학술논문
Fully Automated Detection and Segmentation Pipeline for the Bone Marrow of the Lytic Bone of Multiple Myeloma Patients
Document Type
Conference
Author
Koutoulakis, Emmanouil; Trivizakis, Eleftherios; Koutoulidis, Vassilis; Moulopoulos, Lia A.; Terpos, Evangelos; Ntanasis-Stathopoulos, Ioannis; Malandrakis, Panagiotis; Grigoropoulos, Panagiotis; Papadopoulos, Panagiotis; Nikiforaki, Katerina; Papanikolaou, Nickolas; Fotiadis, Dimitrios I.; Marias, Kostas
Source
2023 IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology Data Science and Engineering in Healthcare, Medicine and Biology, 2023 IEEE EMBS Special Topic Conference on. :39-40 Dec, 2023
Subject
Language
Abstract
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.Clinical Relevance: The proposed deep learning-based pipeline for segmentation has the potential to fully automate the time-consuming process of delineating bone marrow in multiple myeloma patients, significantly improving patient monitoring.