% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Adler:298417,
author = {T. Adler$^*$ and J.-H. Nölke$^*$ and A. Reinke$^*$ and M.
D. Tizabi$^*$ and S. Gruber$^*$ and D. Trofimova$^*$ and L.
Ardizzone and P. F. Jaeger$^*$ and F. Buettner$^*$ and U.
Köthe and L. Maier-Hein$^*$},
title = {{A}pplication-driven validation of posteriors in inverse
problems.},
journal = {Medical image analysis},
volume = {101},
issn = {1361-8415},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {DKFZ-2025-00273},
pages = {103474},
year = {2025},
note = {#EA:E130#LA:E130#},
abstract = {Current deep learning-based solutions for image analysis
tasks are commonly incapable of handling problems to which
multiple different plausible solutions exist. In response,
posterior-based methods such as conditional Diffusion Models
and Invertible Neural Networks have emerged; however, their
translation is hampered by a lack of research on adequate
validation. In other words, the way progress is measured
often does not reflect the needs of the driving practical
application. Closing this gap in the literature, we present
the first systematic framework for the application-driven
validation of posterior-based methods in inverse problems.
As a methodological novelty, it adopts key principles from
the field of object detection validation, which has a long
history of addressing the question of how to locate and
match multiple object instances in an image. Treating modes
as instances enables us to perform mode-centric validation,
using well-interpretable metrics from the application
perspective. We demonstrate the value of our framework
through instantiations for a synthetic toy example and two
medical vision use cases: pose estimation in surgery and
imaging-based quantification of functional tissue parameters
for diagnostics. Our framework offers key advantages over
common approaches to posterior validation in all three
examples and could thus revolutionize performance assessment
in inverse problems.},
keywords = {Deep learning (Other) / Inverse problems (Other) / Metrics
(Other) / Posterior (Other) / Validation (Other)},
cin = {E130 / FM01 / E290},
ddc = {610},
cid = {I:(DE-He78)E130-20160331 / I:(DE-He78)FM01-20160331 /
I:(DE-He78)E290-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39892221},
doi = {10.1016/j.media.2025.103474},
url = {https://inrepo02.dkfz.de/record/298417},
}