# Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET

## TL;DR

This study highlights the importance of using task-based metrics rather than solely relying on Dice scores to evaluate AI segmentation methods in PET imaging, ensuring better clinical relevance.

## Contribution

The paper demonstrates that Dice scores may not align with clinical task performance, advocating for objective task-based evaluation in AI-based PET segmentation.

## Key findings

- Dice scores can be inconsistent with clinical task performance
- Task-based evaluation provides more clinically relevant assessment
- Retrospective analysis on multi-center trial data supports these conclusions

## Abstract

Artificial intelligence (AI)-based methods are showing substantial promise in segmenting oncologic positron emission tomography (PET) images. For clinical translation of these methods, assessing their performance on clinically relevant tasks is important. However, these methods are typically evaluated using metrics that may not correlate with the task performance. One such widely used metric is the Dice score, a figure of merit that measures the spatial overlap between the estimated segmentation and a reference standard (e.g., manual segmentation). In this work, we investigated whether evaluating AI-based segmentation methods using Dice scores yields a similar interpretation as evaluation on the clinical tasks of quantifying metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of primary tumor from PET images of patients with non-small cell lung cancer. The investigation was conducted via a retrospective analysis with the ECOG-ACRIN 6668/RTOG 0235 multi-center clinical trial data. Specifically, we evaluated different structures of a commonly used AI-based segmentation method using both Dice scores and the accuracy in quantifying MTV/TLG. Our results show that evaluation using Dice scores can lead to findings that are inconsistent with evaluation using the task-based figure of merit. Thus, our study motivates the need for objective task-based evaluation of AI-based segmentation methods for quantitative PET.