The impact of deep learning on diagnostic performance in the differentiation of benign and malignant thyroid nodules.

AIMS: This study aims to use deep learning (DL) to classify thyroid nodules as benign and malignant with ultrasonography (US). In addition, this study investigates the impact of DL on the diagnostic success of radiologists with different experiences. Material and methods: This study included 576 US images of thyroid nodules. The dataset was divided into 80% training and 20% test sets. Four radiologists with different levels of experience classified the images in the test set as benign-malignant. A DL model was then trained with the train set and predicted benign-malignant for the test set. Then, the output of the DL model for each nodule in the test set was presented to 4 radiologists, who were asked to make a benign-malignant classification again considering these DL results. RESULTS: The accuracy of the DL model was 0.9391. The accuracy for junior resident (JR) 1, JR 2, senior resident (SR), and senior radiologist (Srad) before DL-assisting were 0.7043, 0.7826, 0.8435, and 0.8522 respectively. The accuracy in DL-assisted classifications was 0.9130, 0.8696, 0.9304, and 0.9043 for JR 1, JR2, SR, and Srad, respectively. DL assistance changed the decisions of less experienced radiologists more than more experienced radiologists. Conclusion: The DL model has superior accuracy in classifying thyroid nodules as benign-malignant with US images than radiologists with different levels of experience. Additionally, all radiologists, and most notably less experienced radiology residents, increased their accuracy in DL-assisted predictions.

MR Image Fusion-Based Parotid Gland Tumor Detection.

The differentiation of benign and malignant parotid gland tumors is of major significance as it directly affects the treatment process. In addition, it is also a vital task in terms of early and accurate diagnosis of parotid gland tumors and the determination of treatment planning accordingly. As in other diseases, the differentiation of tumor types involves several challenging, time-consuming, and laborious processes. In the study, Magnetic Resonance (MR) images of 114 patients with parotid gland tumors are used for training and testing purposes by Image Fusion (IF). After the Apparent Diffusion Coefficient (ADC), Contrast-enhanced T1-w (T1C-w), and T2-w sequences are cropped, IF (ADC, T1C-w), IF (ADC, T2-w), IF (T1C-w, T2-w), and IF (ADC, T1C-w, T2-w) datasets are obtained for different combinations of these sequences using a two-dimensional Discrete Wavelet Transform (DWT)-based fusion technique. For each of these four datasets, ResNet18, GoogLeNet, and DenseNet-201 architectures are trained separately, and thus, 12 models are obtained in the study. A Graphical User Interface (GUI) application that contains the most successful of these trained architectures for each data is also designed to support the users. The designed GUI application not only allows the fusing of different sequence images but also predicts whether the label of the fused image is benign or malignant. The results show that the DenseNet-201 models for IF (ADC, T1C-w), IF (ADC, T2-w), and IF (ADC, T1C-w, T2-w) are better than the others, with accuracies of 95.45%, 95.96%, and 92.93%, respectively. It is also noted in the study that the most successful model for IF (T1C-w, T2-w) is ResNet18, and its accuracy is equal to 94.95%.

An Enhanced Mask R-CNN Approach for Pulmonary Embolism Detection and Segmentation.

Pulmonary embolism (PE) refers to the occlusion of pulmonary arteries by blood clots, posing a mortality risk of approximately 30%. The detection of pulmonary embolism within segmental arteries presents greater challenges compared with larger arteries and is frequently overlooked. In this study, we developed a computational method to automatically identify pulmonary embolism within segmental arteries using computed tomography (CT) images. The system architecture incorporates an enhanced Mask R-CNN deep neural network trained on PE-containing images. This network accurately localizes pulmonary embolisms in CT images and effectively delineates their boundaries. This study involved creating a local data set and evaluating the model predictions against pulmonary embolisms manually identified by expert radiologists. The sensitivity, specificity, accuracy, Dice coefficient, and Jaccard index values were obtained as 96.2%, 93.4%, 96.%, 0.95, and 0.89, respectively. The enhanced Mask R-CNN model outperformed the traditional Mask R-CNN and U-Net models. This study underscores the influence of Mask R-CNN's loss function on model performance, providing a basis for the potential improvement of Mask R-CNN models for object detection and segmentation tasks in CT images.

Neural decoding of inferior colliculus multiunit activity for sound category identification with temporal correlation and transfer learning.

Natural sounds are easily perceived and identified by humans and animals. Despite this, the neural transformations that enable sound perception remain largely unknown. It is thought that the temporal characteristics of sounds may be reflected in auditory assembly responses at the inferior colliculus (IC) and which may play an important role in identification of natural sounds. In our study, natural sounds will be predicted from multi-unit activity (MUA) signals collected in the IC. Data is obtained from an international platform publicly accessible. The temporal correlation values of the MUA signals are converted into images. We used two different segment sizes and with a denoising method, we generated four subsets for the classification. Using pre-trained convolutional neural networks (CNNs), features of the images were extracted and the type of heard sound was classified. For this, we applied transfer learning from Alexnet, Googlenet and Squeezenet CNNs. The classifiers support vector machines (SVM), k-nearest neighbour (KNN), Naive Bayes and Ensemble were used. The accuracy, sensitivity, specificity, precision and F1 score were measured as evaluation parameters. By using all the tests and removing the noise, the accuracy improved significantly. These results will allow neuroscientists to make interesting conclusions.

Can Chat GPT be Utilized in Scientific and Undergraduate Studies?

In this study, we are investigating the academic usability of Chat GPT, which has been gaining increasing popularity recently, as well as its potential for use in undergraduate study. In this context, based on our experiments, we believe that Chat GPT needs further development in certain aspects. While it shows promising potential for academic research in the future, currently, it can be stated that there is a need for improvement in this regard. But we foresee that Chat GPT can be used more effectively in undergraduate study. In our experience, Chat GPT has provided very reasonable results in this regard.

Deep Network-Based Comprehensive Parotid Gland Tumor Detection.

RATIONALE AND OBJECTIVES: Salivary gland tumors constitute 2%-6% of all head and neck tumors and are most common in the parotid gland. Magnetic resonance (MR) imaging is the most sensitive imaging modality for diagnosis. Tumor type, localization, and relationship with surrounding structures are important factors for treatment. Therefore, parotid gland tumor segmentation is important. Specialists widely use manual segmentation in diagnosis and treatment. However, considering the development of artificial intelligence-based models today, it is seen that artificial intelligence-based automatic segmentation models can be used instead of manual segmentation, which is a time-consuming technique. Therefore, we segmented parotid gland tumor (PGT) using deep learning-based architectures in the paper. MATERIALS AND METHODS: The dataset used in the study includes 102 T1-w, 102 contrast-enhanced T1-w (T1C-w), and 102 T2-w MR images. After cropping the raw and manually segmented images by experts, we obtained the masks of these images. After standardizing the image sizes, we split these images into approximately 80% training set and 20% test set. Hereabouts, we trained six models for these images using ResNet18 and Xception-based DeepLab v3+. We prepared a user-friendly Graphical User Interface application that includes each of these models. RESULTS: From the results, the accuracy and weighted Intersection over Union values of the ResNet18-based DeepLab v3+ architecture trained for T1C-w, which is the most successful model in the study, are equal to 0.96153 and 0.92601, respectively. Regarding the results and the literature, it can be seen that the proposed system is competitive in terms of both using MR images and training the models independently for T1-w, T1C-w, and T2-w. Expressing that PGT is usually segmented manually in the literature, we predict that our study can contribute significantly to the literature. CONCLUSION: In this study, we prepared and presented a software application that can be easily used by users for automatic PGT segmentation. In addition to predicting the reduction of costs and workload through the study, we developed models with meaningful performance metrics according to the literature.

LSS-VGG16: Diagnosis of Lumbar Spinal Stenosis With Deep Learning.

STUDY DESIGN: This was a retrospective study. OBJECTION: Lumbar Spinal Stenosis (LSS) is a disease that causes chronic low back pain and can often be confused with herniated disk. In this study, a deep learning-based classification model is proposed to make LSS diagnosis quickly and automatically with an objective tool. SUMMARY OF BACKGROUND DATA: LSS is a disease that causes negative consequences such as low back pain, foot numbness, and pain. Diagnosis of this disease is difficult because it is confused with herniated disk and requires serious expertise. The shape and amount of this stenosis are very important in deciding the surgery and the surgical technique to be applied in these patients. When the spinal canal narrows, as a result of compression on these nerves and/or pressure on the vessels feeding the nerves, poor nutrition of the nerves causes loss of function and structure. Image processing techniques are applied in biomedical images such as MR and CT and high classification success is achieved. In this way, computer-aided diagnosis systems can be realized to help the specialist in the diagnosis of different diseases. METHODS: To demonstrate the success of the proposed model, different deep learning methods and traditional machine learning techniques have been studied. RESULTS: The highest classification success was obtained in the VGG16 method, with 87.70%. CONCLUSIONS: The proposed LSS-VGG16 model reveals that a computer-aided diagnosis system can be created for the diagnosis of spinal canal stenosis. In addition, it was observed that higher classification success was achieved compared with similar studies in the literature. This shows that the proposed LSS-VGG16 model will be an important resource for scientists who will work in this field.

Biphasic majority voting-based comparative COVID-19 diagnosis using chest X-ray images.

The COVID-19 pandemic has been affecting the world since December 2019, and nowadays, the number of infected is increasing rapidly. Chest X-ray images are clinical adjuncts that can be used in the diagnosis of COVID-19 disease. Because of the rapid spread of COVID-19 disease worldwide and the limited number of expert radiologists, the proposed method uses the automatic diagnosis method rather than a manual diagnosis method. In the paper, COVID-19 Positive/Negative (2275 Positive, 4626 Negative) and Normal/Pneumonia (2313 Normal, 2313 Pneumonia) are diagnosed using chest X-ray images. Herein, 80 % and 20 % of the images are used in the training and validation set, respectively. In the proposed method, six different classifiers are trained using chest X-ray images, and the five most successful classifiers are used in both phases. In Phase-1 and Phase-2, image features are extracted using the Bag of Features method for Cosine K-Nearest Neighbor (KNN), Linear Discriminant, Logistic Regression, Bagged Trees Ensemble, Medium Gaussian Support Vector Machine (SVM), excluding SqueezeNet Deep Learning (K = 2000 and K = 1500 for Phase-1 and Phase-2, respectively). In both phases, the five most successful classifiers are determined, and images classify with the help of the Majority Voting (Mathematical Evaluation) method. The application of the proposed method is designed for users to diagnose COVID-19 Positive, Normal, and Pneumonia. The results show that accuracy values obtained by Majority Voting (Mathematical Evaluation) method for Phase-1 and Phase-2 are equal to 99.86 % and 99.28 %, respectively. Thus, it indicates that the accuracy of the whole system is 99.63 %. When we analyze the classification performance metrics for Phase-1 and Phase-2, Specificity (%), Precision (%), Recall (%), F1 Score (%), Area Under Curve (AUC), and Matthews Correlation Coefficient (MCC) are equal to 99.98-99.83-99.07-99.51-0.9974-0.9855 and 99.73-99.69-98.63-99.23-0.9928-0.9518, respectively. Moreover, if the classification performance metrics of the whole system are examined, it is seen that Specificity (%), Precision (%), Recall (%), F1 Score (%), AUC, and MCC are 99.88, 99.78, 98.90, 99.40, 0.9956, and 0.9720, respectively. When the studies in the literature are examined, the results show that the proposed model is better than its counterparts. Because the best performance metrics for the dataset used were obtained in this study. In addition, since the biphasic majority voting technique is used in the study, it is seen that the proposed model is more reliable. On the other hand, although there are tens of thousands of studies on this subject, the usability of these models is debatable since most of them do not have graphical user interface applications. Already, in artificial intelligence technologies, besides the performance of the developed models, their usability is also important. Because the developed models can generally be used by people who are less knowledgeable about artificial intelligence.

Automatic Diagnosis of Attention Deficit Hyperactivity Disorder with Continuous Wavelet Transform and Convolutional Neural Network.

Objective: The attention deficit hyperactivity disorder has a negative impact on the child's educational life and relationships with the social environment during childhood and adolescence. The connection between temperament traits and The attention deficit hyperactivity disorder has been proven by various studies. As far as we know, there is no machine learning study to diagnose. The attention deficit hyperactivity disorder in a dataset created using temperament characteristics. Methods: Machine learning-based semi-automatic/fully automatic expert decision support systems are frequently used for the diagnosis of various diseases. In this study, it was aimed to reveal the success of a semi-automatic expert decision support system in the diagnosis of attention deficit hyperactivity disorder by using temperament characteristics. The high classification success achieved is a resource for a potential diagnosis of attention deficit hyperactivity disorder expert decision support system. In this respect, this study includes original qualities and innovations. Results: Many different deep learning methods were used in the research. Deep learning methods are models that achieve high success by using a large number of images in various image processing competitions. The images of the signals in the data set were first obtained by Continuous Wavelet Transform. The highest classification success in our data set was obtained with the Squeeze Net model with 88.33%. Conclusion: The model we propose shows that an automatic system based on artificial intelligence can be created, as well as revealing the relationship between temperament characteristics in the diagnosis of attention deficit hyperactivity in the data set we created.

Detection of microaneurysms using ant colony algorithm in the early diagnosis of diabetic retinopathy.

Microaneurysms are lesions in the shape of small circular dilations which result from thinning in peripheral retinal blood vessels due to diabetes and increasing intra-retinal blood pressure. Because it is considered as the most important clinical finding in the diagnosis of diabetic retinopathy, accurate detection of these lesions bear utmost importance in the early diagnosis of diabetic retinopathy. The present study aims to accurately, effectively and automatically detect microaneurysms which are difficult to detect in color fundus images in early stage. To this aim, ant colony algorithm, which is an important optimization method, was used instead of conventional image processing techniques. First, retinal vascular structure was extracted from color fundus images in Messidor and DiaretDB1 data sets. Afterwards, the segmentation of microaneurysms was effectively carried out using ant colony algorithm. The same procedure was also applied to five different image processing and clustering algorithms (watershed, random walker, k-means, maximum entropy and region growing) in order to compare the performance of the proposed method with other methods. Microaneurysm images manually detected by a specialist eye doctor were used to measure the performances of above-mentioned methods. The similarities among microaneurysms which were automatically and manually segmented were tested using Dice and Jaccard similarity index values. Dice index values obtained from the study vary between 0.52 and 0.98 in maximum entropy, 0.55 and 0.88 in watershed, 0.75 and 0.86 in region growing, 0.55 and 0.78 in k-means, and 0.66 and 0.83 in random walker, and 0.81 and 0.9 in ant colony. Similar performance values were also obtained in Jaccard index. The results show that different performances were observed in the conventional segmentation of microaneurysms depending on the image quality. On the other hand, the ant colony based method proposed in this paper displays a more stabilized and higher performance irrespective of image contrast. Therefore, it is evident that the proposed method successfully detects microaneurysms even in low quality images, thus helping specialists diagnose them in an easier way.

Voice Acoustic Analysis of Pediatric Vocal Nodule Patients Using Ratios Calculated With Biomedical Image Segmentation.

OBJECTIVE: The aim of this study was to determine nodules using newly developed software with a computer-assisted visual process technique for the calculation of size. The effects of the ratios of nodule base and width were evaluated with voice acoustic analysis. METHODS: A total of 72 patients with pediatric vocal nodule were evaluated. Nodules were marked with the ImageJ News program on photographs obtained from the video recordings in the videostroboscopic examination and classified according to the Shah et al scale. Segmentation was applied automatically. The ratios were taken as base of nodule/width and base of nodule/vocal cord. In the voice acoustic analysis, basic frequencies (mean F0), jitter (local %), shimmer (local %), and harmonicity (mean harmonics-to-noise [mean HNR]) were evaluated. RESULTS: A statistically significant negative correlation was determined between the mean F0 value and the nodule base/width ratio (P = 0.042, r = -0.240). A negative statistically significant relationship was determined between jitter (%) and vocal nodule base/width (P = 0.009, r = -0.305). A statistically significant positive correlation was determined between mean HNR and vocal nodule base/width (P = 0.034, r = 0.324). In discriminant analysis, correct classification of the Shah et al scale degrees of the classifying variables was 73.6%. CONCLUSION: Through collaboration with the biomedical engineering department, the results of this study determined new ratios in patients with pediatric vocal nodule. In voice acoustic analysis, the mean F0 was more affected by the width of the nodule, mean HNR was affected by the length of the base of the nodule, and jitter (%) was affected by the width of the nodule.

Visual Interpretation of Biomedical Time Series Using Parzen Window-Based Density-Amplitude Domain Transformation.

This study proposes a new method suitable for the visual analysis of biomedical time series that is based on the examination of biomedical signals in the density-amplitude domain. Toward this goal, we employed two publicly available datasets. In the first stage of the study, density coefficients were computed separately by using the Parzen Windowing method for each class of raw attribute data. Then, differences between classes were determined visually by using density coefficients and their related amplitudes. Visual interpretation of the processed data gave more successful classification results compared with the raw data in the first stage. Next the density-amplitude representations of the raw data were classified using classifiers (SVM, KNN and Naïve Bayes). The raw data (time-amplitude) and their frequency-amplitude representation were also classified using the same classification methods. The statistical results showed that the proposed method based on the density-amplitude representation increases the classification success up to 55% compared with methods using the time-amplitude domain and up to 75% compared with methods based on the frequency-amplitude domain. Finally, we have highlighted several statistical analysis suggestions as a result of the density-amplitude representation.

Classification of EEG recordings by using fast independent component analysis and artificial neural network.

Since there is no definite decisive factor evaluated by the experts, visual analysis of EEG signals in time domain may be inadequate. Routine clinical diagnosis requests to analysis of EEG signals. Therefore, a number of automation and computer techniques have been used for this aim. In this study we aim at designing a MLPNN classifier based on the Fast ICA that accurately identifies whether the associated subject is normal or epileptic. By analyzing a data set consisting of 100 normal and 100 epileptic EEG time series, we have found that the MLPNN classifier based on the Fast ICA achieved and sensitivity rate of 98%, and specificity rate of 90.5%. The results demonstrate that the testing performance of the neural network diagnostic system is found to be satisfactory and we think that this system can be used in clinical studies. Since the time series analysis of EEG signals is unsatisfactory and requires specialist clinicians to evaluate, this application brings objectivity to the evaluation of EEG signals.

Comparison of subspace-based methods with AR parametric methods in epileptic seizure detection.

Electroencephalography is an important clinical tool for the evaluation and treatment of neurophysiologic disorders related to epilepsy. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. In this study, we have proposed subspace-based methods to analyze and characterize epileptiform discharges in the form of 3-Hz spike and wave complex in patients with absence seizure. The variations in the shape of the EEG power spectra were examined in order to obtain medical information. These power spectra were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of epileptic seizure. Global performance of the proposed methods was evaluated by means of the visual inspection of power spectral densities (PSDs). Graphical results comparing the performance of the proposed methods with that of the autoregressive techniques were given. The results demonstrate consistently superior performance of the proposed methods over the autoregressive ones.

Comparison of AR and Welch methods in epileptic seizure detection.

Brain is one of the most critical organs of the body. Synchronous neuronal discharges generate rhythmic potential fluctuations, which can be recorded from the scalp through electroencephalography. The electroencephalogram (EEG) can be roughly defined as the mean electrical activity measured at different sites of the head. EEG patterns correlated with normal functions and diseases of the central nervous system. In this study, EEG signals were analyzed by using autoregressive (parametric) and Welch (non-parametric) spectral estimation methods. The parameters of autoregressive (AR) method were estimated by using Yule-Walker, covariance and modified covariance methods. EEG spectra were then used to compare the applied estimation methods in terms of their frequency resolution and the effects in determination of spectral components. The variations in the shape of the EEG power spectra were examined in order to epileptic seizures detection. Performance of the proposed methods was evaluated by means of power spectral densities (PSDs). Graphical results comparing the performance of the proposed methods with that of Welch technique were given. The results demonstrate consistently superior performance of the covariance methods over Yule-Walker AR and Welch methods.

Automatic seizure detection in EEG using logistic regression and artificial neural network.

The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. In this study, multiple signal classification (MUSIC), autoregressive (AR) and periodogram methods were used to get power spectra in patients with absence seizure. The EEG power spectra were used as an input to a classifier. We introduce two fundamentally different approaches for designing classification models (classifiers); the traditional statistical method based on logistic regression (LR) and the emerging computationally powerful techniques based on artificial neural networks (ANNs). LR as well as multilayer perceptron neural network (MLPNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The MLPNN based classifier outperformed the LR based counterpart. Within the same group, the MLPNN-based classifier was more accurate than the LR-based classifier.

Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing.

Since EEG is one of the most important sources of information in therapy of epilepsy, several researchers tried to address the issue of decision support for such a data. In this paper, we introduce two fundamentally different approaches for designing classification models (classifiers); the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on artificial neural networks (ANNs). Logistic regression as well as feedforward error backpropagation artificial neural networks (FEBANN) and wavelet neural networks (WNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. In these methods we used FFT and autoregressive (AR) model by using maximum likelihood estimation (MLE) of EEG signals as an input to classification system with two discrete outputs: epileptic seizure or nonepileptic seizure. By identifying features in the signal we want to provide an automatic system that will support a physician in the diagnosing process. By applying AR with MLE in connection with WNN, we obtained novel and reliable classifier architecture. The network is constructed by the error backpropagation neural network using Morlet mother wavelet basic function as node activation function. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The WNN-based classifier outperformed the FEBANN and logistic regression based counterpart. Within the same group, the WNN-based classifier was more accurate than the FEBANN-based classifier, and the logistic regression-based classifier.