Hamza Eren Guzel

Dr. Hamza Eren Guzel

Izmir City Hospital, İzmir, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
24 November 2023 in Journal of Personalized Medicine
Verified
Journal Article
Open access
PDF file
Babak SaraviBabak Saravi
Babak Saravi
Hamza Eren GuzelHamza Eren Guzel
Hamza Eren Guzel
AZAlisia Zink
Alisia Zink
SÜSara Ülkümen
Sara Ülkümen
Sebastien Couillard-DespresSebastien Couillard-Despres
Sebastien Couillard-Despres
FHFrank Hassel
Frank Hassel
Computed tomography (CT) offers detailed insights into the internal anatomy of patients, particularly for spinal vertebrae examination. However, CT scans are associated with higher radiation exposure and cost compared to conventional X-ray imaging. In this study, we applied a Generative Adversarial Network (GAN) framework to reconstruct 3D spinal vertebrae structures from synthetic biplanar X-ray images, specifically focusing on anterior and lateral views. The synthetic X-ray images were generated using the DRRGenerator module in 3D Slicer by incorporating segmentations of spinal vertebrae in CT scans for the region of interest. This approach leverages a novel feature fusion technique based on X2CT-GAN to combine information from both views and employs a combination of mean squared error (MSE) loss and adversarial loss to train the generator, resulting in high-quality synthetic 3D spinal vertebrae CTs. A total of n = 440 CT data were processed. We evaluated the performance of our model using multiple metrics, including mean absolute error (MAE) (for each slice of the 3D volume (MAE0) and for the entire 3D volume (MAE)), cosine similarity, peak signal-to-noise ratio (PSNR), 3D peak signal-to-noise ratio (PSNR-3D), and structural similarity index (SSIM). The average PSNR was 28.394 dB, PSNR-3D was 27.432, SSIM was 0.468, cosine similarity was 0.484, MAE0 was 0.034, and MAE was 85.359. The results demonstrated the effectiveness of this approach in reconstructing 3D spinal vertebrae structures from biplanar X-rays, although some limitations in accurately capturing the fine bone structures and maintaining the precise morphology of the vertebrae were present. This technique has the potential to enhance the diagnostic capabilities of low-cost X-ray machines while reducing radiation exposure and cost associated with CT scans, paving the way for future applications in spinal imaging and diagnosis.

28 June 2020 in Journal of Urological Surgery
Verified
Journal Article
Closed access
DBDeniz Bolat
Deniz Bolat
AEAnıl EKER
Anıl EKER
Hamza Eren GuzelHamza Eren Guzel
Hamza Eren Guzel
TDTansu Değirmenci
Tansu Değirmenci

13 February 2026 in Academic Radiology
Verified
Journal Article
Closed access
Hamza Eren GuzelHamza Eren Guzel
Hamza Eren Guzel
LOLaura Oleaga
Laura Oleaga
AKAli Murat Koç
Ali Murat Koç
VJVanesa Junquero
Vanesa Junquero
CMCristina Merino
Cristina Merino

9 May 2025 in Frontiers in Radiology
Verified
Journal Article
Open access
PDF file
Hamza Eren GuzelHamza Eren Guzel
Hamza Eren Guzel
GAGöktuğ Aşcı
Göktuğ Aşcı
ODOytun Demirbilek
Oytun Demirbilek
TÖTuğçe Doğa Özdemir
Tuğçe Doğa Özdemir
PEPelin Berfin Erekli
Pelin Berfin Erekli
Objective: This study aimed to determine the diagnostic precision of a deep learning algorithm for the classificaiton of non-contrast brain CT reports. Methods: A total of 1,861 non-contrast brain CT reports were randomly selected, anonymized, and annotated for urgency level by two radiologists, with review by a senior radiologist. The data, encrypted and stored in Excel format, were securely maintained on a university cloud system. Using Python 3.8.16, the reports were classified into four urgency categories: emergency, not emergency but needs timely attention, clinically non-significant and normal. The dataset was split, with 800 reports used for training and 200 for validation. The DistilBERT model, featuring six transformer layers and 66 million trainable parameters, was employed for text classification. Training utilized the Adam optimizer with a learning rate of 2e-5, a batch size of 32, and a dropout rate of 0.1 to prevent overfitting. The model achieved a mean F1 score of 0.85 through 5-fold cross-validation, demonstrating strong performance in categorizing radiology reports. Results: Of the 1,861 scans, 861 cases were identified as fit for study through the senior radiologist and self-hosted Label Studio interpretations. It was observed that the algorithm achieved a sensitivity of 91% and a specificity of 90% in the measurements made on the test data. The F1 score was measured as 0.89 for the best fold. The algorithm most successfully distinguished emergency results with positive predictive values that were unexpectedly lower than in previously reported studies. Beam hardening artifacts and excessive noise, compromising the quality of CT scan images, were significantly associated with decreased model performance. Conclusion: The proposed deep learning algorithm demonstrated high diagnostic accuracy, sensitivity, and specificity in classifying non-contrast brain CT reports. These results indicate the feasibility of automated identification of critical cases, which may support workflow efficiency and timely patient management in radiology practice.

18 October 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
Babak SaraviBabak Saravi
Babak Saravi
Hamza Eren GuzelHamza Eren Guzel
Hamza Eren Guzel
AZAlisia Zink
Alisia Zink
SÜSara Ülkümen
Sara Ülkümen
Sebastien Couillard-DespresSebastien Couillard-Despres
Sebastien Couillard-Despres
FHFrank Hassel
Frank Hassel
Computed tomography (CT) offers detailed insights into the internal anatomy of patients, partic-ularly for spinal vertebrae examination. However, CT scans are associated with higher radiation exposure and cost compared to conventional X-ray imaging. In this study, we applied a Genera-tive Adversarial Network (GAN) framework to reconstruct 3D spinal vertebrae structures from synthetic biplanar X-ray images, specifically focusing on anterior and lateral views. The synthetic X-ray images were generated using the DRRGenerator module in 3D Slicer, by incorporating segmentations of spinal vertebrae in CT scans for the region of interest focussing. The approach leverages a novel feature fusion technique based on X2CT-GAN to combine information from both views and employs a combination of Mean Squared Error (MSE) loss and adversarial loss to train the generator, resulting in high-quality synthetic 3D spinal vertebrae CTs. A total of n=440 CT data were processed. We evaluated the performance of our model using multiple metrics, in-cluding Mean Absolute Error (MAE) (for each slice of the 3D volume [MAE0] and for the entire 3D volume [MAE]), Cosine Similarity, Peak Signal-to-Noise Ratio (PSNR), 3D Peak Sig-nal-to-Noise Ratio (PSNR-3D), and Structural Similarity Index (SSIM). The average PSNR was 28.394 dB, PSNR-3D was 27.432, SSIM was 0.468, cosine similarity was 0.484, MAE0 was 0.034, and MAE was 85.359. The results demonstrated the effectiveness of the approach in reconstruct-ing 3D spinal vertebrae structures from biplanar X-rays, although some limitations in accurately capturing the fine bone structures and maintaining the precise morphology of the vertebrae were present. This technique has the potential to enhance the diagnostic capabilities of low-cost X-ray machines while reducing radiation exposure and cost associated with CT scans, paving the way for future applications in spinal imaging and diagnosis.

23 May 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
Hamza Eren GuzelHamza Eren Guzel
Hamza Eren Guzel
CÖCemre Özenbaş
Cemre Özenbaş
Babak SaraviBabak Saravi
Babak Saravi
Background: Accurate identification and positioning of thoracic devices on chest radiographs is critical for patient safety in intensive care. Multimodal large language models (LLMs) offer potentially generalizable automated evaluation, but their performance in this domain is underexplored. Methods: Three multimodal LLMs (GPT-4o, gpt-4o-2024-08-06; Gemini 3.1 Flash Lite Preview; Claude Sonnet 4.6) were evaluated on 4813 chest radiographs from the RANZCR CLiP dataset for device presence and positioning of ETT, NGT, CVC, and Swan–Ganz catheters. Performance was quantified with 95% Wilson confidence intervals, balanced accuracy, MCC, Cochran’s Q, Bonferroni-corrected McNemar, and Cohen’s/Fleiss’ kappa. Six additional analyses were performed: a blinded paired reader study (n = 377; two board-certified radiologists, blinded to ground truth and to all LLM outputs), external validation on PadChest (n = 200, device-presence detection only—PadChest lacks granular position labels), three-variant prompt-sensitivity analysis (n = 103), repeat-inference stability across three runs (n = 50), systematic error taxonomy, and a failure-case analysis. Results: Device-presence performance varied widely across models; abnormal-position sensitivity was uniformly poor (MCC ≤ 0.028; balanced accuracy 0.41–0.53). Inter-model agreement was poor to slight (Fleiss’ κ: 0.005–0.383 for presence; −0.280 to −0.025 for classification). Radiologists numerically outperformed all three LLMs in 42/42 paired comparisons; the superiority was statistically significant after Bonferroni correction in 33/42 (32/42 at p < 0.001). PadChest replicated the negative finding for device-presence detection (malposition not externally validated). Prompts and inference stochasticity introduced 2–3× sensitivity swings and run-to-run κ from 0.20 to 0.85. Case failures concentrated systematically in multi-device cases (p < 0.0001) but not in abnormal-position cases (p = 0.14). Conclusions: Current general-purpose multimodal LLMs are not yet reliable for autonomous thoracic-device assessment; their failure patterns are structurally characterizable across models, prompts, and case types and support, at most a circumscribed role, as adjunct device-presence screening tools. The findings do not generalize to purpose-built, regulator-approved clinical AI systems.