Gutenberg Open Science: Convolutional neural network-based kidney volume estimation from low-dose unenhanced computed tomography scans

Please use this identifier to cite or link to this item: http://doi.org/10.25358/openscience-9820

Full metadata record

DC Field	Value	Language
dc.contributor.author	Müller, Lukas	-
dc.contributor.author	Tibyampansha, Dativa	-
dc.contributor.author	Mildenberger, Peter	-
dc.contributor.author	Panholzer, Torsten	-
dc.contributor.author	Jungmann, Florian	-
dc.contributor.author	Halfmann, Moritz C.	-
dc.date.accessioned	2023-12-19T09:51:59Z	-
dc.date.available	2023-12-19T09:51:59Z	-
dc.date.issued	2023	-
dc.identifier.uri	https://openscience.ub.uni-mainz.de/handle/20.500.12030/9838	-
dc.description.abstract	Purpose Kidney volume is important in the management of renal diseases. Unfortunately, the currently available, semi-automated kidney volume determination is time-consuming and prone to errors. Recent advances in its automation are promising but mostly require contrast-enhanced computed tomography (CT) scans. This study aimed at establishing an automated estimation of kidney volume in non-contrast, low-dose CT scans of patients with suspected urolithiasis. Methods The kidney segmentation process was automated with 2D Convolutional Neural Network (CNN) models trained on manually segmented 2D transverse images extracted from low-dose, unenhanced CT scans of 210 patients. The models’ segmentation accuracy was assessed using Dice Similarity Coefficient (DSC), for the overlap with manually-generated masks on a set of images not used in the training. Next, the models were applied to 22 previously unseen cases to segment kidney regions. The volume of each kidney was calculated from the product of voxel number and their volume in each segmented mask. Kidney volume results were then validated against results semi-automatically obtained by radiologists. Results The CNN-enabled kidney volume estimation took a mean of 32 s for both kidneys in a CT scan with an average of 1026 slices. The DSC was 0.91 and 0.86 and for left and right kidneys, respectively. Inter-rater variability had consistencies of ICC = 0.89 (right), 0.92 (left), and absolute agreements of ICC = 0.89 (right), 0.93 (left) between the CNN-enabled and semi-automated volume estimations. Conclusion In our work, we demonstrated that CNN-enabled kidney volume estimation is feasible and highly reproducible in low-dose, non-enhanced CT scans. Automatic segmentation can thereby quantitatively enhance radiological reports.	en_GB
dc.language.iso	eng	de
dc.rights	CC BY	*
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/	*
dc.subject.ddc	610 Medizin	de_DE
dc.subject.ddc	610 Medical sciences	en_GB
dc.title	Convolutional neural network-based kidney volume estimation from low-dose unenhanced computed tomography scans	en_GB
dc.type	Zeitschriftenaufsatz	de
dc.identifier.doi	http://doi.org/10.25358/openscience-9820	-
jgu.type.dinitype	article	en_GB
jgu.type.version	Published version	de
jgu.type.resource	Text	de
jgu.organisation.department	FB 04 Medizin	de
jgu.organisation.number	2700	-
jgu.organisation.name	Johannes Gutenberg-Universität Mainz	-
jgu.rights.accessrights	openAccess	-
jgu.journal.title	BMC medical imaging	de
jgu.journal.volume	23	de
jgu.pages.alternative	187	de
jgu.publisher.year	2023	-
jgu.publisher.name	BioMed Central	de
jgu.publisher.place	London	de
jgu.publisher.issn	1471-2342	de
jgu.organisation.place	Mainz	-
jgu.subject.ddccode	610	de
jgu.publisher.doi	10.1186/s12880-023-01142-y	de
jgu.organisation.ror	https://ror.org/023b0x485	-
jgu.subject.dfg	Lebenswissenschaften	de
Appears in collections:	DFG-491381577-G

Files in This Item:

	File	Description	Size	Format
	convolutional_neural_networkb-20231213133841741.pdf		4.17 MB	Adobe PDF	View/Open

Show simple item record