Browsing by Author "Celepli, Pinar"

Now showing 1 - 6 of 6

Application of Radiomics Analysis on Mammography for Differentiating Benign and Malignant Masses
(Springer Nature, 2025) Lafcı, Oğuz; Akkur, Erkan; Celepli, Pinar; Öztekin, Pelin Seher; Eroğul, Osman; Koşar, Pinar Nercis
Radiomics is emerging as a promising quantitative tool for extracting imaging features. The diagnostic accuracy of mammography may be altered by the reader’s experience. To build a radiomics model to differentiate benign and malignant mammographic masses and to evaluate whether the diagnostic performance of mammography could be improved by radiomics. In this retrospective study, 101 patients were included in the training set, and 36 patients were included in the test set. A total of 127 radiomics features were extracted from each mammographic mass using both craniocaudal (CC) and mediolateral oblique projection (MLO) images. RELIEF algorithm and Mann–Whitney-U test were used for feature selection. Seven machine learning algorithms were applied to construct a predictive model. Machine learning algorithms were trained by stratified tenfold cross-validation on the training set. The classification performance of the radiomics models was compared with the diagnostic predictions of two radiologists with different experience levels by using receiver operating characteristic curve (ROC) analysis. A total of 15 radiomics features remained after the pre-processing. “XGBoost” presented the best differentiation ability among the seven machine learning methods and yielded 0.871 area under the curve (AUC), 0.888 accuracy, 0.895 sensitivity, and 0.875 specificity. The breast radiologist yielded 0.901 (AUC), 0.916 accuracy, 0.956 sensitivity, and 0.846 specificity. The inexperienced radiologist yielded 0.819 (AUC), 0.833 accuracy, 0.869 sensitivity, and 0.769 specificity. The radiomics-based model shows favorable outcomes in differentiating benign and malignant mammographic masses. Quantifiable assessment of mammography could enhance radiology practice, especially for inexperienced radiologists. © 2025 Elsevier B.V., All rights reserved.
Citation - WoS: 1
Citation - Scopus: 1
Artichoke for Biochemistry, Histology, and Gene Expression in Obstructive Jaundice
(Assoc Medica Brasileira, 2022) Celepli, Salih; Colak, Bayram; Celepli, Pinar; Bigat, İrem; Batur, Hatice Gul; Soysal, Furkan; Sahin, Mustafa
OBJECTIVE: This study aimed to evaluate the hepatoprotective effect of artichoke leaf extract (Cynara scolymus) in experimental obstructive jaundice. METHODS: Rats were separated into three groups, namely, sham, control, and artichoke leaf extract. Ischemia was created for 60 min, and then liver tissue and blood samples were taken at the 90th minute of reperfusion. Artichoke leaf extract was given at a 300 mg/kg dose 2 h before the operation. Antioxidant enzyme activities and biochemical parameters were examined from the tissue and serum. Histopathological findings of the liver were scored semiquantitatively. RESULTS: Antioxidant enzyme activities in the artichoke leaf extract group were statistically significantly higher than that in the other two groups. Biochemical parameters, which show hepatocellular damage, were found to be similar in both sham and artichoke leaf extract groups. Although the values in the sham group were higher than the artichoke group in terms of protein and gene expressions, no statistically significant difference was found between these two groups. Regarding the hepatocellular effects of obstructive jaundice, the artichoke leaf extract group showed lower scores than the control group in all histopathological scores. CONCLUSION: The results of this study showed that artichoke leaf extract had a hepatoprotective effect that was associated with the antioxidant and anti-inflammatory effects of artichoke leaf extract.
Citation - WoS: 4
Citation - Scopus: 5
Cd47 Expression and Tumor-Associated Immune Cells in Breast Cancer and Their Correlation With Molecular Subtypes and Prognostic Factors
(Elsevier Gmbh, 2022) Celepli, Pinar; Karabulut, Sefika; Bigat, Irem; Celepli, Salih; Hucumenoglu, Sema
Objective: Breast cancer is the most common malignancy in women and a heterogeneous disease at the molecular level. Since most breast cancer cases are not of a special type, it is suggested that tumor-associated macrophages and tumor-infiltrating lymphocytes, which are involved in tumor growth, invasion, angiogenesis, and metastasis, may be important factors that should be evaluated together with standard criteria to determine the prognosis of cancer and assist in treatment decisions and outcome stratification. In this study, CD47 expression, which is involved in macrophage-mediated immune escape, tumor-infiltrating lymphocytes, and tumor-associated macrophages were evaluated in breast cancer molecular subgroups and correlated with prognostic factors. Material and method: The immunohistochemistry of CD47, CD163, and CD3 was analyzed on the tissue micro -arrays of 278 invasive breast cancer cases. Results: The CD47, CD163, and CD3 expressions were found to be correlated with various clinicopathological parameters in breast cancer. High levels of CD47, CD163, and CD3 expressions had a significant correlation with the ER status and PR status, Ki-67 proliferation index, and molecular subtype (P < 0.05). The CD47 expression had a significant correlation with the CD3 and CD163 expressions (p = 0.021 and p = 0.001, respectively). Conclusions: Our results suggest that CD47, CD163, and CD3 may be among the prognostic factors of breast cancer. The combined use of CD47, CD163, and CD3 can be a new prognostic factor for patients with breast cancer, especially as a therapeutic target in hormone receptor-negative breast cancer cases and those with a high proliferation index.
Citation - WoS: 3
Citation - Scopus: 3
Effects of Artichoke Leaf Extract on Hepatic Ischemia- Reperfusion Injury
(Assoc Medica Brasileira, 2022) Celepli, Salih; Colak, Bayram; Celepli, Pinar; Bigat, İrem; Batur, Hatice Gul; Soysal, Furkan; Sahin, Mustafa
OBJECTIVE: The aim of this study was to evaluate the hepatoprotective effect and mechanism of action of artichoke leaf extract in hepatic ischemia/ reperfusion injury. METHODS: Rats were divided into three groups such as sham, control, and artichoke leaf extract groups. Antioxidant enzyme activities and biochemical parameters were examined from the tissue and serum obtained from the subjects. Histopathological findings were scored semiquantitatively. RESULTS: Statistically, the antioxidant activity was highest in the artichoke leaf extract group, the difference in biochemical parameters and C-reactive protein was significant compared with the control group, and the histopathological positive effects were found to be significantly higher. CONCLUSIONS: As a result, artichoke leaf extract had a hepatoprotective effect and that this effect was related to the antioxidant and antiinflammatory effects of artichoke.
Citation - WoS: 3
Citation - Scopus: 3
The Effects of Capparis Ovata Seed Oil on the Healing of Traumatic Skin Wounds
(Turkish Assoc Trauma Emergency Surgery, 2022) Celepli, Salih; Colak, Bayram; Sezer, Umran Aydemir; Celepli, Pinar; Bigat, Irem; Duymus, Mehmet Esat; Sahin, Mustafa
BACKGROUND: Capparis ovata contains alkaloids, lipids, polyphenols, flavonoids, and also is rich in antioxidants. Conventionally, in Turkey, the flower buds, root, bark, and fruits of C. ovata are used for their analgesic, anti-inflammatory, anti-rheumatism, tonic, and diuretic effects. The aim of this study was to examine the effect on wound healing of C. ovata seed oil (COSO), which is known to have antioxidant, anti-inflammatory, and antibacterial properties. METHODS: In the study, 20 Wistar albino female rats were randomly divided into two groups of 10 animals each. A standard full -thick-ness skin defect was created on the back area of the rats. In both groups, after cleaning the wounds with saline daily, no active substance other than saline was applied to the control group, while 1 cc/day COSO was applied to the wounds of the rats in the study group. On the post-operative 14th day, the rats were reanesthetized and wound area measurements were made. Then, excision was performed to include 1 cm of intact tissue around the wound, which remained unhealed, and samples were taken for histopathological examination. RESULTS: The changes in wound areas showed that after 14 days, the improvement in the group treated with caper oil (32.78; 95% confidence interval, 17.21-48.36) was significantly higher than that of the control group (65.41; 95% confidence interval, 49.84-80.98) (p=0.009). The histopathological scores showed a significant difference between the groups in respect of epithelial formation, inflam-mation, and fibrosis development. No epithelial tissue formation was observed in the control group (90%), and more incomplete re-epithelization and focal epidermal hyperplasia were observed in the treatment group (60%). Fibrosis development was mild and weak (70%) in the control group and was evaluated as severe and intense (60%) in the treatment group. Perivascular edema was mild (50%) and vascularity was immature (60% - an indicator of neovascularization) in the treatment group. These histopathological results showed that the treatment group inflammation phase was completed and the proliferation phase started, as well as the effectiveness of the use of caper oil on epithelization, angiogenesis, and fibrosis, which are important histopathological parameters in the evaluation of wound healing compared to the control group. CONCLUSION: From the results of this study, it was concluded that COSO significantly enhances the healing of full-thickness skin wounds and this effect is primarily related to its anti-inflammatory effect.
Shap-Based Identification of Potential Acoustic Biomarkers in Patients With Post-Thyroidectomy Voice Disorder
(MDPI, 2025) Celepli, Salih; Bigat, Irem; Karakas, Bilgi; Tezcan, Huseyin Mert; Yar, Mehmet Dincay; Celepli, Pinar; Erogul, Osman
Objective: The objective of this study was to identify potential robust acoustic biomarkers for functional post-thyroidectomy voice disorder (PTVD) that may support early diagnosis and personalized treatment strategies, using acoustic analysis and explainable machine learning methods. Methods: Spectral and cepstral features were extracted from /a/ and /i/ voice recordings collected preoperatively and 4-6 weeks postoperatively from a total of 126 patients. Various Support Vector Machine (SVM) and Boosting models were trained. SHapley Additive exPlanations (SHAP) analysis was applied to enhance interpretability. SHAP values from training and test sets were compared via scatter plots to identify stable candidate biomarkers with high consistency. Results: GentleBoost (AUC = 0.85) and LogitBoost (AUC = 0.81) demonstrated the highest classification performance. Performance metrics across all models were evaluated for statistical significance. DeLong's test was conducted to assess differences between ROC curves. The features iCPP, aCPP, and aHNR were identified as stable candidate biomarkers, exhibiting consistent SHAP distributions in both training and test sets in terms of direction and magnitude. These features showed statistically significant correlations with PTVD (p < 0.05) and demonstrated strong effect sizes (Cohen's d = -2.95, -1.13, -0.60). Their diagnostic relevance was further supported by post hoc power analyses (iCPP: 1.00; aCPP: 0.998). Conclusions: SHAP-supported machine learning models offer an objective and clinically meaningful approach for evaluating PTVD. The identified features may serve as potential biomarkers to guide individualized voice therapy decisions during the early postoperative period.