Onur Mutlu

Mr. Onur Mutlu

Faculty of Science, Karadeniz Technical University, Trabzon, Turkey (Türkiye)
orcid
Research Assistant in the Department of Computer Science, Fa...

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

5 August 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
Ugur SevikUgur Sevik
Ugur Sevik
Onur MutluOnur Mutlu
Onur Mutlu
Background/Objectives: The diagnosis of pediatric dental conditions from panoramic radiographs is uniquely challenging due to the dynamic nature of the mixed dentition phase, which can lead to subjective and inconsistent interpretations. This study aims to develop and rigorously validate an advanced deep learning model to enhance diagnostic accuracy and efficiency in pediatric dentistry, providing an objective tool to support clinical decision-making. Methods: An initial comparative study of four state-of-the-art YOLO variants (YOLOv8, v9, v10, and v11) was conducted to identify the optimal architecture for detecting four common findings: Dental Caries, Deciduous Tooth, Root Canal Treatment, and Pulpotomy. A stringent two-tiered validation strategy was employed: a primary public dataset (n = 644 images) was used for training and model selection, while a completely independent external dataset (n = 150 images) was used for final testing. All annotations were validated by a dual-expert team comprising a board-certified pediatric dentist and an experienced oral and maxillofacial radiologist. Results: Based on its leading performance on the internal validation set, YOLOv11x was selected as the optimal model, achieving a mean Average Precision (mAP50) of 0.91. When evaluated on the independent external test set, the model demonstrated robust generalization, achieving an overall F1-Score of 0.81 and a mAP50 of 0.82. It yielded clinically valuable recall rates for therapeutic interventions (Root Canal Treatment: 88%; Pulpotomy: 86%) and other conditions (Deciduous Tooth: 84%; Dental Caries: 79%). Conclusions: Validated through a rigorous dual-dataset and dual-expert process, the YOLOv11x model demonstrates its potential as an accurate and reliable tool for automated detection in pediatric panoramic radiographs. This work suggests that such AI-driven systems can serve as valuable assistive tools for clinicians by supporting diagnostic workflows and contributing to the consistent detection of common dental findings in pediatric patients.

29 October 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
Ugur SevikUgur Sevik
Ugur Sevik
Onur MutluOnur Mutlu
Onur Mutlu
Background/Objectives: The prevailing paradigm in ophthalmic AI involves siloed, single-disease models, which fails to address the complexity of differential diagnosis in clinical practice. This study aimed to develop and validate a unified deep learning framework for the automated multi-class classification of a wide spectrum of retinal pathologies from fundus photographs, moving beyond the single-disease paradigm to create a comprehensive screening tool. Methods: A publicly available dataset was manually curated by an ophthalmologist, resulting in 1841 images across nine classes, including Diabetic Retinopathy, Glaucoma, and Healthy retinas. After extensive data augmentation to mitigate class imbalance, three pre-trained CNN architectures (ResNet-152, EfficientNetV2, and a YOLOv11-based classifier) were comparatively evaluated. The models were trained using transfer learning and their performance was assessed on an independent test set using accuracy, macro-averaged F1-score, and Area Under the Curve (AUC). Results: The YOLOv11-based classifier demonstrated superior performance over the other architectures on the validation set. On the final independent test set, it achieved a robust overall accuracy of 0.861 and a macro-averaged F1-score of 0.861. The model yielded a validation set AUC of 0.961, which was statistically superior to both ResNet-152 (p < 0.001) and EfficientNetV2 (p < 0.01) as confirmed by the DeLong test. Conclusions: A unified deep learning framework, leveraging a YOLOv11 backbone, can accurately classify nine distinct retinal conditions from a single fundus photograph. This holistic approach moves beyond the limitations of single-disease algorithms, offering considerable promise as a comprehensive AI-driven screening tool to augment clinical decision-making and enhance diagnostic efficiency in ophthalmology.

16 February 2026 in Odontology
Verified
Journal Article
Open access
PDF file
Onur MutluOnur Mutlu
Onur Mutlu
EAElif Aslan
Elif Aslan
AMAli Mert
Ali Mert
Automated diagnostic charting on panoramic radiographs is essential for optimizing clinical workflows and reducing diagnostic variability. This study aims to perform a comparative performance analysis of two next-generation deep learning architectures, YOLOv11 and YOLOv12, for the automated detection of 13 different dental conditions. A hybrid dataset consisting of 2,297 panoramic radiographs was compiled, comprising 1,579 images from a single institution and 718 external images from Roboflow Universe to test generalization. The models were trained to detect conditions including caries, implants, bone loss, and impactions using a standardized training protocol. Performance was evaluated using mean Average Precision (mAP@0.5), Precision, Recall, and F1-score on both internal and external test sets. YOLOv11 demonstrated superior performance compared to YOLOv12, achieving a mAP@0.5 of 0.857 on the internal test set. Furthermore, YOLOv11 exhibited robust generalization capabilities, maintaining a mAP@0.5 of 0.806 on the unseen external dataset. While detection rates were high for well-defined objects like crowns and implants, performance was lower for subtle pathologies such as bone loss and caries. The findings identify YOLOv11 as the more robust and reliable architecture for multi-class dental object detection compared to the newer YOLOv12. The proposed model holds significant potential as a clinical decision support tool, serving as a reliable "second opinion" to enhance diagnostic accuracy and efficiency in daily practice.

3 July 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Ugur SevikUgur Sevik
Ugur Sevik
Onur MutluOnur Mutlu
Onur Mutlu
Background/Objectives: The diagnosis of pediatric dental conditions from panoramic radiographs is uniquely challenging due to the dynamic nature of the mixed dentition phase, which can lead to subjective and inconsistent interpretations. This study aims to develop and rigorously validate an advanced deep learning model to enhance diagnostic accuracy and efficiency in pediatric dentistry, providing an objective tool to support clinical decision-making. Methods: YOLO object detection models was developed for the automated identification of four conditions: Dental Caries, Deciduous Tooth, Root Canal Treatment, and Pulpotomy. A stringent two-tiered validation strategy was employed: a primary public dataset (n=644 images) was used for training and the comparative selection of YOLOv11x, while a completely independent external dataset (n=150 images) was used for final testing. All annotations across both datasets were validated by a dual-expert team, comprising a radiologist and a pediatric dentist, ensuring high-quality ground truth. Results: On internal validation, YOLOv11x was selected as the optimal model, achieving a superior mean Average Precision (mAP50) of 0.91. More significantly, when evaluated on the independent external test set, the model demonstrated robust generalization with an overall F1-Score of 0.81 and an mAP50 of 0.82. It yielded strong recall rates for therapeutic interventions (Root Canal Treatment: 88%, Pulpotomy: 86%) and clinically relevant rates for other conditions (Deciduous Tooth: 84%, Dental Caries: 79%). Conclusions: Validated through a rigorous dual-dataset and dual-expert process, the YOLOv11x model proves to be an accurate and reliable tool for automated detection in pediatric panoramic radiographs. This work provides strong evidence that AI-driven systems can augment clinical decision-making, enhance diagnostic precision, and ultimately contribute to improved dental healthcare outcomes for children.

18 March 2026 in PLOS ONE
Verified
Journal Article
Open access
PDF file
Ugur SevikUgur Sevik
Ugur Sevik
Onur MutluOnur Mutlu
Onur Mutlu
Accurate classification of skin burn depth is vital for determining appropriate treatment and accelerating the healing process. This study conducts a comparative analysis of YOLO-based deep learning architectures for the automated classification of skin burns. Analyses were performed on a robust, multi-source dataset created by combining a proprietary collection of 358 retrospective images from Karadeniz Technical University Farabi Hospital with two large public datasets from Roboflow Universe and Kaggle. All images were meticulously labeled into four burn degrees by expert general surgeons. To enhance model performance and generalizability, various data augmentation and preprocessing techniques were applied. Segmentation-based versions of YOLOv8 and YOLOv11 with different architectural sizes (medium, large, extra-large) were evaluated using metrics such as precision, recall, F1-Score, and mAP. The findings revealed that the YOLOv11x-seg model demonstrated marked superiority over all other tested architectures, achieving an F1-Score of 0.87 and a mAP@0.5 of 0.91. Statistical analysis confirmed the significance of these results. The study demonstrates that the YOLOv11x-seg architecture offers significant potential as a rapid and objective decision support tool in clinical settings. This work makes an original contribution to improving burn diagnosis by integrating a state-of-the-art deep learning model into medical image analysis.