IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING

D 2025

IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING

STOKLASA, Roman

Základní údaje

Originální název

IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING

Autoři

STOKLASA, Roman

Vydání

NEW YORK, 2025 IEEE 22ND INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, od s. 1-5, 5 s. 2025

Nakladatel

IEEE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Označené pro přenos do RIV

Ano

Organizační jednotka

Fakulta informatiky

ISBN

979-8-3315-2053-3

ISSN

DOI

https://doi.org/10.1109/ISBI60581.2025.10981263

UT WoS

001546451000589

Klíčová slova anglicky

harmonization; normalization; CDF; histogram matching; federated learning; FL; MRI; brain; tumor

Štítky

cbia-web, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 18. 11. 2025 11:16, RNDr. Roman Stoklasa, Ph.D.

Anotace

V originále

Deployment of machine learning algorithms into real-world practice is still a difficult task. One of the challenges lies in the unpredictable variability of input data, which may differ significantly among individual users, institutions, scanners, etc. The input data variability can be decreased by using suitable data preprocessing with robust data harmonization. In this paper, we present a method of image harmonization using Cumulative Distribution Function (CDF) matching based on curve fitting. This approach does not ruin local variability and individual important features. The transformation of image intensities is non-linear but still "smooth and elastic", as compared to other known histogram matching algorithms. Non-linear transformation allows for a very good match to the template. At the same time, elasticity constraints help to preserve local variability among individual inputs, which may encode important features for subsequent machine-learning processing. The pre-defined template CDF offers a better and more intuitive control for the input data transformation compared to other methods, especially ML-based ones. Even though we developed our method for MRI images, the method is generic enough to apply to other types of imaging data.

Návaznosti

LM2023050, projekt VaV

Název: Národní infrastruktura pro biologické a medicínské zobrazování

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Czech BioImaging: Národní výzkumná infrastruktura pro biologické a medicínské zobrazování

NU21-08-00359, projekt VaV

Název: Klasifikace mozkových tumorů pomocí pokročilých metod analýzy dat multimodálního MR zobrazení difuze

Investor: Ministerstvo zdravotnictví ČR, Klasifikace mozkových tumorů pomocí pokročilých metod analýzy dat multimodálního MR zobrazení difuze, Podprogram 1 - standardní

Citovat

STOKLASA, Roman. IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING. Online. In 2025 IEEE 22ND INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI. NEW YORK: IEEE, 2025, s. 1-5. ISBN 979-8-3315-2053-3. Dostupné z: https://doi.org/10.1109/ISBI60581.2025.10981263.

@inproceedings{2469994,
   author = {Stoklasa, Roman},
   address = {NEW YORK},
   booktitle = {2025 IEEE 22ND INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI},
   doi = {https://doi.org/10.1109/ISBI60581.2025.10981263},
   keywords = {harmonization; normalization; CDF; histogram matching; federated learning; FL; MRI; brain; tumor},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {NEW YORK},
   isbn = {979-8-3315-2053-3},
   pages = {1-5},
   publisher = {IEEE},
   title = {IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING},
   year = {2025}
}

TY  - CONF
ID  - 2469994
AU  - Stoklasa, Roman
PY  - 2025
TI  - IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING
PB  - IEEE
CY  - NEW YORK
SN  - 9798331520533
KW  - harmonization
KW  - normalization
KW  - CDF
KW  - histogram matching
KW  - federated learning
KW  - FL
KW  - MRI
KW  - brain
KW  - tumor
N2  - Deployment of machine learning algorithms into real-world practice is still a difficult task. One of the challenges lies in the unpredictable variability of input data, which may differ significantly among individual users, institutions, scanners, etc. The input data variability can be decreased by using suitable data preprocessing with robust data harmonization. In this paper, we present a method of image harmonization using Cumulative Distribution Function (CDF) matching based on curve fitting. This approach does not ruin local variability and individual important features. The transformation of image intensities is non-linear but still "smooth and elastic", as compared to other known histogram matching algorithms. Non-linear transformation allows for a very good match to the template. At the same time, elasticity constraints help to preserve local variability among individual inputs, which may encode important features for subsequent machine-learning processing. The pre-defined template CDF offers a better and more intuitive control for the input data transformation compared to other methods, especially ML-based ones. Even though we developed our method for MRI images, the method is generic enough to apply to other types of imaging data.
ER  -

STOKLASA, Roman. IMAGE HARMONIZATION USING ROBUST RESTRICTED CDF MATCHING. Online. In \textit{2025 IEEE 22ND INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI}. NEW YORK: IEEE, 2025, s.~1-5. ISBN~979-8-3315-2053-3. Dostupné z: https://doi.org/10.1109/ISBI60581.2025.10981263.

Přehled o publikaci