Title: Identification of primary central nervous system lymphoma from high-grade glioma based on a ¹⁸F-FDG PET/CT radiomics nomogram compared with deep learning: a multicentre study

Authors: Xin Jin; Yujing Zhou; Lili Qu; Jingtao Wang; Shoumei Yan; Kaiyue Li; Hang Zhou; Li Ma; Xin Li

Addresses: Department of Nuclear Medicine, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China; Imaging Centre of Jinan Third People's Hospital, #1 Wangsheren North Street, Gongye North Road, Jinan, 250132, Shandong Province, China ' Department of Nuclear Medicine, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China ' Department of Nuclear Medicine, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China ' Department of Haematology, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China ' Department of Nuclear Medicine, Shandong Cancer Hospital and Institute, Shandong First Medical University, #440 Jiyan Road, Jinan, 250117, Shandong Province, China ' Department of Nuclear Medicine, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China ' Department of Nuclear Medicine, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China ' Department of Nuclear Medicine, Shandong Cancer Hospital and Institute, Shandong First Medical University, #440 Jiyan Road, Jinan, 250117, Shandong Province, China ' Department of Nuclear Medicine, Qilu Hospital of Shandong University, #107 Wenhua West Road, Jinan, 250012, Shandong Province, China

Abstract: Diagnosing central nervous system space-occupying lesions still depend on stereotactic biopsy. Therefore, a non-invasive imaging method is urgently required to distinguish between the two. This retrospective study enrolled 66 patients (38 with PCNSL and 28 with HGG) who underwent ¹⁸F-fluorodeoxyglucose-positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) between July 2017 and July 2022 to investigate the ability of ¹⁸F-FDG PET/CT -based radiomics features in differentially diagnosing PCNSL and HGG. A group of 40 patients was assigned as the training cohort, while another group of 26 patients as the validation cohort. A total of 788 radiomics features were extracted from ¹⁸F-FDG PET/CT images in the training cohort. Two features were selected by the LASSO method from 788 features to build the logistic model and radiomics nomogram. The AUC of the radiomics nomogram for discriminating PCNSL from HGG was 0.960 [95% confidence interval (CI): 0.909-1] and 0.920 (95% CI: 0.794-1) in the training and validation cohorts, respectively. The training and validation revealed that the established radiomics nomogram model of ¹⁸F-FDG PET/CT displayed excellent discrimination capabilities in PCNSL and HGG, and may have the potential to improve diagnostic accuracy and patient outcomes.

Keywords: radiomics; deep learning; ¹⁸F-FDG PET/CT; high-grade glioma; HGG; primary central nervous system lymphoma; PCNSL.

DOI: 10.1504/IJBIC.2025.146394

International Journal of Bio-Inspired Computation, 2025 Vol.25 No.3, pp.168 - 176

Received: 17 Apr 2024
Accepted: 13 Jun 2024
Published online: 28 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article