Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Centric Strategies for Overcoming PET/CT Heterogeneity: Insights from the AutoPET III Lesion Segmentation Challenge

Balint Kovacs, Shuhan Xiao, Maximilian Rokuss, Constantin Ulrich, Fabian Isensee, Klaus H. Maier-Hein

TL;DR

Two targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging are developed, designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition.

Abstract

The third autoPET challenge introduced a new data-centric task this year, shifting the focus from model development to improving metastatic lesion segmentation on PET/CT images through data quality and handling strategies. In response, we developed targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging. Our approach encompasses two key elements. First, to address potential alignment errors between CT and PET modalities as well as the prevalence of punctate lesions, we modified the baseline data augmentation scheme and extended it with misalignment augmentation. This adaptation aims to improve segmentation accuracy, particularly for tiny metastatic lesions. Second, to tackle the variability in image dimensions significantly affecting the prediction time, we implemented a dynamic ensembling and test-time augmentation (TTA) strategy. This method optimizes the use of ensembling and TTA within a 5-minute prediction time limit, effectively leveraging the generalization potential for both small and large images. Both of our solutions are designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition. We made the challenge repository with our modifications publicly available at \url{https://github.com/MIC-DKFZ/miccai2024_autopet3_datacentric}.

Data-Centric Strategies for Overcoming PET/CT Heterogeneity: Insights from the AutoPET III Lesion Segmentation Challenge

TL;DR

Two targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging are developed, designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition.

Abstract

The third autoPET challenge introduced a new data-centric task this year, shifting the focus from model development to improving metastatic lesion segmentation on PET/CT images through data quality and handling strategies. In response, we developed targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging. Our approach encompasses two key elements. First, to address potential alignment errors between CT and PET modalities as well as the prevalence of punctate lesions, we modified the baseline data augmentation scheme and extended it with misalignment augmentation. This adaptation aims to improve segmentation accuracy, particularly for tiny metastatic lesions. Second, to tackle the variability in image dimensions significantly affecting the prediction time, we implemented a dynamic ensembling and test-time augmentation (TTA) strategy. This method optimizes the use of ensembling and TTA within a 5-minute prediction time limit, effectively leveraging the generalization potential for both small and large images. Both of our solutions are designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition. We made the challenge repository with our modifications publicly available at \url{https://github.com/MIC-DKFZ/miccai2024_autopet3_datacentric}.
Paper Structure (11 sections, 1 figure, 1 table)

This paper contains 11 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Challenge Design - The Data-Centric Task
  4. Data augmentation strategy
  5. Network training
  6. Image segmentation postprocessing
  7. Dynamic ensembling and test-time augmentation
  8. Evaluation
  9. Results
  10. Discussion and conclusion
  11. Acknowledgments.

Figures (1)

  • Figure 1: Misalignment augmentation applied to the dataset. The PET image remains unchanged, while the CT image is transformed to introduce additional slight plausible misalignments between the image modalities. The ground truth is coupled with the PET modality due to its stronger relevance for identifying metastatic lesions.