SOS Team Members

Dr. Oezdemir Cetin

Postdoctoral Researcher


work +49 6151 16-57 366

Work S3/06 201
Merckstrasse 25
64283 Darmstadt

Oezdemir Cetin joined the SOS Lab as a visiting professor in February 2018. Subsequently, his project entitled “Rapid segmentation and tracking of yeast cells in microfluidic structures using convolutional neural networks for the measurement of cell fluorescence,” submitted to the AvH Philipp Schwartz Initiative, was accepted in 2020. Extending his project work by shifting it to histopathology images, he continues to work with Frankfurt University Hospital. The updated study mainly concerns the follow-up and counting of cancer cells in histopathology images. Various machine learning techniques are used for this.

His research interests include computational pathology and topics such as bayesian inference, vision transformation, graph networks, multiple-instance learning, and uncertainty in deep learning.

Passionate students who want to work in the computational pathology field can contact me for more information about the topics listed below.

Publications (selected)

Cetin, O., Lai, J., Ziegler, P., Wild, P., Dogali, G. & Koeppl, H. (2023, December). Keypoint-Driven Unsupervised Learning for Histopathology Image Registration. In 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 3514-3520). IEEE.
Gul, A. G., Cetin, O., Reich, C., Flinner, N., Prangemeier, T., & Koeppl, H. (2022, April). Histopathological image classification based on self-supervised vision transformer and weak labels. In Medical Imaging 2022: Digital and Computational Pathology(Vol. 12039, pp. 366-373). SPIE.
Cetin, O., Shu, Y., Flinner, N., Ziegler, P., Wild, P., & Koeppl, H. (2022, February). Multi-magnification networks for deformable image registration on histopathology images. In 10th International Workshop on Biomedical Image Registration.
Cetin, O., Chen, M., Ziegler, P., Wild, P., & Koeppl, H. (2022, December). Deep learning-based restaining of histopathological images. In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1467-1474). IEEE.
Reich, C., Prangemeier, T., Cetin, Ö., & Koeppl, H. (2021). OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data. arXiv preprint arXiv:2110.10640.
Cetin, O., Seymen, V., & Sakoglu, U. (2020). Multiple sclerosis lesion detection in multimodal MRI using simple clustering-based segmentation and classification. Informatics in Medicine Unlocked, 20, 100409.

Student Projects (on going)

Master Thesis
Wenxin Zhao Multiobject Optimization since 15.10.2023
Can Pehlivan Advancing Cell Segmentation: Comparative Analysis of Attention-Based and Visual Transformers since 15.09.2023

Student Projects (completed)

Master Thesis
Ailian Tian Determining the Capabilities and Limitations of Latent Diffusion Models for Whole Slide Image Synthesis: A Case Study 31.10.2023
Jennifer Leichtle A Comparative Analysis of Cell Segmentation Techniques for Histopathological Images 25.07.2023
Junming Lai Enhancing Non-Rigid Medical Image Registration Performance through Keypoint-Based Frameworks 20.07.2023
Xin Li Representing Uncertainty in Weakly Supervised Deep Learning for Histopathology Image Segmentation 23.03.2023
Nan Yin A vision transformer-based Graph neural network for Immune cell segmentation 16.03.2023
Yankun Wu Virtual stain transformation of histopathological images based on deep-learning 21.09.2022
Mingzhi Chen Contrastive learning-based stain transformation for cancer grading 03.03.2022
Yahia Brini Image-based molecular subtyping of cancer through deep learning 20.01.2022
Yiran Shu Deep neural network based non-rigid image registration for histopathological images 14.01.2022
Ahmet Gökberk Gül Histopathological Image Classification Based on Self-Supervised Vision Transformer 25.11.2021
Rijan Kusatha Multiple instance learning for cancer molecular subtype classification 03.09.2021
Jiajun Deng Image registration for multi-stained histopathologicalwhole slide images 27.08.2021
Berkay Canel Segmentation of Multiple Sclerosis Lesions on Magnetic Resonance Data of the Human Brain with Convolutional Neural Networks 18.12.2020

Student Projects (available)