Categorization of Alzheimer's disease stages using deep learning approaches with McNemar's test.

Early diagnosis is crucial in Alzheimer's disease both clinically and for preventing the rapid progression of the disease. Early diagnosis with awareness studies of the disease is of great importance in terms of controlling the disease at an early stage. Additionally, early detection can reduce treatment costs associated with the disease. A study has been carried out on this subject to have the great importance of detecting Alzheimer's disease at a mild stage and being able to grade the disease correctly. This study's dataset consisting of MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) was split into training and testing sets, and deep learning-based approaches were used to obtain results. The dataset consists of three classes: Alzheimer's disease (AD), Cognitive Normal (CN), and Mild Cognitive Impairment (MCI). The achieved results showed an accuracy of 98.94% for CN vs AD in the one vs one (1 vs 1) classification with the EfficientNetB0 model and 99.58% for AD vs CNMCI in the one vs All (1 vs All) classification with AlexNet model. In addition, in the study, an accuracy of 98.42% was obtained with the EfficientNet121 model in MCI vs CN classification. These results indicate the significant potential for mild stage Alzheimer's disease detection of Alzheimer's disease. Early detection of the disease in the mild stage is a critical factor in preventing the progression of Alzheimer's disease. In addition, a variant of the non-parametric statistical McNemar's Test was applied to determine the statistical significance of the results obtained in the study. Statistical significance of 1 vs 1 and 1 vs all classifications were obtained for EfficientNetB0, DenseNet, and AlexNet models.

Cloud type classification using deep learning with cloud images.

Clouds play a pivotal role in determining the weather, impacting the daily lives of everyone. The cloud type can offer insights into whether the weather will be sunny or rainy and even serve as a warning for severe and stormy conditions. Classified into ten distinct classes, clouds provide valuable information about both typical and exceptional weather patterns, whether they are short or long-term in nature. This study aims to anticipate cloud formations and classify them based on their shapes and colors, allowing for preemptive measures against potentially hazardous situations. To address this challenge, a solution is proposed using image processing and deep learning technologies to classify cloud images. Several models, including MobileNet V2, Inception V3, EfficientNetV2L, VGG-16, Xception, ConvNeXtSmall, and ResNet-152 V2, were employed for the classification computations. Among them, Xception yielded the best outcome with an impressive accuracy of 97.66%. By integrating artificial intelligence technologies that can accurately detect and classify cloud types into weather forecasting systems, significant improvements in forecast accuracy can be achieved. This research presents an innovative approach to studying clouds, harnessing the power of image processing and deep learning. The ability to classify clouds based on their visual characteristics opens new avenues for enhanced weather prediction and preparedness, ultimately contributing to the overall accuracy and reliability of weather forecasts.

Enhancing Tissue Equivalence in 7Li Heavy Ion Therapy with MC Algorithm Optimized Polymer-Based Bioinks.

The unique physical properties of heavy ion beams, particularly their distinctive depth-dose distribution and sharp lateral dose reduction profiles, have led to their widespread adoption in tumor therapy worldwide. However, the physical properties of heavy ion beams must be investigated to deliver a sufficient dose to tumors without damaging organs at risk. These studies should be performed on phantoms made of biomaterials that closely mimic human tissue. Polymers can serve as soft tissue substitutes and are suitable materials for building radiological phantoms due to their physical, mechanical, biological, and chemical properties. Extensive research, development, and applications of polymeric biomaterials have been encouraged due to these properties. In this study, we investigated the ionization, recoils, phonon release, collision events, and lateral straggle properties of polymeric biomaterials that closely resemble soft tissue using lithium-ion beams and Monte Carlo Transport of Ions in Matter simulation. The results indicated that the Bragg peak position closest to soft tissue was achieved with a 7.3% difference in polymethylmethacrylate, with an average recoils value of 10.5%. Additionally, average values of 33% were observed in collision events and 22.6% in lateral straggle. A significant contribution of this study to the existing literature lies in the exploration of secondary interactions alongside the assessment of linear energy transfer induced by the 7Li beam used for treatment. Furthermore, we analyzed the tissue-equivalent properties of polymer biomaterials using heavy ion beams, taking into account phonon release resulting from ionization, recoils, lateral straggle, and all other interactions. This approach allows for the evaluation of the most suitable polymeric biomaterials for heavy ion therapy while considering the full range of interactions involved.

Crohn's Disease Prediction Using Sequence Based Machine Learning Analysis of Human Microbiome.

Human microbiota refers to the trillions of microorganisms that inhabit our bodies and have been discovered to have a substantial impact on human health and disease. By sampling the microbiota, it is possible to generate massive quantities of data for analysis using Machine Learning algorithms. In this study, we employed several modern Machine Learning techniques to predict Inflammatory Bowel Disease using raw sequence data. The dataset was obtained from NCBI preprocessed graph representations and converted into a structured form. Seven well-known Machine Learning frameworks, including Random Forest, Support Vector Machines, Extreme Gradient Boosting, Light Gradient Boosting Machine, Gaussian Naïve Bayes, Logistic Regression, and k-Nearest Neighbor, were used. Grid Search was employed for hyperparameter optimization. The performance of the Machine Learning models was evaluated using various metrics such as accuracy, precision, fscore, kappa, and area under the receiver operating characteristic curve. Additionally, Mc Nemar's test was conducted to assess the statistical significance of the experiment. The data was constructed using k-mer lengths of 3, 4 and 5. The Light Gradient Boosting Machine model overperformed over other models with 67.24%, 74.63% and 76.47% accuracy for k-mer lengths of 3, 4 and 5, respectively. The LightGBM model also demonstrated the best performance in each metric. The study showed promising results predicting disease from raw sequence data. Finally, Mc Nemar's test results found statistically significant differences between different Machine Learning approaches.

MC TRIM Algorithm in Mandibula Phantom in Helium Therapy.

Helium ion beam therapy, one of the particle therapies developed and studied in the 1950s for cancer treatment, resulted in clinical trials starting at Lawrence Berkeley National Laboratory in 1975. While proton and carbon ion therapies have been implemented in research institutions and hospitals globally after the end of the trials, progress in comprehending the physical, biological, and clinical findings of helium ion beam therapy has been limited, particularly due to its limited accessibility. Ongoing efforts aim to establish programs that evaluate the use of helium ion beams for clinical and research purposes, especially in the treatment of sensitive clinical cases. Additionally, helium ions have superior physical properties to proton beams, such as lower lateral scattering and larger LET. Moreover, they exhibit similar physical characteristics to carbon, oxygen, and neon ions, which are all used in heavy ion therapy. However, they demonstrate a sharper lateral penumbra with a lower radiobiological absence of certainties and lack the degradation of variations in dose distributions caused by excessive fragmenting of heavier-ion beams, especially at greater depths of penetration. In this context, the status and the prospective advancements of helium ion therapy are examined by investigating ionization, recoil, and lateral scattering values using MC TRIM algorithms in mandible plate phantoms designed from both tissue and previously studied biomaterials, providing an overview for dental cancer treatment. An average difference of 1.9% in the Bragg peak positions and 0.211 mm in lateral scattering was observed in both phantoms. Therefore, it is suggested that the 4He ion beam can be used in the treatment of mandibular tumors, and experimental research is recommended using the proposed biomaterial mandible plate phantom.

Deep Learning in Diagnosis of Dental Anomalies and Diseases: A Systematic Review.

Deep learning and diagnostic applications in oral and dental health have received significant attention recently. In this review, studies applying deep learning to diagnose anomalies and diseases in dental image material were systematically compiled, and their datasets, methodologies, test processes, explainable artificial intelligence methods, and findings were analyzed. Tests and results in studies involving human-artificial intelligence comparisons are discussed in detail to draw attention to the clinical importance of deep learning. In addition, the review critically evaluates the literature to guide and further develop future studies in this field. An extensive literature search was conducted for the 2019-May 2023 range using the Medline (PubMed) and Google Scholar databases to identify eligible articles, and 101 studies were shortlisted, including applications for diagnosing dental anomalies (n = 22) and diseases (n = 79) using deep learning for classification, object detection, and segmentation tasks. According to the results, the most commonly used task type was classification (n = 51), the most commonly used dental image material was panoramic radiographs (n = 55), and the most frequently used performance metric was sensitivity/recall/true positive rate (n = 87) and accuracy (n = 69). Dataset sizes ranged from 60 to 12,179 images. Although deep learning algorithms are used as individual or at least individualized architectures, standardized architectures such as pre-trained CNNs, Faster R-CNN, YOLO, and U-Net have been used in most studies. Few studies have used the explainable AI method (n = 22) and applied tests comparing human and artificial intelligence (n = 21). Deep learning is promising for better diagnosis and treatment planning in dentistry based on the high-performance results reported by the studies. For all that, their safety should be demonstrated using a more reproducible and comparable methodology, including tests with information about their clinical applicability, by defining a standard set of tests and performance metrics.

Monte Carlo Simulation of TRIM Algorithm in Ceramic Biomaterial in Proton Therapy.

Biomaterials play a crucial role in enhancing human health and quality of life. They are employed in applications such as tissue substitution, diagnostic tools, medical supplies, therapeutic treatments, regenerative medicine, and radiation dosimetric studies. However, their predisposition to proton therapy, which is a trending treatment in the world, has not been adequately studied. Ceramic biomaterials, known for their hardness and durability, offer versatile uses, especially in bone tissue replacements. The wide range of physical, mechanical, and chemical properties exhibited by ceramics has spurred extensive research, development, and application in this field. This study focuses on investigating and analyzing the ionization, recoils, phonon release, collision events, and lateral scattering properties of ceramic biomaterials that closely resemble bone tissue in proton therapy applications. Monte Carlo (MC) Transport of Ions in Matter (TRIM) simulation tools were utilized for this analysis. The results showed that Silicon dioxide exhibited the Bragg peak position closest to bone tissue, with a deviation of 10.6%. The average recoils differed by 1.7%, and the lateral scattering differed by 3.6%. The main innovation of this study lies in considering interactions such as recoil, collision events, phonon production, and lateral scattering when selecting biomaterials, despite their limited digitization and understanding. By evaluating all these interactions, the study aimed to identify the most suitable ceramic biomaterial to replace bone tissue in proton therapy.

Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer.

Data from omics studies have been used for prediction and classification of various diseases in biomedical and bioinformatics research. In recent years, Machine Learning (ML) algorithms have been used in many different fields related to healthcare systems, especially for disease prediction and classification tasks. Integration of molecular omics data with ML algorithms has offered a great opportunity to evaluate clinical data. RNA sequence (RNA-seq) analysis has been emerged as the gold standard for transcriptomics analysis. Currently, it is being used widely in clinical research. In our present work, RNA-seq data of extracellular vesicles (EV) from healthy and colon cancer patients are analyzed. Our aim is to develop models for prediction and classification of colon cancer stages. Five different canonical ML and Deep Learning (DL) classifiers are used to predict colon cancer of an individual with processed RNA-seq data. The classes of data are formed on the basis of both colon cancer stages and cancer presence (healthy or cancer). The canonical ML classifiers, which are k-Nearest Neighbor (kNN), Logistic Model Tree (LMT), Random Tree (RT), Random Committee (RC), and Random Forest (RF), are tested with both forms of the data. In addition, to compare the performance with canonical ML models, One-Dimensional Convolutional Neural Network (1-D CNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) DL models are utilized. Hyper-parameter optimizations of DL models are constructed by using genetic meta-heuristic optimization algorithm (GA). The best accuracy in cancer prediction is obtained with RC, LMT, and RF canonical ML algorithms as 97.33%. However, RT and kNN show 95.33% performance. The best accuracy in cancer stage classification is achieved with RF as 97.33%. This result is followed by LMT, RC, kNN, and RT with 96.33%, 96%, 94.66%, and 94%, respectively. According to the results of the experiments with DL algorithms, the best accuracy in cancer prediction is obtained with 1-D CNN as 97.67%. BiLSTM and LSTM show 94.33% and 93.67% performance, respectively. In classification of the cancer stages, the best accuracy is achieved with BiLSTM as 98%. 1-D CNN and LSTM show 97% and 94.33% performance, respectively. The results reveal that both canonical ML and DL models may outperform each other for different numbers of features.

Machine learning based orthodontic treatment planning for mixed dentition borderline cases suffering from moderate to severe crowding: An experimental research study.

BACKGROUND: Pedodontists and general practitioners may need support in planning the early orthodontic treatment of patients with mixed dentition, especially in borderline cases. The use of machine learning algorithms is required to be able to consistently make treatment decisions for such cases. OBJECTIVE: This study aimed to use machine learning algorithms to facilitate the process of deciding whether to choose serial extraction or expansion of maxillary and mandibular dental arches for early treatment of borderline patients suffering from moderate to severe crowding. METHODS: The dataset of 116 patients who were previously treated by senior orthodontists and divided into two groups according to their treatment modalities were examined. Machine Learning algorithms including Multilayer Perceptron, Linear Logistic Regression, k-nearest Neighbors, Naïve Bayes, and Random Forest were trained on this dataset. Several metrics were used for the evaluation of accuracy, precision, recall, and kappa statistic. RESULTS: The most important 12 features were determined with the feature selection algorithm. While all algorithms achieved over 90% accuracy, Random Forest yielded 95% accuracy, with high reliability values (kappa = 0.90). CONCLUSION: The employment of machine learning methods for the treatment decision with or without extraction in the early treatment of patients in the mixed dentition can be particularly useful for pedodontists and general practitioners.

A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models.

Endoscopic procedures for diagnosing gastrointestinal tract findings depend on specialist experience and inter-observer variability. This variability can cause minor lesions to be missed and prevent early diagnosis. In this study, deep learning-based hybrid stacking ensemble modeling has been proposed for detecting and classifying gastrointestinal system findings, aiming at early diagnosis with high accuracy and sensitive measurements and saving workload to help the specialist and objectivity in endoscopic diagnosis. In the first level of the proposed bi-level stacking ensemble approach, predictions are obtained by applying 5-fold cross-validation to three new CNN models. A machine learning classifier selected at the second level is trained according to the obtained predictions, and the final classification result is reached. The performances of the stacking models were compared with the performances of the deep learning models, and McNemar's statistical test was applied to support the results. According to the experimental results, stacking ensemble models performed with a significant difference with 98.42% ACC and 98.19% MCC in the KvasirV2 dataset and 98.53% ACC and 98.39% MCC in the HyperKvasir dataset. This study is the first to offer a new learning-oriented approach that efficiently evaluates CNN features and provides objective and reliable results with statistical testing compared to state-of-the-art studies on the subject. The proposed approach improves the performance of deep learning models and outperforms the state-of-the-art studies in the literature.

Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches.

OBJECTIVES: This study aims to detect frontal pelvic radiograph femoral neck fracture using deep learning techniques. PATIENTS AND METHODS: This retrospective study was conducted between January 2013 and January 2018. A total of 234 frontal pelvic X-ray images collected from 65 patients (32 males, 33 females; mean age 74.9 years; range, 33 to 89 years) were augmented to 2106 images to achieve a satisfactory dataset. A total of 1,341 images were fractured femoral necks while 765 were non-fractured ones. The proposed convolutional neural network (CNN) architecture contained five blocks, each containing a convolutional layer, batch normalization layer, rectified linear unit, and maximum pooling layer. After the last block, a dropout layer existed with a probability of 0.5. The last three layers of the architecture were a fully connected layer of two classes, a softmax layer and a classification layer that computes cross entropy loss. The training process was terminated after 50 epochs and an Adam Optimizer was used. Learning rate was dropped by a factor of 0.5 on every five epochs. To reduce overfitting, regularization term was added to the weights of the loss function. The training process was repeated for pixel sizes 50x50, 100x100, 200x200, and 400x400. The genetic algorithm (GA) approach was employed to optimize the hyperparameters of the CNN architecture and to minimize the error after testing the model created by the CNN architecture in the training phase. RESULTS: Performance in terms of sensitivity, specificity, accuracy, F1 score, and Cohen's kappa coefficient were evaluated using five- fold cross validation tests. Best performance was obtained when cropped images were rescaled to 50x50 pixels. The kappa metric showed more reliable classifier performance when 50x50 pixels image size was used to feed the CNN. The classifier performance was more reliable according to other image sizes. Sensitivity and specificity rates were computed to be 83% and 73%, respectively. With the inclusion of the GA, this rate increased by 1.6%. The detection rate of fractured bones was found to be 83%. A kappa coefficient of 55% was obtained, indicating an acceptable agreement. CONCLUSION: This experimental study utilized deep learning techniques in the detection of bone fractures in radiography. Although the dataset was unbalanced, the results can be considered promising. It was observed that use of smaller image size decreases computational cost and provides better results according to evaluation metrics.

Retrieving relevant experiments: The case of microRNA microarrays.

Content-based retrieval of biological experiments in large public repositories is a recent challenge in computational biology and bioinformatics. The task is, in general, to search in a database using a query-by-example without any experimental meta-data annotation. Here, we consider a more specific problem that seeks a solution for retrieving relevant microRNA experiments from microarray repositories. A computational framework is proposed with this objective. The framework adapts a normal-uniform mixture model for identifying differentially expressed microRNAs in microarray profiling experiments. A rank-based thresholding scheme is offered to binarize real-valued experiment fingerprints based on differential expression. An effective similarity metric is introduced to compare categorical fingerprints, which in turn infers the relevance between two experiments. Two different views of experimental relevance are evaluated, one for disease association and another for embryonic germ layer, to discern the retrieval ability of the proposed model. To the best of our knowledge, the experiment retrieval task is investigated for the first time in the context of microRNA microarrays.