Browsing by Author "Dundar, M. Murat"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    A machine learning model for orthodontic extraction/non-extraction decision in a racially and ethnically diverse patient population
    (Elsevier, 2023-09) Mason, Taylor; Kelly, Kynnedy M.; Eckert, George; Dean, Jeffrey A.; Dundar, M. Murat; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of Dentistry
    Introduction The purpose of the present study was to create a machine learning (ML) algorithm with the ability to predict the extraction/non-extraction decision in a racially and ethnically diverse sample. Methods Data was gathered from the records of 393 patients (200 non-extraction and 193 extraction) from a racially and ethnically diverse population. Four ML models (logistic regression [LR], random forest [RF], support vector machine [SVM], and neural network [NN]) were trained on a training set (70% of samples) and then tested on the remaining samples (30%). The accuracy and precision of the ML model predictions were calculated using the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. The proportion of correct extraction/non-extraction decisions was also calculated. Results The LR, SVM, and NN models performed best, with an AUC of the ROC of 91.0%, 92.5%, and 92.3%, respectively. The overall proportion of correct decisions was 82%, 76%, 83%, and 81% for the LR, RF, SVM, and NN models, respectively. The features found to be most helpful to the ML algorithms in making their decisions were maxillary crowding/spacing, L1-NB (mm), U1-NA (mm), PFH:AFH, and SN-MP(̊), although many other features contributed significantly. Conclusions ML models can predict the extraction decision in a racially and ethnically diverse patient population with a high degree of accuracy and precision. Crowding, sagittal, and vertical characteristics all featured prominently in the hierarchy of components most influential to the ML decision-making process.
  • Thumbnail Image
    Item
    Can we predict orthodontic extraction patterns by using machine learning?
    (Wiley, 2023) Leavitt, Landon; Volovic, James; Steinhauer, Lily; Mason, Taylor; Eckert, George; Dean, Jeffrey A.; Dundar, M. Murat; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of Dentistry
    Objective To investigate the utility of machine learning (ML) in accurately predicting orthodontic extraction patterns in a heterogeneous population. Materials and Methods The material of this retrospective study consisted of records of 366 patients treated with orthodontic extractions. The dataset was randomly split into training (70%) and test sets (30%) and was stratified according to race/ethnicity and gender. Fifty-five cephalometric and demographic input data were used to train and test multiple ML algorithms. The extraction patterns were labelled according to the previous treatment plan. Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM) algorithms were used to predict the patient's extraction patterns. Results The highest class accuracy percentages were obtained for the upper and lower 1st premolars (U/L4s) (RF: 81.63%, LR: 63.27%, SVM: 63.27%) and upper 1st premolars only (U4s) extraction patterns (RF: 61.11%, LR: 72.22%, SVM: 72.22%). However, all methods revealed low class accuracy rates (<50%) for the upper 1st and lower 2nd premolars (U4/L5s), upper 2nd and lower 1st premolars (U5/L4s), and upper and lower 2nd premolars (U/L5s) extraction patterns. For the overall accuracy, RF yielded the highest percentage with 54.55%, followed by SVM with 52.73% and LR with 49.09%. Conclusion All tested supervised ML techniques yielded good accuracy in predicting U/L4s and U4s extraction patterns. However, they predicted poorly for the U4/L5s, U5/L4s, and U/L5s extraction patterns. Molar relationship, mandibular crowding, and overjet were found to be the most predictive indicators for determining extraction patterns.
  • Thumbnail Image
    Item
    Deep-Learning-Based High-Intensity Focused Ultrasound Lesion Segmentation in Multi-Wavelength Photoacoustic Imaging
    (MDPI, 2023-09-08) Wu, Xun; Sanders, Jean L.; Dundar, M. Murat; Oralkan, Ömer; Computer and Information Science, School of Science
    Photoacoustic (PA) imaging can be used to monitor high-intensity focused ultrasound (HIFU) therapies because ablation changes the optical absorption spectrum of the tissue, and this change can be detected with PA imaging. Multi-wavelength photoacoustic (MWPA) imaging makes this change easier to detect by repeating PA imaging at multiple optical wavelengths and sampling the optical absorption spectrum more thoroughly. Real-time pixel-wise classification in MWPA imaging can assist clinicians in monitoring HIFU lesion formation and will be a crucial milestone towards full HIFU therapy automation based on artificial intelligence. In this paper, we present a deep-learning-based approach to segment HIFU lesions in MWPA images. Ex vivo bovine tissue is ablated with HIFU and imaged via MWPA imaging. The acquired MWPA images are then used to train and test a convolutional neural network (CNN) for lesion segmentation. Traditional machine learning algorithms are also trained and tested to compare with the CNN, and the results show that the performance of the CNN significantly exceeds traditional machine learning algorithms. Feature selection is conducted to reduce the number of wavelengths to facilitate real-time implementation while retaining good segmentation performance. This study demonstrates the feasibility and high performance of the deep-learning-based lesion segmentation method in MWPA imaging to monitor HIFU lesion formation and the potential to implement this method in real time.
  • Thumbnail Image
    Item
    High-throughput segmentation of unmyelinated axons by deep learning
    (Springer Nature, 2022-01-24) Plebani, Emanuele; Biscola, Natalia P.; Havton, Leif A.; Rajwa, Bartek; Shemonti, Abida Sanjana; Jaffey, Deborah; Powley, Terry; Keast, Janet R.; Lu, Kun‑Han; Dundar, M. Murat; Computer and Information Science, School of Science
    Axonal characterizations of connectomes in healthy and disease phenotypes are surprisingly incomplete and biased because unmyelinated axons, the most prevalent type of fibers in the nervous system, have largely been ignored as their quantitative assessment quickly becomes unmanageable as the number of axons increases. Herein, we introduce the first prototype of a high-throughput processing pipeline for automated segmentation of unmyelinated fibers. Our team has used transmission electron microscopy images of vagus and pelvic nerves in rats. All unmyelinated axons in these images are individually annotated and used as labeled data to train and validate a deep instance segmentation network. We investigate the effect of different training strategies on the overall segmentation accuracy of the network. We extensively validate the segmentation algorithm as a stand-alone segmentation tool as well as in an expert-in-the-loop hybrid segmentation setting with preliminary, albeit remarkably encouraging results. Our algorithm achieves an instance-level F1 score of between 0.7 and 0.9 on various test images in the stand-alone mode and reduces expert annotation labor by 80% in the hybrid setting. We hope that this new high-throughput segmentation pipeline will enable quick and accurate characterization of unmyelinated fibers at scale and become instrumental in significantly advancing our understanding of connectomes in both the peripheral and the central nervous systems.
  • Thumbnail Image
    Item
    Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality
    (Public Library of Science, 2024) Rajwa, Bartek; Naved, Md Mobasshir Arshed; Adibuzzaman, Mohammad; Grama, Ananth Y.; Khan, Babar A.; Dundar, M. Murat; Rochet, Jean-Christophe; Computer Science, Luddy School of Informatics, Computing, and Engineering
    As the world emerges from the COVID-19 pandemic, there is an urgent need to understand patient factors that may be used to predict the occurrence of severe cases and patient mortality. Approximately 20% of SARS-CoV-2 infections lead to acute respiratory distress syndrome caused by the harmful actions of inflammatory mediators. Patients with severe COVID-19 are often afflicted with neurologic symptoms, and individuals with pre-existing neurodegenerative disease have an increased risk of severe COVID-19. Although collectively, these observations point to a bidirectional relationship between severe COVID-19 and neurologic disorders, little is known about the underlying mechanisms. Here, we analyzed the electronic health records of 471 patients with severe COVID-19 to identify clinical characteristics most predictive of mortality. Feature discovery was conducted by training a regularized logistic regression classifier that serves as a machine-learning model with an embedded feature selection capability. SHAP analysis using the trained classifier revealed that a small ensemble of readily observable clinical features, including characteristics associated with cognitive impairment, could predict in-hospital mortality with an accuracy greater than 0.85 (expressed as the area under the ROC curve of the classifier). These findings have important implications for the prioritization of clinical measures used to identify patients with COVID-19 (and, potentially, other forms of acute respiratory distress syndrome) having an elevated risk of death.
  • Thumbnail Image
    Item
    A machine learning toolkit for CRISM image analysis
    (Elsevier, 2022-04) Plebani, Emanuele; Ehlmann, Bethany L.; Leask, Ellen K.; Fox, Valerie K.; Dundar, M. Murat; Computer and Information Science, School of Science
    Hyperspectral images collected by remote sensing have played a significant role in the discovery of aqueous alteration minerals, which in turn have important implications for our understanding of the changing habitability on Mars. Traditional spectral analyzes based on summary parameters have been helpful in converting hyperspectral cubes into readily visualizable three channel maps highlighting high-level mineral composition of the Martian terrain. These maps have been used as a starting point in the search for specific mineral phases in images. Although the amount of labor needed to verify the presence of a mineral phase in an image is quite limited for phases that emerge with high abundance, manual processing becomes laborious when the task involves determining the spatial extent of detected phases or identifying small outcrops of secondary phases that appear in only a few pixels within an image. Thanks to extensive use of remote sensing data and rover expeditions, significant domain knowledge has accumulated over the years about mineral composition of several regions of interest on Mars, which allow us to collect reliable labeled data required to train machine learning algorithms. In this study we demonstrate the utility of machine learning in two essential tasks for hyperspectral data analysis: nonlinear noise removal and mineral classification. We develop a simple yet effective hierarchical Bayesian model for estimating distributions of spectral patterns and extensively validate this model for mineral classification on several test images. Our results demonstrate that machine learning can be highly effective in exposing tiny outcrops of specific phases in orbital data that are not uncovered by traditional spectral analysis. We package implemented scripts, documentation illustrating use cases, and pixel-scale training data collected from dozens of well-characterized images into a new toolkit. We hope that this new toolkit will provide advanced and effective processing tools and improve community’s ability to map compositional units in remote sensing data quickly, accurately, and at scale.