MM

Monitoring the changes in bone marrow during therapy for multiple myeloma patients is a crucial task. Osteolytic lesions can cause deformation of the bones, affecting the robustness of traditional segmentation tools. A two-model deep learning analysis is explored in this study. A detection model reduces pixel imbalances between the background and the bone marrow pixels, achieving a mAP of 0.878±0.005. A residual U-Net segments the bone marrow, yielding a DSC of 0.856±0.003. The proposed deep learning-based segmentation pipeline allows accurate and fast annotation of the bone marrow in multiple myeloma patients.

Multiple myeloma is a plasma cell neoplasm with genetic complexity that originates in pre-malignant stages due to genomic alterations, leading to malignant plasma cell proliferation. The completeness of data is significantly affecting multi-omics studies since the more sources included in the analysis, the more likely it is for key data to be missing. In this study, an ensemble meta-model that uses transfer learning from multiple single-source models was developed to assess the progression of multiple myeloma by leveraging radiocytogenetics. The proposed meta-model achieved the highest performance with an AUC of 0.75±0.07 and a SP of 0.84±0.02 among other single-source and radiocytogenetic models.