Diagnostics

Research

19 pages, 4173 KiB

Open AccessArticle

A Deep Learning-Based Automatic Segmentation and 3D Visualization Technique for Intracranial Hemorrhage Detection Using Computed Tomography Images

by Muntakim Mahmud Khan, Muhammad E. H. Chowdhury, A. S. M. Shamsul Arefin, Kanchon Kanti Podder, Md. Sakib Abrar Hossain, Abdulrahman Alqahtani, M. Murugappan, Amith Khandakar, Adam Mushtak and Md. Nahiduzzaman

Diagnostics 2023, 13(15), 2537; https://doi.org/10.3390/diagnostics13152537 - 31 Jul 2023

Cited by 5 | Viewed by 1955

Abstract

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and [...] Read more.

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and other potentially life-threatening complications. There are a wide range of severity levels, sizes, and morphologies of ICHs, making accurate identification challenging. Hemorrhages that are small are more likely to be missed, particularly in healthcare systems that experience high turnover when it comes to computed tomography (CT) investigations. Although many neuroimaging modalities have been developed, CT remains the standard for diagnosing trauma and hemorrhage (including non-traumatic ones). A CT scan-based diagnosis can provide time-critical, urgent ICH surgery that could save lives because CT scan-based diagnoses can be obtained rapidly. The purpose of this study is to develop a machine-learning algorithm that can detect intracranial hemorrhage based on plain CT images taken from 75 patients. CT images were preprocessed using brain windowing, skull-stripping, and image inversion techniques. Hemorrhage segmentation was performed using multiple pre-trained models on preprocessed CT images. A U-Net model with DenseNet201 pre-trained encoder outperformed other U-Net, U-Net++, and FPN (Feature Pyramid Network) models with the highest Dice similarity coefficient (DSC) and intersection over union (IoU) scores, which were previously used in many other medical applications. We presented a three-dimensional brain model highlighting hemorrhages from ground truth and predicted masks. The volume of hemorrhage was measured volumetrically to determine the size of the hematoma. This study is essential in examining ICH for diagnostic purposes in clinical practice by comparing the predicted 3D model with the ground truth. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

12 pages, 2331 KiB

Open AccessArticle

Identification of TLE Focus from EEG Signals by Using Deep Learning Approach

by Cansel Ficici, Ziya Telatar, Onur Kocak and Osman Erogul

Diagnostics 2023, 13(13), 2261; https://doi.org/10.3390/diagnostics13132261 - 04 Jul 2023

Viewed by 1128

Abstract

Temporal lobe epilepsy, a neurological disease that causes seizures as a result of excessive neural activities in the brain, is the most common type of focal seizure, accounting for 30–35% of all epilepsies. Detection of epilepsy and localization of epileptic focus are essential [...] Read more.

Temporal lobe epilepsy, a neurological disease that causes seizures as a result of excessive neural activities in the brain, is the most common type of focal seizure, accounting for 30–35% of all epilepsies. Detection of epilepsy and localization of epileptic focus are essential for treatment planning and epilepsy surgery. Currently, epileptic focus is decided by expert physician by examining the EEG records and determining EEG channel where epileptic patterns begins and continues intensely during seizure. Examination of long EEG recordings is very time-consuming process, requires attention and decision can vary depending on physician. In this study, to assist physicians in detecting epileptic focus side from EEG recordings, a novel deep learning-based computer-aided diagnosis system is presented. In the proposed framework, ictal epochs are detected using long short-term memory network fed with EEG subband features obtained by discrete wavelet transform, and then, epileptic focus identification is realized by using asymmetry score. This algorithm was tested on EEG database obtained from the Ankara University hospital. Experimental results showed ictal and interictal epochs were classified with accuracy of 86.84%, sensitivity of 86.96% and specificity of 89.68% on Ankara University hospital dataset, and 96.67% success rate was obtained on Bonn EEG dataset. In addition, epileptic focus was identified with accuracy of 96.10%, sensitivity of 100% and specificity of 93.80% by using the proposed deep learning-based algorithm and university hospital dataset. These results showed that proposed method can be used properly in clinical applications, epilepsy treatment and surgical planning as a medical decision support system. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

23 pages, 103553 KiB

Open AccessArticle

Evaluation of Emotions from Brain Signals on 3D VAD Space via Artificial Intelligence Techniques

by Ümran Işık, Ayşegül Güven and Turgay Batbat

Diagnostics 2023, 13(13), 2141; https://doi.org/10.3390/diagnostics13132141 - 22 Jun 2023

Cited by 1 | Viewed by 1213

Abstract

Recent achievements have made emotion studies a rising field contributing to many areas, such as health technologies, brain–computer interfaces, psychology, etc. Emotional states can be evaluated in valence, arousal, and dominance (VAD) domains. Most of the work uses only VA due to the [...] Read more.

Recent achievements have made emotion studies a rising field contributing to many areas, such as health technologies, brain–computer interfaces, psychology, etc. Emotional states can be evaluated in valence, arousal, and dominance (VAD) domains. Most of the work uses only VA due to the easiness of differentiation; however, very few studies use VAD like this study. Similarly, segment comparisons of emotion analysis with handcrafted features also use VA space. At this point, we primarily focused on VAD space to evaluate emotions and segmentations. The DEAP dataset is used in this study. A comprehensive analytical approach is implemented with two sub-studies: first, segmentation (Segments I–VIII), and second, binary cross-comparisons and evaluations of eight emotional states, in addition to comparisons of selected segments (III, IV, and V), class separation levels (5, 4–6, and 3–7), and unbalanced and balanced data with SMOTE. In both sub-studies, Wavelet Transform is applied to electroencephalography signals to separate the brain waves into their bands (α, β, γ, and θ bands), twenty-four attributes are extracted, and Sequential Minimum Optimization, K-Nearest Neighbors, Fuzzy Unordered Rule Induction Algorithm, Random Forest, Optimized Forest, Bagging, Random Committee, and Random Subspace are used for classification. In our study, we have obtained high accuracy results, which can be seen in the figures in the second part. The best accuracy result in this study for unbalanced data is obtained for Low Arousal–Low Valence–High Dominance and High Arousal–High Valence–Low Dominance emotion comparisons (Segment III and 4.5–5.5 class separation), and an accuracy rate of 98.94% is obtained with the IBk classifier. Data-balanced results mostly seem to outperform unbalanced results. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

12 pages, 801 KiB

Open AccessArticle

Constructing the Schizophrenia Recognition Method Employing GLCM Features from Multiple Brain Regions and Machine Learning Techniques

by Şerife Gengeç Benli and Merve Andaç

Diagnostics 2023, 13(13), 2140; https://doi.org/10.3390/diagnostics13132140 - 22 Jun 2023

Cited by 2 | Viewed by 1354

Abstract

Accurately diagnosing schizophrenia, a complex psychiatric disorder, is crucial for effectively managing the treatment process and methods. Various types of magnetic resonance (MR) images have the potential to serve as biomarkers for schizophrenia. The aim of this study is to numerically analyze differences [...] Read more.

Accurately diagnosing schizophrenia, a complex psychiatric disorder, is crucial for effectively managing the treatment process and methods. Various types of magnetic resonance (MR) images have the potential to serve as biomarkers for schizophrenia. The aim of this study is to numerically analyze differences in the textural characteristics that may occur in the bilateral amygdala, caudate, pallidum, putamen, and thalamus regions of the brain between individuals with schizophrenia and healthy controls via structural MR images. Towards this aim, Gray Level Co-occurence Matrix (GLCM) features obtained from five regions of the right, left, and bilateral brain were classified using machine learning methods. In addition, it was analyzed in which hemisphere these features were more distinctive and which method among Adaboost, Gradient Boost, eXtreme Gradient Boosting, Random Forest, k-Nearest Neighbors, Linear Discriminant Analysis (LDA), and Naive Bayes had higher classification success. When the results were examined, it was demonstrated that the GLCM features of these five regions in the left hemisphere could be classified as having higher performance in schizophrenia compared to healthy individuals. Using the LDA algorithm, classification success was achieved with a 100% AUC, 94.4% accuracy, 92.31% sensitivity, 100% specificity, and an F1 score of 91.9% in healthy and schizophrenic individuals. Thus, it has been revealed that the textural characteristics of the five predetermined regions, instead of the whole brain, are an important indicator in identifying schizophrenia. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

16 pages, 4623 KiB

Open AccessArticle

In-Domain Transfer Learning Strategy for Tumor Detection on Brain MRI

by Duygu Sinanc Terzi and Nuh Azginoglu

Diagnostics 2023, 13(12), 2110; https://doi.org/10.3390/diagnostics13122110 - 19 Jun 2023

Cited by 5 | Viewed by 1580

Abstract

Transfer learning has gained importance in areas where there is a labeled data shortage. However, it is still controversial as to what extent natural image datasets as pre-training sources contribute scientifically to success in different fields, such as medical imaging. In this study, [...] Read more.

Transfer learning has gained importance in areas where there is a labeled data shortage. However, it is still controversial as to what extent natural image datasets as pre-training sources contribute scientifically to success in different fields, such as medical imaging. In this study, the effect of transfer learning for medical object detection was quantitatively compared using natural and medical image datasets. Within the scope of this study, transfer learning strategies based on five different weight initialization methods were discussed. A natural image dataset MS COCO and brain tumor dataset BraTS 2020 were used as the transfer learning source, and Gazi Brains 2020 was used for the target. Mask R-CNN was adopted as a deep learning architecture for its capability to effectively handle both object detection and segmentation tasks. The experimental results show that transfer learning from the medical image dataset was found to be 10% more successful and showed 24% better convergence performance than the MS COCO pre-trained model, although it contains fewer data. While the effect of data augmentation on the natural image pre-trained model was 5%, the same domain pre-trained model was measured as 2%. According to the most widely used object detection metric, transfer learning strategies using MS COCO weights and random weights showed the same object detection performance as data augmentation. The performance of the most effective strategies identified in the Mask R-CNN model was also tested with YOLOv8. Results showed that even if the amount of data is less than the natural dataset, in-domain transfer learning is more efficient than cross-domain transfer learning. Moreover, this study demonstrates the first use of the Gazi Brains 2020 dataset, which was generated to address the lack of labeled and qualified brain MRI data in the medical field for in-domain transfer learning. Thus, knowledge transfer was carried out from the deep neural network, which was trained with brain tumor data and tested on a different brain tumor dataset. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

11 pages, 1054 KiB

Open AccessArticle

Distinguishing Parkinson’s Disease with GLCM Features from the Hankelization of EEG Signals

by Mehmet Fatih Karakaş and Fatma Latifoğlu

Diagnostics 2023, 13(10), 1769; https://doi.org/10.3390/diagnostics13101769 - 17 May 2023

Cited by 3 | Viewed by 1264

Abstract

This study proposes a novel method that uses electroencephalography (EEG) signals to classify Parkinson’s Disease (PD) and demographically matched healthy control groups. The method utilizes the reduced beta activity and amplitude decrease in EEG signals that are associated with PD. The study involved [...] Read more.

This study proposes a novel method that uses electroencephalography (EEG) signals to classify Parkinson’s Disease (PD) and demographically matched healthy control groups. The method utilizes the reduced beta activity and amplitude decrease in EEG signals that are associated with PD. The study involved 61 PD patients and 61 demographically matched controls groups, and EEG signals were recorded in various conditions (eyes closed, eyes open, eyes both open and closed, on-drug, off-drug) from three publicly available EEG data sources (New Mexico, Iowa, and Turku). The preprocessed EEG signals were classified using features obtained from gray-level co-occurrence matrix (GLCM) features through the Hankelization of EEG signals. The performance of classifiers with these novel features was evaluated using extensive cross-validations (CV) and leave-one-out cross-validation (LOOCV) schemes. This method under 10 × 10 fold CV, the method was able to differentiate PD groups from healthy control groups using a support vector machine (SVM) with an accuracy of 92.4 ± 0.01, 85.7 ± 0.02, and 77.1 ± 0.06 for New Mexico, Iowa, and Turku datasets, respectively. After a head-to-head comparison with state-of-the-art methods, this study showed an increase in the classification of PD and controls. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

25 pages, 3837 KiB

Open AccessArticle

Quantitative Brain MRI Metrics Distinguish Four Different ALS Phenotypes: A Machine Learning Based Study

by Venkateswaran Rajagopalan, Krishna G. Chaitanya and Erik P. Pioro

Diagnostics 2023, 13(9), 1521; https://doi.org/10.3390/diagnostics13091521 - 24 Apr 2023

Cited by 5 | Viewed by 1794

Abstract

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease whose diagnosis depends on the presence of combined lower motor neuron (LMN) and upper motor neuron (UMN) degeneration. LMN degeneration assessment is aided by electromyography, whereas no equivalent exists to assess UMN dysfunction. Magnetic [...] Read more.

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease whose diagnosis depends on the presence of combined lower motor neuron (LMN) and upper motor neuron (UMN) degeneration. LMN degeneration assessment is aided by electromyography, whereas no equivalent exists to assess UMN dysfunction. Magnetic resonance imaging (MRI) is primarily used to exclude conditions that mimic ALS. We have identified four different clinical/radiological phenotypes of ALS patients. We hypothesize that these ALS phenotypes arise from distinct pathologic processes that result in unique MRI signatures. To our knowledge, no machine learning (ML)-based data analyses have been performed to stratify different ALS phenotypes using MRI measures. During routine clinical evaluation, we obtained T1-, T2-, PD-weighted, diffusion tensor (DT) brain MRI of 15 neurological controls and 91 ALS patients (UMN-predominant ALS with corticospinal tract CST) hyperintensity, n = 21; UMN-predominant ALS without CST hyperintensity, n = 26; classic ALS, n = 23; and ALS patients with frontotemporal dementia, n = 21). From these images, we obtained 101 white matter (WM) attributes (including DT measures, graph theory measures from DT and fractal dimension (FD) measures using T1-weighted), 10 grey matter (GM) attributes (including FD based measures from T1-weighted), and 10 non-imaging attributes (2 demographic and 8 clinical measures of ALS). We employed classification and regression tree, Random Forest (RF) and also artificial neural network for the classifications. RF algorithm provided the best accuracy (70–94%) in classifying four different phenotypes of ALS patients. WM metrics played a dominant role in classifying different phenotypes when compared to GM or clinical measures. Although WM measures from both right and left hemispheres need to be considered to identify ALS phenotypes, they appear to be differentially affected by the degenerative process. Longitudinal studies can confirm and extend our findings. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

19 pages, 6407 KiB

Open AccessArticle

An Ensemble of Deep Learning Object Detection Models for Anatomical and Pathological Regions in Brain MRI

by Ramazan Terzi

Diagnostics 2023, 13(8), 1494; https://doi.org/10.3390/diagnostics13081494 - 20 Apr 2023

Cited by 1 | Viewed by 2190

Abstract

This paper proposes ensemble strategies for the deep learning object detection models carried out by combining the variants of a model and different models to enhance the anatomical and pathological object detection performance in brain MRI. In this study, with the help of [...] Read more.

This paper proposes ensemble strategies for the deep learning object detection models carried out by combining the variants of a model and different models to enhance the anatomical and pathological object detection performance in brain MRI. In this study, with the help of the novel Gazi Brains 2020 dataset, five different anatomical parts and one pathological part that can be observed in brain MRI were identified, such as the region of interest, eye, optic nerves, lateral ventricles, third ventricle, and a whole tumor. Firstly, comprehensive benchmarking of the nine state-of-the-art object detection models was carried out to determine the capabilities of the models in detecting the anatomical and pathological parts. Then, four different ensemble strategies for nine object detectors were applied to boost the detection performance using the bounding box fusion technique. The ensemble of individual model variants increased the anatomical and pathological object detection performance by up to 10% in terms of the mean average precision (mAP). In addition, considering the class-based average precision (AP) value of the anatomical parts, an up to 18% AP improvement was achieved. Similarly, the ensemble strategy of the best different models outperformed the best individual model by 3.3% mAP. Additionally, while an up to 7% better FAUC, which is the area under the TPR vs. FPPI curve, was achieved on the Gazi Brains 2020 dataset, a 2% better FAUC score was obtained on the BraTS 2020 dataset. The proposed ensemble strategies were found to be much more efficient in finding the anatomical and pathological parts with a small number of anatomic objects, such as the optic nerve and third ventricle, and producing higher TPR values, especially at low FPPI values, compared to the best individual methods. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

27 pages, 4518 KiB

Open AccessArticle

Quantitative Electroencephalography Analysis for Improved Assessment of Consciousness Levels in Deep Coma Patients Using a Proposed Stimulus Stage

by Çiğdem Gülüzar Altıntop, Fatma Latifoğlu, Aynur Karayol Akın and Ayşe Ülgey

Diagnostics 2023, 13(8), 1383; https://doi.org/10.3390/diagnostics13081383 - 10 Apr 2023

Cited by 1 | Viewed by 2215

Abstract

“Coma” is defined as an inability to obey commands, to speak, or to open the eyes. So, a coma is a state of unarousable unconsciousness. In a clinical setting, the ability to respond to a command is often used to infer consciousness. Evaluation [...] Read more.

“Coma” is defined as an inability to obey commands, to speak, or to open the eyes. So, a coma is a state of unarousable unconsciousness. In a clinical setting, the ability to respond to a command is often used to infer consciousness. Evaluation of the patient’s level of consciousness (LeOC) is important for neurological evaluation. The Glasgow Coma Scale (GCS) is the most widely used and popular scoring system for neurological evaluation and is used to assess a patient’s level of consciousness. The aim of this study is the evaluation of GCSs with an objective approach based on numerical results. So, EEG signals were recorded from 39 patients in a coma state with a new procedure proposed by us in a deep coma state (GCS: between 3 and 8). The EEG signals were divided into four sub-bands as alpha, beta, delta, and theta, and their power spectral density was calculated. As a result of power spectral analysis, 10 different features were extracted from EEG signals in the time and frequency domains. The features were statistically analyzed to differentiate the different LeOC and to relate with the GCS. Additionally, some machine learning algorithms have been used to measure the performance of the features for distinguishing patients with different GCSs in a deep coma. This study demonstrated that GCS 3 and GCS 8 patients were classified from other levels of consciousness in terms of decreased theta activity. To the best of our knowledge, this is the first study to classify patients in a deep coma (GCS between 3 and 8) with 96.44% classification performance. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Graphical abstract

24 pages, 6851 KiB

Open AccessArticle

A Novel Automatic Audiometric System Design Based on Machine Learning Methods Using the Brain’s Electrical Activity Signals

by Mustafa Küçükakarsu, Ahmet Reşit Kavsaoğlu, Fayadh Alenezi, Adi Alhudhaif, Raghad Alwadie and Kemal Polat

Diagnostics 2023, 13(3), 575; https://doi.org/10.3390/diagnostics13030575 - 03 Feb 2023

Cited by 1 | Viewed by 2133

Abstract

This study uses machine learning to perform the hearing test (audiometry) processes autonomously with EEG signals. Sounds with different amplitudes and wavelengths given to the person tested in standard hearing tests are assigned randomly with the interface designed with MATLAB GUI. The person [...] Read more.

This study uses machine learning to perform the hearing test (audiometry) processes autonomously with EEG signals. Sounds with different amplitudes and wavelengths given to the person tested in standard hearing tests are assigned randomly with the interface designed with MATLAB GUI. The person stated that he heard the random size sounds he listened to with headphones but did not take action if he did not hear them. Simultaneously, EEG (electro-encephalography) signals were followed, and the waves created in the brain by the sounds that the person attended and did not hear were recorded. EEG data generated at the end of the test were pre-processed, and then feature extraction was performed. The heard and unheard information received from the MATLAB interface was combined with the EEG signals, and it was determined which sounds the person heard and which they did not hear. During the waiting period between the sounds given via the interface, no sound was given to the person. Therefore, these times are marked as not heard in EEG signals. In this study, brain signals were measured with Brain Products Vamp 16 EEG device, and then EEG raw data were created using the Brain Vision Recorder program and MATLAB. After the data set was created from the signal data produced by the heard and unheard sounds in the brain, machine learning processes were carried out with the PYTHON programming language. The raw data created with MATLAB was taken with the Python programming language, and after the pre-processing steps were completed, machine learning methods were applied to the classification algorithms. Each raw EEG data has been detected by the Count Vectorizer method. The importance of each EEG signal in all EEG data has been calculated using the TF-IDF (Term Frequency-Inverse Document Frequency) method. The obtained dataset has been classified according to whether people can hear the sound. Naïve Bayes, Light Gradient Strengthening Machine (LGBM), support vector machine (SVM), decision tree, k-NN, logistic regression, and random forest classifier algorithms have been applied in the analysis. The algorithms selected in our study were preferred because they showed superior performance in ML and succeeded in analyzing EEG signals. Selected classification algorithms also have features of being used online. Naïve Bayes, Light Gradient Strengthening Machine (LGBM), support vector machine (SVM), decision tree, k-NN, logistic regression, and random forest classifier algorithms were used. In the analysis of EEG signals, Light Gradient Strengthening Machine (LGBM) was obtained as the best method. It was determined that the most successful algorithm in prediction was the prediction of the LGBM classification algorithm, with a success rate of 84%. This study has revealed that hearing tests can also be performed using brain waves detected by an EEG device. Although a completely independent hearing test can be created, an audiologist or doctor may be needed to evaluate the results. Full article

(This article belongs to the Special Issue Application of Deep Learning in the Diagnosis of Brain Diseases)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Application of Deep Learning in the Diagnosis of Brain Diseases

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI