Yazar "Kose, Taha Emre" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Comparison of mandibular morphometric parameters in digital panoramic radiography in gender determination using machine learning
    (Springer, 2024) Pertek, Hanife; Kamasak, Mustafa; Kotan, Soner; Hatipoglu, Fatma Pertek; Hatipoglu, Omer; Kose, Taha Emre
    ObjectiveThis study aimed to evaluate the usability of morphometric features obtained from mandibular panoramic radiographs in gender determination using machine learning algorithms.Materials and methodsHigh-resolution radiographs of 200 patients aged 20-77 (41.0 +/- 12.7) were included in the study. Twelve different morphometric measurements were extracted from each digital panoramic radiography included in the study. These measurements were used as features in the machine learning phase in which six different machine learning algorithms were used (k-nearest neighbor, decision trees, support vector machines, naive Bayes, linear discrimination analysis, and neural networks). To evaluate the reliability, we have performed tenfold cross-validation and we repeated this 10 times for every classification process. This process enhances the reliability of the results for other datasets.ResultsWhen all 12 features are used together, the accuracy rate is found to be 82.6 +/- 0.5%. The classification accuracies are also compared using each feature alone. Three features that give the highest accuracy are coronoid height (80.9 +/- 0.9%), condyle height (78.2 +/- 0.5%), and ramus height (77.2 +/- 0.4%), respectively. When compared to the classification algorithms, the highest accuracy was obtained with the naive Bayes algorithm with a rate of 84.0 +/- 0.4%.ConclusionMachine learning techniques can accurately determine gender by analyzing mandibular morphometric structures from digital panoramic radiographs. The most precise results are achieved by evaluating the structures in combination, using attributes obtained from applying the MRMR algorithm to all features.
  • Küçük Resim Yok
    Öğe
    Prediction of root canal lengths and pulp volume of the maxillary permanent first molar based on stature, crown diameters, and facial morphometry
    (Springer, 2023) Hatipoglu, Fatma Pertek; Aricioglu, Banu; Hatipoglu, Oemer; Kose, Taha Emre; Gunacar, Dilara Nil
    This study purposed to develop statistical models to predict palatal (PRL), mesial (MRL), and distal (DRL) root canal length and pulp volume (PV) of the maxillary first permanent molar using stature, gender, mesiodistal (MD), and buccopalatal (BP) crown diameters and some facial morphometries. 57 individuals were included in the study. Cone beam computed tomography was used to measure root canal lengths and PV. The PV calculation was carried out using the software ITK-SNAP 3.4.0. PRL was positively correlated with BP, stature, middle facial height, interalar distance, and bicommissural distance (BCD) (p < 0.05). DRL was positively correlated with BP, MD, and stature (p < 0.05). MRL was positively correlated with BP, MD, stature, lower face height, bizygomatic distance, and BCD (p < 0.05). PV was negatively correlated with age and BCD (p < 0.05). Although all models have significant predictive power for the root lengths and PV, no model could explain variances greater than 30%. The highest and lowest predictive ability was obtained for PRL and DRL, respectively. While the most significant predictor was BP for PRL and DRL, it was the age for PV.