Noninvasive diagnosis of oral squamous cell carcinoma by multi-level deep residual learning on optical coherence tomography images

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.

A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors

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.

A brain tumor computer-aided diagnosis method with automatic lesion segmentation and ensemble decision strategy

Objectives

Gliomas 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.

Methods

Overall, 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.

Results

The 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).

Conclusion

The 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.

Automatic Detection System for Velopharyngeal Insufficiency Based on Acoustic Signals from Nasal and Oral Channels

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.

Measurement method of tear meniscus height based on deep learning

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 r ²0.94. 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.

A pairwise functional connectivity similarity measure method based on few-shot learning for early MCI detection

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.

Issues in Melanoma Detection: Semisupervised Deep Learning Algorithm Development via a Combination of Human and Artificial Intelligence

BACKGROUND

Automatic skin lesion recognition has shown to be effective in increasing access to reliable dermatology evaluation; however, most existing algorithms rely solely on images. Many diagnostic rules, including the 3-point checklist, are not considered by artificial intelligence algorithms, which comprise human knowledge and reflect the diagnosis process of human experts.

OBJECTIVE

In this paper, we aimed to develop a semisupervised model that can not only integrate the dermoscopic features and scoring rule from the 3-point checklist but also automate the feature-annotation process.

METHODS

We first trained the semisupervised model on a small, annotated data set with disease and dermoscopic feature labels and tried to improve the classification accuracy by integrating the 3-point checklist using ranking loss function. We then used a large, unlabeled data set with only disease label to learn from the trained algorithm to automatically classify skin lesions and features.

RESULTS

After adding the 3-point checklist to our model, its performance for melanoma classification improved from a mean of 0.8867 (SD 0.0191) to 0.8943 (SD 0.0115) under 5-fold cross-validation. The trained semisupervised model can automatically detect 3 dermoscopic features from the 3-point checklist, with best performances of 0.80 (area under the curve [AUC] 0.8380), 0.89 (AUC 0.9036), and 0.76 (AUC 0.8444), in some cases outperforming human annotators.

CONCLUSIONS

Our proposed semisupervised learning framework can help with the automatic diagnosis of skin disease based on its ability to detect dermoscopic features and automate the label-annotation process. The framework can also help combine semantic knowledge with a computer algorithm to arrive at a more accurate and more interpretable diagnostic result, which can be applied to broader use cases.

An MRI Scans-Based Alzheimer's Disease Detection via Convolutional Neural Network and Transfer Learning

Alzheimer’s disease (AD) is the most common type (>60%) of dementia and can wreak havoc on the psychological and physiological development of sufferers and their carers, as well as the economic and social development. Attributed to the shortage of medical staff, automatic diagnosis of AD has become more important to relieve the workload of medical staff and increase the accuracy of medical diagnoses. Using the common MRI scans as inputs, an AD detection model has been designed using convolutional neural network (CNN). To enhance the fine-tuning of hyperparameters and, thus, the detection accuracy, transfer learning (TL) is introduced, which brings the domain knowledge from heterogeneous datasets. Generative adversarial network (GAN) is applied to generate additional training data in the minority classes of the benchmark datasets. Performance evaluation and analysis using three benchmark (OASIS-series) datasets revealed the effectiveness of the proposed method, which increases the accuracy of the detection model by 2.85−3.88%, 2.43−2.66%, and 1.8−40.1% in the ablation study of GAN and TL, as well as the comparison with existing works, respectively.

Automated Detection of Acute Myocardial Infarction Using Asynchronous Electrocardiogram Signals-Preview of Implementing Artificial Intelligence With Multichannel Electrocardiographs Obtained From Smartwatches: Retrospective Study

Background

When using a smartwatch to obtain electrocardiogram (ECG) signals from multiple leads, the device has to be placed on different parts of the body sequentially. The ECG signals measured from different leads are asynchronous. Artificial intelligence (AI) models for asynchronous ECG signals have barely been explored.

Objective

We aimed to develop an AI model for detecting acute myocardial infarction using asynchronous ECGs and compare its performance with that of the automatic ECG interpretations provided by a commercial ECG analysis software. We sought to evaluate the feasibility of implementing multiple lead–based AI-enabled ECG algorithms on smartwatches. Moreover, we aimed to determine the optimal number of leads for sufficient diagnostic power.

Methods

We extracted ECGs recorded within 24 hours from each visit to the emergency room of Ajou University Medical Center between June 1994 and January 2018 from patients aged 20 years or older. The ECGs were labeled on the basis of whether a diagnostic code corresponding to acute myocardial infarction was entered. We derived asynchronous ECG lead sets from standard 12-lead ECG reports and simulated a situation similar to the sequential recording of ECG leads via smartwatches. We constructed an AI model based on residual networks and self-attention mechanisms by randomly masking each lead channel during the training phase and then testing the model using various targeting lead sets with the remaining lead channels masked.

Results

The performance of lead sets with 3 or more leads compared favorably with that of the automatic ECG interpretations provided by a commercial ECG analysis software, with 8.1%-13.9% gain in sensitivity when the specificity was matched. Our results indicate that multiple lead-based AI-enabled ECG algorithms can be implemented on smartwatches. Model performance generally increased as the number of leads increased (12-lead sets: area under the receiver operating characteristic curve [AUROC] 0.880; 4-lead sets: AUROC 0.858, SD 0.008; 3-lead sets: AUROC 0.845, SD 0.011; 2-lead sets: AUROC 0.813, SD 0.018; single-lead sets: AUROC 0.768, SD 0.001). Considering the short amount of time needed to measure additional leads, measuring at least 3 leads—ideally more than 4 leads—is necessary for minimizing the risk of failing to detect acute myocardial infarction occurring in a certain spatial location or direction.

Conclusions

By developing an AI model for detecting acute myocardial infarction with asynchronous ECG lead sets, we demonstrated the feasibility of multiple lead-based AI-enabled ECG algorithms on smartwatches for automated diagnosis of cardiac disorders. We also demonstrated the necessity of measuring at least 3 leads for accurate detection. Our results can be used as reference for the development of other AI models using sequentially measured asynchronous ECG leads via smartwatches for detecting various cardiac disorders.

Expert consensus document on automated diagnosis of the electrocardiogram: The task force on automated diagnosis of the electrocardiogram in Japan. Part 1: Nomenclature for diagnosis and abnormal findings

As these terms should accurately represent the abnormal findings and conditions as much as possible, we propose to unify these terms into terminologies that are not confusing and easy to understand for everyone.

Measuring Maximum Head Circumference Within the Picture Archiving and Communication System: A Fully Automatic Approach

This study describes an automatic technique to accurately determine the maximum head circumference (MHC) measurement from MRI studies within the Picture Archiving and Communications System, and can automatically add this measurement to the final radiology report. Participants were selected through a retrospective chart review of patients referred to the neurosurgery clinic. Forty-nine pediatric patients with ages ranging from 5 months to 11 years were included in the study. We created 14 printed ring structures to mirror the head circumference values at various ages along the x-axis of the Nellhaus chart. The 3D-printed structures were used to create MRI phantoms. Analytical obtainment of circumference values from the 3D objects and phantom images allowed for a fair estimation and correction of errors on the image-based-measuring instrument. Then, standard manual MHC measurements were performed and compared to values obtained from the patients' MRI T1 images using the tuned instrument proposed in this document. A T-test revealed no statistical difference between the manual assessments and the ones obtained by the automation p = 0.357, α = 0.05. This automatic application augments the more error-prone manual MHC measurement, and can add a numerical value to the final radiology report as a standard application.

Improving the Generalizability of Infantile Cataracts Detection via Deep Learning-Based Lens Partition Strategy and Multicenter Datasets

Infantile cataract is the main cause of infant blindness worldwide. Although previous studies developed artificial intelligence (AI) diagnostic systems for detecting infantile cataracts in a single center, its generalizability is not ideal because of the complicated noises and heterogeneity of multicenter slit-lamp images, which impedes the application of these AI systems in real-world clinics. In this study, we developed two lens partition strategies (LPSs) based on deep learning Faster R-CNN and Hough transform for improving the generalizability of infantile cataracts detection. A total of 1,643 multicenter slit-lamp images collected from five ophthalmic clinics were used to evaluate the performance of LPSs. The generalizability of Faster R-CNN for screening and grading was explored by sequentially adding multicenter images to the training dataset. For the normal and abnormal lenses partition, the Faster R-CNN achieved the average intersection over union of 0.9419 and 0.9107, respectively, and their average precisions are both > 95%. Compared with the Hough transform, the accuracy, specificity, and sensitivity of Faster R-CNN for opacity area grading were improved by 5.31, 8.09, and 3.29%, respectively. Similar improvements were presented on the other grading of opacity density and location. The minimal training sample size required by Faster R-CNN is determined on multicenter slit-lamp images. Furthermore, the Faster R-CNN achieved real-time lens partition with only 0.25 s for a single image, whereas the Hough transform needs 34.46 s. Finally, using Grad-Cam and t-SNE techniques, the most relevant lesion regions were highlighted in heatmaps, and the high-level features were discriminated. This study provides an effective LPS for improving the generalizability of infantile cataracts detection. This system has the potential to be applied to multicenter slit-lamp images.

Deep symmetric three-dimensional convolutional neural networks for identifying acute ischemic stroke via diffusion-weighted images

BACKGROUND

Acute ischemic stroke (AIS) results in high morbidity, disability, and mortality. Early and automatic diagnosis of AIS can help clinicians administer the appropriate interventions.

OBJECTIVE

To develop a deep symmetric 3D convolutional neural network (DeepSym-3D-CNN) for automated AIS diagnosis via diffusion-weighted imaging (DWI) images.

METHODS

This study includes 190 study subjects (97 AIS and 93 Non-AIS) by collecting both DWI and Apparent Diffusion Coefficient (ADC) images. 3D DWI brain images are split into left and right hemispheres and input into two paths. A map with 125×253×14×12 features is extracted by each path of Inception Modules. After the features computed from two paths are subtracted through L-2 normalization, four multi-scale convolution layers produce the final predation. Three comparative models using DWI images including MedicalNet with transfer learning, Simple DeepSym-3D-CNN (each 3D Inception Module is replaced by a simple 3D-CNN layer), and L-1 DeepSym-3D-CNN (L-2 normalization is replaced by L-1 normalization) are constructed. Moreover, using ADC images and the combination of DWI and ADC images as inputs, the performance of DeepSym-3D-CNN is also investigated. Performance levels of all three models are evaluated by 5-fold cross-validation and the values of area under ROC curve (AUC) are compared by DeLong's test.

RESULTS

DeepSym-3D-CNN achieves an accuracy of 0.850 and an AUC of 0.864. DeLong's test of AUC values demonstrates that DeepSym-3D-CNN significantly outperforms other comparative models (p < 0.05). The highlighted regions in the feature maps of DeepSym-3D-CNN spatially match with AIS lesions. Meanwhile, DeepSym-3D-CNN using DWI images presents the significant higher AUC than that either using ADC images or using DWI-ADC images based on DeLong's test (p < 0.05).

CONCLUSIONS

DeepSym-3D-CNN is a potential method for automatically identifying AIS via DWI images and can be extended to other diseases with asymmetric lesions.

Alzheimer's Disease Classification With a Cascade Neural Network

Classification of Alzheimer's Disease (AD) has been becoming a hot issue along with the rapidly increasing number of patients. This task remains tremendously challenging due to the limited data and the difficulties in detecting mild cognitive impairment (MCI). Existing methods use gait [or EEG (electroencephalogram)] data only to tackle this task. Although the gait data acquisition procedure is cheap and simple, the methods relying on gait data often fail to detect the slight difference between MCI and AD. The methods that use EEG data can detect the difference more precisely, but collecting EEG data from both HC (health controls) and patients is very time-consuming. More critically, these methods often convert EEG records into the frequency domain and thus inevitably lose the spatial and temporal information, which is essential to capture the connectivity and synchronization among different brain regions. This paper proposes a cascade neural network with two steps to achieve a faster and more accurate AD classification by exploiting gait and EEG data simultaneously. In the first step, we propose attention-based spatial temporal graph convolutional networks to extract the features from the skeleton sequences (i.e., gait) captured by Kinect (a commonly used sensor) to distinguish between HC and patients. In the second step, we propose spatial temporal convolutional networks to fully exploit the spatial and temporal information of EEG data and classify the patients into MCI or AD eventually. We collect gait and EEG data from 35 cognitively health controls, 35 MCI, and 17 AD patients to evaluate our proposed method. Experimental results show that our method significantly outperforms other AD diagnosis methods (91.07 vs. 68.18%) in the three-way AD classification task (HC, MCI, and AD). Moreover, we empirically found that the lower body and right upper limb are more important for the early diagnosis of AD than other body parts. We believe this interesting finding can be helpful for clinical researches.

Automated Detection of TMJ Osteoarthritis Based on Artificial Intelligence

The purpose of this study was to develop a diagnostic tool to automatically detect temporomandibular joint osteoarthritis (TMJOA) from cone beam computed tomography (CBCT) images with artificial intelligence. CBCT images of patients diagnosed with temporomandibular disorder were included for image preparation. Single-shot detection, an object detection model, was trained with 3,514 sagittal CBCT images of the temporomandibular joint that showed signs of osseous changes in the mandibular condyle. The region of interest (condylar head) was defined and classified into 2 categories-indeterminate for TMJOA and TMJOA-according to image analysis criteria for the diagnosis of temporomandibular disorder. The model was tested with 2 sets of 300 images in total. The average accuracy, precision, recall, and F1 score over the 2 test sets were 0.86, 0.85, 0.84, and 0.84, respectively. Automated detection of TMJOA from sagittal CBCT images is possible by using a deep neural networks model. It may be used to support clinicians with diagnosis and decision making for treatments of TMJOA.

Dyslexia Diagnosis by EEG Temporal and Spectral Descriptors: An Anomaly Detection Approach

Diagnosis of learning difficulties is a challenging goal. There are huge number of factors involved in the evaluation procedure that present high variance among the population with the same difficulty. Diagnosis is usually performed by scoring subjects according to results obtained in different neuropsychological (performance-based) tests specifically designed to this end. One of the most frequent disorders is developmental dyslexia (DD), a specific difficulty in the acquisition of reading skills not related to mental age or inadequate schooling. Its prevalence is estimated between 5% and 12% of the population. Traditional tests for DD diagnosis aim to measure different behavioral variables involved in the reading process. In this paper, we propose a diagnostic method not based on behavioral variables but on involuntary neurophysiological responses to different auditory stimuli. The experiments performed use electroencephalography (EEG) signals to analyze the temporal behavior and the spectral content of the signal acquired from each electrode to extract relevant (temporal and spectral) features. Moreover, the relationship of the features extracted among electrodes allows to infer a connectivity-like model showing brain areas that process auditory stimuli in a synchronized way. Then an anomaly detection system based on the reconstruction residuals of an autoencoder using these features has been proposed. Hence, classification is performed by the proposed system based on the differences in the resulting connectivity models that have demonstrated to be a useful tool for differential diagnosis of DD as well as a method to step towards gaining a better knowledge of the brain processes involved in DD. The results corroborate that nonspeech stimulus modulated at specific frequencies related to the sampling processes developed in the brain to capture rhymes, syllables and phonemes produces effects in specific frequency bands that differentiate between controls and DD subjects. The proposed method showed relatively high sensitivity above 0.6, and up to 0.9 in some of the experiments.

Comparison of Deep-Learning and Conventional Machine-Learning Methods for the Automatic Recognition of the Hepatocellular Carcinoma Areas from Ultrasound Images

The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.

Deep Learning-Based Method of Diagnosing Hyperlipidemia and Providing Diagnostic Markers Automatically

INTRODUCTION

The research of auxiliary diagnosis has always been one of the hotspots in the world. The implementation of auxiliary diagnosis support algorithm for medical text data faces challenges with interpretability and creditability. The improvement of clinical diagnostic techniques means not only the improvement of diagnostic accuracy but also the further study of diagnostic basis. Traditional research methods for diagnostic markers often require a large amount of time and economic costs. Research objects are often dozens of samples, and it is, therefore, difficult to synthesize large amounts of data. Therefore, the comprehensiveness and reliability of traditional methods have yet to be improved. Therefore, the establishment of a model that can automatically diagnose diseases and automatically provide a diagnostic basis at the same time has a positive effect on the improvement of medical diagnostic techniques.

METHODS

Here, we established an auxiliary diagnostic tool based on attention deep learning algorithm to diagnostic hyperlipemia and automatically predict the corresponding diagnostic markers using hematological parameters. In this paper, we not only demonstrated the ability of the proposed model to automatically diagnose diseases using text-based medical data, such as physiological parameters, but also demonstrated its ability to forecast disease diagnostic markers. Human physiological parameters are used as input to the model, and the doctor's diagnosis results as an output. Through the attention layer, the degree of attention of the model to different physiological parameters can be obtained, that is, the model provides a diagnostic basis.

RESULTS

It achieved 94% ACC, 97.48% AUC, 96% sensitivity and 92% specificity with the test dataset. All the above samples are drawn from clinical practice. Moreover, the model predicted the diagnostic markers of hyperlipidemia by the attention mechanism, and the results were fully agreeable to the golden criteria.

DISCUSSION

The auxiliary diagnosis system proposed in this paper not only achieves the accurate and robust performance, and can be used for the preliminary diagnosis of patients, but also showing its great potential to discover new diagnostic markers. Therefore, it not only can improve the efficiency of clinical diagnosis but also shorten the research period of researching a diagnosis basis to an extent. It has a positive significance to the development of the medical diagnosis level.

[Establishment of Application Database for Electrocardiograph in Different Scenes]

It is significant to establish scene ECG database which improves the automatic diagnostic function of electrocardiograph under different application scenarios. We built the ECG database in different scene according to the hospital level (grade 3, grade 2, grade 1) and clinical environment (intensive care and acute wards, outpatient clinics and general wards). Sample size was obtained according to the incidence of various ECG diagnoses. The database covers ECG signal, ECG waveform, ECG characteristic values, ECG diagnostic results by experts and clinical information of patients etc. It not only provides important reference for electrocardiograph manufacturers to evaluate and test the parameters of automatic diagnosis under different clinical scene, but also provides valuable scientific research and teaching resources for medical workers.

Diagnosis of Alzheimer's disease with Sobolev gradient-based optimization and 3D convolutional neural network

Alzheimer's disease is a neuropsychiatric, progressive, also an irreversible disease. There is not an effective cure for the disease. However, early diagnosis has an important role for treatment planning to delay its progression since the treatments have the most impact at the early stage of the disease. Neuroimages obtained by different imaging techniques (for example, diffusion tensor-based and magnetic resonance-based imaging) provide powerful information and help to diagnose the disease. In this work, a deeply supervised and robust method has been developed using three dimensional features to provide objective and accurate diagnosis from magnetic resonance images. The main contributions are (a) a new three dimensional convolutional neural network topology; (b) a new Sobolev gradient-based optimization with weight values for each decision parameters; (c) application of the proposed topology and optimizer to diagnose Alzheimer's disease; (d) comparisons of the results obtained from the recent techniques that have been implemented for Alzheimer's disease diagnosis. Experimental results and quantitative evaluations indicated that the proposed network model is able to achieve to extract desired features from images and provides automated diagnosis with 98.06% accuracy.

An Approach to Automatic Hard Exudate Detection in Retina Color Images by a Telemedicine System Based on the d-Eye Sensor and Image Processing Algorithms

Hard exudates are one of the most characteristic and dangerous signs of diabetic retinopathy. They can be marked during the routine ophthalmological examination and seen in color fundus photographs (i.e., using a fundus camera). The purpose of this paper is to introduce an algorithm that can extract pathological changes (i.e., hard exudates) in diabetic retinopathy. This was a retrospective, nonrandomized study. A total of 100 photos were included in the analysis—50 sick and 50 normal eyes. Small lesions in diabetic retinopathy could be automatically diagnosed by the system with an accuracy of 98%. During the experiments, the authors used classical image processing methods such as binarization or median filtration, and data was read from the d-Eye sensor. Sixty-seven patients (39 females and 28 males with ages ranging between 50 and 64) were examined. The results have shown that the proposed solution accuracy level equals 98%. Moreover, the algorithm returns correct classification decisions for high quality images and low quality samples. Furthermore, we consider taking retina photos using mobile phones rather than fundus cameras, which is more practical. The paper presents an innovative approach. The results are introduced and the algorithm is described.

Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion

AIM

To investigate and compare the efficacy of two machine-learning technologies with deep-learning (DL) and support vector machine (SVM) for the detection of branch retinal vein occlusion (BRVO) using ultrawide-field fundus images.

METHODS

This study included 237 images from 236 patients with BRVO with a mean±standard deviation of age 66.3±10.6y and 229 images from 176 non-BRVO healthy subjects with a mean age of 64.9±9.4y. Training was conducted using a deep convolutional neural network using ultrawide-field fundus images to construct the DL model. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and area under the curve (AUC) were calculated to compare the diagnostic abilities of the DL and SVM models.

RESULTS

For the DL model, the sensitivity, specificity, PPV, NPV and AUC for diagnosing BRVO was 94.0% (95%CI: 93.8%-98.8%), 97.0% (95%CI: 89.7%-96.4%), 96.5% (95%CI: 94.3%-98.7%), 93.2% (95%CI: 90.5%-96.0%) and 0.976 (95%CI: 0.960-0.993), respectively. In contrast, for the SVM model, these values were 80.5% (95%CI: 77.8%-87.9%), 84.3% (95%CI: 75.8%-86.1%), 83.5% (95%CI: 78.4%-88.6%), 75.2% (95%CI: 72.1%-78.3%) and 0.857 (95%CI: 0.811-0.903), respectively. The DL model outperformed the SVM model in all the aforementioned parameters (P<0.001).

CONCLUSION

These results indicate that the combination of the DL model and ultrawide-field fundus ophthalmoscopy may distinguish between healthy and BRVO eyes with a high level of accuracy. The proposed combination may be used for automatically diagnosing BRVO in patients residing in remote areas lacking access to an ophthalmic medical center.

3D convolutional neural network for differentiating pre-invasive lesions from invasive adenocarcinomas appearing as ground-glass nodules with diameters ≤3 cm using HRCT

Background

Identification of pre-invasive lesions (PILs) and invasive adenocarcinomas (IACs) can facilitate treatment selection. This study aimed to develop an automatic classification framework based on a 3D convolutional neural network (CNN) to distinguish different types of lung cancer using computed tomography (CT) data.

Methods

The CT data of 1,545 patients suffering from pre-invasive or invasive lung cancer were collected from Fudan University Shanghai Cancer Center. All of the data were preprocessed through lung mask extraction and 3D reconstruction to adapt to different imaging scanners or protocols. The general flow for the classification framework consisted of nodule detection and cancer classification. The performance of our classification algorithm was evaluated using a receiver operating characteristic (ROC) analysis, with diagnostic results from three experienced radiologists.

Results

The sensitivity, specificity, accuracy, and AUC (area under the ROC curve) values of our proposed automatic classification method were 88.5%, 80.1%, 84.0%, and 89.2%, respectively. The results of the CNN classification method were compared to those of three experienced radiologists. The AUC value of our method (AUC =0.892) was higher than those of all radiologists (radiologist 1: 80.5%; radiologist 2: 83.9%; and radiologist 3: 86.7%).

Conclusions

The 3D CNN-based classification algorithm is a promising tool for the diagnosis of pre-invasive and invasive lung cancer and for the treatment choice decision.

A Computational Model for the Automatic Diagnosis of Attention Deficit Hyperactivity Disorder Based on Functional Brain Volume

In this paper, we investigated the problem of computer-aided diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) using machine learning techniques. With the ADHD-200 dataset, we developed a Support Vector Machine (SVM) model to classify ADHD patients from typically developing controls (TDCs), using the regional brain volumes as predictors. Conventionally, the volume of a brain region was considered to be an anatomical feature and quantified using structural magnetic resonance images. One major contribution of the present study was that we had initially proposed to measure the regional brain volumes using fMRI images. Brain volumes measured from fMRI images were denoted as functional volumes, which quantified the volumes of brain regions that were actually functioning during fMRI imaging. We compared the predictive power of functional volumes with that of regional brain volumes measured from anatomical images, which were denoted as anatomical volumes. The former demonstrated higher discriminative power than the latter for the classification of ADHD patients vs. TDCs. Combined with our two-step feature selection approach which integrated prior knowledge with the recursive feature elimination (RFE) algorithm, our SVM classification model combining functional volumes and demographic characteristics achieved a balanced accuracy of 67.7%, which was 16.1% higher than that of a relevant model published previously in the work of Sato et al. Furthermore, our classifier highlighted 10 brain regions that were most discriminative in distinguishing between ADHD patients and TDCs. These 10 regions were mainly located in occipital lobe, cerebellum posterior lobe, parietal lobe, frontal lobe, and temporal lobe. Our present study using functional images will likely provide new perspectives about the brain regions affected by ADHD.

[Development of Automatic Diagnosis and Evaluation System for ECG Recorder]

ECG Recorder's automatic diagnosis function is uneven, it brings a lot of inconvenience to clinicians in the diagnosis and treatment. We developed the automatic diagnosis and evaluation system for ECG recorder based on data platform in General Hospital of PLA, in order to evaluate the automatic diagnosis function of ECG recorder and improve the level of automatic diagnosis, and through a large number of data evaluation results, to provides the standard basis of ECG recorder's automatic diagnosis.

A smartphone-based automatic diagnosis system for facial nerve palsy

Facial nerve palsy induces a weakness or loss of facial expression through damage of the facial nerve. A quantitative and reliable assessment system for facial nerve palsy is required for both patients and clinicians. In this study, we propose a rapid and portable smartphone-based automatic diagnosis system that discriminates facial nerve palsy from normal subjects. Facial landmarks are localized and tracked by an incremental parallel cascade of the linear regression method. An asymmetry index is computed using the displacement ratio between the left and right side of the forehead and mouth regions during three motions: resting, raising eye-brow and smiling. To classify facial nerve palsy, we used Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), and Leave-one-out Cross Validation (LOOCV) with 36 subjects. The classification accuracy rate was 88.9%.

The effects of automated artifact removal algorithms on electroencephalography-based Alzheimer's disease diagnosis

Over the last decade, electroencephalography (EEG) has emerged as a reliable tool for the diagnosis of cortical disorders such as Alzheimer's disease (AD). EEG signals, however, are susceptible to several artifacts, such as ocular, muscular, movement, and environmental. To overcome this limitation, existing diagnostic systems commonly depend on experienced clinicians to manually select artifact-free epochs from the collected multi-channel EEG data. Manual selection, however, is a tedious and time-consuming process, rendering the diagnostic system “semi-automated.” Notwithstanding, a number of EEG artifact removal algorithms have been proposed in the literature. The (dis)advantages of using such algorithms in automated AD diagnostic systems, however, have not been documented; this paper aims to fill this gap. Here, we investigate the effects of three state-of-the-art automated artifact removal (AAR) algorithms (both alone and in combination with each other) on AD diagnostic systems based on four different classes of EEG features, namely, spectral, amplitude modulation rate of change, coherence, and phase. The three AAR algorithms tested are statistical artifact rejection (SAR), blind source separation based on second order blind identification and canonical correlation analysis (BSS-SOBI-CCA), and wavelet enhanced independent component analysis (wICA). Experimental results based on 20-channel resting-awake EEG data collected from 59 participants (20 patients with mild AD, 15 with moderate-to-severe AD, and 24 age-matched healthy controls) showed the wICA algorithm alone outperforming other enhancement algorithm combinations across three tasks: diagnosis (control vs. mild vs. moderate), early detection (control vs. mild), and disease progression (mild vs. moderate), thus opening the doors for fully-automated systems that can assist clinicians with early detection of AD, as well as disease severity progression assessment.

Review of Medical Image Classification using the Adaptive Neuro-Fuzzy Inference System

Image classification is an issue that utilizes image processing, pattern recognition and classification methods. Automatic medical image classification is a progressive area in image classification, and it is expected to be more developed in the future. Because of this fact, automatic diagnosis can assist pathologists by providing second opinions and reducing their workload. This paper reviews the application of the adaptive neuro-fuzzy inference system (ANFIS) as a classifier in medical image classification during the past 16 years. ANFIS is a fuzzy inference system (FIS) implemented in the framework of an adaptive fuzzy neural network. It combines the explicit knowledge representation of an FIS with the learning power of artificial neural networks. The objective of ANFIS is to integrate the best features of fuzzy systems and neural networks. A brief comparison with other classifiers, main advantages and drawbacks of this classifier are investigated.