Precise volumetric assessment of brain tumors is relevant for treatment planning and monitoring. However, manual segmentations are time-consuming and impeded by intra- and interrater variabilities.
To investigate the performance of a deep-learning model (DLM) to automatically detect and segment primary central nervous system lymphoma (PCNSL) on clinical MRI.
Sixty-nine scans (at initial and/or follow-up imaging) from 43 patients with PCNSL referred for clinical MRI tumor assessment.
T -/T -weighted, T -weighted contrast-enhanced (T CE), and FLAIR at 1.0, 1.5, and 3.0T from different vendors and study centers.
Fully automated voxelwise segmentation of tumor components was performed using a 3D convolutional neural network (DeepMedic) trained on gliomas (n = 220). DLM segmentations were compared to manual segmentations performed in a 3D voxelwise manner by two readers (radiologist and neurosurgeon; consensus reading) from T CE and FLAIR, which served as the reference standard.
Dice similarity coefficient (DSC) for comparison of spatial overlap with the reference standard, Pearson’s correlation coefficient (r) to assess the relationship between volumetric measurements of segmentations, and Wilcoxon rank-sum test for comparison of DSCs obtained in initial and follow-up imaging.
The DLM detected 66 of 69 PCNSL, representing a sensitivity of 95.7%. Compared to the reference standard, DLM achieved good spatial overlap for total tumor volume (TTV, union of tumor volume in T CE and FLAIR; average size 77.16 ± 62.4 cm , median DSC: 0.76) and tumor core (contrast enhancing tumor in T CE; average size: 11.67 ± 13.88 cm , median DSC: 0.73). High volumetric correlation between automated and manual segmentations was observed (TTV: r = 0.88, P < 0.0001; core: r = 0.86, P < 0.0001). Performance of automated segmentations was comparable between pretreatment and follow-up scans without significant differences (TTV: P = 0.242, core: P = 0.177).
In clinical MRI scans, a DLM initially trained on gliomas provides segmentation of PCNSL comparable to manual segmentation, despite its complex and multifaceted appearance. Segmentation performance was high in both initial and follow-up scans, suggesting its potential for application in longitudinal tumor imaging.

© 2020 The Authors. Journal of Magnetic Resonance Imaging published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.