Wos Kapalı Erişimli Yayınlar

Permanent URI for this collectionhttps://hdl.handle.net/11727/10753

Browse

Filters

2019 - 201912020 - 20211

Settings

Author: search.filters.author.Beyaz, Salih

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Comparison of Different Machine Learning Approaches to Detect Femoral Neck Fractures in X-Ray Images
    (2021) Acici, Koray; Sumer, Emre; Beyaz, Salih; 0000-0002-3821-6419; 0000-0001-8502-9184; 0000-0002-5788-5116; AGA-5711-2022; K-8820-2019
    Femoral neck fractures are a serious health problem, especially in the elderly population. Misdiagnosis leads to improper treatment and adversely affects the quality of life of the patients. On the other hand, when looking from the perspective of orthopedic surgeons, their workload increases during the pandemic, and the rates of correct diagnosis may decrease with fatigue. Therefore, it becomes essential to help healthcare professionals diagnose correctly and facilitate treatment planning. The main purpose of this study is to develop a framework to detect fractured femoral necks in PXRs (Pelvic X-ray, Pelvic Radiographs) while also researching how different machine learning approaches affect different data distributions. Conventional, LBP (Local Binary Patterns), and HOG (Histogram of Gradients) features were extracted manually from gray-level images to feed the canonical machine learning classifiers. Gray-level and three-channel images were used as inputs to extract the features automatically by CNNs (Convolutional Neural Network). LSTMs (Long Short-Term Memory) and BILSTMs (Bidirectional Long Short-Term Memory) were fed by automatically extracted features. Metaheuristic optimization algorithms, GA (Genetic Algorithm) and PSO (Particle Swarm Optimization), were utilized to optimize hyper-parameters such as the number of the feature maps and the size of the filters in the convolutional layers of the CNN architecture. The majority voting was applied to the results of the different classifiers. For the imbalanced dataset, the best performance was achieved by the 2-layer LSTM architecture that used features extracted from the fifth max-pooling layer of the CNN architecture optimized by GA. For the balanced dataset, the best performance was obtained by the CNN architecture optimized by PSO in terms of the Kappa evaluation metric. Although metaheuristic optimization algorithms such as GA and PSO do not guarantee the optimal solution, they can improve the performance on a not extremely imbalanced dataset especially in terms of sensitivity and Kappa evaluation metrics. On the other hand, for a balanced dataset, more reliable results can be obtained without using metaheuristic optimization algorithms but including them can result in an acceptable agreement in terms of the Kappa metric.
  • No Thumbnail Available
    Item
    Do diabetic patients who undergo transtibial amputation receive adequate treatment?
    (2019) Beyaz, Salih; 0000-0002-5788-5116; 30946028; M-2609-2013
    AIMS: To determine if patients who undergo below-knee amputation (BKA) for intractable wounds caused by diabetes complications receive adequate treatment before surgery. MATERIALS AND METHODS: The study included a total of 528 patients who underwent transtibial amputation for diabetic foot. All patients were assessed on the basis of duration of preoperative treatment, HbO therapy, negative wound pressure therapy (NPWT), peripheral vascular angioplasty (PVA) treatment, wound cultures, antibiotic medications, consultations with plastic and vascular surgeons, need for hemodialysis treatment, use of anticoagulant treatment as an inpatient, and assessment of blood sugar regulation by an endocrinologist. HbA1c, BUN, Creatinine, ESR, and CRP values attained for preoperative assessment were noted. RESULTS: Eighteen patients (3.5%) received HbO therapy, 35 (67%) NPWT therapy and 347 (65.7%) anticoagulant treatment. Wound cultures were taken in 317 patients (60.5%) and 390 (73.9%) received preoperative antibiotic treatment. 45 (8.6%) patients were assessed by plastic surgeon with 22 (4.2%) subsequently undergoing surgery by the plastic surgeon. Vascular surgeons assessed 163 patients (30.9%) and performed procedures on 45 patients (8.6%). Endocrinologists assessed 316 patients (59.8%) and implemented blood sugar regulation. PVA treatment was performed in 246 patients (466%). Patients who were managed medically for more than 7 days after the initial assessment received more HbO therapy (p=0.037), anticoagulant treatment (p=0.015), IV antibiotics (0.001), blood sugar regulation attempts (p=0.001), and PVA therapy (0.001) and had more cultures taken (p=0.001). These patients also received overall more diagnostic and treatment modalities than those that received definitive surgical intervention within 7 days. CONCLUSIONS: The duration of time patients with diabetes-related foot problems who see orthopedic surgeons for longer periods of time receive more treatment modalities and are referred more often to specialists before transtibial amputation surgery. We believe that delayed presentation is one of the main obstacles prohibiting adequate treatment for these patients.