Tristan Kirscher

I am a PhD candidate in Applied Mathematics and Artificial Intelligence at the University of Strasbourg, jointly affiliated with ICube IMAGeS and Institut Strauss. My research focuses on uncertainty quantification for deep learning–based segmentation in radiotherapy, with emphasis on calibration, robustness, and clinical decision support. I am supervised by S. Faisan (PhD, HDR), P. Meyer (PhD, HDR), and X. Coubez (PhD).

I am currently a visiting PhD researcher at the German Cancer Research Center (DKFZ), working with Prof. Klaus Maier-Hein’s Medical Image Computing group on uncertainty-aware and robust deep learning for radiotherapy segmentation, focusing on safe deployment in clinical workflows.

Previously, I worked as a Computer Vision Research Engineer at SYSNAV, designing and deploying real-time computer vision models for autonomous navigation systems.

I hold an MSc in Statistics and Economics from ENSAE — Institut Polytechnique de Paris (Data Science, Statistics & Learning track) and an MSc in Engineering from École des Mines de Saint-Étienne (Big Data & Data Science specialization). I also completed an ERASMUS+ exchange at KIT Karlsruhe.

My broader research interests lie in uncertainty-aware and robust deep learning for safety-critical computer vision, with a focus on probabilistic and statistical learning methods for reliable decision-making in medical imaging and healthcare.

news

May, 2026	Paper accepted at MIDL 2026
Jan, 2026	Visiting PhD Researcher at DKFZ Heidelberg
Jan, 2026	Awarded the CNRS GdR IASIS Doctoral Mobility Grant
Oct, 2025	1st Place at MICCAI 2025 CURVAS-PDACVI Challenge
Jul, 2025	Paper accepted at MICCAI 2025

selected publications

MIDL
TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation

Tristan Kirscher, Alexandra Ertl, Klaus Maier-Hein, and 3 more authors

In Medical Imaging with Deep Learning, 2026

Abs arXiv Bib

Pancreatic ductal adenocarcinoma (PDAC) segmentation on contrast-enhanced CT is inherently ambiguous: inter-rater disagreement among experts reflects genuine uncertainty rather than annotation noise. Standard deep learning approaches assume a single ground truth, producing probabilistic outputs that can be poorly calibrated and difficult to interpret under such ambiguity. We present TwinTrack, a framework that addresses this gap through post-hoc calibration of ensemble segmentation probabilities to the empirical mean human response (MHR), the fraction of expert annotators labeling a voxel as tumor. Calibrated probabilities are thus directly interpretable as the expected proportion of annotators assigning the tumor label, explicitly modeling inter-rater disagreement. The proposed post-hoc calibration procedure is simple and requires only a small multi-rater calibration set. It consistently improves calibration metrics over standard approaches when evaluated on the MICCAI 2025 CURVAS-PDACVI multi-rater benchmark.
@inproceedings{kirscher2026twintrack, title = {TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation}, author = {Kirscher, Tristan and Ertl, Alexandra and Maier-Hein, Klaus and Coubez, Xavier and Meyer, Philippe and Faisan, Sylvain}, booktitle = {Medical Imaging with Deep Learning}, year = {2026}, address = {Taipei, Taiwan}, }
MICCAI
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning

Tristan Kirscher, Sylvain Faisan, Xavier Coubez, and 2 more authors

In Medical Image Computing and Computer Assisted Intervention – MICCAI 2025, 2025

Abs arXiv Bib

Pediatric medical image segmentation remains challenging due to limited annotated data and significant anatomical variability across developmental stages. We propose PSAT, a framework that leverages adult data augmentations and transfer learning strategies to improve pediatric segmentation performance.
@inproceedings{kirscher2025psat, title = {PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning}, author = {Kirscher, Tristan and Faisan, Sylvain and Coubez, Xavier and Barrier, Loris and Meyer, Philippe}, booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025}, year = {2025}, address = {Daejeon, South Korea}, }
ICLR-W
A Novel Methodological Framework for the Analysis of Health Trajectories and Survival Outcomes in Heart Failure Patients

Juliette Murris, Tristan Amadei, Tristan Kirscher, and 3 more authors

In ICLR 2024 Workshop on Learning from Time Series For Health, 2024

Abs arXiv Bib

This work introduces a novel methodological framework for analyzing health trajectories and survival outcomes in heart failure patients. We combine NLP techniques for characterizing patient trajectories, unsupervised clustering with a new metric for measuring diagnosis distances, and survival analysis to assess patient outcomes.
@inproceedings{murris2024health, title = {A Novel Methodological Framework for the Analysis of Health Trajectories and Survival Outcomes in Heart Failure Patients}, author = {Murris, Juliette and Amadei, Tristan and Kirscher, Tristan and Klein, Antoine and Tropeano, Anne-Isabelle and Katsahian, Sandrine}, booktitle = {ICLR 2024 Workshop on Learning from Time Series For Health}, year = {2024}, address = {Vienna, Austria}, }