Universität zu Köln

Koechli, Carole, Vu, Erwin ORCID: 0000-0002-3298-517X, Sager, Philipp, Naf, Lukas, Fischer, Tim ORCID: 0000-0002-1807-9146, Putora, Paul M., Ehret, Felix ORCID: 0000-0001-6177-1755, Fuerweger, Christoph, Schroder, Christina, Forster, Robert, Zwahlen, Daniel R., Muacevic, Alexander and Windisch, Paul ORCID: 0000-0003-1040-4888 (2022). Convolutional Neural Networks to Detect Vestibular Schwannomas on Single MRI Slices: A Feasibility Study. Cancers, 14 (9). BASEL: MDPI. ISSN 2072-6694

Full text not available from this repository.

Abstract

Simple Summary Due to the fact that they take inter-slice information into account, 3D- and 2.5D-convolutional neural networks (CNNs) potentially perform better in tumor detection tasks than 2D-CNNs. However, this potential benefit is at the expense of increased computational power and the need for segmentations as an input. Therefore, in this study we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. We retrained (539 patients) and internally validated (94 patients) a pretrained CNN using contrast-enhanced MRI slices from one institution. Furthermore, we externally validated the CNN using contrast-enhanced MRI slices from another institution. This resulted in an accuracy of 0.949 (95% CI 0.935-0.963) and 0.912 (95% CI 0.866-0.958) for the internal and external validation, respectively. Our findings indicate that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased requirement for computational power and the fact that there is no need for segmentations. In this study. we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. A pretrained CNN (ResNet-34) was retrained and internally validated using contrast-enhanced T1-weighted (T1c) MRI slices from one institution. In a second step, the model was externally validated using T1c- and T1-weighted (T1) slices from a different institution. As a substitute, bisected slices were used with and without tumors originating from whole transversal slices that contained part of the unilateral VS. The model predictions were assessed based on the categorical accuracy and confusion matrices. A total of 539, 94, and 74 patients were included for training, internal validation, and external T1c validation, respectively. This resulted in an accuracy of 0.949 (95% CI 0.935-0.963) for the internal validation and 0.912 (95% CI 0.866-0.958) for the external T1c validation. We suggest that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased demand for computational power and the fact that there is no need for segmentations. However, further research is needed on the difference between 2D-CNNs and more complex architectures.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Koechli, Carole UNSPECIFIED UNSPECIFIED UNSPECIFIED Vu, Erwin UNSPECIFIED orcid.org/0000-0002-3298-517X UNSPECIFIED Sager, Philipp UNSPECIFIED UNSPECIFIED UNSPECIFIED Naf, Lukas UNSPECIFIED UNSPECIFIED UNSPECIFIED Fischer, Tim UNSPECIFIED orcid.org/0000-0002-1807-9146 UNSPECIFIED Putora, Paul M. UNSPECIFIED UNSPECIFIED UNSPECIFIED Ehret, Felix UNSPECIFIED orcid.org/0000-0001-6177-1755 UNSPECIFIED Fuerweger, Christoph UNSPECIFIED UNSPECIFIED UNSPECIFIED Schroder, Christina UNSPECIFIED UNSPECIFIED UNSPECIFIED Forster, Robert UNSPECIFIED UNSPECIFIED UNSPECIFIED Zwahlen, Daniel R. UNSPECIFIED UNSPECIFIED UNSPECIFIED Muacevic, Alexander UNSPECIFIED UNSPECIFIED UNSPECIFIED Windisch, Paul UNSPECIFIED orcid.org/0000-0003-1040-4888 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-688558
DOI:	10.3390/cancers14092069
Journal or Publication Title:	Cancers
Volume:	14
Number:	9
Date:	2022
Publisher:	MDPI
Place of Publication:	BASEL
ISSN:	2072-6694
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language ARTIFICIAL-INTELLIGENCE; DECISION-MAKING; GENE-EXPRESSION; SEGMENTATION; IMAGES Multiple languages Oncology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/68855