首页|First Affiliated Hospital of Dalian Medical University Reports Findings in Artif icial Intelligence (Multicenter investigation of preoperative distinction betwee n primary central nervous system lymphomas and glioblastomas through interpretab le ...)

First Affiliated Hospital of Dalian Medical University Reports Findings in Artif icial Intelligence (Multicenter investigation of preoperative distinction betwee n primary central nervous system lymphomas and glioblastomas through interpretab le ...)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating in Liaonin g, People’s Republic of China, by NewsRx journalists, research stated, “Research into the effectiveness and applicability of deep learning, radiomics, and their integrated models based on Magnetic Resonance Imaging (MRI) for preoperative di fferentiation between Primary Central Nervous System Lymphoma (PCNSL) and Gliobl astoma (GBM), along with an exploration of the interpretability of these models. A retrospective analysis was performed on MRI images and clinical data from 261 patients across two medical centers.” The news reporters obtained a quote from the research from the First Affiliated Hospital of Dalian Medical University, “The data were split into a training set (n = 153, medical center 1) and an external test set (n = 108, medical center 2) . Radiomic features were extracted using Pyradiomics to build the Radiomics Mode l. Deep learning networks, including the transformer-based MobileVIT Model and C onvolutional Neural Networks (CNN) based ConvNeXt Model, were trained separately . By applying the ‘late fusion’ theory, the radiomics model and deep learning mo del were fused to produce the optimal Max- Fusion Model. Additionally, Shapley Ad ditive exPlanations (SHAP) and Grad-CAM were employed for interpretability analy sis. In the external test set, the Radiomics Model achieved an Area under the re ceiver operating characteristic curve (AUC) of 0.86, the MobileVIT Model had an AUC of 0.91, the ConvNeXt Model demonstrated an AUC of 0.89, and the Max-Fusion Model showed an AUC of 0.92. The Delong test revealed a significant difference i n AUC between the Max-Fusion Model and the Radiomics Model (P = 0.02). The Max-F usion Model, combining different models, presents superior performance in distin guishing PCNSL and GBM, highlighting the effectiveness of model fusion for enhan ced decision-making in medical applications.”

LiaoningPeople’s Republic of ChinaAs iaArtificial IntelligenceCancerCentral Nervous SystemEmerging Technologi esGlioblastomasHealth and MedicineHematologyHospitalsImmunoproliferati ve DisordersLymphatic Diseases and ConditionsLymphomaLymphoproliferative D isordersMachine LearningOncology

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Sep.18)