Computer aided diagnosis system using deep convolutional neural networks for ADHD subtypes

A systematic literature review of machine learning techniques for the detection of attention-deficit/hyperactivity disorder using MRI and/or EEG data

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental condition common in teenagers across the globe. Neuroimaging and Machine Learning (ML) advancements have revolutionized its diagnosis and treatment approaches. Although, the researchers are continuously developing automated ADHD diagnostic tools, there is no reliable ML-based diagnostic system for clinicians. Thus, the study aims to systematically review ML and DL-based approaches for ADHD diagnosis, leveraging brain data from magnetic resonance imaging (MRI) and electroencephalogram (EEG) data. A methodical review for the period 2016 to 2022 is conducted by following the PRISMA guidelines. Four reputable repositories, namely PubMed, IEEE, ScienceDirect, and Springer are searched for the related literature on ADHD diagnosis using MRI/EEG data. 87 studies are selected after screening abstracts of the papers. We critically conducted an analysis of these studies by examining various aspects related to training ML/DL-models, including diverse datasets, hyperparameter tuning, overfitting, and interpretability. The quality and risk assessment is conducted using the QUADAS2 tool to determine the bias due to patient selection, index test, reference standard, and flow and timing. Our rigours analysis observed significant diversity in dataset acquisition and its size, feature extraction and selection techniques, validation strategies and classifier choices. Our findings emphasize the need for generalizability, transparency, interpretability, and reproducibility in future research. The challenges and potential solutions associated with integrating diagnostic models into clinical settings are also discussed. The identified research gaps will guide researchers in developing a reliable ADHD diagnostic system that addresses the associated challenges.

Classification algorithm for motor imagery fusing CNN and attentional mechanisms based on functional near-infrared spectroscopy brain image

With the continuing development of brain-computer interface technology, the analysis and interpretation of brain signals are becoming increasingly important. In the field of brain-computer interfaces, motor imagery (MI) is an important paradigm for generating specific brain signals through thought alone, rather than actual movement, for computer decoding. Functional near-infrared spectroscopy (fNIRS) imaging technology has been increasingly used in brain-computer interfaces due to its advantages of non-invasiveness, low resource requirements, low cost, and high spatial resolution. Scientists have done a lot of work in channel selection, feature selection, and then applying traditional machine learning methods for classification, but the results achieved so far are still insufficient to meet the conditions for realizing fNIRS brain-computer interfaces. To achieve a higher level of classification of fNIRS signals, we propose a method that fuses CNN and attention mechanisms to analyze the near-infrared signals of motor imagery and mental arithmetic data, which is fed into a neural network by deriving signals of changes in oxygenated hemoglobin (HbO) and deoxygenated hemoglobin (HbR) concentrations through the modified Beer-Lambert law, and then applied to the fNIRS dataset of 29 healthy subjects to validate the proposed method. In the fNIRS-based BCI, the average classification accuracy of the MI signal from HbR and HbO reaches 85.92% and 86.21%, respectively, and the average classification accuracy of the MA signal reaches 89.66% and 88.79%, respectively. The advantage of our approach is that it is lightweight and improves the classification accuracy of current BCI fNIRS signals.

Optimal interval and feature selection in activity data for detecting attention deficit hyperactivity disorder

Attention deficit hyperactivity disorder (ADHD) is a heterogeneous neurobehavioral disorder that is common in children and adolescents. Inattention, impulsivity, and hyperactivity are the key symptoms of ADHD patients. Traditional clinical assessments delay ADHD diagnosis and increase undiagnosed cases and costs, as well. The use of deep learning (DL) and machine learning (ML)-based objective techniques for diagnosing ADHD has grown exponentially in recent years as the efficiency of early diagnosis has improved. This research highlights the significance of utilizing feature selection techniques before constructing machine learning models on activity datasets. It also explores the distinctions between specific time-interval activity data and broader interval activity data in identifying ADHD patients from the clinical control group. Five ML models were developed and tested to assess the performance of two sets of features and different categories of activity data in predicting ADHD. The study concludes with the following findings: (i) the model's performance showed a notable improvement of 0.11 in accuracy with the adoption of a precise feature selection process; (ii) activity data recorded in the morning and at night are more significant predictors of ADHD compared to other times; (iii) the utilization of specific time interval data is crucial for ADHD prediction; (iv) the random forest performs better than the other machine learning models used in the study, with 84% accuracy, 79% precision, 85% F1-score, and 92% recall. As we move into an era where early disease prediction is possible, combining artificial intelligence methods with activity data could create a strong framework for helping doctors make decisions that can be used far beyond hospitals.

Exploring role of prefrontal cortex region of brain in children having ADHD with machine learning: Implications and insights

OBJECTIVE

Attention deficit hyperactivity disorder (ADHD), is a general neurodevelopmental syndrome. This affects both adults and children, causing issues like hyperactivity, inattention, and impulsivity. Diagnosis, typically reliant on patient narratives and questionnaires, can sometimes be inaccurate, leading to distress. We propose utilizing empirical mode decomposition (EMD) for feature extraction and a machine learning (ML) algorithm to categorize ADHD and control.

METHOD

Publicly available Kaggle dataset is used for research. The EMD technique decomposes an electroencephalogram (EEG) waveform to 12 intrinsic mode functions (IMFs). Thirty-one statistical parameters are generated over the first 6 IMFs to create an input feature vector for the deep belief network (DBN) classifier. Principal component analysis (PCA) is utilized to reduce dimension.

FINDINGS

Experimental results are compared on prefrontal cortex channels Fp1 and Fp2. After an in-depth evaluation of all metrics, it is observed that, in patients with ADHD, the prefrontal cortex regulates attention, behavior, and emotion. Our findings align with established neuroscience. The critical functions of the brain, such as organization, planning, attention, and decision making, are performed by the frontal lobe.

NOVELTY

Our work provides a novel approach to understanding the disorder's underlying neurobiological mechanisms. It has the potential to deepen our understanding of the condition, improve diagnostic accuracy, personalize treatment methods, and, ultimately, improve outcomes for those affected.

ADHD/CD-NET: automated EEG-based characterization of ADHD and CD using explainable deep neural network technique

In this study, attention deficit hyperactivity disorder (ADHD), a childhood neurodevelopmental disorder, is being studied alongside its comorbidity, conduct disorder (CD), a behavioral disorder. Because ADHD and CD share commonalities, distinguishing them is difficult, thus increasing the risk of misdiagnosis. It is crucial that these two conditions are not mistakenly identified as the same because the treatment plan varies depending on whether the patient has CD or ADHD. Hence, this study proposes an electroencephalogram (EEG)-based deep learning system known as ADHD/CD-NET that is capable of objectively distinguishing ADHD, ADHD + CD, and CD. The 12-channel EEG signals were first segmented and converted into channel-wise continuous wavelet transform (CWT) correlation matrices. The resulting matrices were then used to train the convolutional neural network (CNN) model, and the model's performance was evaluated using 10-fold cross-validation. Gradient-weighted class activation mapping (Grad-CAM) was also used to provide explanations for the prediction result made by the 'black box' CNN model. Internal private dataset (45 ADHD, 62 ADHD + CD and 16 CD) and external public dataset (61 ADHD and 60 healthy controls) were used to evaluate ADHD/CD-NET. As a result, ADHD/CD-NET achieved classification accuracy, sensitivity, specificity, and precision of 93.70%, 90.83%, 95.35% and 91.85% for the internal evaluation, and 98.19%, 98.36%, 98.03% and 98.06% for the external evaluation. Grad-CAM also identified significant channels that contributed to the diagnosis outcome. Therefore, ADHD/CD-NET can perform temporal localization and choose significant EEG channels for diagnosis, thus providing objective analysis for mental health professionals and clinicians to consider when making a diagnosis.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-023-10028-2.

Data leakage in deep learning studies of translational EEG

A growing number of studies apply deep neural networks (DNNs) to recordings of human electroencephalography (EEG) to identify a range of disorders. In many studies, EEG recordings are split into segments, and each segment is randomly assigned to the training or test set. As a consequence, data from individual subjects appears in both the training and the test set. Could high test-set accuracy reflect data leakage from subject-specific patterns in the data, rather than patterns that identify a disease? We address this question by testing the performance of DNN classifiers using segment-based holdout (in which segments from one subject can appear in both the training and test set), and comparing this to their performance using subject-based holdout (where all segments from one subject appear exclusively in either the training set or the test set). In two datasets (one classifying Alzheimer's disease, and the other classifying epileptic seizures), we find that performance on previously-unseen subjects is strongly overestimated when models are trained using segment-based holdout. Finally, we survey the literature and find that the majority of translational DNN-EEG studies use segment-based holdout. Most published DNN-EEG studies may dramatically overestimate their classification performance on new subjects.

An intelligent LinkNet-34 model with EfficientNetB7 encoder for semantic segmentation of brain tumor

A brain tumor is an unnatural expansion of brain cells that can't be stopped, making it one of the deadliest diseases of the nervous system. The brain tumor segmentation for its earlier diagnosis is a difficult task in the field of medical image analysis. Earlier, segmenting brain tumors was done manually by radiologists but that requires a lot of time and effort. Inspite of this, in the manual segmentation there was possibility of making mistakes due to human intervention. It has been proved that deep learning models can outperform human experts for the diagnosis of brain tumor in MRI images. These algorithms employ a huge number of MRI scans to learn the difficult patterns of brain tumors to segment them automatically and accurately. Here, an encoder-decoder based architecture with deep convolutional neural network is proposed for semantic segmentation of brain tumor in MRI images. The proposed method focuses on the image downsampling in the encoder part. For this, an intelligent LinkNet-34 model with EfficientNetB7 encoder based semantic segmentation model is proposed. The performance of LinkNet-34 model is compared with other three models namely FPN, U-Net, and PSPNet. Further, the performance of EfficientNetB7 used as encoder in LinkNet-34 model has been compared with three encoders namely ResNet34, MobileNet_V2, and ResNet50. After that, the proposed model is optimized using three different optimizers such as RMSProp, Adamax and Adam. The LinkNet-34 model has outperformed with EfficientNetB7 encoder using Adamax optimizer with the value of jaccard index as 0.89 and dice coefficient as 0.915.

Risk of data leakage in estimating the diagnostic performance of a deep-learning-based computer-aided system for psychiatric disorders

Deep-learning approaches with data augmentation have been widely used when developing neuroimaging-based computer-aided diagnosis (CAD) systems. To prevent the inflated diagnostic performance caused by data leakage, a correct cross-validation (CV) method should be employed, but this has been still overlooked in recent deep-learning-based CAD studies. The goal of this study was to investigate the impact of correct and incorrect CV methods on the diagnostic performance of deep-learning-based CAD systems after data augmentation. To this end, resting-state electroencephalogram (EEG) data recorded from post-traumatic stress disorder patients and healthy controls were augmented using a cropping method with different window sizes, respectively. Four different CV approaches were used to estimate the diagnostic performance of the CAD system, i.e., subject-wise CV (sCV), overlapped sCV (oSCV), trial-wise CV (tCV), and overlapped tCV (otCV). Diagnostic performances were evaluated using two deep-learning models based on convolutional neural network. Data augmentation can increase the performance with all CVs, but inflated diagnostic performances were observed when using incorrect CVs (tCV and otCV) due to data leakage. Therefore, the correct CV (sCV and osCV) should be used to develop a deep-learning-based CAD system. We expect that our investigation can provide deep-insight for researchers who plan to develop neuroimaging-based CAD systems for psychiatric disorders using deep-learning algorithms with data augmentation.

Subtype classification of attention deficit hyperactivity disorder with hierarchical binary hypothesis testing framework

Objective. The diagnosis of attention deficit hyperactivity disorder (ADHD) subtypes is important for the refined treatment of ADHD children. Although automated diagnosis methods based on machine learning are performed with structural and functional magnetic resonance imaging (sMRI and fMRI) data which have full observation of brains, they are not satisfactory with the accuracy of less than80%for the ADHD subtype diagnosis.Approach. To improve the accuracy and obtain the biomarker of ADHD subtypes, we proposed a hierarchical binary hypothesis testing (H-BHT) framework by using brain functional connectivity (FC) as input bio-signals. The framework includes a two-stage procedure with a decision tree strategy and thus becomes suitable for the subtype classification. Also, typical FC is extracted in both two stages of identifying ADHD subtypes. That means the important FC is found out for the subtype recognition.Main results. We apply the proposed H-BHT framework to resting state fMRI datasets from ADHD-200 consortium. The results are achieved with the average accuracy97.1%and an average kappa score 0.947. Discriminative FC between ADHD subtypes is found by comparing the P-values of typical FC.Significance. The proposed framework not only is an effective structure for ADHD subtype classification, but also provides useful reference for multiclass classification of mental disease subtypes.

Classification of attention deficit/hyperactivity disorder based on EEG signals using a EEG-Transformer model∗

Objective. Attention-deficit/hyperactivity disorder (ADHD) is the most common neurodevelopmental disorder in adolescents that can seriously impair a person's attention function, cognitive processes, and learning ability. Currently, clinicians primarily diagnose patients based on the subjective assessments of the Diagnostic and Statistical Manual of Mental Disorders-5, which can lead to delayed diagnosis of ADHD and even misdiagnosis due to low diagnostic efficiency and lack of well-trained diagnostic experts. Deep learning of electroencephalogram (EEG) signals recorded from ADHD patients could provide an objective and accurate method to assist physicians in clinical diagnosis.Approach. This paper proposes the EEG-Transformer deep learning model, which is based on the attention mechanism in the traditional Transformer model, and can perform feature extraction and signal classification processing for the characteristics of EEG signals. A comprehensive comparison was made between the proposed transformer model and three existing convolutional neural network models.Main results. The results showed that the proposed EEG-Transformer model achieved an average accuracy of 95.85% and an average AUC value of 0.9926 with the fastest convergence speed, outperforming the other three models. The function and relationship of each module of the model are studied by ablation experiments. The model with optimal performance was identified by the optimization experiment.Significance. The EEG-Transformer model proposed in this paper can be used as an auxiliary tool for clinical diagnosis of ADHD, and at the same time provides a basic model for transferable learning in the field of EEG signal classification.

Insight into ADHD diagnosis with deep learning on Actimetry: Quantitative interpretation of occlusion maps in age and gender subgroups

Attention Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood that often persists into adulthood. Objectively diagnosing ADHD can be challenging due to the reliance on subjective questionnaires in clinical assessment. Fortunately, recent advancements in artificial intelligence (AI) have shown promise in providing objective diagnoses through the analysis of medical images or activity recordings. These AI-based techniques have demonstrated accurate ADHD diagnosis; however, the growing complexity of deep learning models has introduced a lack of interpretability. These models often function as black boxes, unable to offer meaningful insights into the data patterns that characterize ADHD.

OBJECTIVE

This paper proposes a methodology to interpret the output of an AI-based diagnosis system for combined ADHD in age and gender-stratified populations.

METHODS

Our system is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks (CNNs) to classify spectrograms of activity windows. These windows are interpreted using occlusion maps to highlight the time-frequency patterns explaining ADHD activity.

RESULTS

Significant differences in the frequency patterns between ADHD and controls both in diurnal and nocturnal activity were found for all the populations. Temporal dispersion also presented differences in the male population.

CONCLUSION

The proposed interpretation techniques for CNNs highlighted gender- and age-related differences between ADHD patients and controls. Leveraging these differences could potentially lead to improved diagnostic accuracy, especially if a larger and more balanced dataset is utilized.

SIGNIFICANCE

Our findings pave the way for the development of an AI-based diagnosis system for ADHD that offers interpretability, thereby providing valuable insights into the underlying etiology of the disease.

Alterations in the Glycan Composition of Serum Glycoproteins in Attention-Deficit Hyperactivity Disorder

Changes in protein glycosylation are associated with most biological processes, and the importance of glycomic analysis in the research of disorders is constantly increasing, including in the neurodevelopmental field. We glycoprofiled sera in 10 children with attention-deficit hyperactivity disorder (ADHD) and 10 matching healthy controls for 3 types of samples: whole serum, sera after depletion of abundant proteins (albumin and IgG), and isolated IgG. The analytical methods used were a lectin-based glycoprotein microarray enabling high-throughput glycan analysis and matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) as a standard method for the identification of glycan structures. For microarray analysis, the samples printed on microarray slides were incubated with biotinylated lectins and detected using the fluorescent conjugate of streptavidin by a microarray scanner. In the ADHD patient samples, we found increased antennary fucosylation, decreased di-/triantennary N-glycans with bisecting N-acetylglucosamine (GlcNAc), and decreased α2-3 sialylation. The results obtained by both independent methods were consistent. The study's sample size and design do not allow far-reaching conclusions to be drawn. In any case, there is a strong demand for a better and more comprehensive diagnosis of ADHD, and the obtained results emphasize that the presented approach brings new horizons to studying functional associations of glycan alterations in ADHD.

Automated Sagittal Skeletal Classification of Children Based on Deep Learning

Malocclusions are a type of cranio-maxillofacial growth and developmental deformity that occur with high incidence in children. Therefore, a simple and rapid diagnosis of malocclusions would be of great benefit to our future generation. However, the application of deep learning algorithms to the automatic detection of malocclusions in children has not been reported. Therefore, the aim of this study was to develop a deep learning-based method for automatic classification of the sagittal skeletal pattern in children and to validate its performance. This would be the first step in establishing a decision support system for early orthodontic treatment. In this study, four different state-of-the-art (SOTA) models were trained and compared by using 1613 lateral cephalograms, and the best performance model, Densenet-121, was selected was further subsequent validation. Lateral cephalograms and profile photographs were used as the input for the Densenet-121 model, respectively. The models were optimized using transfer learning and data augmentation techniques, and label distribution learning was introduced during model training to address the inevitable label ambiguity between adjacent classes. Five-fold cross-validation was conducted for a comprehensive evaluation of our method. The sensitivity, specificity, and accuracy of the CNN model based on lateral cephalometric radiographs were 83.99, 92.44, and 90.33%, respectively. The accuracy of the model with profile photographs was 83.39%. The accuracy of both CNN models was improved to 91.28 and 83.98%, respectively, while the overfitting decreased after addition of label distribution learning. Previous studies have been based on adult lateral cephalograms. Therefore, our study is novel in using deep learning network architecture with lateral cephalograms and profile photographs obtained from children in order to obtain a high-precision automatic classification of the sagittal skeletal pattern in children.

Weighted Average Ensemble Deep Learning Model for Stratification of Brain Tumor in MRI Images

Brain tumor diagnosis at an early stage can improve the chances of successful treatment and better patient outcomes. In the biomedical industry, non-invasive diagnostic procedures, such as magnetic resonance imaging (MRI), can be used to diagnose brain tumors. Deep learning, a type of artificial intelligence, can analyze MRI images in a matter of seconds, reducing the time it takes for diagnosis and potentially improving patient outcomes. Furthermore, an ensemble model can help increase the accuracy of classification by combining the strengths of multiple models and compensating for their individual weaknesses. Therefore, in this research, a weighted average ensemble deep learning model is proposed for the classification of brain tumors. For the weighted ensemble classification model, three different feature spaces are taken from the transfer learning VGG19 model, Convolution Neural Network (CNN) model without augmentation, and CNN model with augmentation. These three feature spaces are ensembled with the best combination of weights, i.e., weight1, weight2, and weight3 by using grid search. The dataset used for simulation is taken from The Cancer Genome Atlas (TCGA), having a lower-grade glioma collection with 3929 MRI images of 110 patients. The ensemble model helps reduce overfitting by combining multiple models that have learned different aspects of the data. The proposed ensemble model outperforms the three individual models for detecting brain tumors in terms of accuracy, precision, and F1-score. Therefore, the proposed model can act as a second opinion tool for radiologists to diagnose the tumor from MRI images of the brain.

ATFE-Net: Axial Transformer and Feature Enhancement-based CNN for ultrasound breast mass segmentation

Breast mass is one of the main clinical symptoms of breast cancer. Recently, many CNN-based methods for breast mass segmentation have been proposed. However, these methods have difficulties in capturing long-range dependencies, causing poor segmentation of large-scale breast masses. In this paper, we propose an axial Transformer and feature enhancement-based CNN (ATFE-Net) for ultrasound breast mass segmentation. Specially, an axial Transformer (Axial-Trans) module and a Transformer-based feature enhancement (Trans-FE) module are proposed to capture long-range dependencies. Axial-Trans module only calculates self-attention in width and height directions of input feature maps, which reduces the complexity of self-attention significantly from O(n2) to O(n). In addition, Trans-FE module can enhance feature representation by capturing dependencies between different feature layers, since deeper feature layers have richer semantic information and shallower feature layers have more detailed information. The experimental results show that our ATFE-Net achieved better performance than several state-of-the-art methods on two publicly available breast ultrasound datasets, with Dice coefficient of 82.46% for BUSI and 86.78% for UDIAT, respectively.

High Dimensional Convolutional Neural Network for EEG Connectivity-Based Diagnosis of ADHD

Background

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adults and its early detection is effective in the successful treatment of children. Electroencephalography (EEG) has been widely used for classifying ADHD and normal children. In recent years, deep learning leads to more accurate classification.

Objective

This study aims to adapt convolutional neural networks (CNNs) for classifying ADHD and normal children based on the connectivity measure of their EEG signals.

Material and Methods

In this experimental study, the dataset consisted of 61 ADHD and 60 normal children from which 13021 epochs were extracted as input for model training and evaluation. Synchronization likelihood (SL) and wavelet coherence (WC) were considered connectivity measures. The neighborhood between EEG channels was arranged in a two-dimensional matrix for better representation. Four-dimensional (4D) and six-dimensional (6D) connectivity tensors were composed as model inputs. Two architectures were developed, one 4D and 6D CNN for SL and WC-based diagnosis of ADHD, respectively.

Results

A 5-fold cross-validation was utilized to assess developed models. The average accuracy of 98.56% for 4D CNN and 98.85% for 6D CNN in epoch-based classification were obtained. In the case of subject-based classification, the accuracy was 99.17% for both models.

Conclusion

Based on the evaluation metrics of the proposed models, ADHD children can be diagnosed and ADHD and normal children can be successfully distinguished.

Parallelistic Convolution Neural Network Approach for Brain Tumor Diagnosis

Today, Magnetic Resonance Imaging (MRI) is a prominent technique used in medicine, produces a significant and varied range of tissue contrasts in each imaging modalities, and is frequently employed by medical professionals to identify brain malignancies. With brain tumor being a very deadly disease, early detection will help increase the likelihood that the patient will receive the appropriate medical care leading to either a full elimination of the tumor or the prolongation of the patient’s life. However, manually examining the enormous volume of magnetic resonance imaging (MRI) images and identifying a brain tumor or cancer is extremely time-consuming and requires the expertise of a trained medical expert or brain doctor to manually detect and diagnose brain cancer using multiple Magnetic Resonance images (MRI) with various modalities. Due to this underlying issue, there is a growing need for increased efforts to automate the detection and diagnosis process of brain tumor without human intervention. Another major concern most research articles do not consider is the low quality nature of MRI images which can be attributed to noise and artifacts. This article presents a Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm to precisely handle the problem of low quality MRI images by eliminating noisy elements and enhancing the visible trainable features of the image. The enhanced image is then fed to the proposed PCNN to learn the features and classify the tumor using sigmoid classifier. To properly train the model, a publicly available dataset is collected and utilized for this research. Additionally, different optimizers and different values of dropout and learning rates are used in the course of this study. The proposed PCNN with Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm achieved an accuracy of 98.7%, sensitivity of 99.7%, and specificity of 97.4%. In comparison with other state-of-the-art brain tumor methods and pre-trained deep transfer learning models, the proposed PCNN model obtained satisfactory performance.

A Radiomics-Based Machine Learning Model for Prediction of Tumor Mutational Burden in Lower-Grade Gliomas

Simple Summary

Lower-grade glioma (LGG) is a kind of center nervous system neoplasm that arises from the glial cells. Lower-grade glioma patients have a median survival time in the range of 1.5–8 years based on the tumor genotypes. In term of epidemiology, most of the lower-grade glioma patients are diagnosed at young adult of age, which led to an early age of death. For exact diagnosis and effective treatment, a pathological result from biopsy sample is required. However, it is long turnaround time. In this study, using pre-operative magnetic resonance images, we developed a non-invasive model to classify tumor mutational burden (TMB), a prognostic factor of treatment response in lower-grade glioma patients, with an accuracy of 0.7936. To our knowledge, our study represents the best model for classification of TMB in LGG patients at present.

Abstract

Glioma is a Center Nervous System (CNS) neoplasm that arises from the glial cells. In a new scheme category of the World Health Organization 2016, lower-grade gliomas (LGGs) are grade II and III gliomas. Following the discovery of suppression of negative immune regulation, immunotherapy is a promising effective treatment method for lower-grade glioma patients. However, the therapy is not effective for all types of LGGs, and tumor mutational burden (TMB) has been shown to be a potential biomarker for the susceptibility and prognosis of immunotherapy in lower-grade glioma patients. Hence, predicting TMB benefits brain cancer patients. In this study, we investigated the correlation between MRI (magnetic resonance imaging)-based radiomic features and TMB in LGG by applying machine learning methods. Six machine learning classifiers were examined on the features extracted from the genetic algorithm. Subsequently, a light gradient boosting machine (LightGBM) succeeded in selecting 11 radiomics signatures for TMB classification. Our LightGBM model resulted in high accuracy of 0.7936, and reached a balance between sensitivity and specificity, achieving 0.76 and 0.8107, respectively. To our knowledge, our study represents the best model for classification of TMB in LGG patients at present.

Accurate Identification of ADHD among Adults Using Real-Time Activity Data

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopment disorder that affects millions of children and typically persists into adulthood. It must be diagnosed efficiently and consistently to receive adequate treatment, otherwise, it can have a detrimental impact on the patient’s professional performance, mental health, and relationships. In this work, motor activity data of adults suffering from ADHD and clinical controls has been preprocessed to obtain 788 activity-related statistical features. Afterwards, principal component analysis has been carried out to obtain significant features for accurate classification. These features are then fed into six different machine learning algorithms for classification, which include C4.5, kNN, Random Forest, LogitBoost, SVM, and Naive Bayes. The detailed evaluation of the results through 10-fold cross-validation reveals that SVM outperforms other classifiers with an accuracy of 98.43%, F-measure of 98.42%, sensitivity of 98.33%, specificity of 98.56% and AUC of 0.983. Thus, a PCA-based SVM approach appears to be an effective choice for accurate identification of ADHD patients among other clinical controls using real-time analysis of activity data.

Fault Diagnosis Method of Planetary Gearbox Based on Compressed Sensing and Transfer Learning

This paper suggests a novel method for diagnosing planetary gearbox faults. It addresses the issue of network bandwidth limitation during wireless data transmission and the problem of relying on expert experience and insufficient training samples in traditional fault diagnosis. The continuous wavelet transform was combined with the AlexNet convolutional neural network using transfer learning and the compressed theory of sense. The original vibration signal was compressed and reconstructed using the compressed sampling orthogonal matching pursuit reconstruction algorithm. A continuous wavelet transform was used to convert the compressed signal into a time–frequency image. The pretrained AlexNet model was selected as the migration object, the network model was fine-tuned and retrained, and the trained AlexNet model was used to diagnose the fault using the model-based migration method. It was demonstrated by the experimental results when the compression ratio CR = 0.5. Compared to other network models, the classification accuracy rate is 97.78%. This method has specific reference value and application prospects and good feature extraction and fault classification capabilities.

NDCN-Brain: An Extensible Dynamic Functional Brain Network Model

As an extension of the static network, the dynamic functional brain network can show continuous changes in the brain’s connections. Then, limited by the length of the fMRI signal, it is difficult to show every instantaneous moment in the construction of a dynamic network and there is a lack of effective prediction of the dynamic changes of the network after the signal ends. In this paper, an extensible dynamic brain function network model is proposed. The model utilizes the ability of extracting and predicting the instantaneous state of the dynamic network of neural dynamics on complex networks (NDCN) and constructs a dynamic network model structure that can provide more than the original signal range. Experimental results show that every snapshot in the network obtained by the proposed method has a usable network structure and that it also has a good classification result in the diagnosis of cognitive impairment diseases.

A content-based image retrieval system for the diagnosis of lymphoma using blood micrographs: An incorporation of deep learning with a traditional learning approach

Lymphomas, or cancers of the lymphatic system, account for around half of all blood cancers diagnosed each year. Lymphoma is a condition that is difficult to diagnose, and accurate diagnosis is critical for effective treatment. Manual microscopic analysis of blood cells requires the involvement of medical experts, whose precision is dependent on their abilities, and it takes time. This paper describes a content-based image retrieval system that uses deep learning-based feature extraction and a traditional learning method for feature reduction to retrieve similar images from a database to aid early/initial lymphoma diagnosis. The proposed algorithm employs a pre-trained network called ResNet-101 to extract image features required to distinguish four types of cells: lymphoma cells, blasts, lymphocytes, and other cells. The issue of class imbalance is resolved by over-sampling the training data followed by data augmentation. Deep learning features are extracted using the activations of the feature layer in the pre-trained net, then dimensionality reduction techniques are used to select discriminant features for the image retrieval system. Euclidean distance is used as the similarity measure to retrieve similar images from the database. The experimentation uses a microscopic blood image dataset with 1673 leukocytes of the categories blasts, lymphoma, lymphocytes, and other cells. The proposed algorithm achieves 98.74% precision in lymphoma cell classification and 99.22% precision @10 for lymphoma cell image retrieval. Experimental findings confirm our approach's practicability and effectiveness. Extended studies endorse the idea of using the prescribed system in actual medical applications, helping doctors diagnose lymphoma, dramatically reducing human resource requirements.

EPSPatNet86: eight-pointed star pattern learning network for detection ADHD disorder using EEG signals

Objective.The main objective of this work is to present a hand-modelled one-dimensional signal classification system to detect Attention-Deficit Hyperactivity Disorder (ADHD) disorder using electroencephalography (EEG) signals.Approach.A novel handcrafted feature extraction method is presented in this research. Our proposed method uses a directed graph and an eight-pointed star pattern (EPSPat). Also, tunable q wavelet transforms (TQWT), wavelet packet decomposition (WPD), statistical extractor, iterative Chi2 (IChi2) selector, and the k-nearest neighbors (kNN) classifier have been utilized to develop the EPSPat based learning model. This network uses two wavelet decomposition methods (TQWT and WPD), and 85 wavelet coefficient bands are extracted. The proposed EPSPat and statistical feature creator generate features from the 85 wavelet coefficient bands and the original EEG signal. The learning network is termed EPSPatNet86. The main purpose of the presented EPSPatNet86 is to detect abnormalities of the EEG signals. Therefore, 85 wavelet subbands have been generated to extract features. The created 86 feature vectors have been evaluated using the Chi2 selector and the kNN classifier in the loss value calculation phase. The final features vector is created by employing a minimum loss-valued eight feature vectors. The IChi2 selector selects the best feature vector, which is fed to the kNN classifier. An EEG signal dataset has been used to demonstrate the presented model's EEG signal classification ability. We have used an ADHD EEG dataset since ADHD is a commonly seen brain-related ailment.Main results.Our developed EPSPatNet86 model can detect the ADHD EEG signals with 97.19% and 87.60% accuracy using 10-fold cross and subject-wise validations, respectively.Significance.The calculated results demonstrate that the presented EPSPatNet86 attained satisfactory EEG classification ability. Results show that we can apply our developed EPSPatNet86 model to other EEG signal datasets to detect abnormalities.

Automatic Classification of Hepatic Cystic Echinococcosis Using Ultrasound Images and Deep Learning

BACKGROUND

Hepatic cystic echinococcosis is the main form of hepatic echinococcosis, which is a life-threatening liver disease caused by parasites that requires a precise diagnosis and proper treatment.

OBJECTIVE

This study focuses on the automatic classification system of five different subtypes of hepatic cystic echinococcosis based on ultrasound images and deep learning algorithms.

METHODS

Three popular deep convolutional neural networks (VGG19, Inception-v3, and ResNet18) with and without pretrained weights were selected to test their performance on the classification task, and the experiments were followed by a 5-fold cross-validation process.

RESULTS

A total of 1820 abdominal ultrasound images covering five subtypes of hepatic cystic echinococcosis from 967 patients were used in the study. The classification accuracy for the models with pretrained weights (fine-tuning) ranged from 88.2 to 90.6%. The best accuracy of 90.6% was obtained by VGG19. For comparison, the models without pretrained weights (from scratch) achieved a lower accuracy, ranging from 69.4 to 75.1%.

CONCLUSION

Deep convolutional neural networks with pretrained weights are capable of recognizing different subtypes of hepatic cystic echinococcosis from ultrasound images, which are expected to be applied in the computer-aided diagnosis systems in future work.

Automated classification of attention deficit hyperactivity disorder and conduct disorder using entropy features with ECG signals

BACKGROUND

The most prevalent neuropsychiatric disorder among children is attention deficit hyperactivity disorder (ADHD). ADHD presents with a high prevalence of comorbid disorders such as conduct disorder (CD). The lack of definitive confirmatory diagnostic tests for ADHD and CD make diagnosis challenging. The distinction between ADHD, ADHD + CD and CD is important as the course and treatment are different. Electrocardiography (ECG) signals may become altered in behavioral disorders due to brain-heart autonomic interactions. We have developed a software tool to categorize ADHD, ADHD + CD and CD automatically on ECG signals.

METHOD

ECG signals from participants were decomposed using empirical wavelet transform into various modes, from which entropy features were extracted. Robust ten-fold cross-validation with adaptive synthetic sampling (ADASYN) and z-score normalization were performed at each fold. Analysis of variance (ANOVA) technique was employed to determine the variability within the three classes, and obtained the most discriminatory features. Highly significant entropy features were then fed to classifiers.

RESULTS

Our model yielded the best classification results with the bagged tree classifier: 87.19%, 87.71% and 86.29% for accuracy, sensitivity and specificity, respectively.

CONCLUSION

The proposed expert system can potentially assist mental health professionals in the stratification of the three classes, for appropriate intervention using accessible ECG signals.

Deep diagnostic agent forest (DDAF): A deep learning pathogen recognition system for pneumonia based on CT

BACKGROUND

Even though antibiotics agents are widely used, pneumonia is still one of the most common causes of death around the world. Some severe, fast-spreading pneumonia can even cause huge influence on global economy and life security. In order to give optimal medication regimens and prevent infectious pneumonia's spreading, recognition of pathogens is important.

METHOD

In this single-institution retrospective study, 2,353 patients with their CT volumes are included, each of whom was infected by one of 12 known kinds of pathogens. We propose Deep Diagnostic Agent Forest (DDAF) to recognize the pathogen of a patient based on ones' CT volume, which is a challenging multiclass classification problem, with large intraclass variations and small interclass variations and very imbalanced data.

RESULTS

The model achieves 0.899 ± 0.004 multi-way area under curves of receiver (AUC) for level-I pathogen recognition, which are five rough groups of pathogens, and 0.851 ± 0.003 AUC for level-II recognition, which are 12 fine-level pathogens. The model also outperforms the average result of seven human readers in level-I recognition and outperforms all readers in level-II recognition, who can only reach an average result of 7.71 ± 4.10% accuracy.

CONCLUSION

Deep learning model can help in recognition pathogens using CTs only, which might help accelerate the process of etiological diagnosis.

Medical Images Encryption Based on Adaptive-Robust Multi-Mode Synchronization of Chen Hyper-Chaotic Systems

In this paper, a novel medical image encryption method based on multi-mode synchronization of hyper-chaotic systems is presented. The synchronization of hyper-chaotic systems is of great significance in secure communication tasks such as encryption of images. Multi-mode synchronization is a novel and highly complex issue, especially if there is uncertainty and disturbance. In this work, an adaptive-robust controller is designed for multimode synchronized chaotic systems with variable and unknown parameters, despite the bounded disturbance and uncertainty with a known function in two modes. In the first case, it is a main system with some response systems, and in the second case, it is a circular synchronization. Using theorems it is proved that the two synchronization methods are equivalent. Our results show that, we are able to obtain the convergence of synchronization error and parameter estimation error to zero using Lyapunov's method. The new laws to update time-varying parameters, estimating disturbance and uncertainty bounds are proposed such that stability of system is guaranteed. To assess the performance of the proposed synchronization method, various statistical analyzes were carried out on the encrypted medical images and standard benchmark images. The results show effective performance of the proposed synchronization technique in the medical images encryption for telemedicine application.