avatar

Jingsong Liu

Enjoy researching. Live in Munich.

About me

I am a PhD Student in the Prof. Schüffler’s Lab, focus on the pathology image analysis using deep learning methodes.

Previously, I completed my M.Sc. degree in Mechatronik und Robotiks at Technical University of Munich, where I was a student researcher at Visual Computing & AI lab and Computer Aided Medical Procedures & Augmented Reality(CAMP) at TUM working on indoor 3D scene synthesis and medical image analysis separately. I was also a teaching assistant of the course Introduction to Deep Learning (IN2346).

Besides, I used to co-found and work at Dishi Medical Robots company, which aims to develop China’s first retinal surgery robots. I had a wonderful time with the great team there.

My research interests broadly lie in the field of Deep Learning, Medical Images and Robotics.

In my free time, I enjoy going to the gym and playing football on our own-founded football club with friends.

Publications

(* denotes equal contribution and † denotes shared last authorship.)

Attention Pooling Enhances NCA-based Classification of Microscopy Images

Submission

HASD: Hierarchical Adaption for pathology Slide-level Domain-shift

Jingsong Liu*, Han Li*, Chen Yang, Michael Deutges, Ario Sadafi, Xin You, Katharina Breininger, Nassir Navab, Peter J. Schüffler†
MICCAI, 2025
Paper / Code

Prior-RadGraphFormer: A Prior-Knowledge-Enhanced Transformer for Generating Radiology Graphs from X-Rays

Yiheng Xiong*, Jingsong Liu*, Kamilia Zaripova*, Sahand Sharifzadeh, Matthias Keicher†, Nassir Navab†
MICCAI Workshop on GRaphs in biomedicAl Image anaLysis (GRAIL), 2023
Paper / Code

Theoretical error analysis of spotlight-based instrument localization for retinal surgery

Mingchuan Zhou, Felix Hennerkes, Jingsong Liu, Zhongliang Jiang, Thomas Wendler, M Ali Nasseri, Iulian Iordachita, Nassir Navab
Robotica
Paper

Teaching

Seminar: CuToMeMaLeCoPa (Current Topics in Medical Machine Learning and Computational Pathology, IN1709)

SS2024/WS2024/SS2025, Teaching Assistant

Lecture: I2DL (Introduction to Deep Learning, IN2346)

SS2021, Teaching Assistant

Talk

ECDP (European Congress on Digital Pathology)

2024, Vilnius, Lithuania

Saturn3 (Spatial and Temporal Resolution of Intratumoral Heterogeneity in 3 hard-to-treat Cancers)

2025, Nesselwang, Germany

News

06/25: Our paper “HASD: Hierarchical Adaption for pathology Slide-level Domain-shift” accepted to MICCAI 2025 (Daejeon, 🇰🇷)!

More