Oguzhan Tokur

Dr. Oguzhan Tokur

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 July 2024 in Journal of Ultrasound in Medicine
Verified
Journal Article
Open access
POPelin Seher Oztekin
Pelin Seher Oztekin
OKOguzhan KATAR
Oguzhan KATAR
TOTulay Omma
Tulay Omma
SESerap Erel
Serap Erel
OTOguzhan Tokur
Oguzhan Tokur
U Rajendra AcharyaU Rajendra Acharya
U Rajendra Acharya
Objectives: Breast cancer is a type of cancer caused by the uncontrolled growth of cells in the breast tissue. In a few cases, erroneous diagnosis of breast cancer by specialists and unnecessary biopsies can lead to various negative consequences. In some cases, radiologic examinations or clinical findings may raise the suspicion of breast cancer, but subsequent detailed evaluations may not confirm cancer. In addition to causing unnecessary anxiety and stress to patients, such diagnosis can also lead to unnecessary biopsy procedures, which are painful, expensive, and prone to misdiagnosis. Therefore, there is a need for the development of more accurate and reliable methods for breast cancer diagnosis.Methods: In this study, we proposed an artificial intelligence (AI)‐based method for automatically classifying breast solid mass lesions as benign vs malignant. In this study, a new breast cancer dataset (Breast‐XD) was created with 791 solid mass lesions belonging to 752 different patients aged 18 to 85 years, which were examined by experienced radiologists between 2017 and 2022.Results: Six classifiers, support vector machine (SVM), K‐nearest neighbor (K‐NN), random forest (RF), decision tree (DT), logistic regression (LR), and XGBoost, were trained on the training samples of the Breast‐XD dataset. Then, each classifier made predictions on 159 test data that it had not seen before. The highest classification result was obtained using the explainable XGBoost model (X2GAI) with an accuracy of 94.34%. An explainable structure is also implemented to build the reliability of the developed model.Conclusions: The results obtained by radiologists and the X2GAI model were compared according to the diagnosis obtained from the biopsy. It was observed that our developed model performed well in cases where experienced radiologists gave false positive results.

19 January 2022 in Emergency Radiology
Verified
Journal Article
Closed access
PDF file
BUBerna Uçan
Berna Uçan
OTOguzhan Tokur
Oguzhan Tokur
Sonay AydinSonay Aydin
Sonay Aydin

4 November 2025 in BMC Cancer
Verified
Journal Article
Open access
PDF file
OTOguzhan Tokur
Oguzhan Tokur
SASonay Aydin
Sonay Aydin
FKFunda Kilinc
Funda Kilinc
TDTulin Degirmenci
Tulin Degirmenci
POPelin Seher Oztekin
Pelin Seher Oztekin
The evaluation of axillary lymph nodes (ALNs) using ultrasound (US) plays a crucial role in the diagnosis and management of breast cancer. This study aims to assess the diagnostic performance of both quantitative and qualitative features of suspicious ALNs using superb microvascular imaging (SMI). To the best of our knowledge, this is the first prospective study in the literature to evaluate the largest number of suspicious ALNs using SMI and to analyze the combined diagnostic value of these findings. Our prospective study involved 102 patients with suspicious lymph nodes in the axilla. SMI method was employed individually to assess distribution, appearance, and number of vascular structures. After histopathological or follow-up confimation, images were re-evaluated. We also examined the diagnostic value of various combinations of these vascular features. Lastly, two radiologists, each with 22 and 4 years of experience, independently reviewed the images, blinded to clinical and pathological data, to assess interobserver agreement. A total of 108 lymph nodes were evaluated in 102 patients, including 67 benign and 41 malignant cases. The diagnostic performance of various combinations in receiver operating characteristic (ROC) analysis revealed that the highest accuracy (78.70%) and area under the curve (AUC) value in ROC analysis were achieved by distribution-appearance combinations (AUC: 0.776, p < 0.001). Interobserver agreement was significant for both the SMI and PDUS methods. In patients diagnosed with breast cancer, the diagnostic accuracy for suspicious axillary lymph nodes reached 92.76%, with an AUC value of 0.855. In conclusion, our findings suggest that SMI facilitates more accurate identification of suspicious axillary lymph nodes prior to surgical intervention.

30 May 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
TCTurkhun Cetin
Turkhun Cetin
OTOguzhan Tokur
Oguzhan Tokur
HBHayrunnisa Bekis Bozkurt
Hayrunnisa Bekis Bozkurt
Sonay AydinSonay Aydin
Sonay Aydin
KMKemal Bugra Memis
Kemal Bugra Memis
MKMecit Kantarci
Mecit Kantarci
Shear wave elastography (SWE) has become popular in clinical practice for many diseases. However, there is not adequate research on spleen-related diseases. This study aimed to investigate the potential of quantitative values obtained through SWE in evaluating spleen pathologies in the pediatric population and to demonstrate its performance to differentiate splenomegaly-related diseases. The research group retrospectively included children with pathological diagnoses related to the spleen from November 2016 to April 2021, and they were categorized into three groups, including portal hypertension (PH), benign lymphoid hyperplasia (BLH), and malignant infiltration (MI). Spleen sizes and parenchymal stiffness were also calculated for each group. Subsequently, mean spleen stiffness in each group was compared with normal values within the same age group. In total, 2781 children (1379 children for the study group; 1402 children for the control group) were enrolled in the study. The highest stiffness was observed in the PH group, which is statistically higher than others (p < 0.05). Although the mean spleen stiffness in the group with BLH was higher than the control and MI group, the difference was not statistically significant (p = 0.08). The mean stiffness in the group with MI was significantly lower than both the control group (p = 0.005) and PH (p = 0.01). In conclusion, using SWE in the differential diagnosis of etiologies causing splenomegaly could make an important contribution.

1 July 2022 in Journal of Clinical Ultrasound
Verified
Journal Article
Closed access
Sonay AydinSonay Aydin
Sonay Aydin
OTOguzhan Tokur
Oguzhan Tokur
OKOmer Kazci
Omer Kazci
BEBunyamin Ece
Bunyamin Ece
EKErdal Karavaş
Erdal Karavaş
MKMecit Kantarci
Mecit Kantarci

6 May 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
TCTurkhun Cetin
Turkhun Cetin
OTOguzhan Tokur
Oguzhan Tokur
HBHayrunnisa Bekis Bozkurt
Hayrunnisa Bekis Bozkurt
Sonay AydinSonay Aydin
Sonay Aydin
KMKemal Bugra Memis
Kemal Bugra Memis
MKMecit Kantarci
Mecit Kantarci
: Shear-wave elastography (SWE) has become popular in clinical practice for many diseases.However, there are not adequate research for spleen-related diseases.This study aimed to investigate the potential of quantitative values obtained through SWE in evaluating spleen pathologies in the pediatric population and to demonstrate its perfomance to differentiate splenomegaly-related diseases.Research group retrospectively included children with pathological diagnoses related to spleen from November 2016 to April 2021 and they were categorized three groups as portal hypertension (PH), benign lymphoid hyperplasia (BLH), malignant infiltration (MI).Spleen sizes and parenchymal stiffness were also calculated for each group.Subsequently, mean spleen stiffness in each compared with normal values within the same age group.In total 2781 children (1379 children for study group, 1402 children for control group) were enrolled to the study.The highest stiffness were observed in the PH group, which is statistically higher than others (p<0.05). Although the mean spleen stiffness in the group with BLH was higher than the control and MI group, the difference was not statistically significant (p=0.08).The mean stiffness in the group with MI was significantly lower than both the control group (p=0.005) and PH (p=0.01).In conclusion, using SWE in the differential diagnosis of etiologies causing splenomegaly, could make important contribution.