Ismail Okan Yildirim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ismail Okan Yildirim has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Ahmet Sigirci
Bilkent City Hospital, Department of Pediatric Radiology, Ankara, Türkiye
3 shared publications - Ahmet Taner Elmas
Division of Pediatric Nephrology, Department of Pediatrics, Faculty of Medicine, İnönü University, 44280 Malatya, Türkiye
2 shared publications - Ali Atan
Department of Urology, Gazi University School of Medicine, Ankara, Turkey
2 shared publications - Altug Tuncel
Department of Urology, University of Health Sciences, Ankara Bilkent City Hospital, Ankara, Turkey
2 shared publications - Betül Sözeri
University of Health Sciences
2 shared publications - Cagri Senocak
Department of Urology, Ankara Ataturk Sanatorium Training and Research Hospital, Ministry of Health, University of Health Sciences, Ankara, Turkey
2 shared publications
Latest Publications
- Open Access
- 30 June 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (13) , 2054
Perilesional Diffusion Tensor Imaging for Differentiating Malignant and Benign Causes of Intracerebral Hemorrhage
Background/Objectives: To evaluate the discriminative value of perilesional microstructural alterations assessed by diffusion tensor imaging (DTI) parameters in differentiating malignant and benign causes of intracerebral hemorrhage. Methods: This retrospective study included patients with intracerebral hemorrhage classified as benign or malignant based on follow-up findings and histopathological diagnosis. Fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD), mean diffusivity (MD), lesion-to-normal (L/N) ratios, and perilesional edema index (PEI) were extracted from standardized perilesional regions. Diffusion parameters were compared between groups, and their discriminative performance was assessed using ROC analysis and logistic regression. Results: A total of 41 patients (20 benign, 21 malignant) were included. Malignant cases demonstrated significantly greater PEI and distinct diffusion abnormalities, with markedly higher AD, RD, and MD values, as well as elevated L/N ratios (all p < 0.001). FA was significantly reduced in malignant cases (p = 0.016). Conclusions: Diffusivity metrics—particularly AD, RD, and MD values and their L/N ratios—demonstrated excellent diagnostic performance in differentiating malignant from benign causes of intracerebral hemorrhage, further informed by the PEI, and may support clinical decision-making in diagnostically challenging cases.
- 30 June 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (13) , 2054
Open AccessPerilesional Diffusion Tensor Imaging for Differentiating Malignant and Benign Causes of Intracerebral Hemorrhage
Background/Objectives: To evaluate the discriminative value of perilesional microstructural alterations assessed by diffusion tensor imaging (DTI) parameters in differentiating malignant and benign causes of intracerebral hemorrhage. Methods: This retrospective study included patients with intracerebral hemorrhage classified as benign or malignant based on follow-up findings and histopathological diagnosis. Fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD), mean diffusivity (MD), lesion-to-normal (L/N) ratios, and perilesional edema index (PEI) were extracted from standardized perilesional regions. Diffusion parameters were compared between groups, and their discriminative performance was assessed using ROC analysis and logistic regression. Results: A total of 41 patients (20 benign, 21 malignant) were included. Malignant cases demonstrated significantly greater PEI and distinct diffusion abnormalities, with markedly higher AD, RD, and MD values, as well as elevated L/N ratios (all p < 0.001). FA was significantly reduced in malignant cases (p = 0.016). Conclusions: Diffusivity metrics—particularly AD, RD, and MD values and their L/N ratios—demonstrated excellent diagnostic performance in differentiating malignant from benign causes of intracerebral hemorrhage, further informed by the PEI, and may support clinical decision-making in diagnostically challenging cases.
- Open Access
- 12 December 2025
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in TURKISH JOURNAL OF MEDICAL SCIENCES
- Vol. 55 (6) , 1497-1503
Evaluation of the efficacy of radiofrequency ablation therapy in cases with parathyroid adenoma
Background/aim: Radiofrequency ablation of solitary parathyroid adenoma has been used to treat primary hyperparathyroidism (pHPT) in high-risk patients for parathyroidectomy. This study aimed to evaluate the clinical efficacy of radiofrequency ablation for treating pHPT in patients with parathyroid adenomas. Materials and methods: The sample for this retrospective study comprised all consecutive patients with solitary parathyroid adenoma treated with radiofrequency ablation between 2013 and 2021. Patients’ baseline serum calcium and parathyroid hormone (PTH) values were obtained. The patients were followed up with serial biochemical measurements after the intervention, then at the first-week, first-month, third-month, sixth-month, and twelfth-month follow-ups. The study’s primary outcome was a biochemical cure, defined as the reestablishment of normal serum calcium and PTH levels, persisting for at least 6 months after the ablation. Results: The changes in the serum calcium and PTH levels were significant (p < 0.05). The biochemical cure rate was 30.2% at 1 year. At the end of 1 year, the rate of patients with normal serum calcium levels was 86.6%, whereas the rate of patients with normal serum calcium and higher PTH levels was 55.8%. Conclusion: Radiofrequency ablation of a solitary parathyroid adenoma may be considered an alternative treatment for pHPT, given that more than half of the cases investigated in this study had normocalcemic hyperparathyroidism at 1 year.
- 12 December 2025
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in TURKISH JOURNAL OF MEDICAL SCIENCES
- Vol. 55 (6) , 1497-1503
Open AccessEvaluation of the efficacy of radiofrequency ablation therapy in cases with parathyroid adenoma
Background/aim: Radiofrequency ablation of solitary parathyroid adenoma has been used to treat primary hyperparathyroidism (pHPT) in high-risk patients for parathyroidectomy. This study aimed to evaluate the clinical efficacy of radiofrequency ablation for treating pHPT in patients with parathyroid adenomas. Materials and methods: The sample for this retrospective study comprised all consecutive patients with solitary parathyroid adenoma treated with radiofrequency ablation between 2013 and 2021. Patients’ baseline serum calcium and parathyroid hormone (PTH) values were obtained. The patients were followed up with serial biochemical measurements after the intervention, then at the first-week, first-month, third-month, sixth-month, and twelfth-month follow-ups. The study’s primary outcome was a biochemical cure, defined as the reestablishment of normal serum calcium and PTH levels, persisting for at least 6 months after the ablation. Results: The changes in the serum calcium and PTH levels were significant (p < 0.05). The biochemical cure rate was 30.2% at 1 year. At the end of 1 year, the rate of patients with normal serum calcium levels was 86.6%, whereas the rate of patients with normal serum calcium and higher PTH levels was 55.8%. Conclusion: Radiofrequency ablation of a solitary parathyroid adenoma may be considered an alternative treatment for pHPT, given that more than half of the cases investigated in this study had normocalcemic hyperparathyroidism at 1 year.
- 25 April 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (1) , 186-201
Advancing Pulmonary Embolism Detection with Integrated Deep Learning Architectures
The main aim of this study is to introduce a new hybrid deep learning model for biomedical image classification. We propose a novel convolutional neural network (CNN), named HybridNeXt, for detecting pulmonary embolism (PE) from computed tomography (CT) images. To evaluate the HybridNeXt model, we created a new dataset consisting of two classes: (1) PE and (2) control. The HybridNeXt architecture combines different advanced CNN blocks, including MobileNet, ResNet, ConvNeXt, and Swin Transformer. We specifically designed this model to combine the strengths of these well-known CNNs. The architecture also includes stem, downsampling, and output stages. By adjusting the parameters, we developed a lightweight version of HybridNeXt, suitable for clinical use. To further improve the classification performance and demonstrate transfer learning capability, we proposed a deep feature engineering (DFE) method using a multilevel discrete wavelet transform (MDWT). This DFE model has three main phases: (i) feature extraction from raw images and wavelet bands, (ii) feature selection using iterative neighborhood component analysis (INCA), and (iii) classification using a k-nearest neighbors (kNN) classifier. We first trained HybridNeXt on the training images, creating a pretrained HybridNeXt model. Then, using this pretrained model, we extracted features and applied the proposed DFE method for classification. The HybridNeXt model achieved a test accuracy of 90.14%, while our DFE model improved accuracy to 96.35%. Overall, the results confirm that our HybridNeXt architecture is highly accurate and effective for biomedical image classification. The presented HybridNeXt and HybridNeXt-based DFE methods can potentially be applied to other image classification tasks.
- 25 April 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (1) , 186-201
Advancing Pulmonary Embolism Detection with Integrated Deep Learning Architectures
The main aim of this study is to introduce a new hybrid deep learning model for biomedical image classification. We propose a novel convolutional neural network (CNN), named HybridNeXt, for detecting pulmonary embolism (PE) from computed tomography (CT) images. To evaluate the HybridNeXt model, we created a new dataset consisting of two classes: (1) PE and (2) control. The HybridNeXt architecture combines different advanced CNN blocks, including MobileNet, ResNet, ConvNeXt, and Swin Transformer. We specifically designed this model to combine the strengths of these well-known CNNs. The architecture also includes stem, downsampling, and output stages. By adjusting the parameters, we developed a lightweight version of HybridNeXt, suitable for clinical use. To further improve the classification performance and demonstrate transfer learning capability, we proposed a deep feature engineering (DFE) method using a multilevel discrete wavelet transform (MDWT). This DFE model has three main phases: (i) feature extraction from raw images and wavelet bands, (ii) feature selection using iterative neighborhood component analysis (INCA), and (iii) classification using a k-nearest neighbors (kNN) classifier. We first trained HybridNeXt on the training images, creating a pretrained HybridNeXt model. Then, using this pretrained model, we extracted features and applied the proposed DFE method for classification. The HybridNeXt model achieved a test accuracy of 90.14%, while our DFE model improved accuracy to 96.35%. Overall, the results confirm that our HybridNeXt architecture is highly accurate and effective for biomedical image classification. The presented HybridNeXt and HybridNeXt-based DFE methods can potentially be applied to other image classification tasks.
- Open Access
- 30 June 2023
- Published by Cukurova Medical Journal in Cukurova Medical Journal
- Vol. 48 (2) , 706-714
Morphometric examination of the hepatobiliary duct system in healthy individuals and patients with cholelithiasis: A radio-anatomic magnetic resonance cholangiopancreatography study
Purpose: Cholelithiasis is a common gallbladder disease with high morbidity and treatment cost. Although the disease has many formation factors such as bile duct obstruction, congenital anomalies, genetic and metabolic diseases, the main cause is gallstones. The aim of this study is to examine the radio-anatomic and demographic characteristics of the bile ducts of patients who have cholelithiasis due to gallstones by using magnetic resonance cholangiopancreatography (MRCP) and to compare with healthy individuals. Materials and Methods: The study was carried out by retrospectively scanning the MRCP images of 113 patients diagnosed with cholelithiasis and 87 healthy individuals who were referred to the hospital for various indications and had no gallbladder pathology. Results: According to the Spearman rho correlation test performed by ignoring gender, a significant correlation was found between right hepatic duct diameter (RHD-D) and right hepatic duct – cystic duct angle (RHDCD-A), and between left hepatic duct diameter (LHD-D) and common bile duct diameter (CBD-D). In the correlation analysis performed only among males, a significant correlation was found between RHDCD-A and right hepatic duct – left hepatic duct angle (RLHD-A), RHDCD-A and common hepatic duct diameter (CHD-D) parameters. In the correlation analysis performed only among women, a significant relationship was found between age and RHD-D, LHD-D, CHD-D, CBD-D, between RHDCD-A and cystic duct – gallbladder angle (CDG-A), RHD-D, and between CHD-D and cystic duct diameter (CD-D). Conclusion: This study will contribute to literature by revealing the morphometric characteristics and radio- anatomic information of the hepatobiliary systems of both patients with cholelithiasis and healthy individuals.
- 30 June 2023
- Published by Cukurova Medical Journal in Cukurova Medical Journal
- Vol. 48 (2) , 706-714
Open AccessMorphometric examination of the hepatobiliary duct system in healthy individuals and patients with cholelithiasis: A radio-anatomic magnetic resonance cholangiopancreatography study
Purpose: Cholelithiasis is a common gallbladder disease with high morbidity and treatment cost. Although the disease has many formation factors such as bile duct obstruction, congenital anomalies, genetic and metabolic diseases, the main cause is gallstones. The aim of this study is to examine the radio-anatomic and demographic characteristics of the bile ducts of patients who have cholelithiasis due to gallstones by using magnetic resonance cholangiopancreatography (MRCP) and to compare with healthy individuals. Materials and Methods: The study was carried out by retrospectively scanning the MRCP images of 113 patients diagnosed with cholelithiasis and 87 healthy individuals who were referred to the hospital for various indications and had no gallbladder pathology. Results: According to the Spearman rho correlation test performed by ignoring gender, a significant correlation was found between right hepatic duct diameter (RHD-D) and right hepatic duct – cystic duct angle (RHDCD-A), and between left hepatic duct diameter (LHD-D) and common bile duct diameter (CBD-D). In the correlation analysis performed only among males, a significant correlation was found between RHDCD-A and right hepatic duct – left hepatic duct angle (RLHD-A), RHDCD-A and common hepatic duct diameter (CHD-D) parameters. In the correlation analysis performed only among women, a significant relationship was found between age and RHD-D, LHD-D, CHD-D, CBD-D, between RHDCD-A and cystic duct – gallbladder angle (CDG-A), RHD-D, and between CHD-D and cystic duct diameter (CD-D). Conclusion: This study will contribute to literature by revealing the morphometric characteristics and radio- anatomic information of the hepatobiliary systems of both patients with cholelithiasis and healthy individuals.
- 15 January 2023
- Published by LookUs Bilisim A.S. in Medical Records
- Vol. 5 (1) , 20-3
Development of Artificial Intelligence Based Clinical Decision Support System on Medical Images for the Classification of COVID-19
Aim: The first imaging method to play an vital role in the diagnosis of COVID-19 illness is the chest X-ray. Because of the abundance of large-scale annotated picture datasets, convolutional neural networks (CNNs) have shown considerable performance in image recognition/classification. The current study aims to construct a successful deep learning model that can distinguish COVID-19 from healthy controls using chest X-ray images.Material and Methods: The dataset in the study consists of subjects with 912 negative and 912 positive PCR results. A prediction model was built using VGG-16 with transfer learning for classifying COVID-19 chest X-ray images. The data set was split at random into 80% training and 20% testing groups.Results: The accuracy, F1 score, sensitivity, specificity, positive and negative values from the model that can successfully distinguish COVID-19 from healthy controls are 97.3%, 97.3%, 97.8%, 96.7%, 96.7%, and 97.8% regarding the testing dataset, respectively.Conclusion: The suggested technique might greatly improve on current radiology-based methodologies and serve as a beneficial tool for clinicians/radiologists in diagnosing and following up on COVID-19 patients.
- 15 January 2023
- Published by LookUs Bilisim A.S. in Medical Records
- Vol. 5 (1) , 20-3
Development of Artificial Intelligence Based Clinical Decision Support System on Medical Images for the Classification of COVID-19
Aim: The first imaging method to play an vital role in the diagnosis of COVID-19 illness is the chest X-ray. Because of the abundance of large-scale annotated picture datasets, convolutional neural networks (CNNs) have shown considerable performance in image recognition/classification. The current study aims to construct a successful deep learning model that can distinguish COVID-19 from healthy controls using chest X-ray images.Material and Methods: The dataset in the study consists of subjects with 912 negative and 912 positive PCR results. A prediction model was built using VGG-16 with transfer learning for classifying COVID-19 chest X-ray images. The data set was split at random into 80% training and 20% testing groups.Results: The accuracy, F1 score, sensitivity, specificity, positive and negative values from the model that can successfully distinguish COVID-19 from healthy controls are 97.3%, 97.3%, 97.8%, 96.7%, 96.7%, and 97.8% regarding the testing dataset, respectively.Conclusion: The suggested technique might greatly improve on current radiology-based methodologies and serve as a beneficial tool for clinicians/radiologists in diagnosing and following up on COVID-19 patients.
- 21 May 2022
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 279 (11) , 5389-5399
Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors
Purpose To create a new artificial intelligence approach based on deep learning (DL) from multiparametric MRI in the differential diagnosis of common parotid tumors. Methods Parotid tumors were classified using the InceptionResNetV2 DL model and majority voting approach with MRI images of 123 patients. The study was conducted in three stages. At stage I, the classification of the control, pleomorphic adenoma, Warthin tumor and malignant tumor (MT) groups was examined, and two approaches in which MRI sequences were given in combined and non-combined forms were established. At stage II, the classification of the benign tumor, MT and control groups was made. At stage III, patients with a tumor in the parotid gland and those with a healthy parotid gland were classified. Results A stage I, the accuracy value for classification in the non-combined and combined approaches was 86.43% and 92.86%, respectively. This value at stage II and stage III was found respectively as 92.14% and 99.29%. Conclusions The approach presented in this study classifies parotid tumors automatically and with high accuracy using DL models.
- 21 May 2022
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 279 (11) , 5389-5399
Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors
Purpose To create a new artificial intelligence approach based on deep learning (DL) from multiparametric MRI in the differential diagnosis of common parotid tumors. Methods Parotid tumors were classified using the InceptionResNetV2 DL model and majority voting approach with MRI images of 123 patients. The study was conducted in three stages. At stage I, the classification of the control, pleomorphic adenoma, Warthin tumor and malignant tumor (MT) groups was examined, and two approaches in which MRI sequences were given in combined and non-combined forms were established. At stage II, the classification of the benign tumor, MT and control groups was made. At stage III, patients with a tumor in the parotid gland and those with a healthy parotid gland were classified. Results A stage I, the accuracy value for classification in the non-combined and combined approaches was 86.43% and 92.86%, respectively. This value at stage II and stage III was found respectively as 92.14% and 99.29%. Conclusions The approach presented in this study classifies parotid tumors automatically and with high accuracy using DL models.
- Open Access
- 26 November 2021
- Published by Elsevier in Radiology Case Reports
- Vol. 17 (2) , 310-313
Treatment of a patient with carotid blowout syndrome with a new deconstructive embolization technique
- 26 November 2021
- Published by Elsevier in Radiology Case Reports
- Vol. 17 (2) , 310-313
Open AccessTreatment of a patient with carotid blowout syndrome with a new deconstructive embolization technique
- 24 August 2021
- Published by Wiley in International Journal Of Clinical Practice
- Vol. 75 (11) , e14746
Multi‐parameter‐based radiological diagnosis of Chiari Malformation using Machine Learning Technology
Background The known primary radiological diagnosis of Chiari Malformation-I (CM-I) is based on the degree of tonsillar herniation (TH) below the Foramen Magnum (FM). However, recent data also shows the association of such malformation with smaller posterior cranial fossa (PCF) volume and the anatomical issues regarding the Odontoid. This study presents the achieved result regarding some detected potential radiological findings that may aid CM-I diagnosis using several machine learning (ML) algorithms. Materials and Methods Midsagittal T1-weighted MR images were collected in 241 adult patients diagnosed with CM, eleven morphometric measures of the posterior cerebral fossa were performed. Patients whose imaging was performed in the same centre and on the same device were included in the study. By matching age and gender, radiological exams of 100 clinically/radiologically proven symptomatic CM-I cases and 100 healthy controls were assessed. Eleven morphometric measures of the posterior cerebral fossa were examined using 5 designed ML algorithms. Results The mean age of patients was 29.92 ± 15.03 years. The primary presenting symptoms were headaches (62%). Syringomyelia and retrocurved-odontoid were detected in 34% and 8% of patients, respectively. All of the morphometric measures were significantly different between the groups, except for the distance from the dens axis to the posterior margin of FM. The Radom Forest model is found to have the best 1.0 (14 of 14) ratio of accuracy in regard to 14 different combinations of morphometric features. Conclusion Our study indicates the potential usefulness of ML-guided PCF measurements, other than TH, that may be used to predict and diagnose CM-I accurately. Combining two or three preferable osseous structure-based measurements may increase the accuracy of radiological diagnosis of CM-I.
- 24 August 2021
- Published by Wiley in International Journal Of Clinical Practice
- Vol. 75 (11) , e14746
Multi‐parameter‐based radiological diagnosis of Chiari Malformation using Machine Learning Technology
Background The known primary radiological diagnosis of Chiari Malformation-I (CM-I) is based on the degree of tonsillar herniation (TH) below the Foramen Magnum (FM). However, recent data also shows the association of such malformation with smaller posterior cranial fossa (PCF) volume and the anatomical issues regarding the Odontoid. This study presents the achieved result regarding some detected potential radiological findings that may aid CM-I diagnosis using several machine learning (ML) algorithms. Materials and Methods Midsagittal T1-weighted MR images were collected in 241 adult patients diagnosed with CM, eleven morphometric measures of the posterior cerebral fossa were performed. Patients whose imaging was performed in the same centre and on the same device were included in the study. By matching age and gender, radiological exams of 100 clinically/radiologically proven symptomatic CM-I cases and 100 healthy controls were assessed. Eleven morphometric measures of the posterior cerebral fossa were examined using 5 designed ML algorithms. Results The mean age of patients was 29.92 ± 15.03 years. The primary presenting symptoms were headaches (62%). Syringomyelia and retrocurved-odontoid were detected in 34% and 8% of patients, respectively. All of the morphometric measures were significantly different between the groups, except for the distance from the dens axis to the posterior margin of FM. The Radom Forest model is found to have the best 1.0 (14 of 14) ratio of accuracy in regard to 14 different combinations of morphometric features. Conclusion Our study indicates the potential usefulness of ML-guided PCF measurements, other than TH, that may be used to predict and diagnose CM-I accurately. Combining two or three preferable osseous structure-based measurements may increase the accuracy of radiological diagnosis of CM-I.
- 1 March 2021
- Published by Springer Nature in Pediatric Nephrology
- Vol. 36 (7) , 2125-2128
A hypertensive girl with failure to thrive accompanied by gastrointestinal symptoms: Answers
- 1 March 2021
- Published by Springer Nature in Pediatric Nephrology
- Vol. 36 (7) , 2125-2128
A hypertensive girl with failure to thrive accompanied by gastrointestinal symptoms: Answers