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

Ziping Liu, Joyce C. Mhlanga, Barry A. Siegel, Abhinav K. Jha

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

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.

Original languageEnglish
Title of host publicationMedical Imaging 2023
Subtitle of host publicationImage Perception, Observer Performance, and Technology Assessment
EditorsClaudia R. Mello-Thoms, Yan Chen
PublisherSPIE
ISBN (Electronic)9781510660397
DOIs
StatePublished - 2023
EventMedical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment - San Diego, United States
Duration: Feb 21 2023Feb 23 2023

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12467
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment
Country/TerritoryUnited States
CitySan Diego
Period02/21/2302/23/23

Keywords

  • Task-based evaluation
  • artificial intelligence
  • positron emission tomography
  • quantification
  • segmentation

Fingerprint

Dive into the research topics of 'Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET'. Together they form a unique fingerprint.

Cite this