首页|Nanjing University of Posts and Telecommunications Reports Findings in B-Cell Ly mphoma (Survival prediction in diffuse large B-cell lymphoma patients: multimoda l PET/CT deep features radiomic model utilizing automated machine learning)
Nanjing University of Posts and Telecommunications Reports Findings in B-Cell Ly mphoma (Survival prediction in diffuse large B-cell lymphoma patients: multimoda l PET/CT deep features radiomic model utilizing automated machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Oncology - B-Cell Lymp homa is the subject of a report. According to news reporting originating in Nanj ing, People’s Republic of China, by NewsRx journalists, research stated, “We sou ght to develop an effective combined model for predicting the survival of patien ts with diffuse large B-cell lymphoma (DLBCL) based on the multimodal PET-CT dee p features radiomics signature (DFR-signature). 369 DLBCL patients from two medi cal centers were included in this study.” The news reporters obtained a quote from the research from the Nanjing Universit y of Posts and Telecommunications, “Their PET and CT images were fused to constr uct the multimodal PET-CT images using a deep learning fusion network. Then the deep features were extracted from those fused PET-CT images, and the DFR-signatu re was constructed through an Automated machine learning (AutoML) model. Combine d with clinical indexes from the Cox regression analysis, we constructed a combi ned model to predict the progression-free survival (PFS) and the overall surviva l (OS) of patients. In addition, the combined model was evaluated in the concord ance index (C-index) and the time-dependent area under the ROC curve (tdAUC). A total of 1000 deep features were extracted to build a DFR-signature. Besides the DFR-signature, the combined model integrating metabolic and clinical factors pe rformed best in terms of PFS and OS. For PFS, the C-indices are 0.784 and 0.739 in the training cohort and internal validation cohort, respectively. For OS, the C-indices are 0.831 and 0.782 in the training cohort and internal validation co hort. DFR-signature constructed from multimodal images improved the classificati on accuracy of prognosis for DLBCL patients.”
NanjingPeople’s Republic of ChinaAsi aB-Cell LymphomaCancerCyborgsEmerging TechnologiesHealth and MedicineHematologyImmunoproliferative DisordersLarge B-Cell LymphomaLymphatic Dis eases and ConditionsLymphomaLymphoproliferative DisordersMachine LearningOncology
NETL
NSTL
