AutoPETIII: The Tracer Frontier. What Frontier?

TL;DR

This paper presents an automatic lesion segmentation method for PET/CT scans that works across different tracers using nnUNetv2 and an ensemble approach, advancing the automation in medical imaging diagnostics.

Contribution

It introduces a tracer-agnostic lesion segmentation framework utilizing nnUNetv2 and ensemble models, addressing the challenge of unknown tracers in PET/CT scans.

Findings

Effective lesion segmentation across multiple tracers.

Ensemble models improve segmentation accuracy.

Automated tracer selection enhances robustness.

Abstract

For the last three years, the AutoPET competition gathered the medical imaging community around a hot topic: lesion segmentation on Positron Emitting Tomography (PET) scans. Each year a different aspect of the problem is presented; in 2024 the multiplicity of existing and used tracers was at the core of the challenge. Specifically, this year's edition aims to develop a fully automatic algorithm capable of performing lesion segmentation on a PET/CT scan, without knowing the tracer, which can either be a FDG or PSMA-based tracer. In this paper we describe how we used the nnUNetv2 framework to train two sets of 6 fold ensembles of models to perform fully automatic PET/CT lesion segmentation as well as a MIP-CNN to choose which set of models to use for segmentation.