# DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis

**Authors:** Roxanne De Maeyer, Yannick Brackenier, Vicky De Ridder, Simon DeKeyser, Maarten Larmuseau, Jef Vandemeulebroucke  
**Lab:** Vrije Universiteit Brussel · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40018) · [PDF](https://arxiv.org/pdf/2610.40018) · [Code](https://github.com/nuclivision/pet-dinov2-2d) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40018.html)

## Abstract

DINO (self-DIstillation with NO labels) has become a stan- dard for self-supervised pre-training, producing features that generalise across datasets and downstream tasks. In medical imaging it has been adopted mainly for radiology (X-ray, CT and MRI), where even natural- image DINO features transfer well. In the literature, these features have been reported to transfer worse to functional imaging such as PET. Yet PET-specific DINO models have barely been introduced, and even less validated across multiple tasks and datasets. We present PET-DINOv2-2D, the first DINOv2 model pre-trained on 2D PET, and benchmark it against open-source encoders: the origi- nal DINOv2 (pre-trained on the LVD-142M natural-image dataset) and OmniRad (pre-trained on CT, MRI and ultrasound). Using the same lightweight heads for every backbone, and despite far less pre-training data, PET-DINOv2-2D matches or outperforms both on three down- stream PET tasks: normal/abnormal classification, lesion segmentation and recurrence-free survival prognosis. Its advantage is largest when few labels are available, suggesting that PET pre-training gives more transferable, label-efficient features. Code is made available at https://github.com/nuclivision/pet-dinov2-2d/.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.