Murat UCAN

Dr. Murat UCAN

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
4 April 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
ASAynur Sevinc
Aynur Sevinc
Murat UCANMurat UCAN
Murat UCAN
BKBuket Kaya
Buket Kaya
Background/Objectives: Although transformer-based deep learning architectures are preferred in many hybrid architectures due to their flexibility, they generally perform poorly on image classification tasks with small datasets. An important improvement in performance when transformer architectures work with limited data is the use of distillation techniques. The impact of distillation techniques on classification accuracy in transformer-based models has not yet been extensively investigated. Methods: This study investigates the impact of distillation techniques on the classification performance of transformer-based deep learning architectures trained on limited data. We use transformer-based models ViTx32 and ViTx16 without distillation and DeiT and BeiT with distillation. A four-class dataset of brain MRI images is used for training and testing. Results: Our experiments show that the DeiT and BeiT architectures with distillation achieve performance gains of 2.2% and 1%, respectively, compared to ViTx16. A more detailed analysis shows that the distillation techniques improve the detection of non-patient individuals by about 4%. Our study also includes a detailed analysis of the training times for each architecture. Conclusions: The results of the experiments show that using distillation techniques in transformer-based deep learning models can significantly improve classification accuracy when working with limited data. Based on these findings, we recommend the use of transformer-based models with distillation, especially in medical applications and other areas where flexible models are developed with limited data.

5 February 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
SEYFETTIN VURANSEYFETTIN VURAN
SEYFETTIN VURAN
Murat UCANMurat UCAN
Murat UCAN
MAMehmet Akin
Mehmet Akin
MKMehmet Kaya
Mehmet Kaya
Background/Objectives: As reported by the World Health Organization, Mpox (monkeypox) is an important disease present in 110 countries, mostly in South Asia and Africa. The number of Mpox cases has increased rapidly, and the medical world is worried about the emergence of a new pandemic. Detection of Mpox by traditional methods (using test kits) is a costly and slow process. For this reason, there is a need for methods that have high success rates and can diagnose Mpox disease from skin images with a deep-learning-based autonomous method. Methods: In this work, we propose a multi-class, fast, and reliable autonomous disease diagnosis model using transformer-based deep learning architectures and skin lesion images, including for Mpox disease. Our other aim is to investigate the effects of self-supervised learning, self-distillation, and shifted window techniques on classification success when multi-class skin lesion images are trained with transformer-based deep learning architectures. The Mpox Skin Lesion Dataset, Version 2.0, which was publicly released in 2024, was used in the training, validation, and testing processes of the study. Results: The SwinTransformer architecture we proposed in our study achieved about 8% higher accuracy evaluation metric classification success compared to its closest competitor in the literature. ViT, MAE, DINO, and SwinTransformer architectures achieved 93.10%, 84.60%, 90.40%, and 93.71% accuracy classification success, respectively. Conclusions: The results obtained in the study showed that Mpox disease and other skin lesion images can be diagnosed with high success and can support doctors in decision-making. In addition, the study provides important results that can be used in other medical fields where the number of images is low in terms of transformer-based architecture and technique to use.

30 December 2022 in Biomedical Signal Processing and Control
Verified
Journal Article
Closed access
EBErtan Bütün
Ertan Bütün
Murat UCANMurat UCAN
Murat UCAN
MKMehmet Kaya
Mehmet Kaya

25 October 2022
Verified
Conference Paper
Closed access
Murat UCANMurat UCAN
Murat UCAN
BKBuket Kaya
Buket Kaya
MKMehmet Kaya
Mehmet Kaya
Many diseases and cancerous cells can be detected using images taken by gastroenterology specialists. Accurate and rapid detection of gastroenterological diseases is very important for the treatment processes to be applied and for the patient’s recovery. In this study, a data set containing data from 8 different diseases (Esophagitis, Dyed and Lifted Polyps, Dyed Resection Margins, Cecum, Pylorus, Z-line, Polyps, Ulcerative colitis) was used. A deep learning network was trained using the EfficientNet architecture and the test results were given in the study. In addition, comparisons were made with other studies using the same data set and the same parameters in the literature. Studies have shown that gastrological images can be successfully classified with an accuracy of 0.935. Class-based classification results are also shared in detail for 8 diseases in the results section of the study. The results showed that the trained architecture would contribute to minimizing human error in disease detection.


1 February 2019 in Journal of Network and Computer Applications
Verified
Journal Article
Closed access
MTMehmet Fatih Tuysuz
Mehmet Fatih Tuysuz
Murat UCANMurat UCAN
Murat UCAN
RTRamona Trestian
Ramona Trestian