Primary central nervous system lymphoma MRI
Reported signal characteristics include:
T1
Typically hypointense to grey matter
T1 C+ (Gd)
typical high-grade tumours show intense homogeneous enhancement while low-grade tumours have absent to moderate enhancement
Peripheral ring enhancement may be seen in immunocompromised patients (HIV/AIDS)
T2
Variable
Majority are iso to hypointense to grey matter
Isointense: 33%
Hypointense: 20% 9 – when present this is a helpful distinguishing feature
Hyperintense: 15-47%, more common in tumours with necrosis
DWI/ADC
Restricted diffusion with ADC values lower than normal brain, typically between 400 and 600 x 10-6 mm2/s (lower than high-grade gliomas and metastases)
A number of studies have suggested that the lower the ADC values of the tumour the poorer the response to tumour and higher likelihood of recurrence
AADC is particularly useful in assessing response to chemotherapy, with increases in ADC values to above those of normal brain predictive of complete response
MR spectroscopy
Large choline peak
Reversed choline/creatinine ratio
Markedly decreased NAA
Lactate peak may also be seen
MR perfusion
Only modest if any increase in rCBV (much less marked than in high-grade gliomas, where angiogenesis is a prominent feature).
Volume
Precise volumetric assessment of brain tumors is relevant for treatment planning and monitoring. However, manual segmentations are time-consuming and impeded by intra- and inter rater 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.
Study type: Retrospective.
Population: Sixty-nine scans (at initial and/or follow-up imaging) from 43 patients with PCNSL referred for clinical MRI tumor assessment.
Field strength/sequence: T1 weighted image -/T2 weighted image, T1 -weighted contrast-enhanced (T1 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 T1 CE and FLAIR, which served as the reference standard.
Statistical tests: Dice similarity coefficient (DSC) for comparison of spatial overlap with the reference standard, Pearson’s correlation coefficient ® 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 T1 CE and FLAIR; average size 77.16 ± 62.4 cm3 , median DSC: 0.76) and tumor core (contrast enhancing tumor in T1 CE; average size: 11.67 ± 13.88 cm3 , 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).
Data conclusion: 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.
Level of evidence: 3 TECHNICAL EFFICACY STAGE: 2 1).
WhatsApp us