Universität zu Köln

Kottlors, Jonathan ORCID: 0000-0001-5021-6895, Geissen, Simon, Jendreizik, Hannah, Grosse Hokamp, Nils ORCID: 0000-0001-7928-0487, Fervers, Philipp ORCID: 0000-0003-3663-3486, Pennig, Lenhard, Laukamp, Kai, Kabbasch, Christoph, Maintz, David, Schlamann, Marc and Borggrefe, Jan ORCID: 0000-0003-2908-7560 (2021). Contrast-Enhanced Black Blood MRI Sequence Is Superior to Conventional T1 Sequence in Automated Detection of Brain Metastases by Convolutional Neural Networks. Diagnostics, 11 (6). BASEL: MDPI. ISSN 2075-4418

Full text not available from this repository.

Abstract

Background: in magnetic resonance imaging (MRI), automated detection of brain metastases with convolutional neural networks (CNN) represents an extraordinary challenge due to small lesions sometimes posing as brain vessels as well as other confounders. Literature reporting high false positive rates when using conventional contrast enhanced (CE) T1 sequences questions their usefulness in clinical routine. CE black blood (BB) sequences may overcome these limitations by suppressing contrast-enhanced structures, thus facilitating lesion detection. This study compared CNN performance in conventional CE T1 and BB sequences and tested for objective improvement of brain lesion detection. Methods: we included a subgroup of 127 consecutive patients, receiving both CE T1 and BB sequences, referred for MRI concerning metastatic spread to the brain. A pretrained CNN was retrained with a customized monolayer classifier using either T1 or BB scans of brain lesions. Results: CE T1 imaging-based training resulted in an internal validation accuracy of 85.5% vs. 92.3% in BB imaging (p < 0.01). In holdout validation analysis, T1 image-based prediction presented poor specificity and sensitivity with an AUC of 0.53 compared to 0.87 in BB-imaging-based prediction. Conclusions: detection of brain lesions with CNN, BB-MRI imaging represents a highly effective input type when compared to conventional CE T1-MRI imaging. Use of BB-MRI can overcome the current limitations for automated brain lesion detection and the objectively excellent performance of our CNN suggests routine usage of BB sequences for radiological analysis.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Kottlors, Jonathan UNSPECIFIED orcid.org/0000-0001-5021-6895 UNSPECIFIED Geissen, Simon UNSPECIFIED UNSPECIFIED UNSPECIFIED Jendreizik, Hannah UNSPECIFIED UNSPECIFIED UNSPECIFIED Grosse Hokamp, Nils UNSPECIFIED orcid.org/0000-0001-7928-0487 UNSPECIFIED Fervers, Philipp UNSPECIFIED orcid.org/0000-0003-3663-3486 UNSPECIFIED Pennig, Lenhard UNSPECIFIED UNSPECIFIED UNSPECIFIED Laukamp, Kai UNSPECIFIED UNSPECIFIED UNSPECIFIED Kabbasch, Christoph UNSPECIFIED UNSPECIFIED UNSPECIFIED Maintz, David UNSPECIFIED UNSPECIFIED UNSPECIFIED Schlamann, Marc UNSPECIFIED UNSPECIFIED UNSPECIFIED Borggrefe, Jan UNSPECIFIED orcid.org/0000-0003-2908-7560 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-576537
DOI:	10.3390/diagnostics11061016
Journal or Publication Title:	Diagnostics
Volume:	11
Number:	6
Date:	2021
Publisher:	MDPI
Place of Publication:	BASEL
ISSN:	2075-4418
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language COMPUTER-AIDED DETECTION; SEGMENTATION; MANAGEMENT Multiple languages Medicine, General & Internal Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/57653