Search

Advances in AI techniques have fueled research on using EEG data for psychiatric disorder diagnosis. Despite EEG's cost-effectiveness and high temporal resolution, low Signal-to-Noise Ratio (SNR) hampers critical marker extraction and model improvement, while denoising techniques will lead to a loss of effective information in EEG. The aim of this study is to employ AI methods for the processing of raw EEG data. The primary objectives of the processing are twofold: first, to acquire more reliable markers for schizophrenia, and second, to construct a superior automatic classification for schizophrenia. To remove the noises and retain task-related (classification tasks) effective information mostly, we introduce an Effective Information Estimation Framework (EIEF) based on three key principles: the task-centered approach, leveraging 1D-CNNs' test metrics to gauge effective information proportion, and feedback. We address a theoretical foundation by integrating these principles into mathematical derivations to propose the mathematical model of EIEF. In experiments, we established a paradigm pool of 66 denoising paradigms, with EIEF successfully identifying the optimal paradigms (on two datasets) for restoring effective information. Utilizing the processed dataset, we trained a 3D-CNN for automatic schizophrenia diagnosis, achieving outstanding test accuracies of 99.94 % on dataset 1 and 98.02 % on dataset 2 in subject-dependent evaluations, and accuracies of 89.85 % on dataset 1 and 98.02 % on dataset 2 in subject-independent evaluations. Additionally, we extracted 38 features from each channel of both processed and raw datasets, revealing that 20.86 % (dataset 1) of feature distribution differences between the patients and the healthy exhibited significant changes after implementing the optimal paradigm. We enhance model performance and extract more reliable electrobiological markers. These findings have promising implications for advancing the field of the clinical diagnosis and pathological analysis of Schizophrenia. [ABSTRACT FROM AUTHOR]

Background and Objective: Gastritis represents one of the most prevalent gastrointestinal diseases and has a multifactorial etiology, many forms of manifestation, and various symptoms. Diagnosis of gastritis is made based on clinical, endoscopic, and histological criteria, and although it is a thorough process, many cases are misdiagnosed or overlooked. This systematic review aims to provide an extensive overview of current artificial intelligence (AI) applications in gastritis diagnosis and evaluate the precision of these systems. This evaluation could highlight the role of AI as a helpful and useful tool in facilitating timely and accurate diagnoses, which in turn could improve patient outcomes. Methods: We have conducted an extensive and comprehensive literature search of PubMed, Scopus, and Web of Science, including studies published until July 2024. Results: Despite variations in study design, participant numbers and characteristics, and outcome measures, our observations suggest that implementing an AI automatic diagnostic tool into clinical practice is currently feasible, with the current systems achieving high levels of accuracy, sensitivity, and specificity. Our findings indicate that AI outperformed human experts in most studies, with multiple studies exhibiting an accuracy of over 90% for AI compared to human experts. These results highlight the significant potential of AI to enhance diagnostic accuracy and efficiency in gastroenterology. Conclusions: AI-based technologies can now automatically diagnose using images provided by gastroscopy, digital pathology, and radiology imaging. Deep learning models exhibited high levels of accuracy, sensitivity, and specificity while assessing the diagnosis, staging, and risk of neoplasia for different types of gastritis, results that are superior to those of human experts in most studies. [ABSTRACT FROM AUTHOR]

Clinical lesions progress continuously but previous grading strategies are not fine-grained enough to model the continuously changing features of lesions. For lack of temporal sequential medical data to provide lesion progression information, we propose to use the severity ranking of disease lesions as spatial ranking label to represent temporal progression. Absolute ranking labels and relative ranking labels are calculated from severity ranking of datasets. A two-branch framework with spatial-temporal feature encoder is designed which using ranking labels to exploit the ranking relation between query and reference images. Furthermore, ranking loss is designed to enforce that sample features should be distributed in the feature space based on ranking scores. Our model achieves five-grade accuracy of 0.9204 on myopic maculopathy dataset. Compared with discrete grading, great improvement for automatic diagnosis is achieved. Experiments on B-mode fatty liver ultrasound dataset and glaucoma dataset also show generality of our algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Ingenius, Revista Ciencia y Tecnología is the property of Universidad Politecnica Salesiana and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The quick spread of coronavirus disease (COVID-19) has resulted in a global pandemic and more than fifteen million confirmed cases. To battle this spread, clinical imaging techniques, for example, computed tomography (CT), can be utilized for diagnosis. Automatic identification software tools are essential for helping to screen COVID-19 using CT images. However, there are few datasets available, making it difficult to train deep learning (DL) networks. To address this issue, a generative adversarial network (GAN) is proposed in this work to generate more CT images. The Whale Optimization Algorithm (WOA) is used to optimize the hyperparameters of GAN's generator. The proposed method is tested and validated with different classification and meta-heuristics algorithms using the SARS-CoV-2 CT-Scan dataset, consisting of COVID-19 and non-COVID-19 images. The performance metrics of the proposed optimized model, including accuracy (99.22%), sensitivity (99.78%), specificity (97.78%), F1-score (98.79%), positive predictive value (97.82%), and negative predictive value (99.77%), as well as its confusion matrix and receiver operating characteristic (ROC) curves, indicate that it performs better than state-of-the-art methods. This proposed model will help in the automatic screening of COVID-19 patients and decrease the burden on medicinal services frameworks. [ABSTRACT FROM AUTHOR]

Electroencephalogram is a low-cost, non-invasive, and high-entropy signal and thus has huge potential for clinical diagnosis of neurological diseases and brain–computer interface applications. Schizophrenia is one of the most severe diseases that show behavioral manifestations that are easily uncovered by specialists. In this context, the electroencephalogram analysis becomes more important for the automatic diagnosis of schizophrenia disease in the clinical process. In this study, a deep learning architecture, namely ResNet, aims to classify schizophrenia is proposed. The proposed system transforms wavelet sub-bands of the electroencephalogram into two-dimensional image space, which is considered the main unique contribution of the study. Thus, the disease indicators and features included in images could be figured out. Moreover, a discussion on the class activation maps was made to give a wide perspective on the features related to the disease. The proposed system was implemented on a large-scale electroencephalogram database containing records from unhealthy and healthy patients in various phases. The ResNet was implemented in three modes to give a thorough perspective in terms of the metrics of the diagnosis accuracy. The proposed system achieves 92.94% diagnosis accuracy rate, and the result shows that the proposed transformation-based solution is owing to the features related to schizophrenia disease. [ABSTRACT FROM AUTHOR]

Automated diagnosis, as a temporary medical supplement, has gained significant attention in research in recent years. Existing methods employ sequence generation approaches to inquire about symptoms and diagnose diseases. However, these methods ignore the fact that: 1) doctors utilize their past experience and similar cases to aid in diagnosis in real-world scenarios; 2) doctors inquire about key symptoms that serve as vital diagnostic evidence within limited conversations. To address these issues, we propose an end-to-end model KDPoG. Firstly, in addition to use the symptom and attribute embedding, we propose patient-oriented graph enhanced representation learning, which is built by a patient-oriented graph and learned with heterogeneous graph convolution networks. Furthermore, based on the encoder built with gated attention units, we propose knowledge-guided attention mechanism learning, which incorporates conditional probabilities of co-occurrence between symptom pairs. Finally, we utilize two linear layers as the classification module to achieve symptom probing and disease diagnosis. We conduct extensive experiments on four public datasets, which demonstrate that our proposed model outperforms the state-of-the-art methods. We achieve an average absolute improvement of over 2% in disease diagnosis accuracy. Particularly, on the Muzhi-10 dataset, we observe an absolute improvement of over 14.7% in symptom recall rate.

Retinal tears (RTs) are usually detected by B-scan ultrasound images, particularly for individuals with complex eye conditions. However, traditional manual techniques for reading ultrasound images have the potential to overlook or inaccurately diagnose conditions. Thus, the development of rapid and accurate approaches for the diagnosis of an RT is highly important and urgent. The present study introduces a novel hybrid deep-learning model called DCT-Net to enable the automatic and precise diagnosis of RTs. The implemented model utilizes a vision transformer as the backbone and feature extractor. Additionally, in order to accommodate the edge characteristics of the lesion areas, a novel module called the residual deformable convolution has been incorporated. Furthermore, normalization is employed to mitigate the issue of overfitting and, a Softmax layer has been included to achieve the final classification following the acquisition of the global and local representations. The study was conducted by using both our proprietary dataset and a publicly available dataset. In addition, interpretability of the trained model was assessed by generating attention maps using the attention rollout approach. On the private dataset, the model demonstrated a high level of performance, with an accuracy of 97.78%, precision of 97.34%, recall rate of 97.13%, and an F1 score of 0.9682. On the other hand, the model developed by using the public funds image dataset demonstrated an accuracy of 83.82%, a sensitivity of 82.69% and a specificity of 82.40%. The findings, therefore present a novel framework for the diagnosis of RTs that is characterized by a high degree of efficiency, accuracy and interpretability. Accordingly, the technology exhibits considerable promise and has the potential to serve as a reliable tool for ophthalmologists.

Radiologists confront formidable challenges when confronted with the intricate task of classifying brain tumors through the analysis of MRI images. Our forthcoming manuscript introduces an innovative and highly effective methodology that capitalizes on the capabilities of Least Squares Support Vector Machines (LS-SVM) in tandem with the rich insights drawn from Multi-Scale Morphological Texture Features (MMTF) extracted from T1-weighted MR images. Our methodology underwent meticulous evaluation on a substantial dataset encompassing 139 cases, consisting of 119 cases of aberrant tumors and 20 cases of normal brain images. The outcomes we achieved are nothing short of extraordinary. Our LS-SVM-based approach vastly outperforms competing classifiers, demonstrating its dominance with an exceptional accuracy rate of 98.97%. This represents a substantial 3.97% improvement over alternative methods, accompanied by a notable 2.48% enhancement in Sensitivity and a substantial 10% increase in Specificity. These results conclusively surpass the performance of traditional classifiers such as Support Vector Machines (SVM), Radial Basis Function (RBF), and Artificial Neural Networks (ANN) in terms of classification accuracy. The outstanding performance of our model in the realm of brain tumor diagnosis signifies a substantial leap forward in the field, holding the promise of delivering more precise and dependable tools for radiologists and healthcare professionals in their pivotal role of identifying and classifying brain tumors using MRI imaging techniques. [ABSTRACT FROM AUTHOR]

In the directions of modern medicine, a new area of processing and analysis of visual data is actively developing - a radio municipality - a computer technology that allows you to deeply analyze medical images, such as computed tomography (CT), magnetic resonance imaging (MRI), chest radiography (CXR), electrocardiography and electrocardiography. This approach allows us to extract quantitative texture signs from signals and distinguish informative features to describe the heart's pathology, providing a personified approach to diagnosis and treatment. Cardiovascular diseases (SVD) are one of the main causes of death in the world, and early detection is crucial for timely intervention and improvement of results. This experiment aims to increase the accuracy of deep learning algorithms to determine cardiovascular diseases. To achieve the goal, the methods of deep learning were considered used to analyze cardiograms. To solve the tasks set in the work, 50 patients were used who are classified by three indicators, 13 anomalous, 24 nonbeat, and 1 healthy parameter, which is taken from the MIT-BIH Arrhythmia database. [ABSTRACT FROM AUTHOR]

Background: Oral Squamous Cell Carcinoma (OSCC) is one of the most severe cancers in the world, and its early detection is crucial for saving patients. There is an inevitable necessity to develop the automatic noninvasive OSCC diagnosis approach to identify the malignant tissues on Optical Coherence Tomography (OCT) images. Methods: This study presents a novel Multi‐Level Deep Residual Learning (MDRL) network to identify malignant and benign(normal) tissues from OCT images and trains the network in 460 OCT images captured from 37 patients. The diagnostic performances are compared with different methods in the image‐level and the resected patch‐level. Results: The MDRL system achieves the excellent diagnostic performance, with 91.2% sensitivity, 83.6% specificity, 87.5% accuracy, 85.3% PPV, and 90.2% NPV in image‐level, with 0.92 AUC value. Besides, it also implements 100% sensitivity, 86.7% specificity, 93.1% accuracy, 87.5% PPV, and 100% NPV in the resected patch‐level. Conclusion: The developed deep learning system expresses superior performance in noninvasive oral squamous cell carcinoma diagnosis, compared with traditional CNNs and a specialist. [ABSTRACT FROM AUTHOR]

Abstract Introduction Estimation of brain amyloid accumulation is valuable for evaluation of patients with cognitive impairment in both research and clinical routine. The development of high throughput and accurate strategies for the determination of amyloid status could be an important tool in patient selection for clinical trials and amyloid directed treatment. Here, we propose the use of deep learning to quantify amyloid accumulation using standardized uptake value ratio (SUVR) and classify amyloid status based on their PET images. Methods A total of 1309 patients with cognitive impairment scanned with [11C]PIB PET/CT or PET/MRI were included. Two convolutional neural networks (CNNs) for reading-based amyloid status and SUVR prediction were trained using 75% of the PET/CT data. The remaining PET/CT (n = 300) and all PET/MRI (n = 100) data was used for evaluation. Results The prevalence of amyloid positive patients was 61%. The amyloid status classification model reproduced the expert reader’s classification with 99% accuracy. There was a high correlation between reference and predicted SUVR (R 2 = 0.96). Both reference and predicted SUVR had an accuracy of 97% compared to expert classification when applying a predetermined SUVR threshold of 1.35 for binary classification of amyloid status. Conclusion The proposed CNN models reproduced both the expert classification and quantitative measure of amyloid accumulation in a large local dataset. This method has the potential to replace or simplify existing clinical routines and can facilitate fast and accurate classification well-suited for a high throughput pipeline.

The use of information technology in the teaching of English majors in colleges and universities enriches the teaching means, especially the data mining technology that optimizes the digital teaching method. In this paper, starting from English writing, based on the functional requirements of writing training, we constructed a writing training process and utilized the NMF method to mine and decompose the English news text topics. In conjunction with the writing training, the data mining technology centered on the Rete algorithm was used to carry out automatic diagnosis of English composition on the basis of natural language processing. On the basis of mining and analyzing the English news text, the effect of English writing scoring was compared, and its enhancement effect on English composition was verified through controlled tests. The average writing score of the experimental group was 19.62, of which the full score was 25. The mean writing score of the control group is 16.38, which is 3.24 points lower than that of the experimental group. Significance Sig.=0.0004

Radiologists confront formidable challenges when confronted with the intricate task of classifying brain tumors through the analysis of MRI images. Our forthcoming manuscript introduces an innovative and highly effective methodology that capitalizes on the capabilities of Least Squares Support Vector Machines (LS-SVM) in tandem with the rich insights drawn from Multi-Scale Morphological Texture Features (MMTF) extracted from T1-weighted MR images. Our methodology underwent meticulous evaluation on a substantial dataset encompassing 139 cases, consisting of 119 cases of aberrant tumors and 20 cases of normal brain images. The outcomes we achieved are nothing short of extraordinary. Our LS-SVM-based approach vastly outperforms competing classifiers, demonstrating its dominance with an exceptional accuracy rate of 98.97%. This represents a substantial 3.97% improvement over alternative methods, accompanied by a notable 2.48% enhancement in Sensitivity and a substantial 10% increase in Specificity. These results conclusively surpass the performance of traditional classifiers such as Support Vector Machines (SVM), Radial Basis Function (RBF), and Artificial Neural Networks (ANN) in terms of classification accuracy. The outstanding performance of our model in the realm of brain tumor diagnosis signifies a substantial leap forward in the field, holding the promise of delivering more precise and dependable tools for radiologists and healthcare professionals in their pivotal role of identifying and classifying brain tumors using MRI imaging techniques.

Induction machines (IMs) play a critical role in various industrial processes but are susceptible to degenerative failures, such as broken rotor bars. Effective diagnostic techniques are essential in addressing these issues. In this study, we propose the utilization of convolutional neural networks (CNNs) for detection of broken rotor bars. To accomplish this, we generated a dataset comprising current samples versus angular position using finite element method magnetics (FEMM) software for a squirrel-cage rotor with 28 bars, including scenarios with 0 to 6 broken bars at every possible relative position. The dataset consists of a total of 16,050 samples per motor. We evaluated the performance of six different CNN architectures, namely Inception V4, NasNETMobile, ResNET152, SeNET154, VGG16, and VGG19. Our automatic classification system demonstrated an impressive 99% accuracy in detecting broken rotor bars, with VGG19 performing exceptionally well. Specifically, VGG19 exhibited high accuracy, precision, recall, and F1-Score, with values approaching 0.994 and 0.998. Notably, VGG19 exhibited crucial activations in its feature maps, particularly after domain-specific training, highlighting its effectiveness in fault detection. Comparing CNN architectures assists in selecting the most suitable one for this application based on processing time, effectiveness, and training losses. This research suggests that deep learning can detect broken bars in induction machines with accuracy comparable to that of traditional methods by analyzing current signals using CNNs. [ABSTRACT FROM AUTHOR]

Velopharyngeal insufficiency (VPI) is a type of pharyngeal function dysfunction that causes speech impairment and swallowing disorder. Speech therapists play a key role on the diagnosis and treatment of speech disorders. However, there is a worldwide shortage of experienced speech therapists. Artificial intelligence-based computer-aided diagnosing technology could be a solution for this. This paper proposes an automatic system for VPI detection at the subject level. It is a non-invasive and convenient approach for VPI diagnosis. Based on the principle of impaired articulation of VPI patients, nasal- and oral-channel acoustic signals are collected as raw data. The system integrates the symptom discriminant results at the phoneme level. For consonants, relative prominent frequency description and relative frequency distribution features are proposed to discriminate nasal air emission caused by VPI. For hypernasality-sensitive vowels, a cross-attention residual Siamese network (CARS-Net) is proposed to perform automatic VPI/non-VPI classification at the phoneme level. CARS-Net embeds a cross-attention module between the two branches to improve the VPI/non-VPI classification model for vowels. We validate the proposed system on a self-built dataset, and the accuracy reaches 98.52%. This provides possibilities for implementing automatic VPI diagnosis. [ABSTRACT FROM AUTHOR]

Fungal keratitis (FK) is a common and severe corneal disease, which is widely spread in tropical and subtropical areas. Early diagnosis and treatment are vital for patients, with confocal microscopy cornea imaging being one of the most effective methods for the diagnosis of FK. However, most cases are currently diagnosed by the subjective judgment of ophthalmologists, which is time-consuming and heavily depends on the experience of the ophthalmologists. In this paper, we introduce a novel structure-aware automatic diagnosis algorithm based on deep convolutional neural networks for the accurate diagnosis of FK. Specifically, a two-stream convolutional network is deployed, combining GoogLeNet and VGGNet, which are two commonly used networks in computer vision architectures. The main stream is used for feature extraction of the input image, while the auxiliary stream is used for feature discrimination and enhancement of the hyphae structure. Then, the features are combined by concatenating the channel dimension to obtain the final output, i.e., normal or abnormal. The results showed that the proposed method achieved accuracy, sensitivity, and specificity of 97.73%, 97.02%, and 98.54%, respectively. These results suggest that the proposed neural network could be a promising computer-aided FK diagnosis solution. [ABSTRACT FROM AUTHOR]

ObjectivesGliomas and brain metastases (Mets) are the most common brain malignancies. The treatment strategy and clinical prognosis of patients are different, requiring accurate diagnosis of tumor types. However, the traditional radiomics diagnostic pipeline requires manual annotation and lacks integrated methods for segmentation and classification. To improve the diagnosis process, a gliomas and Mets computer-aided diagnosis method with automatic lesion segmentation and ensemble decision strategy on multi-center datasets was proposed.MethodsOverall, 1,022 high-grade gliomas and 775 Mets patients’ preoperative MR images were adopted in the study, including contrast-enhanced T1-weighted (T1-CE) and T2-fluid attenuated inversion recovery (T2-flair) sequences from three hospitals. Two segmentation models trained on the gliomas and Mets datasets, respectively, were used to automatically segment tumors. Multiple radiomics features were extracted after automatic segmentation. Several machine learning classifiers were used to measure the impact of feature selection methods. A weight soft voting (RSV) model and ensemble decision strategy based on prior knowledge (EDPK) were introduced in the radiomics pipeline. Accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) were used to evaluate the classification performance.ResultsThe proposed pipeline improved the diagnosis of gliomas and Mets with ACC reaching 0.8950 and AUC reaching 0.9585 after automatic lesion segmentation, which was higher than those of the traditional radiomics pipeline (ACC:0.8850, AUC:0.9450).ConclusionThe proposed model accurately classified gliomas and Mets patients using MRI radiomics. The novel pipeline showed great potential in diagnosing gliomas and Mets with high generalizability and interpretability.

Introduction: Estimation of brain amyloid accumulation is valuable for evaluation of patients with cognitive impairment in both research and clinical routine. The development of high throughput and accurate strategies for the determination of amyloid status could be an important tool in patient selection for clinical trials and amyloid directed treatment. Here, we propose the use of deep learning to quantify amyloid accumulation using standardized uptake value ratio (SUVR) and classify amyloid status based on their PET images. Methods: A total of 1309 patients with cognitive impairment scanned with [11C]PIB PET/CT or PET/MRI were included. Two convolutional neural networks (CNNs) for reading-based amyloid status and SUVR prediction were trained using 75% of the PET/CT data. The remaining PET/CT (n = 300) and all PET/MRI (n = 100) data was used for evaluation. Results: The prevalence of amyloid positive patients was 61%. The amyloid status classification model reproduced the expert reader's classification with 99% accuracy. There was a high correlation between reference and predicted SUVR (R2 = 0.96). Both reference and predicted SUVR had an accuracy of 97% compared to expert classification when applying a predetermined SUVR threshold of 1.35 for binary classification of amyloid status. Conclusion: The proposed CNN models reproduced both the expert classification and quantitative measure of amyloid accumulation in a large local dataset. This method has the potential to replace or simplify existing clinical routines and can facilitate fast and accurate classification well-suited for a high throughput pipeline. [ABSTRACT FROM AUTHOR]

Advances in the field of image classification using convolutional neural networks (CNNs) have greatly improved the accuracy of medical image diagnosis by radiologists. Numerous research groups have applied CNN methods to diagnose respiratory illnesses from chest X-rays and have extended this work to prove the feasibility of rapidly diagnosing COVID-19 with high degrees of accuracy. One issue in previous research has been the use of datasets containing only a few hundred images of chest X-rays containing COVID-19, causing CNNs to overfit the image data. This leads to lower accuracy when the model attempts to classify new images, as would be clinically expected. In this work, we present a model trained on the COVID-QU-Ex dataset containing 33,920 chest X-ray images, with an equal share of COVID-19, Non-COVID pneumonia, and Normal images. The model is an ensemble of pre-trained CNNs (ResNet50, VGG19, and VGG16) and GLCM textural features. The model achieved a 98.34% binary classification accuracy (COVID-19/no COVID-19) on a test dataset of 6581 chest X-rays and 94.68% for distinguishing between COVID-19, Non-COVID pneumonia, and normal chest X-rays. The results also demonstrate that a higher 98.82% three-class test accuracy can be achieved using the model if the training dataset only contains a few thousand images. However, the generalizability of the model suffers due to the smaller dataset size. This study highlights the benefits of both ensemble CNN techniques and larger dataset sizes for medical image classification performance. [ABSTRACT FROM AUTHOR]

The accuracy of short-circuit fault diagnosis methods for power measuring instruments is still low, which can directly lead to abnormal power data statistics. To address this issue, a convolutional neural network is used to construct an automatic diagnosis model for short circuit faults in power measuring instruments. The model utilizes wavelet packet energy spectrum to extract crucial features from the signal. The model identifies and determines the fault type based on the obtained operation characteristic data and the set short-circuit fault diagnosis criteria. The Sparrow optimization algorithm is used to optimize the model's parameters and enhance its performance. Experimental analysis revealed that after the signal features were extracted by using the wavelet energy spectrum distribution, the error value fluctuated in the range of 0.00 ~ 0.04 with regard to the measured value and was mainly around 0.02. The extracted features achieved high accuracy levels. The designed model exhibited an average diagnostic accuracy of 97.03%, surpassing the other three models by 9.24%, 7.10%, and 4.25%. The presented model can improve the precision and productivity of fault detection, support the safety and reliability of power system operations, and facilitate the collection and analysis of power usage data. [ABSTRACT FROM AUTHOR]

Background. Early diagnosis and monitoring the evolution of the patients is required to be able to have effective preventive attitudes. An easy and cost-effective way of diagnosis is needed for this purpose. The aim of the study was to evaluate the AI level of use in dentistry diagnosis and the fields of its applicability especially for early diagnosis purposes. A secondary objective was to point out the measured performances for automated AI diagnosis by comparison with standard diagnosis procedures. Material and methods. A comprehensive electronic search was performed in November 2022 through PubMed, Scopus, and Web of Science databases. The following keywords were used to search the databases: (”Artificial Intelligence” OR ”neural network” OR ”Deep learning” OR “Machine learning”) AND (”Dentistry” OR “Dental medicine”) AND (” periodontal disease” OR ”periodontics” OR ”Carious lesions” OR ”oral cancer” OR ”restorative” or “early diagnosis”). The risk of bias (RoB) of the included studies was assessed using PROBAST tool. Results. A total of 334 publications were collected after searching the databases. For 218 remaining publications the title and the abstract were assessed. The reviewers agreed to continue with 69 studies for full text assessment. Because 49 studies had not completely fulfilled the inclusion criteria only 20 publications were included in the final analysis. AI automatic data processing for diagnostic purposes was implemented in the field of dental radiology, oral pathology, restorative dentistry, pedodontics, oncology, endodontics, and periodontics. Conclusion. AI based automatic diagnostic is a powerful and reliable tool that has a great future potential for different fields of dental medicine like periodontal disease, oral cancer, and carious lesions.

Damage detection or structural condition assessment is an important objective of structural health monitoring (SHM). The damages or adverse changes in structural conditions can usually be manifested as pattern changes in damage-sensitive features (DSFs) extracted from SHM data; this enables us to shift damage detection to DSF change detection. Online monitoring can accumulate huge amounts of data, finding the changes from the massive DSF data through manual inspection is impractical; thus, automatic detection tools are required. If possible, relevant significance test is also desired to make a rational judgment on the existence of a change. In this sense, the change-point detection technique is an attractive choice, which is increasingly proved to be a powerful change detection tool in various SHM applications. However, existing change-point detection methods in SHM are mainly used for scalar or vector data, thus incapable of detecting changes in features represented by complex data, for example, the probability density functions (PDFs). Detecting abrupt changes in the distributions (represented by PDFs) of the DSF data is of crucial concern in structural condition assessment. However, relevant automatic diagnostic tools have not been well developed in the SHM community. To this end, a novel change-point detection method is developed in the functional data analytic framework for this task. The proposed approach has advantages in detecting changes for massive data and directly handling general PDFs. Considering that the major challenge in PDF-valued data analysis comes from the nonlinear constraints of PDFs, the PDFs are embedded into the Bayes space to develop the detection methodology by using the linear structure of the Bayes space. Comprehensive simulation studies are conducted to validate the effectiveness of the proposed method as well as demonstrate its superiority over the competing method. Finally, a case study involving cable condition assessment of a long-span bridge demonstrates its practical utility in SHM. [ABSTRACT FROM AUTHOR]

Tear meniscus height (TMH) is an important reference parameter in the diagnosis of dry eye disease. However, most traditional methods of measuring TMH are manual or semi-automatic, which causes the measurement of TMH to be prone to the influence of subjective factors, time consuming, and laborious. To solve these problems, a segmentation algorithm based on deep learning and image processing was proposed to realize the automatic measurement of TMH. To accurately segment the tear meniscus region, the segmentation algorithm designed in this study is based on the DeepLabv3 architecture and combines the partial structure of the ResNet50, GoogleNet, and FCN networks for further improvements. A total of 305 ocular surface images were used in this study, which were divided into training and testing sets. The training set was used to train the network model, and the testing set was used to evaluate the model performance. In the experiment, for tear meniscus segmentation, the average intersection over union was 0.896, the dice coefficient was 0.884, and the sensitivity was 0.877. For the central ring of corneal projection ring segmentation, the average intersection over union was 0.932, the dice coefficient was 0.926, and the sensitivity was 0.947. According to the evaluation index comparison, the segmentation model used in this study was superior to the existing model. Finally, the measurement outcome of TMH of the testing set using the proposed method was compared with manual measurement results. All measurement results were directly compared via linear regression; the regression line was y0.98x−0.02, and the overall correlation coefficient was r20.94. Thus, the proposed method for measuring TMH in this paper is highly consistent with manual measurement and can realize the automatic measurement of TMH and assist clinicians in the diagnosis of dry eye disease.

Diabetic retinopathy (DR) is an ocular manifestation of diabetes and the leading cause of visual impairment and blindness across the globe. Early detection and treatment of DR can salvage from visual impairment. The manual screening of DR is a very laborious and time-intensive effort and heavily dependent on professional ophthalmologists. In addition, the subtle distinction among various retinal biomarkers and different grades of DR makes this recognition very challenging. To address the aforementioned problem, deep neural networks have brought many revolutions in the last few years. In this study, we proposed a novel two-stage framework for automatic DR classification. In the first stage, we employed two distinct U-Net models for optic disc (OD) and blood vessel (BV) segmentation during the preprocessing. In the second stage, the enhanced retinal images after OD and BV extraction are used as an input of transfer learning-based model VGGNet, which performs DR detection by identifying retinal biomarkers such as microaneurysms (MA), haemorrhages (HM), and exudates (EX). The proposed model achieved state-of-the-art performance with an average accuracy of 96.60%, 93.95%, 92.25% evaluated on EyePACS-1, Messidor-2, and DIARETDB0, respectively. Extensive experiments and comparison with baseline methods demonstrate that the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Essential tremor (ET) is one of the most common movement disorders in adults, and its early assessment and diagnosis are crucial for disease management in movement disorders. Nowadays, the severity of tremors can only be diagnosed and evaluated by laboratory tests. However, there are certain subjective factors in traditional assessment methods by the naked eye of a neurologist, which often leads to some biases. This study proposes a novel multi-modal signals-based automated quantitative assessment system for tremor severity. Specifically, we develop a two-stage framework that performs posture pattern recognition on the raw data, then extracts kinematic parameters to build an individualized model for each task. Besides, we established a strict clinical paradigm, including 121 ET patients, finely evaluated by a committee of neurologists to build a high-quality database. The models' performances showed that most of the kinematic parameters designed in this study could effectively map the severity of the tremor. The F1 score for classification of the posture task based on deep learning networks was 99.02%, and the quantification of symptom scores based on machine learning models ranged from 94.77 to 99.00%. These results demonstrate the effectiveness of the proposed framework can automatically provide objective and accurate scores for ET symptom assessment. [ABSTRACT FROM AUTHOR]

Automatic diagnosis, as an important research direction in artificial intelligence engineering, has advanced significantly in recent years. In real diagnostic scenarios, after the patient informs the doctor about their most obvious symptoms, the doctor is often required to guide the patient to uncover potential symptom information. The doctor then makes the final diagnosis after obtaining sufficient evidence. Previous work has modeled this as a sequential decision-making process and trained an optimal policy using RL-based methods, achieving a high diagnosis correctness rate. However, the RL-based method only finds symptom sequences that improve reward through random trials, failing to directly capture the inter-relationships between symptom sequences in the inquiry process. Also, the doctors' diagnostic experience, especially symptoms that often co-occur and are located in close proximity to each other in the doctors' inquiry symptom sequence, has not been well explored in previous implementations. To address this, we propose a model that further enhances the learning of doctors' diagnostic experience based on a two-part transformer model that completes symptom inquiry and disease diagnosis separately. We introduce a Doctor Diagnosis Experience Reinforcement Module (DDEM) to the symptom sequence inquiry part, reducing the model's sensitivity to the order of symptom sequences within the same symptom cluster. Then, we further enhance the learning of this symptom distribution by corresponding reinforcement learning reward rules. Also, we propose three new transition rules when transitioning the symptom inquiry model to the disease diagnosis model to enable the symptom inquiry model and the disease diagnosis model to collaborate in a manner that closely aligns with the diagnostic logic used by doctors. Experiments on three public real-world medical dialogue datasets demonstrate that the proposed model improves diagnostic accuracy by 2%, 1.4%, and 0.7% and shows a clear advantage in symptom recall rate, highlighting its effectiveness. [ABSTRACT FROM AUTHOR]

Induction machines (IMs) play a critical role in various industrial processes but are susceptible to degenerative failures, such as broken rotor bars. Effective diagnostic techniques are essential in addressing these issues. In this study, we propose the utilization of convolutional neural networks (CNNs) for detection of broken rotor bars. To accomplish this, we generated a dataset comprising current samples versus angular position using finite element method magnetics (FEMM) software for a squirrel-cage rotor with 28 bars, including scenarios with 0 to 6 broken bars at every possible relative position. The dataset consists of a total of 16,050 samples per motor. We evaluated the performance of six different CNN architectures, namely Inception V4, NasNETMobile, ResNET152, SeNET154, VGG16, and VGG19. Our automatic classification system demonstrated an impressive 99% accuracy in detecting broken rotor bars, with VGG19 performing exceptionally well. Specifically, VGG19 exhibited high accuracy, precision, recall, and F1-Score, with values approaching 0.994 and 0.998. Notably, VGG19 exhibited crucial activations in its feature maps, particularly after domain-specific training, highlighting its effectiveness in fault detection. Comparing CNN architectures assists in selecting the most suitable one for this application based on processing time, effectiveness, and training losses. This research suggests that deep learning can detect broken bars in induction machines with accuracy comparable to that of traditional methods by analyzing current signals using CNNs.

Velopharyngeal insufficiency (VPI) is a type of pharyngeal function dysfunction that causes speech impairment and swallowing disorder. Speech therapists play a key role on the diagnosis and treatment of speech disorders. However, there is a worldwide shortage of experienced speech therapists. Artificial intelligence-based computer-aided diagnosing technology could be a solution for this. This paper proposes an automatic system for VPI detection at the subject level. It is a non-invasive and convenient approach for VPI diagnosis. Based on the principle of impaired articulation of VPI patients, nasal- and oral-channel acoustic signals are collected as raw data. The system integrates the symptom discriminant results at the phoneme level. For consonants, relative prominent frequency description and relative frequency distribution features are proposed to discriminate nasal air emission caused by VPI. For hypernasality-sensitive vowels, a cross-attention residual Siamese network (CARS-Net) is proposed to perform automatic VPI/non-VPI classification at the phoneme level. CARS-Net embeds a cross-attention module between the two branches to improve the VPI/non-VPI classification model for vowels. We validate the proposed system on a self-built dataset, and the accuracy reaches 98.52%. This provides possibilities for implementing automatic VPI diagnosis.

Abstract Background Clinical notes are documents that contain detailed information about the health status of patients. Medical codes generally accompany them. However, the manual diagnosis is costly and error-prone. Moreover, large datasets in clinical diagnosis are susceptible to noise labels because of erroneous manual annotation. Therefore, machine learning has been utilized to perform automatic diagnoses. Previous state-of-the-art (SOTA) models used convolutional neural networks to build document representations for predicting medical codes. However, the clinical notes are usually long-tailed. Moreover, most models fail to deal with the noise during code allocation. Therefore, denoising mechanism and long-tailed classification are the keys to automated coding at scale. Results In this paper, a new joint learning model is proposed to extend our attention model for predicting medical codes from clinical notes. On the MIMIC-III-50 dataset, our model outperforms all the baselines and SOTA models in all quantitative metrics. On the MIMIC-III-full dataset, our model outperforms in the macro-F1, micro-F1, macro-AUC, and precision at eight compared to the most advanced models. In addition, after introducing the denoising mechanism, the convergence speed of the model becomes faster, and the loss of the model is reduced overall. Conclusions The innovations of our model are threefold: firstly, the code-specific representation can be identified by adopted the self-attention mechanism and the label attention mechanism. Secondly, the performance of the long-tailed distributions can be boosted by introducing the joint learning mechanism. Thirdly, the denoising mechanism is suitable for reducing the noise effects in medical code prediction. Finally, we evaluate the effectiveness of our model on the widely-used MIMIC-III datasets and achieve new SOTA results.

Alzheimer's disease is an irreversible neurological disease, therefore prompt diagnosis during its early stage, i.e., early mild cognitive impairment (MCI), is crucial for effective treatment. In this paper, we propose an automatic diagnosis method, a few-shot learning-based pairwise functional connectivity (FC) similarity measure method, to detect early MCI. We first employ a sliding window strategy to generate a dynamic functional connectivity network (FCN) using each subject's rs-fMRI data. Then, normal controls (NCs) and early MCI patients are distinguished by measuring the similarity between the dynamic FC series of corresponding brain regions of interest (ROIs) pairs in different subjects. However, previous studies have shown that FC patterns in different ROI-pairs contribute differently to disease classification. To enable the FCs of different ROI-pairs to make corresponding contributions to disease classification, we adopt a self-attention mechanism to weight the FC features. We evaluated the suggested strategy using rs-fMRI data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and the results point to the viability of our approach for detecting MCI at an early stage.

Artificial intelligence (AI) based on the perspective of data elements is widely used in the healthcare informatics domain. Large amounts of clinical data from electronic medical records (EMRs), electronic health records (EHRs), and electroencephalography records (EEGs) have been generated and collected at an unprecedented speed and scale. For instance, the new generation of wearable technologies enables easy-collecting peoples’ daily health data such as blood pressure, blood glucose, and physiological data, as well as the application of EHRs documenting large amounts of patient data. The cost of acquiring and processing health big data is expected to reduce dramatically with the help of AI technologies and open-source big data platforms such as Hadoop and Spark. The application of AI technologies in health big data presents new opportunities to discover the relationship among living habits, sports, inheritances, diseases, symptoms, and drugs. Meanwhile, with the development of fast-growing AI technologies, many promising methodologies are proposed in the healthcare field recently. In this paper, we review and discuss the application of machine learning (ML) methods in health big data in two major aspects: (1) Special features of health big data including multimodal, incompletion, time validation, redundancy, and privacy. (2) ML methodologies in the healthcare field including classification, regression, clustering, and association. Furthermore, we review the recent progress and breakthroughs of automatic diagnosis in health big data and summarize the challenges, gaps, and opportunities to improve and advance automatic diagnosis in the health big data field. [ABSTRACT FROM AUTHOR]

The paper presents a comparison of automatic skin cancer diagnosis algorithms based on analyses of skin lesions photos. Two approaches are presented: the first one is based on the extraction of features from images using simple feature descriptors, and then the use of selected machine learning algorithms for the purpose of classification, and the second approach uses selected algorithms belonging to the subgroup of machine learning—deep learning, i.e., convolutional neural networks (CNN), which perform both the feature extraction and classification in one algorithm. The following algorithms were analyzed and compared: Logistic Regression, k-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, and Support Vector Machine, and four CNN–VGG-16, ResNet60, InceptionV3, and Inception-ResNetV2 In the first variant, before the classification process, the image features were extracted using 4 different feature descriptors and combined in various combinations in order to obtain the most accurate image features vector, and thus the highest classification accuracy. The presented approaches have been validated using the image dataset from the ISIC database, which includes data from two categories—benign and malignant skin lesions. Common machine learning metrics and saved values of training time were used to evaluate the effectiveness and the performance (computational complexity) of the algorithms. [ABSTRACT FROM AUTHOR]

Simple Summary: To enhance the automatic diagnosis of the prostate cancer using machine learning algorithm, we modify the design of convolutional neural network to support multi-scale denoising of cancer images. Transfer learning is employed to leverage the detection accuracy of the prostate cancer detection model by taking advantages from more unseen data from a source dataset. Compared to existing methodologies, our work improves the accuracy by more than 10%. Ablation studies have conducted to evaluate the contributions of the components of the proposed algorithm, with 2.80%, 3.30%, and 3.13% for image denoising, multi-scale scheme, and transfer learning, respectively. The results reveal the effectiveness of the algorithm and provide insights for five future research directions. Background: Prostate cancer is the 4th most common type of cancer. To reduce the workload of medical personnel in the medical diagnosis of prostate cancer and increase the diagnostic accuracy in noisy images, a deep learning model is desired for prostate cancer detection. Methods: A multi-scale denoising convolutional neural network (MSDCNN) model was designed for prostate cancer detection (PCD) that is capable of noise suppression in images. The model was further optimized by transfer learning, which contributes domain knowledge from the same domain (prostate cancer data) but heterogeneous datasets. Particularly, Gaussian noise was introduced in the source datasets before knowledge transfer to the target dataset. Results: Four benchmark datasets were chosen as representative prostate cancer datasets. Ablation study and performance comparison between the proposed work and existing works were performed. Our model improved the accuracy by more than 10% compared with the existing works. Ablation studies also showed average improvements in accuracy using denoising, multi-scale scheme, and transfer learning, by 2.80%, 3.30%, and 3.13%, respectively. Conclusions: The performance evaluation and comparison of the proposed model confirm the importance and benefits of image noise suppression and transfer of knowledge from heterogeneous datasets of the same domain. [ABSTRACT FROM AUTHOR]

Objective. The diagnosis of chronic thromboembolic pulmonary hypertension (CTEPH) is challenging due to nonspecific early symptoms, complex diagnostic processes, and small lesion sizes. This study aims to develop an automatic diagnosis method for CTEPH using non-contrasted computed tomography (NCCT) scans, enabling automated diagnosis without precise lesion annotation. Approach. A novel cascade network (CN) with multiple instance learning (CNMIL) framework was developed to improve the diagnosis of CTEPH. This method uses a CN architecture combining two Resnet-18 CNN networks to progressively distinguish between normal and CTEPH cases. Multiple instance learning (MIL) is employed to treat each 3D CT case as a 'bag' of image slices, using attention scoring to identify the most important slices. An attention module helps the model focus on diagnostically relevant regions within each slice. The dataset comprised NCCT scans from 300 subjects, including 117 males and 183 females, with an average age of 52.5 ± 20.9 years, consisting of 132 normal cases and 168 cases of lung diseases, including 88 cases of CTEPH. The CNMIL framework was evaluated using sensitivity, specificity, and the area under the curve (AUC) metrics, and compared with common 3D supervised classification networks and existing CTEPH automatic diagnosis networks. Main results . The CNMIL framework demonstrated high diagnostic performance, achieving an AUC of 0.807, accuracy of 0.833, sensitivity of 0.795, and specificity of 0.849 in distinguishing CTEPH cases. Ablation studies revealed that integrating MIL and the CN significantly enhanced performance, with the model achieving an AUC of 0.978 and perfect sensitivity (1.000) in normal classification. Comparisons with other 3D network architectures confirmed that the integrated model outperformed others, achieving the highest AUC of 0.8419. Significance . The CNMIL network requires no additional scans or annotations, relying solely on NCCT. This approach can improve timely and accurate CTEPH detection, resulting in better patient outcomes., (Creative Commons Attribution license.)

ObjectivesTo develop and validate an efficient and automatically computational approach for stratifying glioma grades and predicting survival of lower-grade glioma (LGG) patients using an integration of state-of-the-art convolutional neural network (CNN) and radiomics.MethodThis retrospective study reviewed 470 preoperative MR images of glioma from BraTs public dataset (n=269) and Jinling hospital (n=201). A fully automated pipeline incorporating tumor segmentation and grading was developed, which can avoid variability and subjectivity of manual segmentations. First, an integrated approach by fusing CNN features and radiomics features was employed to stratify glioma grades. Then, a deep-radiomics signature based on the integrated approach for predicting survival of LGG patients was developed and subsequently validated in an independent cohort.ResultsThe performance of tumor segmentation achieved a Dice coefficient of 0.81. The intraclass correlation coefficients (ICCs) of the radiomics features between the segmentation network and physicians were all over 0.75. The performance of glioma grading based on integrated approach achieved the area under the curve (AUC) of 0.958, showing the effectiveness of the integrated approach. The multivariable Cox regression results demonstrated that the deep-radiomics signature remained an independent prognostic factor and the integrated nomogram showed significantly better performance than the clinical nomogram in predicting overall survival of LGG patients (C-index: 0.865 vs. 0.796, P=0.005).ConclusionThe proposed integrated approach can be noninvasively and efficiently applied in prediction of gliomas grade and survival. Moreover, our fully automated pipeline successfully achieved computerized segmentation instead of manual segmentation, which shows the potential to be a reproducible approach in clinical practice.