Multicenter investigation of preoperative distinction between primary central nervous system lymphomas and glioblastomas through interpretable artificial intelligence models.

Objective: Research into the effectiveness and applicability of deep learning, radiomics, and their integrated models based on Magnetic Resonance Imaging (MRI) for preoperative differentiation between Primary Central Nervous System Lymphoma (PCNSL) and Glioblastoma (GBM), along with an exploration o...

Full description

Bibliographic Details
Published in:Neuroradiology Vol. 66; no. 11; pp. 1893 - 1907
Main Authors: Yang, Yun-Feng, Zhao, Endong, Shi, Yutong, Zhang, Hao, Yang, Yuan-Yuan
Format: pictorial research tables/charts Journal Article
Published: Springer Nature Nov2024
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=180654037&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 180654037
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00283940
        NYZ
      jtl: Neuroradiology
      issn: 00283940
      maglogo: N
    pubinfo:
      dt: Nov2024
      vid: 66
      iid: 11
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        180654037
        179410426
        180654037
        180654037
        10.1007/s00234-024-03451-7
        180654037
      ppf: 1893
      ppct: 14
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Multicenter investigation of preoperative distinction between primary central nervous system lymphomas and glioblastomas through interpretable artificial intelligence models.
      aug:
        au:
          Yang, Yun-Feng
          Zhao, Endong
          Shi, Yutong
          Zhang, Hao
          Yang, Yuan-Yuan
        affil: Laboratory for Medical Imaging Informatics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, 200083, Shanghai, China
      sug:
        subj:
          Central Nervous System Neoplasms Radiography
          Central Nervous System Neoplasms Surgery
          Lymphoma Radiography
          Lymphoma Surgery
          Glioma Radiography
          Glioma Surgery
          Preoperative Period
          Artificial Intelligence Utilization
          Prediction Models
          Deep Learning
          Radiomics
          Magnetic Resonance Imaging
          Diagnosis, Differential
          Outcomes Research
          Human
          Male
          Female
          Middle Age
          Multicenter Studies
          Retrospective Design
          Descriptive Statistics
          Convolutional Neural Networks
          ROC Curve
          Predictive Validity
          Image Processing, Computer Assisted
          Data Analysis Software
          Decision Making, Clinical
          Middle Aged: 45-64 years
          Male
          Female
      ab: Objective: Research into the effectiveness and applicability of deep learning, radiomics, and their integrated models based on Magnetic Resonance Imaging (MRI) for preoperative differentiation between Primary Central Nervous System Lymphoma (PCNSL) and Glioblastoma (GBM), along with an exploration of the interpretability of these models. Materials and methods: A retrospective analysis was performed on MRI images and clinical data from 261 patients across two medical centers. 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 Model. Deep learning networks, including the transformer-based MobileVIT Model and Convolutional Neural Networks (CNN) based ConvNeXt Model, were trained separately. By applying the "late fusion" theory, the radiomics model and deep learning model were fused to produce the optimal Max-Fusion Model. Additionally, Shapley Additive exPlanations (SHAP) and Grad-CAM were employed for interpretability analysis. Results: In the external test set, the Radiomics Model achieved an Area under the receiver 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 in AUC between the Max-Fusion Model and the Radiomics Model (P = 0.02). Conclusion: The Max-Fusion Model, combining different models, presents superior performance in distinguishing PCNSL and GBM, highlighting the effectiveness of model fusion for enhanced decision-making in medical applications. Clinical Relevance Statement: The preoperative non-invasive differentiation between PCNSL and GBM assists clinicians in selecting appropriate treatment regimens and clinical management strategies.
      pubtype: Academic Journal
      doctype:
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N