Universität zu Köln

Pennig, Lenhard, Hoyer, Ulrike Cornelia Isabel, Goertz, Lukas, Shahzad, Rahil, Persigehl, Thorsten, Thiele, Frank, Perkuhn, Michael, Ruge, Maximilian, I, Kabbasch, Christoph, Borggrefe, Jan ORCID: 0000-0003-2908-7560, Caldeira, Liliana and Laukamp, Kai Roman (2021). Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on MultiparametricMRIUsing Deep Learning. J. Magn. Reson. Imaging, 53 (1). S. 259 - 269. HOBOKEN: WILEY. ISSN 1522-2586

Full text not available from this repository.

Abstract

Background 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. Purpose 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 T-1-/T-2-weighted, T-1-weighted contrast-enhanced (T1CE), and FLAIR at 1.0, 1.5, and 3.0T from different vendors and study centers. Assessment 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 T1CE 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 (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. Results 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 T1CE and FLAIR; average size 77.16 +/- 62.4 cm(3), median DSC: 0.76) and tumor core (contrast enhancing tumor in T1CE; average size: 11.67 +/- 13.88 cm(3), 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

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Pennig, Lenhard UNSPECIFIED UNSPECIFIED UNSPECIFIED Hoyer, Ulrike Cornelia Isabel UNSPECIFIED UNSPECIFIED UNSPECIFIED Goertz, Lukas UNSPECIFIED UNSPECIFIED UNSPECIFIED Shahzad, Rahil UNSPECIFIED UNSPECIFIED UNSPECIFIED Persigehl, Thorsten UNSPECIFIED UNSPECIFIED UNSPECIFIED Thiele, Frank UNSPECIFIED UNSPECIFIED UNSPECIFIED Perkuhn, Michael UNSPECIFIED UNSPECIFIED UNSPECIFIED Ruge, Maximilian, I UNSPECIFIED UNSPECIFIED UNSPECIFIED Kabbasch, Christoph UNSPECIFIED UNSPECIFIED UNSPECIFIED Borggrefe, Jan UNSPECIFIED orcid.org/0000-0003-2908-7560 UNSPECIFIED Caldeira, Liliana UNSPECIFIED UNSPECIFIED UNSPECIFIED Laukamp, Kai Roman UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-326535
DOI:	10.1002/jmri.27288
Journal or Publication Title:	J. Magn. Reson. Imaging
Volume:	53
Number:	1
Page Range:	S. 259 - 269
Date:	2021
Publisher:	WILEY
Place of Publication:	HOBOKEN
ISSN:	1522-2586
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language MRI FEATURES; BRAIN; RECURRENT; ARCHIVES; TUMORS; AFIP; CNS Multiple languages Radiology, Nuclear Medicine & Medical Imaging Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/32653