comparable specificity. The inter-observer variability analysis indicated a moderate agreement (K=0.53) between the radiologist and the resident, contrasting with fair agreement (K=0.37/0.33) when each was compared with the AI system. Notably, 95% CIs for these diagnostic indexes highlight the AI system's consistent performance across different settings. Conclusions: The findings advocate for the integration of AI into clinical settings to enhance the diagnostic accuracy of radiologists in assessing thyroid nodules. The AI system, designed as a supportive tool rather than a replacement, promises to revolutionize thyroid nodule diagnosis and management by providing a high level of diagnostic precision.

RESUMEN

A thyroid nodule, a common abnormal growth within the thyroid gland, is often identified through ultrasound imaging of the neck. These growths may be solid- or fluid-filled, and their treatment is influenced by factors such as size and location. The Thyroid Imaging Reporting and Data System (TI-RADS) is a classification method that categorizes thyroid nodules into risk levels based on features such as size, echogenicity, margin, shape, and calcification. It guides clinicians in deciding whether a biopsy or other further evaluation is needed. Machine learning (ML) can complement TI-RADS classification, thereby improving the detection of malignant tumors. When combined with expert rules (TI-RADS) and explanations, ML models may uncover elements that TI-RADS misses, especially when TI-RADS training data are scarce. In this paper, we present an automated system for classifying thyroid nodules according to TI-RADS and assessing malignancy effectively. We use ResNet-101 and DenseNet-201 models to classify thyroid nodules according to TI-RADS and malignancy. By analyzing the models' last layer using the Grad-CAM algorithm, we demonstrate that these models can identify risk areas and detect nodule features relevant to the TI-RADS score. By integrating Grad-CAM results with feature probability calculations, we provide a precise heat map, visualizing specific features within the nodule and potentially assisting doctors in their assessments. Our experiments show that the utilization of ResNet-101 and DenseNet-201 models, in conjunction with Grad-CAM visualization analysis, improves TI-RADS classification accuracy by up to 10%. This enhancement, achieved through iterative analysis and re-training, underscores the potential of machine learning in advancing thyroid nodule diagnosis, offering a promising direction for further exploration and clinical application.

Asunto(s)

RESUMEN

Thyroid nodules are lesions requiring diagnosis and follow-up. Tools for detecting and segmenting nodules can help physicians with this diagnosis. Besides immediate diagnosis, automated tools can also enable tracking of the probability of malignancy over time. This paper demonstrates a new algorithm for segmenting thyroid nodules in ultrasound images. The algorithm combines traditional supervised semantic segmentation with unsupervised learning using GANs. The hybrid approach has the potential to upgrade the semantic segmentation model's performance, but GANs have the well-known problems of unstable learning and mode collapse. To stabilize the training of the GAN model, we introduce the concept of closed-loop control of the gain on the loss output of the discriminator. We find gain control leads to smoother generator training and avoids the mode collapse that typically occurs when the discriminator learns too quickly relative to the generator. We also find that the combination of the supervised and unsupervised learning styles encourages both low-level accuracy and high-level consistency. As a test of the concept of controlled hybrid supervised and unsupervised semantic segmentation, we introduce a new model named the StableSeg GAN. The model uses DeeplabV3+ as the generator, Resnet18 as the discriminator, and uses PID control to stabilize the GAN learning process. The performance of the new model in terms of IoU is better than DeeplabV3+, with mean IoU of 81.26% on a challenging test set. The results of our thyroid nodule segmentation experiments show that StableSeg GANs have flexibility to segment nodules more accurately than either comparable supervised segmentation models or uncontrolled GANs.

Asunto(s)

RESUMEN

BACKGROUND: Smartphones are very convenient and accessible communication devices. Smartphone usage over long durations with poor posture can lead to musculoskeletal pain in adult users. OBJECTIVE: To compare pain in the neck, shoulder, upper back, lower back, arm, hand, and eye regions. METHODS: Thirty-five asymptomatic adults aged 18-25 years were divided into two groups: 1. use of an innovative smartphone app for the promotion of ergonomic behaviour (app use) and 2. no use of the innovative smartphone app (no app use). Participants sat upright, holding a smartphone with two hands, eyes 30-40 cm away from the screen, with frequent breaks consisting of stretching the neck and hand muscles while resting the eyes. The task involved taking part in online social networking for a duration of 45 minutes. A body pain chart and the visual analog scale (VAS) were used to evaluate the location and severity of pain. RESULTS: Pain in the neck, shoulder, upper back, arm, and hand regions in the "app use" condition were significantly lower than in the "no app use" condition at 15, 30, and 45 min (p-value<0.05). However, there were negligible differences between the two groups for eye pain, and lower back pain. CONCLUSION: Pain in the neck, shoulder, upper back, and arm regions in adult users in the "app use" condition was less than in the "no app use" condition. We would recommend that adults use the innovative smartphone app to prevent the risk of musculoskeletal pain potentially caused by smartphone usage.

Asunto(s)

RESUMEN

Driver situation awareness is critical for safety. In this paper, we propose a fast, accurate method for obtaining real-time situation awareness using a single type of sensor: monocular cameras. The system tracks the host vehicle's trajectory using sparse optical flow and tracks vehicles in the surrounding environment using convolutional neural networks. Optical flow is used to measure the linear and angular velocity of the host vehicle. The convolutional neural networks are used to measure target vehicles' positions relative to the host vehicle using image-based detections. Finally, the system fuses host and target vehicle trajectories in the world coordinate system using the velocity of the host vehicle and the target vehicles' relative positions with the aid of an Extended Kalman Filter (EKF). We implement and test our model quantitatively in simulation and qualitatively on real-world test video. The results show that the algorithm is superior to state-of-the-art sequential state estimation methods such as visual SLAM in performing accurate global localization and trajectory estimation for host and target vehicles.

Asunto(s)

RESUMEN

Recognizing clinical style is essential for generating intelligent guidance in virtual reality simulators for dental skill acquisition. The aim of this study was to determine the potential of Dynamic Time Warping (DTW) in matching novices' tooth cutting sequences with those of experts. Forty dental students and four expert dentists were enrolled to perform access opening to the root canals with a simulator. Four experts performed in manners that differed widely in the tooth preparation sequence. Forty students were randomly allocated into four groups and were trained following each expert. DTW was performed between each student's sequence and all the expert sequences to determine the best match. Overall, the accuracy of the matching was high (95%). The current results suggest that the DTW is a useful technique to find the best matching expert for a student so that feedback based on that expert's performance can be given to the novice in clinical skill training.

Asunto(s)

RESUMEN

OBJECTIVE: We present a dental training simulator that provides a virtual reality (VR) environment with haptic feedback for dental students to practice dental surgical skills in the context of a crown preparation procedure. The simulator addresses challenges in traditional training such as the subjective nature of surgical skill assessment and the limited availability of expert supervision. METHODS AND MATERIALS: We identified important features for characterizing the quality of a procedure based on interviews with experienced dentists. The features are patterns combining tool position, tool orientation, and applied force. The simulator monitors these features during the procedure, objectively assesses the quality of the performed procedure using hidden Markov models (HMMs), and provides objective feedback on the user's performance in each stage of the procedure. We recruited five dental students and five experienced dentists to evaluate the accuracy of our skill assessment method and the quality of the system's generated feedback. RESULTS: The experimental results show that HMMs with selected features can correctly classify all test sequences into novice and expert categories. The evaluation also indicates a high acceptance rate from experts for the system's generated feedback. CONCLUSION: In this work, we introduce our VR dental training simulator and describe a mechanism for providing objective skill assessment and feedback. The HMM is demonstrated as an effective tool for classifying a particular operator as novice-level or expert-level. The simulator can generate tutoring feedback with quality comparable to the feedback provided by human tutors.

Asunto(s)

RESUMEN

Facial expressions are crucial to human social communication, but the extent to which they are innate and universal versus learned and culture dependent is a subject of debate. Two studies explored the effect of culture and learning on facial expression understanding. In Experiment 1, Japanese and U.S. participants interpreted facial expressions of emotion. Each group was better than the other at classifying facial expressions posed by members of the same culture. In Experiment 2, this reciprocal in-group advantage was reproduced by a neurocomputational model trained in either a Japanese cultural context or an American cultural context. The model demonstrates how each of us, interacting with others in a particular cultural context, learns to recognize a culture-specific facial expression dialect.

Asunto(s)

RESUMEN

OBJECTIVE: Sketching is ubiquitous in medicine. Physicians commonly use sketches as part of their note taking in patient records and to help convey diagnoses and treatments to patients. Medical students frequently use sketches to help them think through clinical problems in individual and group problem solving. Applications ranging from automated patient records to medical education software could benefit greatly from the richer and more natural interfaces that would be enabled by the ability to understand sketches. In this paper we take the first steps toward developing a system that can understand anatomical sketches. METHODS: Understanding an anatomical sketch requires the ability to recognize what anatomical structure has been sketched and from what view (e.g. parietal view of the brain), as well as to identify the anatomical parts and their locations in the sketch (e.g. parts of the brain), even if they have not been explicitly drawn. We present novel algorithms for sketch recognition and for part identification. We evaluate the accuracy of the recognition algorithm on sketches obtained from medical students. We evaluate the part identification algorithm by comparing its results to the judgment of an experienced physician. RESULTS: The sketch recognition algorithm achieves a recognition accuracy of 75.5%, far above the baseline random classification accuracy of 6.7%. Comparison of the results of the part identification algorithm with the judgment of an experienced physician shows close agreement in terms of location, orientation, size, and shape of the identified parts. CONCLUSIONS: The performance of our prototype in terms of accuracy and running time provides strong evidence that development of robust sketch understanding systems for medical domains is an attainable goal. Further work needs to be done to extend the approach to sketches containing multiple and partial anatomical structures, as well as to be able to interpret sketch annotations.

Asunto(s)

RESUMEN

There are two competing theories of facial expression recognition. Some researchers have suggested that it is an example of "categorical perception." In this view, expression categories are considered to be discrete entities with sharp boundaries, and discrimination of nearby pairs of expressive faces is enhanced near those boundaries. Other researchers, however, suggest that facial expression perception is more graded and that facial expressions are best thought of as points in a continuous, low-dimensional space, where, for instance, "surprise" expressions lie between "happiness" and "fear" expressions due to their perceptual similarity. In this article, we show that a simple yet biologically plausible neural network model, trained to classify facial expressions into six basic emotions, predicts data used to support both of these theories. Without any parameter tuning, the model matches a variety of psychological data on categorization, similarity, reaction times, discrimination, and recognition difficulty, both qualitatively and quantitatively. We thus explain many of the seemingly complex psychological phenomena related to facial expression perception as natural consequences of the tasks' implementations in the brain.

Asunto(s)