Comparison between threshold-based and deep learning-based bone segmentation on whole-body CT images

Moreau, Noémie; Rousseau, Caroline; Fourcade, Constance; Santini, Gianmarco; Ferrer, Ludovic; Lacombe, M.; Guillerminet, Camille; Jézéquel, Pascal; Campone, Mario; Normand, Nicolas; Rubeaux, Mathieu

doi:10.1117/12.2580892

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This index is usually applied on Bone Scan with limited results for metastatic breast cancer [ 36 ], but can be successfully applied on PET [ 16 ]. After the automatic segmentation, bone lesions were labeled using a bone mask generated using a network presented in [ 37 ]. PBI was then calculated as the ratio of the bone lesion volume compared to the total bone volume.…”

Section: Materials and Methodsmentioning

confidence: 99%

Automatic Segmentation of Metastatic Breast Cancer Lesions on 18F-FDG PET/CT Longitudinal Acquisitions for Treatment Response Assessment

Moreau

Rousseau

Fourcade

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

Metastatic breast cancer patients receive lifelong medication and are regularly monitored for disease progression. The aim of this work was to (1) propose networks to segment breast cancer metastatic lesions on longitudinal whole-body PET/CT and (2) extract imaging biomarkers from the segmentations and evaluate their potential to determine treatment response. Baseline and follow-up PET/CT images of 60 patients from the EPICUREseinmeta study were used to train two deep-learning models to segment breast cancer metastatic lesions: One for baseline images and one for follow-up images. From the automatic segmentations, four imaging biomarkers were computed and evaluated: SULpeak, Total Lesion Glycolysis (TLG), PET Bone Index (PBI) and PET Liver Index (PLI). The first network obtained a mean Dice score of 0.66 on baseline acquisitions. The second network obtained a mean Dice score of 0.58 on follow-up acquisitions. SULpeak, with a 32% decrease between baseline and follow-up, was the biomarker best able to assess patients’ response (sensitivity 87%, specificity 87%), followed by TLG (43% decrease, sensitivity 73%, specificity 81%) and PBI (8% decrease, sensitivity 69%, specificity 69%). Our networks constitute promising tools for the automatic segmentation of lesions in patients with metastatic breast cancer allowing treatment response assessment with several biomarkers.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%