Correction to: Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutio
- PDF / 144,217 Bytes
- 2 Pages / 595.276 x 790.866 pts Page_size
- 3 Downloads / 248 Views
CORRECTION
Correction to: Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks Sven Koitka 1
&
Lennard Kroll 1
&
Eugen Malamutmann 2
# The Author(s) 2020
Correction to: European Radiology https://doi.org/10.1007/s00330-020-07147-3 The original version of this article, published on 18 September 2020, unfortunately contained a mistake. The following correction has therefore been made in the original: The presentation of the second equation in paragraph “Training details” and of Table 2 was incorrect; the corrected equation and table are given below. The original article has been corrected. N
LDice
C 1 ⋅∑ ¼ 1:0− C−1 c¼2
∑ 2⋅byc;n ⋅yc;n þ ∈
n¼1 N
∑ byc;n þ yc;n þ ∈
n¼1
The online version of the original article can be found at https://doi.org/ 10.1007/s00330-020-07147-3 * Sven Koitka [email protected] 1
Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
2
Department of General, Visceral and Transplantation Surgery, University Hospital Essen, Essen, Germany
&
Arzu Oezcelik 2
&
Felix Nensa 1
Eur Radiol Table 2 Evaluation for the fivefold cross-validation runs (stated as mean overall runs) and ensemble predictions on the test set. AC, abdominal cavity; B, bones; M, muscle; ST, subcutaneous tissue; TC, thoracic cavity Dice score Fivefold CV
Test set
Model U-Net 3D
nf 16 32 64
nparam 5.34 M 21.36 M 85.43 M
AC 0.9509 0.9669 0.9682
B 0.9462 0.9540 0.9561
M 0.9266 0.9379 0.9403
ST 0.9432 0.9574 0.9582
TC 0.8823 0.9336 0.9481
Average 0.9299 0.9500 0.9542
Multi-res U-Net 3D
16 32 64 16 32 64 16 32 64
5.82 M 21.24 M 85.10 M 5.34 M 21.36 M 85.43 M 5.82 M 21.24 M 85.10 M
0.9589 0.9680 0.9692 0.9609 0.9731 0.9739 0.9667 0.9736 0.973
0.9484 0.9554 0.9564 0.9340 0.9390 0.9406 0.9355 0.9409 0.9423
0.9328 0.9399 0.9414 0.9229 0.9309 0.9316 0.9272 0.9328 0.9334
0.9531 0.9596 0.9605 0.9553 0.9610 0.9623 0.9593 0.9627 0.9623
0.9211 0.9414 0.9452 0.9172 0.9598 0.9641 0.9518 0.9629 0.9652
0.9429 0.9529 0.9545 0.9381 0.9528 0.9545 0.9481 0.9546 0.9553
U-Net 3D
Multi-res U-Net 3D
Open Access This article is licensed under a Creative Commons
Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the
article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Publisher’s note Springer Nature remains ne
Data Loading...
