Multicenter Investigation of Preoperative Distinction Between Primary Central Nervous System Lymphomas and Glioblastomas Through Interpretable Artificial Intelligence Models

Overview

Journal Neuroradiology

Specialties Neurology
Radiology

Date 2024 Sep 3

PMID 39225815

Authors

Yun-Feng Yang

Endong Zhao

Yutong Shi

Hao Zhang

Yuan-Yuan Yang

Affiliations

Soon will be listed here.

Abstract

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.

References

Schaff L, Mellinghoff I . Glioblastoma and Other Primary Brain Malignancies in Adults: A Review. JAMA. 2023; 329(7):574-587. PMC: 11445779. DOI: 10.1001/jama.2023.0023. View

Li Y, Suki D, Hess K, Sawaya R . The influence of maximum safe resection of glioblastoma on survival in 1229 patients: Can we do better than gross-total resection?. J Neurosurg. 2015; 124(4):977-88. DOI: 10.3171/2015.5.JNS142087. View

Grommes C, DeAngelis L . Primary CNS Lymphoma. J Clin Oncol. 2017; 35(21):2410-2418. PMC: 5516483. DOI: 10.1200/JCO.2017.72.7602. View

Yu X, Hong W, Ye M, Lai M, Shi C, Li L . Atypical primary central nervous system lymphoma and glioblastoma: multiparametric differentiation based on non-enhancing volume, apparent diffusion coefficient, and arterial spin labeling. Eur Radiol. 2023; 33(8):5357-5367. PMC: 10326108. DOI: 10.1007/s00330-023-09681-2. View

Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout R, Granton P . Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012; 48(4):441-6. PMC: 4533986. DOI: 10.1016/j.ejca.2011.11.036. View

Kunimatsu A, Kunimatsu N, Yasaka K, Akai H, Kamiya K, Watadani T . Machine Learning-based Texture Analysis of Contrast-enhanced MR Imaging to Differentiate between Glioblastoma and Primary Central Nervous System Lymphoma. Magn Reson Med Sci. 2018; 18(1):44-52. PMC: 6326763. DOI: 10.2463/mrms.mp.2017-0178. View

Suh H, Choi Y, Bae S, Ahn S, Chang J, Kang S . Primary central nervous system lymphoma and atypical glioblastoma: Differentiation using radiomics approach. Eur Radiol. 2018; 28(9):3832-3839. DOI: 10.1007/s00330-018-5368-4. View

Xia W, Hu B, Li H, Geng C, Wu Q, Yang L . Multiparametric-MRI-Based Radiomics Model for Differentiating Primary Central Nervous System Lymphoma From Glioblastoma: Development and Cross-Vendor Validation. J Magn Reson Imaging. 2020; 53(1):242-250. DOI: 10.1002/jmri.27344. View

10.

Bathla G, Priya S, Liu Y, Ward C, Le N, Soni N . Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: a comparison of diagnostic performance across different MRI sequences and machine learning techniques. Eur Radiol. 2021; 31(11):8703-8713. DOI: 10.1007/s00330-021-07845-6. View

11.

Zhang Y, Liang K, He J, Ma H, Chen H, Zheng F . Deep Learning With Data Enhancement for the Differentiation of Solitary and Multiple Cerebral Glioblastoma, Lymphoma, and Tumefactive Demyelinating Lesion. Front Oncol. 2021; 11:665891. PMC: 8416477. DOI: 10.3389/fonc.2021.665891. View

12.

McAvoy M, Calvachi Prieto P, Kaczmarzyk J, Sanchez Fernandez I, McNulty J, Smith T . Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks. Sci Rep. 2021; 11(1):15219. PMC: 8313677. DOI: 10.1038/s41598-021-94733-0. View

13.

Guha A, Goda J, Dasgupta A, Mahajan A, Halder S, Gawde J . Classifying primary central nervous system lymphoma from glioblastoma using deep learning and radiomics based machine learning approach - a systematic review and meta-analysis. Front Oncol. 2022; 12:884173. PMC: 9574102. DOI: 10.3389/fonc.2022.884173. View

14.

Xia W, Hu B, Li H, Shi W, Tang Y, Yu Y . Deep Learning for Automatic Differential Diagnosis of Primary Central Nervous System Lymphoma and Glioblastoma: Multi-Parametric Magnetic Resonance Imaging Based Convolutional Neural Network Model. J Magn Reson Imaging. 2021; 54(3):880-887. DOI: 10.1002/jmri.27592. View

15.

Isensee F, Jaeger P, Kohl S, Petersen J, Maier-Hein K . nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2020; 18(2):203-211. DOI: 10.1038/s41592-020-01008-z. View

16.

Bakas S, Akbari H, Sotiras A, Bilello M, Rozycki M, Kirby J . Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data. 2017; 4:170117. PMC: 5685212. DOI: 10.1038/sdata.2017.117. View

17.

Menze B, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J . The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans Med Imaging. 2014; 34(10):1993-2024. PMC: 4833122. DOI: 10.1109/TMI.2014.2377694. View

18.

van Griethuysen J, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77(21):e104-e107. PMC: 5672828. DOI: 10.1158/0008-5472.CAN-17-0339. View

19.

Zwanenburg A, Vallieres M, Abdalah M, Aerts H, Andrearczyk V, Apte A . The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020; 295(2):328-338. PMC: 7193906. DOI: 10.1148/radiol.2020191145. View

20.

Feng A, Li L, Huang T, Li S, He N, Huang L . Differentiating glioblastoma from primary central nervous system lymphoma of atypical manifestation using multiparametric magnetic resonance imaging: A comparative study. Heliyon. 2023; 9(4):e15150. PMC: 10121909. DOI: 10.1016/j.heliyon.2023.e15150. View

21.

Dandois V, De Coene B, Laloux P, Godfraind C, Cosnard G . Increased relative cerebral blood volume (rCBV) in brain lymphoma. J Neuroradiol. 2010; 38(3):191-3. DOI: 10.1016/j.neurad.2010.06.004. View