pith. sign in

arxiv: 2405.07762 · v2 · submitted 2024-05-13 · 📡 eess.IV · cs.CV

A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms

Johan \"Ofverstedt , Elin Lundstr\"om , G\"oran Bergstr\"om , Joel Kullberg , H{\aa}kan Ahlstr\"om This is my paper

Pith reviewed 2026-05-24 00:59 UTC · model grok-4.3

classification 📡 eess.IV cs.CV
keywords supervoxel analysiscoronary CT angiogramage associationimage registrationsex differencesheart volumetissue densitymorphological change
0
0 comments X

The pith

A registration and supervoxel correlation method reveals localized age associations in coronary CT angiograms outside standard heart regions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a method that performs association studies between chronological age and both volumetric and tissue density features extracted at the supervoxel level from coronary computed tomography angiograms. It achieves this by first segmenting the images, then applying inter-subject registration to align them, and finally running a robust supervoxel-based correlation analysis to detect statistical links. When applied in a sex-stratified manner to a large set of 1388 images, the method identifies age-related changes in areas beyond the usual manually segmented heart sub-regions together with clear differences between the sexes in how age relates to volume. A reader would care because the approach offers a way to map aging effects on heart morphology and density at finer spatial scales without depending on predefined anatomical boundaries.

Core claim

The authors developed a method based on image segmentation, inter-subject image registration, and robust supervoxel-based correlation analysis to enable statistical association studies between volumetric and tissue density features in coronary computed tomography angiograms and chronological age. The registration step was evaluated using Dice coefficients for heart chambers and myocardium plus checks of inverse consistency, which indicated acceptable performance in most cases. When the full pipeline was run on a large cohort in sex-stratified fashion, it detected localized associations with age outside commonly analyzed sub-regions and substantial differences between the sexes in the age-to-

What carries the argument

The supervoxel-wise correlation analysis made possible by inter-subject registration, which aligns images so that volume and density features can be compared at corresponding supervoxel locations across subjects.

If this is right

  • The method detects age-related changes in heart volume and density in regions that fall outside standard anatomical segmentations.
  • Substantial differences appear between sexes in the way age associates with volume at the supervoxel scale.
  • The registration component produces high overlap and inverse consistency for heart chambers and myocardium in the majority of cases.
  • The same pipeline can be used to study associations with non-imaging variables other than age.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The approach could be reused on the same images to test associations with other variables such as blood pressure or cholesterol levels.
  • By operating at the supervoxel level rather than whole-region averages, the method may surface associations that are diluted or missed when analysis is restricted to predefined segments.
  • The observed sex differences imply that any future cardiac aging studies using similar imaging should incorporate sex stratification as a standard step.

Load-bearing premise

The inter-subject image registration must produce transformations that achieve high enough overlap and inverse consistency to support reliable feature comparisons at the supervoxel level without alignment artifacts creating the reported associations.

What would settle it

Re-running the association analysis after replacing the registration step with an alternative algorithm or after removing subjects whose registrations show lower Dice overlap would eliminate the localized age associations and the reported sex differences.

Figures

Figures reproduced from arXiv: 2405.07762 by Elin Lundstr\"om, G\"oran Bergstr\"om, H{\aa}kan Ahlstr\"om, Joel Kullberg, Johan \"Ofverstedt.

Figure 1
Figure 1. Figure 1: Illustration of the proposed methodology. Step 1: The images are segmented us [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of the image channels and masks used in the deformable image [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Analysis of the template selection for the female cohort. The sub-figures (a-f) [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Analysis of the template selection for the male cohort. The sub-figures (a-f) [PITH_FULL_IMAGE:figures/full_fig_p012_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Illustration of the SLIC supervoxels (volumetric connected segments), as used in [PITH_FULL_IMAGE:figures/full_fig_p015_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visual examples of the registration performance showing example axial slices of: [PITH_FULL_IMAGE:figures/full_fig_p016_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Performance of image registration in terms of the Dice coefficient of five major [PITH_FULL_IMAGE:figures/full_fig_p018_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Pairwise Pearson correlation coefficients between age and explicit volumetric [PITH_FULL_IMAGE:figures/full_fig_p019_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Pairwise Pearson correlation coefficients between age and explicit volumetric [PITH_FULL_IMAGE:figures/full_fig_p020_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Supervoxel-wise results of Pearson correlation between JD and LAV/LVV, [PITH_FULL_IMAGE:figures/full_fig_p022_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Supervoxel-wise analysis of the local voxel volume, as measured by the JD, [PITH_FULL_IMAGE:figures/full_fig_p023_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Supervoxel-wise analysis of selected axial slices of density images for the (a) [PITH_FULL_IMAGE:figures/full_fig_p024_12.png] view at source ↗
read the original abstract

The study of associations between an individual's age and imaging and non-imaging data is an active research area that attempts to aid understanding of the effects and patterns of aging. In this work we have conducted a supervoxel-wise association study between both volumetric and tissue density features in coronary computed tomography angiograms and the chronological age of a subject, to understand the localized changes in morphology and tissue density with age. To enable a supervoxel-wise study of volume and tissue density, we developed a novel method based on image segmentation, inter-subject image registration, and robust supervoxel-based correlation analysis, to achieve a statistical association study between the images and age. We evaluate the registration methodology in terms of the Dice coefficient for the heart chambers and myocardium, and the inverse consistency of the transformations, showing that the method works well in most cases with high overlap and inverse consistency. In a sex-stratified study conducted on a subset of $n=1388$ images from the SCAPIS study, the supervoxel-wise analysis was able to find localized associations with age outside of the commonly segmented and analyzed sub-regions, and several substantial differences between the sexes in the association of age and volume.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper presents a pipeline for supervoxel-wise association studies of age (and sex) with volumetric and tissue-density features extracted from coronary CT angiograms. The method combines segmentation, inter-subject registration, and robust supervoxel correlation analysis; it is applied to a sex-stratified subset of n=1388 SCAPIS images and reports localized age associations outside standard cardiac sub-regions together with substantial sex differences in volume-age relationships. Registration is evaluated via Dice overlap on chambers/myocardium and inverse consistency, with the claim that the method “works well in most cases.”

Significance. If the registration produces anatomically faithful supervoxel correspondences that are demonstrably free of age- or sex-correlated residual misalignment, the approach could reveal spatially localized cardiac aging patterns that are invisible to conventional whole-chamber or standard-segment analyses, thereby strengthening sex-stratified morphological studies of aging.

major comments (2)
  1. [Registration evaluation] Registration evaluation (abstract and methods): Dice coefficients and inverse-consistency metrics are reported only on the large chambers and myocardium; these aggregate scores on coarse structures do not test whether local misalignments in smaller or more variable regions remain uncorrelated with age or sex. Any such correlation would artifactually generate the reported supervoxel-wise associations and sex differences.
  2. [Abstract and results] Abstract and results sections: the central empirical claim (localized age associations and sex differences) is stated without any quantitative support—effect sizes, p-values, statistical thresholds, confidence intervals, or even the number of significant supervoxels—leaving the strength and reproducibility of the findings impossible to assess from the provided text.
minor comments (1)
  1. The phrase “works well in most cases” is used without accompanying numerical thresholds, failure rates, or per-subject distributions for the Dice and inverse-consistency metrics.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive feedback. We address each major comment below and will revise the manuscript accordingly where appropriate.

read point-by-point responses

  1. Referee: [Registration evaluation] Registration evaluation (abstract and methods): Dice coefficients and inverse-consistency metrics are reported only on the large chambers and myocardium; these aggregate scores on coarse structures do not test whether local misalignments in smaller or more variable regions remain uncorrelated with age or sex. Any such correlation would artifactually generate the reported supervoxel-wise associations and sex differences.

    Authors: We agree that Dice scores and inverse consistency on large chambers and myocardium alone do not fully exclude the possibility of local misalignments correlated with age or sex. In the revised version we will add (i) registration accuracy metrics on smaller substructures where segmentations are available and (ii) explicit checks for correlation between residual misalignment measures and both age and sex. These additions will strengthen the claim that the reported associations are not driven by registration artifacts. revision: yes

  2. Referee: [Abstract and results] Abstract and results sections: the central empirical claim (localized age associations and sex differences) is stated without any quantitative support—effect sizes, p-values, statistical thresholds, confidence intervals, or even the number of significant supervoxels—leaving the strength and reproducibility of the findings impossible to assess from the provided text.

    Authors: The referee correctly notes the absence of quantitative detail. We will revise both the abstract and results sections to report effect sizes, p-values (or equivalent), statistical thresholds used, confidence intervals where applicable, and the number of significant supervoxels (after correction) for the age and sex-stratified findings. revision: yes

Circularity Check

0 steps flagged

Empirical pipeline with no self-referential derivations or load-bearing self-citations

full rationale

The paper describes a data-processing pipeline (segmentation, inter-subject registration, supervoxel feature extraction, and statistical association testing) applied to SCAPIS images. No equations, fitted parameters, or derivations are presented that reduce the reported age-volume or age-density associations to quantities defined by the pipeline itself. Registration is validated with independent metrics (Dice on chambers/myocardium and inverse consistency) that do not enter the definition of the supervoxel features or the correlation statistics. No uniqueness theorems, ansatzes, or self-citations are invoked to justify core choices. The central claims rest on direct empirical measurements from the n=1388 cohort and are therefore self-contained.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Only the abstract is available, so the ledger is limited to the core domain assumption required for the method to function. No free parameters or invented entities are identifiable from the given text.

axioms (1)
  • domain assumption Inter-subject registration achieves sufficient accuracy and inverse consistency for supervoxel-wise comparisons
    The method depends on this to enable cross-subject feature extraction and correlation without alignment-induced artifacts.

pith-pipeline@v0.9.0 · 5770 in / 1188 out tokens · 36610 ms · 2026-05-24T00:59:43.105600+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

37 extracted references · 37 canonical work pages · 1 internal anchor

  1. [1]

    G:)PYmPY;5) 2VY ї ?f - | 12 &

    + is cited as + ESG96 +. In connection with cross-referencing and possible future hyperlinking it is not a good idea to collect more that one literature item in one + +. The so-called Harvard or author-year style of referencing is enabled by the package natbib . With this package the literature can be cited as follows: enumerate [ ] Parenthetical: + WB96 ...

    work page 1996

  2. [2]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION word.in bbl.in ":" * " " * FUNCTION f...

    work page

  3. [3]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION word.in bbl.in ":" * " " * FUNCTION f...

    work page

  4. [4]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION word.in bbl.in ":" * " " * FUNCTION f...

    work page

  5. [5]

    , author Shaji, A

    author Achanta, R. , author Shaji, A. , author Smith, K. , author Lucchi, A. , author Fua, P. , author S \"u sstrunk, S. , year 2012 . title Slic superpixels compared to state-of-the-art superpixel methods . journal IEEE transactions on pattern analysis and machine intelligence volume 34 , pages 2274--2282

    work page 2012

  6. [6]

    , author Janowitz, W.R

    author Agatston, A.S. , author Janowitz, W.R. , author Hildner, F.J. , author Zusmer, N.R. , author Viamonte Jr, M. , author Detrano, R. , year 1990 . title Quantification of coronary artery calcium using ultrafast computed tomography . journal Journal of the American college of cardiology volume 15 , pages 827--832

    work page 1990

  7. [7]

    o nsson, H. , author Tarai, S. , author Guggilla, R.K. , author Strand, R. , author Lundstr \

    author Ahmad, N. , author Dahlberg, H. , author J \"o nsson, H. , author Tarai, S. , author Guggilla, R.K. , author Strand, R. , author Lundstr \"o m, E. , author Bergstr \"o m, G. , author Ahlstr \"o m, H. , author Kullberg, J. , year 2024 . title Voxel-wise body composition analysis using image registration of a three-slice ct imaging protocol: methodol...

    work page 2024

  8. [8]

    , author Angelopoulos, A

    author Antonopoulos, A.S. , author Angelopoulos, A. , author Tsioufis, K. , author Antoniades, C. , author Tousoulis, D. , year 2022 . title Cardiovascular risk stratification by coronary computed tomography angiography imaging: current state-of-the-art . journal European journal of preventive cardiology volume 29 , pages 608--624

    work page 2022

  9. [9]

    , author Suzuki, H

    author Bai, W. , author Suzuki, H. , author Huang, J. , author Francis, C. , author Wang, S. , author Tarroni, G. , author Guitton, F. , author Aung, N. , author Fung, K. , author Petersen, S.E. , et al., year 2020 . title A population-based phenome-wide association study of cardiac and aortic structure and function . journal Nature medicine volume 26 , p...

    work page 2020

  10. [10]

    , author Dalca, A.V

    author Batmanghelich, N.K. , author Dalca, A.V. , author Sabuncu, M.R. , author Golland, P. , year 2013 . title Joint modeling of imaging and genetics , in: booktitle Information Processing in Medical Imaging: 23rd International Conference, IPMI 2013, Asilomar, CA, USA, June 28--July 3, 2013. Proceedings 23 , organization Springer . pp. pages 766--777

    work page 2013

  11. [11]

    o m, G. , author Berglund, G. , author Blomberg, A. , author Brandberg, J. , author Engstr \

    author Bergstr \"o m, G. , author Berglund, G. , author Blomberg, A. , author Brandberg, J. , author Engstr \"o m, G. , author Engvall, J. , author Eriksson, M. , author De Faire, U. , author Flinck, A. , author Hansson, M.G. , et al., year 2015 . title The swedish cardiopulmonary bioimage study: objectives and design . journal Journal of internal medicin...

    work page 2015

  12. [12]

    , author Qin, C

    author Chen, C. , author Qin, C. , author Qiu, H. , author Tarroni, G. , author Duan, J. , author Bai, W. , author Rueckert, D. , year 2020 . title Deep learning for cardiac image segmentation: a review . journal Frontiers in Cardiovascular Medicine volume 7 , pages 25

    work page 2020

  13. [13]

    , author Hu, J

    author Chen, M. , author Hu, J. , author Chen, C. , author Hao, G. , author Hu, S. , author Xu, J. , author Hu, C. , year 2023 . title Radiomics analysis of pericoronary adipose tissue based on plain ct for preliminary screening of coronary artery disease in patients with type 2 diabetes mellitus . journal Acta Radiologica volume 64 , pages 2704--2713

    work page 2023

  14. [14]

    , author Ohkawa, S.i

    author Chida, K. , author Ohkawa, S.i. , author Watanabe, C. , author Shimada, H. , author Ohtsubo, K. , author Sugiura, M. , year 1994 . title A morphological study of the normally aging heart . journal Cardiovascular Pathology volume 3 , pages 1--7

    work page 1994

  15. [15]

    , year 1999

    author Christensen, G.E. , year 1999 . title Consistent linear-elastic transformations for image matching , in: booktitle Biennial International Conference on Information Processing in Medical Imaging , organization Springer . pp. pages 224--237

    work page 1999

  16. [16]

    , year 1945

    author Dice, L.R. , year 1945 . title Measures of the amount of ecologic association between species . journal Ecology volume 26 , pages 297--302

    work page 1945

  17. [17]

    u h, M. , author Yang, B. , author Gatidis, S. , author K \

    author Ecker, V. , author Fr \"u h, M. , author Yang, B. , author Gatidis, S. , author K \"u stner, T. , year 2024 . title Deep regression for biological age estimation in multiple organs: Investigations on 40,000 subjects of the uk biobank , in: booktitle ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ,...

    work page 2024

  18. [18]

    , year 2020

    author Ekstr \"o m, S. , year 2020 . title Efficient GPU-based Image Registration: for Detailed Large-Scale Whole-body Analysis . Ph.D. thesis. Acta Universitatis Upsaliensis

    work page 2020

  19. [19]

    o m, S. , author Malmberg, F. , author Ahlstr \

    author Ekstr \"o m, S. , author Malmberg, F. , author Ahlstr \"o m, H. , author Kullberg, J. , author Strand, R. , year 2020 . title Fast graph-cut based optimization for practical dense deformable registration of volume images . journal Computerized Medical Imaging and Graphics volume 84 , pages 101745

    work page 2020

  20. [20]

    o m, S. , author Pilia, M. , author Kullberg, J. , author Ahlstr \

    author Ekstr \"o m, S. , author Pilia, M. , author Kullberg, J. , author Ahlstr \"o m, H. , author Strand, R. , author Malmberg, F. , year 2021 . title Faster dense deformable image registration by utilizing both cpu and gpu . journal Journal of Medical Imaging volume 8 , pages 014002--014002

    work page 2021

  21. [21]

    , author Alv \'e n, J

    author Fagman, E. , author Alv \'e n, J. , author Westerbergh, J. , author Kitslaar, P. , author Kercsik, M. , author Cederlund, K. , author Duvernoy, O. , author Engvall, J. , author Gon c alves, I. , author Markstad, H. , et al., year 2023 . title High-quality annotations for deep learning enabled plaque analysis in scapis cardiac computed tomography an...

    work page 2023

  22. [22]

    o nsson, H. , author Ekstr \

    author J \"o nsson, H. , author Ekstr \"o m, S. , author Strand, R. , author Pedersen, M.A. , author Molin, D. , author Ahlstr \"o m, H. , author Kullberg, J. , year 2022 . title An image registration method for voxel-wise analysis of whole-body oncological pet-ct . journal Scientific Reports volume 12 , pages 18768

    work page 2022

  23. [23]

    , author Hepp, T

    author Kerber, B. , author Hepp, T. , author K \"u stner, T. , author Gatidis, S. , year 2023 . title Deep learning-based age estimation from clinical computed tomography image data of the thorax and abdomen in the adult population . journal Plos one volume 18 , pages e0292993

    work page 2023

  24. [24]

    , author Schaap, M

    author Kirisli, H.A. , author Schaap, M. , author Klein, S. , author Neefjes, L.A. , author Weustink, A.C. , author Van Walsum, T. , author Niessen, W.J. , year 2010 . title Fully automatic cardiac segmentation from 3d cta data: a multi-atlas based approach , in: booktitle Medical Imaging 2010: Image Processing , organization SPIE . pp. pages 55--63

    work page 2010

  25. [25]

    o m, J. , author Bjerner, T. , author Ahlstr \

    author Langner, T. , author Wikstr \"o m, J. , author Bjerner, T. , author Ahlstr \"o m, H. , author Kullberg, J. , year 2019 . title Identifying morphological indicators of aging with neural networks on large-scale whole-body mri . journal IEEE transactions on medical imaging volume 39 , pages 1430--1437

    work page 2019

  26. [26]

    , author Peterson, T.E

    author Li, X. , author Peterson, T.E. , author Gore, J.C. , author Dawant, B.M. , year 2006 . title Automatic inter-subject registration of whole body images , in: booktitle Biomedical Image Registration: Third International Workshop, WBIR 2006, Utrecht, The Netherlands, July 9-11, 2006. Proceedings 3 , organization Springer . pp. pages 18--25

    work page 2006

  27. [27]

    , author Ribeiro, A.H

    author Lima, E.M. , author Ribeiro, A.H. , author Paix \ a o, G.M. , author Ribeiro, M.H. , author Pinto-Filho, M.M. , author Gomes, P.R. , author Oliveira, D.M. , author Sabino, E.C. , author Duncan, B.B. , author Giatti, L. , et al., year 2021 . title Deep neural network-estimated electrocardiographic age as a mortality predictor . journal Nature commun...

    work page 2021

  28. [28]

    Scalable Simple Linear Iterative Clustering (SSLIC) Using a Generic and Parallel Approach

    author Lowekamp, B.C. , author Chen, D.T. , author Yaniv, Z. , author Yoo, T.S. , year 2018 . title Scalable simple linear iterative clustering (sslic) using a generic and parallel approach . journal arXiv preprint arXiv:1806.08741

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  29. [29]

    , author Giordano, G

    author Olivetti, G. , author Giordano, G. , author Corradi, D. , author Melissari, M. , author Lagrasta, C. , author Gambert, S.R. , author Anversa, P. , year 1995 . title Gender differences and aging: effects on the human heart . journal Journal of the American College of Cardiology volume 26 , pages 1068--1079

    work page 1995

  30. [30]

    o m, H. , author Malmberg, F. , author Ekstr \

    author Pilia, M. , author Kullberg, J. , author Ahlstr \"o m, H. , author Malmberg, F. , author Ekstr \"o m, S. , author Strand, R. , year 2019 . title Average volume reference space for large scale registration of whole-body magnetic resonance images . journal PloS one volume 14 , pages e0222700

    work page 2019

  31. [31]

    , author Schnabel, J.A

    author Rueckert, D. , author Schnabel, J.A. , year 2010 . title Medical image registration , in: booktitle Biomedical image processing . publisher Springer , pp. pages 131--154

    work page 2010

  32. [32]

    , author Eckert, J

    author Schmermund, A. , author Eckert, J. , author Schmidt, M. , author Magedanz, A. , author Voigtl \"a nder, T. , year 2018 . title Coronary computed tomography angiography: a method coming of age . journal Clinical Research in Cardiology volume 107 , pages 40--48

    work page 2018

  33. [33]

    , author Peirlinck, M

    author St Pierre, S.R. , author Peirlinck, M. , author Kuhl, E. , year 2022 . title Sex matters: a comprehensive comparison of female and male hearts . journal Frontiers in Physiology volume 13 , pages 831179

    work page 2022

  34. [34]

    , author Malmberg, F

    author Strand, R. , author Malmberg, F. , author Johansson, L. , author Lind, L. , author Sundbom, M. , author Ahlstr \"o m, H. , author Kullberg, J. , year 2017 . title A concept for holistic whole body mri data analysis, imiomics . journal PloS one volume 12 , pages e0169966

    work page 2017

  35. [35]

    , author Chung, A.C

    author Tang, T.W. , author Chung, A.C. , year 2007 . title Non-rigid image registration using graph-cuts , in: booktitle Medical Image Computing and Computer-Assisted Intervention--MICCAI 2007: 10th International Conference, Brisbane, Australia, October 29-November 2, 2007, Proceedings, Part I 10 , organization Springer . pp. pages 916--924

    work page 2007

  36. [36]

    , author Breit, H.C

    author Wasserthal, J. , author Breit, H.C. , author Meyer, M.T. , author Pradella, M. , author Hinck, D. , author Sauter, A.W. , author Heye, T. , author Boll, D.T. , author Cyriac, J. , author Yang, S. , et al., year 2023 . title Totalsegmentator: Robust segmentation of 104 anatomic structures in ct images . journal Radiology: Artificial Intelligence volume 5

    work page 2023

  37. [37]

    , author Thompson, P.M

    author Yanovsky, I. , author Thompson, P.M. , author Klunder, A.D. , author Toga, A.W. , author Leow, A.D. , year 2007 . title Local volume change maps in nonrigid registration: when are computed changes real , in: booktitle International Conference on Medical Image Computing and Computer Assisted Intervention, Workshop on Statistical Registration , organ...

    work page 2007