A High-Accuracy Mathematical Morphology and Multilayer Perceptron-Based Approach for Melanoma Detection

Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records

Introduction

Medical images and signals are important data sources in the medical field, and they contain key information such as patients' physiology, pathology, and genetics. However, due to the complexity and diversity of medical images and signals, resulting in difficulties in medical knowledge acquisition and decision support.

Methods

In order to solve this problem, this paper proposes an end-to-end framework based on BERT for NER and RE tasks in electronic medical records. Our framework first integrates NER and RE tasks into a unified model, adopting an end-to-end processing manner, which removes the limitation and error propagation of multiple independent steps in traditional methods. Second, by pre-training and fine-tuning the BERT model on large-scale electronic medical record data, we enable the model to obtain rich semantic representation capabilities that adapt to the needs of medical fields and tasks. Finally, through multi-task learning, we enable the model to make full use of the correlation and complementarity between NER and RE tasks, and improve the generalization ability and effect of the model on different data sets.

Results and discussion

We conduct experimental evaluation on four electronic medical record datasets, and the model significantly out performs other methods on different datasets in the NER task. In the RE task, the EMLB model also achieved advantages on different data sets, especially in the multi-task learning mode, its performance has been significantly improved, and the ETE and MTL modules performed well in terms of comprehensive precision and recall. Our research provides an innovative solution for medical image and signal data.

Electrochemical Micro-Immunosensor of Cubic AuPt Dendritic Nanocrystals/Ti3C2-MXenes for Exosomes Detection

Exosomes are extracellular vesicles that exist in body circulation as intercellular message transmitters. Although the potential of tumor-derived exosomes for non-invasive cancer diagnosis is promising, the rapid detection and effective capture of exosomes remains challenging. Herein, a portable electrochemical aptasensor of cubic AuPt dendritic nanocrystals (AuPt DNs)/Ti₃C₂ assisted in signal amplification, and aptamer CD63 modified graphene oxide (GO) was immobilized on a screen-printed carbon electrode (SPCE) as the substrate materials for the direct capture and detection of colorectal carcinoma exosomes. Cubic AuPt DNs/Ti₃C₂ was synthesized according to a simple hydrothermal procedure, and the AuPt DNs/Ti₃C₂-Apt hybrid demonstrated an efficient recognition of exosomes. Under optimal conditions, a detection limit of down to 20 exosomes µL^-1 was achieved with the linear range from 100 exosomes μL^-1 to 5.0 × 10⁵ exosomes μL^-1. The proposed immunosensor could be suitable for the analysis of exosomes and has clinical value in the early diagnosis of cancer.

Design and Implementation of a Prosthesis System Controlled by Electromyographic Signals Means, Characterized with Artificial Neural Networks

Around the world many people loss a body member for many reasons, where advances of technology may be useful to help these people to improve the quality of their lives. Then, designing a technologically advanced prosthesis with natural movements is worthy for scientific, commercial, and social reasons. Thus, research of manufacturing, designing, and signal processing may lead up to a low-cost affordable prosthesis. This manuscript presents a low-cost design proposal for an electromyographic electronic system, which is characterized by a neural network based process. Moreover, a hand-type prosthesis is presented and controlled by using the processed electromyographic signals for a required particular use. For this purpose, the user performs several movements by using the healthy-hand to get some electromyographic signals. After that, the obtained signals are processed in a neural network based controller. Once an usable behavior is obtained, an exact replica of controlled motions are adapted for the other hand by using the designed prosthesis. The characterization process of bioelectrical signals was performed by training twenty characteristics obtained from the original raw signal in contrast with other papers in which seven characteristics have been tested on average. The proposed model reached a 95.2% computer test accuracy and 93% accuracy in a real environment experiment. The platform was tested via online and offline, where the best response was obtained in the online execution time.

Towards the Estimation of Body Weight in Sheep Using Metaheuristic Algorithms from Biometric Parameters in Microsystems

The Body Weight (BW) of sheep is an important indicator for producers. Genetic management, nutrition, and health activities can benefit from weight monitoring. This article presents a polynomial model with an adjustable degree for estimating the weight of sheep from the biometric parameters of the animal. Computer vision tools were used to measure these parameters, obtaining a margin of error of less than 5%. A polynomial model is proposed after the parameters were obtained, where a coefficient and an unknown exponent go with each biometric variable. Two metaheuristic algorithms determine the values of these constants. The first is the most extended algorithm, the Genetic Algorithm (GA). Subsequently, the Cuckoo Search Algorithm (CSA) has a similar performance to the GA, which indicates that the value obtained by the GA is not a local optimum due to the poor parameter selection in the GA. The results show a Root-Mean-Squared Error (RMSE) of 7.68% for the GA and an RMSE of 7.55% for the CSA, proving the feasibility of the mathematical model for estimating the weight from biometric parameters. The proposed mathematical model, as well as the estimation of the biometric parameters can be easily adapted to an embedded microsystem.

Multi-Modal Long-Term Person Re-Identification Using Physical Soft Bio-Metrics and Body Figure

Person re-identification is the task of recognizing a subject across different non-overlapping cameras across different views and times. Most state-of-the-art datasets and proposed solutions tend to address the problem of short-term re-identification. Those models can re-identify a person as long as they are wearing the same clothes. The work presented in this paper addresses the task of long-term re-identification. Therefore, the proposed model is trained on a dataset that incorporates clothes variation. This paper proposes a multi-modal person re-identification model. The first modality includes soft bio-metrics: hair, face, neck, shoulders, and part of the chest. The second modality is the remaining body figure that mainly focuses on clothes. The proposed model is composed of two separate neural networks, one for each modality. For the first modality, a two-stream Siamese network with pre-trained FaceNet as a feature extractor for the first modality is utilized. Part-based Convolutional Baseline classifier with a feature extractor network OSNet for the second modality. Experiments confirm that the proposed model can outperform several state-of-the-art models achieving 81.4 % accuracy on Rank-1, 82.3% accuracy on Rank-5, 83.1% accuracy on Rank-10, and 83.7% accuracy on Rank-20.

Wearable Sensor-Based Human Activity Recognition with Transformer Model

Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human-robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective classification of real-time activity data is, therefore, actively pursued using various machine learning methods. In this study, the transformer model, a deep learning neural network model developed primarily for the natural language processing and vision tasks, was adapted for a time-series analysis of motion signals. The self-attention mechanism inherent in the transformer, which expresses individual dependencies between signal values within a time series, can match the performance of state-of-the-art convolutional neural networks with long short-term memory. The performance of the proposed adapted transformer method was tested on the largest available public dataset of smartphone motion sensor data covering a wide range of activities, and obtained an average identification accuracy of 99.2% as compared with 89.67% achieved on the same data by a conventional machine learning method. The results suggest the expected future relevance of the transformer model for human activity recognition.

Lightweight Neural Network for COVID-19 Detection from Chest X-ray Images Implemented on an Embedded System

At the end of 2019, a severe public health threat named coronavirus disease (COVID-19) spread rapidly worldwide. After two years, this coronavirus still spreads at a fast rate. Due to its rapid spread, the immediate and rapid diagnosis of COVID-19 is of utmost importance. In the global fight against this virus, chest X-rays are essential in evaluating infected patients. Thus, various technologies that enable rapid detection of COVID-19 can offer high detection accuracy to health professionals to make the right decisions. The latest emerging deep-learning (DL) technology enhances the power of medical imaging tools by providing high-performance classifiers in X-ray detection, and thus various researchers are trying to use it with limited success. Here, we propose a robust, lightweight network where excellent classification results can diagnose COVID-19 by evaluating chest X-rays. The experimental results showed that the modified architecture of the model we propose achieved very high classification performance in terms of accuracy, precision, recall, and f1-score for four classes (COVID-19, normal, viral pneumonia and lung opacity) of 21.165 chest X-ray images, and at the same time meeting real-time constraints, in a low-power embedded system. Finally, our work is the first to propose such an optimized model for a low-power embedded system with increased detection accuracy.

Computer-Aided Diagnosis of Malignant Melanoma Using Gabor-Based Entropic Features and Multilevel Neural Networks

The American Cancer Society has recently stated that malignant melanoma is the most serious type of skin cancer, and it is almost 100% curable, if it is detected and treated early. In this paper, we present a fully automated neural framework for real-time melanoma detection, where a low-dimensional, computationally inexpensive but highly discriminative descriptor for skin lesions is derived from local patterns of Gabor-based entropic features. The input skin image is first preprocessed by filtering and histogram equalization to reduce noise and enhance image quality. An automatic thresholding by the optimized formula of Otsu’s method is used for segmenting out lesion regions from the surrounding healthy skin regions. Then, an extensive set of optimized Gabor-based features is computed to characterize segmented skin lesions. Finally, the normalized features are fed into a trained Multilevel Neural Network to classify each pigmented skin lesion in a given dermoscopic image as benign or melanoma. The proposed detection methodology is successfully tested and validated on the public PH2 benchmark dataset using 5-cross-validation, achieving 97.5%, 100% and 96.87% in terms of accuracy, sensitivity and specificity, respectively, which demonstrate competitive performance compared with several recent state-of-the-art methods.