1. Automatic Segmentation of Metastatic Breast Cancer Lesions on 18F-FDG PET/CT Longitudinal Acquisitions for Treatment Response Assessment
- Author
-
Noémie Moreau, Caroline Rousseau, Constance Fourcade, Gianmarco Santini, Aislinn Brennan, Ludovic Ferrer, Marie Lacombe, Camille Guillerminet, Mathilde Colombié, Pascal Jézéquel, Mario Campone, Nicolas Normand, Mathieu Rubeaux, Keosys, Nantes Université (Nantes Univ), Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, Image Perception Interaction (LS2N - équipe IPI), Nantes Université (Nantes Univ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut de Cancérologie de l'Ouest [Angers/Nantes] (UNICANCER/ICO), UNICANCER, and Université d'Angers (UA)
- Subjects
Cancer Research ,automatic segmentation ,Oncology ,disease monitoring ,deep learning ,metastatic breast cancer ,imaging biomarkers ,Neoplasms. Tumors. Oncology. Including cancer and carcinogens ,[SDV.CAN]Life Sciences [q-bio]/Cancer ,Article ,RC254-282 ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] - Abstract
Simple Summary In the recent years, several deep learning methods for medical image segmentation have been developed for different purposes such as diagnosis, radiotherapy planning or to correlate images findings with other clinical data. However, few studies focus on longitudinal images and response assessment. To the best of our knowledge, this is the first study to date evaluating the use of automatic segmentation to obtain imaging biomarkers that can be used to assess treatment response in patients with metastatic breast cancer. Moreover, the statistical analysis of the different biomarkers shows that automatic segmentation can be successfully used for their computation, reaching similar performances compared to manual segmentation. Analysis also demonstrated the potential of the different biomarkers including novel/original ones to determine treatment response. Abstract 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.
- Published
- 2022
- Full Text
- View/download PDF