Universität zu Köln

Woznicki, Piotr, Siedek, Florian, van Gastel, Maatje D. A., Dos Santos, Daniel Pinto, Arjune, Sita ORCID: 0000-0002-6121-4614, Karner, Larina A., Meyer, Franziska, Caldeira, Liliana Lourenco, Persigehl, Thorsten, Gansevoort, Ron T., Grundmann, Franziska ORCID: 0000-0002-5766-7477, Baessler, Bettina and Mueller, Roman-Ulrich (2022). Automated Kidney and Liver Segmentation in MR Images in Patients with Autosomal Dominant Polycystic Kidney Disease: A Multicenter Study. Kidney360, 3 (12). S. 2048 - 2059. WASHINGTON: AMER SOC NEPHROLOGY. ISSN 2641-7650

Full text not available from this repository.

Abstract

Background Imaging-based total kidney volume (TKV) and total liver volume (TLV) are major prognostic factors in autosomal dominant polycystic kidney disease (ADPKD) and end points for clinical trials. However, volumetry is time consuming and reader dependent in clinical practice. Our aim was to develop a fully automated method for joint kidney and liver segmentation in magnetic resonance imaging (MRI) and to evaluate its performance in a multisequence, multicenter setting. Methods The convolutional neural network was trained on a large multicenter dataset consisting of 992 MRI scans of 327 patients. Manual segmentation delivered ground-truth labels. The model's performance was evaluated in a separate test dataset of 93 patients (350 MRI scans) as well as a heterogeneous external dataset of 831 MRI scans from 323 patients. Results The segmentation model yielded excellent performance, achieving a median per study Dice coefficient of 0.92-0.97 for the kidneys and 0.96 for the liver. Automatically computed TKV correlated highly with manual measurements (intraclass correlation coefficient [ICC]: 0.996-0.999) with low bias and high precision (-0.2%+/- 4% for axial images and 0.5%+/- 4% for coronal images). TLV estimation showed an ICC of 0.999 and bias/precision of -0.5%+/- 3%. For the external dataset, the automated TKV demonstrated bias and precision of -1%+/- 7%. Conclusions Our deep learning model enabled accurate segmentation of kidneys and liver and objective assessment of TKV and TLV. Importantly, this approach was validated with axial and coronal MRI scans from 40 different scanners, making implementation in clinical routine care feasible.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Woznicki, Piotr UNSPECIFIED UNSPECIFIED UNSPECIFIED Siedek, Florian UNSPECIFIED UNSPECIFIED UNSPECIFIED van Gastel, Maatje D. A. UNSPECIFIED UNSPECIFIED UNSPECIFIED Dos Santos, Daniel Pinto UNSPECIFIED UNSPECIFIED UNSPECIFIED Arjune, Sita UNSPECIFIED orcid.org/0000-0002-6121-4614 UNSPECIFIED Karner, Larina A. UNSPECIFIED UNSPECIFIED UNSPECIFIED Meyer, Franziska UNSPECIFIED UNSPECIFIED UNSPECIFIED Caldeira, Liliana Lourenco UNSPECIFIED UNSPECIFIED UNSPECIFIED Persigehl, Thorsten UNSPECIFIED UNSPECIFIED UNSPECIFIED Gansevoort, Ron T. UNSPECIFIED UNSPECIFIED UNSPECIFIED Grundmann, Franziska UNSPECIFIED orcid.org/0000-0002-5766-7477 UNSPECIFIED Baessler, Bettina UNSPECIFIED UNSPECIFIED UNSPECIFIED Mueller, Roman-Ulrich UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-682850
DOI:	10.34067/KID.0003192022
Journal or Publication Title:	Kidney360
Volume:	3
Number:	12
Page Range:	S. 2048 - 2059
Date:	2022
Publisher:	AMER SOC NEPHROLOGY
Place of Publication:	WASHINGTON
ISSN:	2641-7650
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language VOLUME Multiple languages Urology & Nephrology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/68285