Araştırma Çıktıları

Permanent URI for this communityhttps://hdl.handle.net/11443/931

Browse

Author: search.filters.author.Kaya, EserSubject: search.filters.subject.lung cancer

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Lung cancer subtype differentiation from positron emission tomography images
    (SCIENTIFIC TECHNICAL RESEARCH COUNCIL TURKEY-TUBITAK, 2020-01-01) Ayyildiz, Oguzhan; Aydin, Zafer; Yilmaz, Bulent; Karacavus, Seyhan; Senkaya, Kubra; Icer, Semra; Tasdemir, Arzu; Kaya, Eser
    Lung cancer is one of the deadly cancer types, and almost 85\% of lung cancers are nonsmall cell lung cancer (NSCLC). In the present study we investigated classification and feature selection methods for the differentiation of two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The major advances in understanding the effects of therapy agents suggest that future targeted therapies will be increasingly subtype specific. We obtained positron emission tomography (PET) images of 93 patients with NSCLC, 39 of which had ADC while the rest had SqCC. Random walk segmentation was applied to delineate three-dimensional tumor volume, and 39 texture features were extracted to grade the tumor subtypes. We examined 11 classifiers with two different feature selection methods and the effect of normalization on accuracy. The classifiers we used were the k-nearest-neighbor, logistic regression, support vector machine, Bayesian network, decision tree, radial basis function network, random forest, AdaBoostM1, and three stacking methods. To evaluate the prediction accuracy we performed a leave-one-out cross-validation experiment on the dataset. We also considered optimizing certain hyperparameters of these models by performing 10-fold cross-validation separately on each training set. We found that the stacking ensemble classifier, which combines a decision tree, AdaBoostM1, and logistic regression methods by a metalearner, was the most accurate method for detecting subtypes of NSCLC, and normalization of feature sets improved the accuracy of the classification method.
  • Thumbnail Image
    Item
    Sunlight may increase the FDG uptake value in primary tumors of patients with non-small cell lung cancer
    (SPANDIDOS PUBL LTD, 2013-01-01) Mutlu, Hasan; Buyukcelik, Abdullah; Kaya, Eser; Kibar, Mustafa; Seyrek, Ertugrul; Yavuz, Sinan; Calikusu, Zuleyha
    Currently, positron emission tomography with computerized tomography (PET-CT) is the most sensitive technique for detecting extracranial metastases in non-small cell lung cancer (NSCLC). It has been reported that there is a correlation between the maximal standardized uptake value (SUVmax) of primary tumors and prognosis in patients with NSCLC. The effect of sunlight exposure on PET-CT SUVmax value is not known. Therefore, we aimed to evaluate the effect of sunlight exposure on PET-CT SUVmax a value in patients with NSCLC. A total of 290 patients with NSCLC from two different regions of Turkey (Kayseri, n=168 and Adana, n=122) that have different climate and sunlight exposure intensity, were included in the study. Age, gender, histology of cancer, cancer stage, smoking status, comorbidity and SUVmax of the primary tumor area at the time of staging were evaluated as prognostic factors. In the multivariate analysis, we detected that the region was the only independent factor affecting SUVmax (P=0.019). We identified that warmer climate and more sunlight exposure significantly increases the SUVmax value of the primary tumor area in patients with NSCLC. Further studies are warranted to clarify the issue.