autoPET/CT IV Banner
Join

📋 Tasks¶

The tasks will handle lesion segmentation for whole-body hybrid imaging for a single-staging PET/CT (Task 1) or a longitudinal CT (Task 2). All public available data and (pre-trained) models (including foundation models) are allowed. Time points and/or imaging modality inputs can be treated individually or jointly. Participants can either develop a

  • novel method and/or
  • focus on data-centric approaches (using the provided baselines), i.e. development on pre- and post-processing pipelines.

You can participate in either one Task or in both Tasks.

🎯 Goal¶

The aim is to develop a) accurate and b) robust lesion segmentation methods that work under varying levels of human-annotated information in either single-staging whole-body PET/CT (Task 1) or a longitudinal CT screening (Task 2).



📋 Task 1: Single-staging whole-body PET/CT¶

In Task 1, we study an interactive human-in-the-loop segmentation scenario and investigate the impact of varying degrees of label information (none to multiple clicks per lesion and background) on the segmentation performance in a multi-tracer and multi-center imaging setting - similar to the previous iterations of the autoPET challenge. The specific challenge in automated segmentation of lesions in PET/CT is to avoid false-positive segmentation of anatomical structures that have physiologically high uptake while capturing all tumor lesions. This task is particularly challenging in a multitracer setting since the physiological uptake partly differs for different tracers: e.g. brain, kidney, heart for FDG and e.g. liver, kidney, spleen, submandibular for PSMA.

We will study the behaviour over 11 interactive segmentation steps. In each step, an additional standardized and pre-simulated tumor (foreground) and background click, represented as a set of 3D coordinates, will be provided alongside the input image. This process will progress incrementally from 0 clicks (1st step) to the full allocation of 10 tumor and 10 background clicks per image (11th step). Please also refer to the evaluation metrics and the structure of the input and output interfaces of the baseline containers.

Input¶
  • CT image (MHA file)
  • PET image (MHA file)
  • Lesion click(s) in foreground and background (JSON file)
Output¶
  • lesion segmentation mask (MHA file)


📋 Task 2: Lesion Segmentation in Longitudinal CT¶

In Task 2, we explore the performance of lesion segmentation in a follow-up scenario with additional information from a previous CT scan. More precisely, the CT images of the baseline and follow-up scan are provided together with the baseline segmentation mask, the lesion centers in the baseline images and the propagated lesion centers in the follow-up images. We investigate the segmentation performance in a novel longitudinal whole-body CT database of >300 cases - similar to autoPET I. A specific challenge lies in the high variability of lesion spread. The tumors can change shape (progression or regression), split or merge, disappear (complete response) or newly appear (metastasis). In addition, in some cases the differentiation between malignant and benign tissue can be difficult.

We aim to investigate to what extent the findings from a previous time point facilitate the task of lesion segmentation in the follow-up. We encourage the usage of registration algorithms to better align the baseline and follow-up CT images, i.e. to transform the baseline lesion (from baseline segmentation) into the follow-up CT scan and target region, but this is not mandatory. Please also refer to the evaluation metrics and the structure of the input and output interfaces of the baseline containers.

Input¶
  • Primary Baseline CT image (MHA file)
  • Secondary Baseline CT image (MHA file)
  • Primary follow-up CT image (MHA file)
  • Secondary follow-up CT image (MHA file)
  • Primary Baseline lesion segmentation mask (MHA file)
  • Secondary Baseline lesion segmentation mask (MHA file)
  • Primary Baseline CT lesion center (JSON file)
  • Secondary Baseline CT lesion center (JSON file)
  • Primary Follow-up CT lesion center (JSON file)
  • Secondary Follow-up CT lesion center (JSON file)
Output¶
  • Primary Follow-Up lesion segmentation mask (MHA file)
  • Secondary Follow-Up lesion segmentation mask (MHA file)