Raşit Eren Büyüktoka

Dr. Raşit Eren Büyüktoka

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
30 July 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
ASAli Salbas
Ali Salbas
RBRaşit Eren Büyüktoka
Raşit Eren Büyüktoka
Background/Objectives: Multimodal large language models (LLMs) are increasingly used in radiology. However, their ability to recognize fundamental imaging features, including modality, anatomical region, imaging plane, contrast-enhancement status, and particularly specific magnetic resonance imaging (MRI) sequences, remains underexplored. This study aims to evaluate and compare the performance of three advanced multimodal LLMs (ChatGPT-4o, Claude 4 Opus, and Gemini 2.5 Pro) in classifying brain MRI sequences. Methods: A total of 130 brain MRI images from adult patients without pathological findings were used, representing 13 standard MRI series. Models were tested using zero-shot prompts for identifying modality, anatomical region, imaging plane, contrast-enhancement status, and MRI sequence. Accuracy was calculated, and differences among models were analyzed using Cochran’s Q test and McNemar test with Bonferroni correction. Results: ChatGPT-4o and Gemini 2.5 Pro achieved 100% accuracy in identifying the imaging plane and 98.46% in identifying contrast-enhancement status. MRI sequence classification accuracy was 97.7% for ChatGPT-4o, 93.1% for Gemini 2.5 Pro, and 73.1% for Claude 4 Opus (p < 0.001). The most frequent misclassifications involved fluid-attenuated inversion recovery (FLAIR) sequences, often misclassified as T1-weighted or diffusion-weighted sequences. Claude 4 Opus showed lower accuracy in susceptibility-weighted imaging (SWI) and apparent diffusion coefficient (ADC) sequences. Gemini 2.5 Pro exhibited occasional hallucinations, including irrelevant clinical details such as “hypoglycemia” and “Susac syndrome.” Conclusions: Multimodal LLMs demonstrate high accuracy in basic MRI recognition tasks but vary significantly in specific sequence classification tasks. Hallucinations emphasize caution in clinical use, underlining the need for validation, transparency, and expert oversight.

12 August 2025 in Academic Radiology
Verified
Journal Article
Closed access
RBRaşit Eren Büyüktoka
Raşit Eren Büyüktoka
ASAli Salbas
Ali Salbas

20 August 2025 in European Radiology
Verified
Journal Article
Closed access
PDF file
BÜBüyüktoka
Büyüktoka
RBRaşit Eren Büyüktoka
Raşit Eren Büyüktoka
MSMurat Surucu
Murat Surucu
EDErekli Derinkaya
Erekli Derinkaya
PBPelin Berfin
Pelin Berfin
EIElif Isiklar
Elif Isiklar

26 August 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
ASAli Salbas
Ali Salbas
RBRaşit Eren Büyüktoka
Raşit Eren Büyüktoka
Background/Objectives: A varicocele is a common, treatable cause of male infertility involving testicular alterations. Shear wave elastography (SWE) is a noninvasive imaging technique that may detect testicular changes. This study aimed to assess the testicular volume and stiffness (using SWE), compare them with healthy controls, and examine the associations with venous diameter and semen parameters. Methods: This prospective comparative study included 69 patients with a varicocele and 76 healthy controls. The testicular stiffness and volume were measured and compared among three groups: testes with a varicocele (Group A), contralateral healthy testes of the same patients (Group B), and testes of healthy individuals (Group C). In varicocele patients, the semen analysis results were compared with testicular stiffness and volume. The statistical analyses included an ANOVA, Kruskal–Wallis tests, a correlation analysis, and a receiver operating characteristic curve analysis. Results: Group A showed a significantly lower testicular volume compared to Group B (p = 0.004) and Group C (p < 0.001), and significantly higher SWE values compared to both groups (p < 0.001). No significant differences were observed between Group B and Group C (volume: p = 0.642; SWE: p = 0.094). In oligospermic varicocele patients, the testicular stiffness tended to be higher, though the difference was not significant (p = 0.051). The correlations between the testicular stiffness and volume (Group A: p = 0.488; Group B: p = 0.872; Group C: p = 0.222), between the venous diameter and stiffness (p = 0.067), and between the venous diameter and testicular volume (p = 0.245) were not statistically significant. The SWE cut-off value of 9.26 kPa provided a sensitivity of 73.1% (95% CI: 62.3–81.7%) and a specificity of 79.6% (95% CI: 72.5–85.2%) for identifying varicoceles. Conclusions: Varicoceles are associated with an increased testicular stiffness and a decreased volume, which may indicate possible structural parenchymal alterations. Shear wave elastography appeared to be capable of noninvasively detecting these changes and may have potential as a quantitative adjunct tool for evaluating testicular parenchymal changes in varicocele patients. However, further studies are required to validate these preliminary findings.

27 October 2025 in Diagnostic and Interventional Radiology
Verified
Journal Article
Open access
PDF file
RBRaşit Eren Büyüktoka
Raşit Eren Büyüktoka
ZAZehra Hilal Adıbelli
Zehra Hilal Adıbelli
MSMurat Sürücü
Murat Sürücü
ÖÖÖzlem Özdemir
Özlem Özdemir
YIYalçın İşLer
Yalçın İşLer
AOAyşenur Oktay
Ayşenur Oktay
Magnetic resonance imaging-based artificial intelligence model predicts neoadjuvant therapy response in triple-negative breast cancer - Diagnostic and Interventional Radiology

22 July 2026 in European Radiology
Verified
Journal Article
Closed access
RBRaşit Eren Büyüktoka
Raşit Eren Büyüktoka
ASAli Salbas
Ali Salbas