% 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”.
@INPROCEEDINGS{Upschulte:1031452,
author = {Upschulte, Eric and Harmeling, Stefan and Amunts, Katrin
and Dickscheid, Timo},
title = {{T}owards {U}niversal {I}nstance {S}egmentation {M}odels in
{B}iomedical {I}maging},
school = {HHU Düssledorf},
reportid = {FZJ-2024-05671},
year = {2024},
abstract = {Precise instance segmentation is a critical part of many
fields of research in biomedical imaging. One key challenge
is applying models to new data domains, typically involving
pre-training a model on a larger corpus of data and
fine-tuning it with new annotations for each specific
domain. This process is labor- intensive and requires
creating and maintaining multiple branched versions of the
model. Working towards universal instance segmentation
models in biomedical imaging, we propose to unify
domain-adapted model branches into a single multi-expert
model, following a foundation model paradigm. Our goal is to
replace most existing fine-tuning scenarios with
prompt-based user instructions, allowing the user to clearly
state the task and object classes of interest. We
hypothesize that such a combined approach improves
generalization, as the base model can benefit from datasets
that were previously only used for fine-tuning. A key
challenge in the creation of such models is to resolve
training conflicts and ambiguity in a pragmatic fashion when
combining different segmentation tasks, datasets, and data
domains. Such conflicts can occur if datasets focus on
different classes in the same domain. For example, some
datasets annotate all cells in microscopy images, while
others focus on cells of a specific cell type. A naïve
combination of such sets would create an ill-posed learning
problem for most models, requiring them to infer their task
from their input, which is undesirable in a universal
setting. Models like SAM and MedSAM highlight the potential
of prompting, but often require external detectors and
fine-tuning. Here, we propose to leverage prompt-based task
descriptions as a tool to manipulate general model behavior,
such that user instructions yield domain expert models. We
test our approach by training a Contour Proposal Network
(CPN) on a multi-modal data collection, including the
TissueNet dataset. Prompts, such as “cell segmentation”
or simply “nuclei”, modulate underlying features,
allowing the CPN to segment the respective object classes in
TissueNet with a mean F1 score of 0.90 (0.88 for cells, 0.92
for nuclei), compared to 0.84 (0.81, 0.87) without
prompting. Overall, the proposed approach introduces an
interactive linguistic component that allows the
conflict-free composition of various segmentation datasets,
thus allowing to unify previously separated segmentation
tasks. With that, we consider it an important step towards
universal models.},
month = {Sep},
date = {2024-09-09},
organization = {8th BigBrain Workshop, Padua (Italy),
9 Sep 2024 - 11 Sep 2024},
subtyp = {After Call},
cin = {INM-1},
cid = {I:(DE-Juel1)INM-1-20090406},
pnm = {5254 - Neuroscientific Data Analytics and AI (POF4-525) /
HIBALL - Helmholtz International BigBrain Analytics and
Learning Laboratory (HIBALL) (InterLabs-0015) / EBRAINS 2.0
- EBRAINS 2.0: A Research Infrastructure to Advance
Neuroscience and Brain Health (101147319) / Helmholtz AI -
Helmholtz Artificial Intelligence Coordination Unit –
Local Unit FZJ (E.40401.62)},
pid = {G:(DE-HGF)POF4-5254 / G:(DE-HGF)InterLabs-0015 /
G:(EU-Grant)101147319 / G:(DE-Juel-1)E.40401.62},
typ = {PUB:(DE-HGF)6},
url = {https://juser.fz-juelich.de/record/1031452},
}