Yusuf Baran Tanrıverdi

Are you here because you scanned a QR code at UPF’s DTIC PhD workshop? Click here!

Benvinguts!

I am Yusuf, born and raised in Istanbul, Turkey. After 22 years of consideration (I am 26, for reference) and obtaining my degree of triple-E from Bahcesehir Uni, I decided to move abroad in 2022. I have lived in France, Italy and Spain. I got my EMJMD in Medical Imaging Applications. As I fell in love with Barcelona during my thesis internship, I started my PhD at UPF’s one and only BCNMedTech. I am currently conducting research on reconstruction of 3D ultrasound prenatal faces (which I call 3DUPF for short, carelessly) under supervision of Prof. Gemma Piella and Federico Sukno.

To get to know me better, here is a list of things I like to do while I wait for my cluster to finish model training:

See a random old movie
Draw landscapes
Build in Cities: Skylines II
Dream about a solarpunk future
Learn languages
Watch long Youtube video essays about one or more of followings.
- Mediterranean empires, mythology, Ireland, urban planning…

I do not consent to my work being used for militaristic, racist, misogynist, queerphobic, or any other discriminatory purposes. Everything presented in this blog reflects my personal opinions and perspectives and does not necessarily represent those of the institute at which I am employed.

news

May 24, 2026	Are you here because you scanned a QR code at UPF's DTIC PhD workshop? Click here!
Apr 20, 2026	Looking for a room in BCN!
Mar 20, 2026	I succesfully defended my research proposal!

latest posts

selected publications

A Pixel-Based Anchor Approach for Nuclei Detection in Cervical Cytology Imaging

Ciro Russo, Yusuf B. Tanriverdi, Alessandro Bria, and 1 more author

In Pattern Recognition. ICPR 2024 International Workshops and Challenges, 2025

Abs DOI

Nuclei detection in cervical cytology images holds significant promise for enhancing the early identification of cervical cancer. In this study, we apply GravityNet, a one-stage end-to-end detector designed ad hoc for detecting small regions, like cervical cell nuclei. This approach is based on pixel-based anchors, which serve as reference points on the image pixel grid and dynamically move towards the suspicious regions by inspecting the surrounding space. We conducted experiments on the publicly available Cervix93 dataset to evaluate the effectiveness of our method. Despite challenges posed by variations in staining techniques and cell morphology, our results show promising performance compared to the current state-of-the-art methods.