MLMarie Lacombe

Marie Lacombe

*This is an algorithmically generated author record based on publicly available information.

Marie Lacombe has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Deep learning approaches for bone and bone lesion segmentation on 18FDG PET/CT imaging in the context of metastatic breast cancer

    by Noemie Moreau, Caroline Rousseau, Constance Fourcade, Gianmarco Santini, Ludovic Ferrer, Marie Lacombe, Camille Guillerminet, Mario Campone, Mathilde Colombie, Mathieu Rubeaux, et al.

    18 FDG PET/CT imaging is commonly used in diagnosis and follow-up of metastatic breast cancer, but its quantitative analysis is complicated by the number and location heterogeneity of metastatic lesions. Considering that bones are the most common location among metastatic sites, this work aims to compare different approaches to segment the bones and bone metastatic lesions in breast cancer.Two deep learning methods based on U-Net were developed and trained to segment either both bones and bone lesions or bone lesions alone on PET/CT images. These methods were cross-validated on 24 patients from the prospective EPICURE seinmeta metastatic breast cancer study and were evaluated using recall and precision to measure lesion detection, as well as the Dice score to assess bones and bone lesions segmentation accuracy.Results show that taking into account bone information in the training process allows to improve the precision of the lesions detection as well as the Dice score of the segmented lesions. Moreover, using the obtained bone and bone lesion masks, we were able to compute a PET bone index (PBI) inspired by the recognized Bone Scan Index (BSI). This automatically computed PBI globally agrees with the one calculated from ground truth delineations.Clinical relevance— We propose a completely automatic deep learning based method to detect and segment bones and bone lesions on 18 FDG PET/CT in the context of metastatic breast cancer. We also introduce an automatic PET bone index which could be incorporated in the monitoring and decision process.


  • Open Access

    Factors Influencing the Intention of Perinatal Nurses to Adopt the Baby-Friendly Hospital Initiative in Southeastern Quebec, Canada: Implications for Practice

    by Guylaine Chabot, Marie Lacombe

    Nurses play a major role in promoting the baby-friendly hospital initiative (BFHI), yet the adoption of this initiative by nurses remains a challenge in many countries, despite evidences of its positive impacts on breastfeeding outcomes. The aim of this study was to identify the factors influencing perinatal nurses to adopt the BFHI in their practice.Methods. A sample of 159 perinatal nurses from six hospital-based maternity centers completed a survey based on the theory of planned behavior. Hierarchical multiple linear regression analyses were performed to assess the relationship between key independent variables and nurses’ intention to adopt the BFHI in their practice. A discriminant analysis of nurses’ beliefs helped identify the targets of actions to foster the adoption the BFHI among nurses.Results. The participants are mainly influenced by factors pertaining to their perceived capacity to overcome the strict criteria of the BFHI, the mothers’ approval of a nursing practice based on the BFHI, and the antenatal preparation of the mothers.Conclusions. This study provides theory-based evidence for the development of effective interventions aimed at promoting the adoption of the BFHI in nurses’ practice.