Ezgi Guler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ezgi Guler has a total of 212 co-authors. Here are the top co-authors by number of shared publications:
Nikhil H. Ramaiya
University Hospitals Cleveland Medical Center, Department of Radiology, 11100 Euclid Ave, Cleveland, OH 44106, USA
6 shared publicationsSree Harsha Tirumani
University Hospitals Cleveland Medical Center, Department of Radiology, 11100 Euclid Ave, Cleveland, OH 44106, USA
5 shared publicationsDaniel A. Smith
University Hospitals Cleveland Medical Center, Department of Radiology, 11100 Euclid Ave, Cleveland, OH 44106, USA
4 shared publications- Mustafa Harman
Department of Radiology, Ege University School of Medicine, İzmir, Turkey
4 shared publications - Nevra Elmas
Department of Radiology, Ege University School of Medicine, İzmir, Turkey
3 shared publications - Nikhil H. Ramaiya
Department of Radiology, University Hospitals Cleveland Medical Center/Case Western Reserve University, 11100 Euclid Avenue, Cleveland, OH 44106, USA
3 shared publications
Latest Publications
- Open Access
- 31 July 2026
- Published by Springer Nature in BMC Medical Imaging
- Vol. 26 (1)
Combined radiological approach for characterization of solid renal masses: a proposed strategy for integrating the RENAL nephrometry score into the clear cell likelihood score
- 31 July 2026
- Published by Springer Nature in BMC Medical Imaging
- Vol. 26 (1)
Open AccessCombined radiological approach for characterization of solid renal masses: a proposed strategy for integrating the RENAL nephrometry score into the clear cell likelihood score
- 10 June 2026
- Published by Ege Journal of Medicine in Ege Tıp Dergisi
- Vol. 65 (2) , 313-320
Integration of radiomics with MRI clear cell likelihood score for classification of clear cell renal cell carcinoma
Aim: To compare the diagnostic performance of the MRI-based clear cell likelihood score (ccLS), radiomics-based machine learning models, and their combination for differentiating clear cell renal cell carcinoma (ccRCC) from other renal tumor subtypes.Materials and Methods: This single-center retrospective study included patients with solid renal masses who underwent multiparametric MRI and had histopathologic confirmation. Lesions were evaluated using ccLS by two independent readers. Radiomic features were extracted from T1-weighted and T2-weighted images following standardized preprocessing. Multiple machine learning pipelines combining different feature selection methods and classifiers were evaluated using stratified 10-fold cross-validation with four repetitions. Using multivariable logistic regression, the radiomics score together with clinical factors and semantic imaging features were evaluated, and a nomogram was constructed based on the selected variables.Results: For differentiating ccRCC from other renal tumor subtypes, the ccLS model achieved an area under the receiver operating characteristic curve (AUC) of 0.832 (0.759–0.899). The best-performing radiomics-based machine learning model achieved a mean AUC of 0.89 ± 0.10. The combined model demonstrated higher diagnostic performance, with a mean AUC of 0.96 ± 0.01.Conclusions: Combining radiomics-based machine learning with established semantic MRI assessments was associated with improved differentiation of ccRCC from other renal tumor subtypes compared with individual approaches. Further validation in larger, multicenter cohorts is warranted before broader clinical application.
- 10 June 2026
- Published by Ege Journal of Medicine in Ege Tıp Dergisi
- Vol. 65 (2) , 313-320
Integration of radiomics with MRI clear cell likelihood score for classification of clear cell renal cell carcinoma
Aim: To compare the diagnostic performance of the MRI-based clear cell likelihood score (ccLS), radiomics-based machine learning models, and their combination for differentiating clear cell renal cell carcinoma (ccRCC) from other renal tumor subtypes.Materials and Methods: This single-center retrospective study included patients with solid renal masses who underwent multiparametric MRI and had histopathologic confirmation. Lesions were evaluated using ccLS by two independent readers. Radiomic features were extracted from T1-weighted and T2-weighted images following standardized preprocessing. Multiple machine learning pipelines combining different feature selection methods and classifiers were evaluated using stratified 10-fold cross-validation with four repetitions. Using multivariable logistic regression, the radiomics score together with clinical factors and semantic imaging features were evaluated, and a nomogram was constructed based on the selected variables.Results: For differentiating ccRCC from other renal tumor subtypes, the ccLS model achieved an area under the receiver operating characteristic curve (AUC) of 0.832 (0.759–0.899). The best-performing radiomics-based machine learning model achieved a mean AUC of 0.89 ± 0.10. The combined model demonstrated higher diagnostic performance, with a mean AUC of 0.96 ± 0.01.Conclusions: Combining radiomics-based machine learning with established semantic MRI assessments was associated with improved differentiation of ccRCC from other renal tumor subtypes compared with individual approaches. Further validation in larger, multicenter cohorts is warranted before broader clinical application.
- Open Access
- 27 April 2026
- Published by Galenos Yayinevi in Türk Radyoloji Seminerleri
- Vol. 14 (1) , 99-113
Benign Focal Lesions of the Liver
Benign Focal Lesions of the Liver - Türk Radyoloji Seminerleri
- 27 April 2026
- Published by Galenos Yayinevi in Türk Radyoloji Seminerleri
- Vol. 14 (1) , 99-113
Open AccessBenign Focal Lesions of the Liver
Benign Focal Lesions of the Liver - Türk Radyoloji Seminerleri
- 7 January 2026
- Published by Elsevier in Transplantation Proceedings
- Vol. 58 (1) , 130-136
Evaluation of Donor Exclusions for Living Donor Liver Transplantation in a Tertiary Center
- 7 January 2026
- Published by Elsevier in Transplantation Proceedings
- Vol. 58 (1) , 130-136
Evaluation of Donor Exclusions for Living Donor Liver Transplantation in a Tertiary Center
- Open Access
- 3 November 2025
- Published by Galenos Yayinevi in Diagnostic and Interventional Radiology
Reply: challenges of applying large language models to image-based interpretation in abdominal radiology
Reply: challenges of applying large language models to image-based interpretation in abdominal radiology - Diagnostic and Interventional Radiology
- 3 November 2025
- Published by Galenos Yayinevi in Diagnostic and Interventional Radiology
Open AccessReply: challenges of applying large language models to image-based interpretation in abdominal radiology
Reply: challenges of applying large language models to image-based interpretation in abdominal radiology - Diagnostic and Interventional Radiology
- Open Access
- 7 August 2025
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (15) , 5566
Adrenal Hematoma Volume as a Predictor of Morbidity and Mortality in Traumatic Adrenal Injury
Background: Traumatic adrenal injury (TAI) is a rare but significant condition that affects 2.5% of patients with thoracoabdominal trauma. The impact of adrenal hematoma volume on clinical outcomes remains underexplored. This study aimed to evaluate factors associated with morbidity and mortality in patients with TAI, with a particular focus on adrenal hematoma volume as a predictive marker. Methods: Retrospective data from patients with radiologically confirmed TAI between 2013 and 2023 was analyzed. Clinical, demographic, and radiological variables were reviewed. Hematoma volume was calculated from computed tomography (CT) imaging and analyzed using univariate and multivariate models. Receiver operating characteristic (ROC) analysis was employed to evaluate its predictive accuracy. Results: Sixty patients were included in the study. The median hematoma volume was 16.0 cm3, with a predominance of injuries on the right side. The morbidity and mortality rates were 18.3% and 8.3%, respectively. Univariate analysis identified a lower Glasgow Coma Scale (GCS) score, higher Injury Severity Score (ISS), and increased hematoma volume as significant factors. In multivariate analysis, hematoma volume and GCS score remained independent predictors of adverse outcomes. A volume threshold of >23 cm3 was associated with significantly higher morbidity and mortality (AUC = 0.80, 95% CI: 0.68–0.92). Conclusions: This study is the first to demonstrate that the volume of adrenal hematoma is an independent predictor of adverse outcomes in patients with traumatic adrenal injury. Integrating volume into clinical assessment may help identify high-risk patients requiring improved observation and management.
- 7 August 2025
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (15) , 5566
Open AccessAdrenal Hematoma Volume as a Predictor of Morbidity and Mortality in Traumatic Adrenal Injury
Background: Traumatic adrenal injury (TAI) is a rare but significant condition that affects 2.5% of patients with thoracoabdominal trauma. The impact of adrenal hematoma volume on clinical outcomes remains underexplored. This study aimed to evaluate factors associated with morbidity and mortality in patients with TAI, with a particular focus on adrenal hematoma volume as a predictive marker. Methods: Retrospective data from patients with radiologically confirmed TAI between 2013 and 2023 was analyzed. Clinical, demographic, and radiological variables were reviewed. Hematoma volume was calculated from computed tomography (CT) imaging and analyzed using univariate and multivariate models. Receiver operating characteristic (ROC) analysis was employed to evaluate its predictive accuracy. Results: Sixty patients were included in the study. The median hematoma volume was 16.0 cm3, with a predominance of injuries on the right side. The morbidity and mortality rates were 18.3% and 8.3%, respectively. Univariate analysis identified a lower Glasgow Coma Scale (GCS) score, higher Injury Severity Score (ISS), and increased hematoma volume as significant factors. In multivariate analysis, hematoma volume and GCS score remained independent predictors of adverse outcomes. A volume threshold of >23 cm3 was associated with significantly higher morbidity and mortality (AUC = 0.80, 95% CI: 0.68–0.92). Conclusions: This study is the first to demonstrate that the volume of adrenal hematoma is an independent predictor of adverse outcomes in patients with traumatic adrenal injury. Integrating volume into clinical assessment may help identify high-risk patients requiring improved observation and management.
- Open Access
- 13 January 2025
- Published by Galenos Yayinevi in Diagnostic and Interventional Radiology
- Vol. 31 (4) , 331-332
Reply: evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images
Reply: evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images - Diagnostic and Interventional Radiology
- 13 January 2025
- Published by Galenos Yayinevi in Diagnostic and Interventional Radiology
- Vol. 31 (4) , 331-332
Open AccessReply: evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images
Reply: evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images - Diagnostic and Interventional Radiology
- 10 December 2024
- Published by Elsevier in Current Problems in Diagnostic Radiology
- Vol. 54 (4) , 460-464
Tumor mutational burden as a marker for radiologic response to immune checkpoint inhibitors
- 10 December 2024
- Published by Elsevier in Current Problems in Diagnostic Radiology
- Vol. 54 (4) , 460-464
Tumor mutational burden as a marker for radiologic response to immune checkpoint inhibitors
- Open Access
- 6 November 2024
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 20 (1) , 1-11
Solitary Fibrous Tumors: A Rare Tumor Arising from Ubiquitous Anatomical Locations
Solitary fibrous tumors (SFTs) are uncommon mesenchymal tumors of fibroblastic/myofibroblastic origin that stem from various anatomical sites. Most SFTs are asymptomatic and noticed incidentally by various imaging modalities. Although SFTs were initially identified in the pleura and erroneously considered to originate solely from serosal layers, extrapleural SFTs have been reported more commonly than their pleural counterparts. Imaging features are similar in different anatomical locations and are mainly related to the tumor’s size and collagen content, characteristically displaying low signal intensity on magnetic resonance imaging. Smaller tumors typically exhibit uniform enhancement, yet necrotic regions may become evident as the tumor size increases, resulting in heterogeneous enhancement. Less than 30% of SFTs demonstrate unfavorable clinical outcomes regardless of their histological features, warranting surgery as the preferred treatment with long-term follow-up. In this article, we have reviewed the clinical manifestations and imaging features of SFTs, discussed their differential diagnosis based on anatomical site, and provided diagnostic pearls.
- 6 November 2024
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 20 (1) , 1-11
Open AccessSolitary Fibrous Tumors: A Rare Tumor Arising from Ubiquitous Anatomical Locations
Solitary fibrous tumors (SFTs) are uncommon mesenchymal tumors of fibroblastic/myofibroblastic origin that stem from various anatomical sites. Most SFTs are asymptomatic and noticed incidentally by various imaging modalities. Although SFTs were initially identified in the pleura and erroneously considered to originate solely from serosal layers, extrapleural SFTs have been reported more commonly than their pleural counterparts. Imaging features are similar in different anatomical locations and are mainly related to the tumor’s size and collagen content, characteristically displaying low signal intensity on magnetic resonance imaging. Smaller tumors typically exhibit uniform enhancement, yet necrotic regions may become evident as the tumor size increases, resulting in heterogeneous enhancement. Less than 30% of SFTs demonstrate unfavorable clinical outcomes regardless of their histological features, warranting surgery as the preferred treatment with long-term follow-up. In this article, we have reviewed the clinical manifestations and imaging features of SFTs, discussed their differential diagnosis based on anatomical site, and provided diagnostic pearls.
- Open Access
- 19 August 2024
- Published by Galenos Yayinevi in Diagnostic and Interventional Radiology
- Vol. 31 (3) , 196-205
Evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images
Evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images - Diagnostic and Interventional Radiology
- 19 August 2024
- Published by Galenos Yayinevi in Diagnostic and Interventional Radiology
- Vol. 31 (3) , 196-205
Open AccessEvaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images
Evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images - Diagnostic and Interventional Radiology