Brain MRI Screening Tool with Federated Learning

D 2024

Brain MRI Screening Tool with Federated Learning

STOKLASA, Roman, Ioannis STATHOPOULOS, Efstratios KARAVASILIS, Efstathios EFSTATHOPOULOS, Marek DOSTÁL et. al.

Základní údaje

Originální název

Brain MRI Screening Tool with Federated Learning

Autoři

STOKLASA, Roman (703 Slovensko, garant, domácí), Ioannis STATHOPOULOS, Efstratios KARAVASILIS, Efstathios EFSTATHOPOULOS, Marek DOSTÁL (203 Česká republika), Miloš KEŘKOVSKÝ (203 Česká republika), Michal KOZUBEK (203 Česká republika) a Luigi SERIO

Vydání

Athens, Greece, 2024 IEEE International Symposium on Biomedical Imaging, od s. 1-5, 5 s. 2024

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"

Organizační jednotka

Fakulta informatiky

ISBN

979-8-3503-1333-8

DOI

http://dx.doi.org/10.1109/ISBI56570.2024.10635396

Klíčová slova anglicky

MRI; brain; tumor; screening; FL; federated; learning

Štítky

cbia-web

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 12. 9. 2024 15:20, RNDr. Roman Stoklasa, Ph.D.

Anotace

V originále

In clinical practice, we often see significant delays between MRI scans and the diagnosis made by radiologists, even for severe cases. In some cases, this may be caused by the lack of additional information and clues, so even the severe cases need to wait in the queue for diagnosis. This can be avoided if there is an automatic software tool, which would supplement additional information, alerting radiologists that the particular patient may be a severe case. We are presenting an automatic brain MRI Screening Tool and we are demonstrating its capabilities for detecting tumor-like pathologies. It is the first version on the path toward a robust multi-pathology screening solution. The tool supports Federated Learning, so multiple institutions may contribute to the model without disclosing their private data. The tool detected 98% of brain tumors in our testing dataset (102 patients) with a precision of 91 %, achieving a segmentation Dice score more than 0.88.

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, Ioannis STATHOPOULOS, Efstratios KARAVASILIS, Efstathios EFSTATHOPOULOS, Marek DOSTÁL, Miloš KEŘKOVSKÝ, Michal KOZUBEK a Luigi SERIO. Brain MRI Screening Tool with Federated Learning. Online. In 2024 IEEE International Symposium on Biomedical Imaging. Athens, Greece: IEEE, 2024, s. 1-5. ISBN 979-8-3503-1333-8. Dostupné z: https://dx.doi.org/10.1109/ISBI56570.2024.10635396.

@inproceedings{2412317,
   author = {Stoklasa, Roman and Stathopoulos, Ioannis and Karavasilis, Efstratios and Efstathopoulos, Efstathios and Dostál, Marek and Keřkovský, Miloš and Kozubek, Michal and Serio, Luigi},
   address = {Athens, Greece},
   booktitle = {2024 IEEE International Symposium on Biomedical Imaging},
   doi = {http://dx.doi.org/10.1109/ISBI56570.2024.10635396},
   keywords = {MRI; brain; tumor; screening; FL; federated; learning},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Athens, Greece},
   isbn = {979-8-3503-1333-8},
   pages = {1-5},
   publisher = {IEEE},
   title = {Brain MRI Screening Tool with Federated Learning},
   year = {2024}
}

TY  - JOUR
ID  - 2412317
AU  - Stoklasa, Roman - Stathopoulos, Ioannis - Karavasilis, Efstratios - Efstathopoulos, Efstathios - Dostál, Marek - Keřkovský, Miloš - Kozubek, Michal - Serio, Luigi
PY  - 2024
TI  - Brain MRI Screening Tool with Federated Learning
PB  - IEEE
CY  - Athens, Greece
SN  - 9798350313338
KW  - MRI
KW  - brain
KW  - tumor
KW  - screening
KW  - FL
KW  - federated
KW  - learning
N2  - In clinical practice, we often see significant delays between MRI scans and the diagnosis made by radiologists, even for severe cases. In some cases, this may be caused by the lack of additional information and clues, so even the severe cases need to wait in the queue for diagnosis. This can be avoided if there is an automatic software tool, which would supplement additional information, alerting radiologists that the particular patient may be a severe case. We are presenting an automatic brain MRI Screening Tool and we are demonstrating its capabilities for detecting tumor-like pathologies. It is the first version on the path toward a robust multi-pathology screening solution. The tool supports Federated Learning, so multiple institutions may contribute to the model without disclosing their private data. The tool detected 98% of brain tumors in our testing dataset (102 patients) with a precision of 91 %, achieving a segmentation Dice score more than 0.88.
ER  -

STOKLASA, Roman, Ioannis STATHOPOULOS, Efstratios KARAVASILIS, Efstathios EFSTATHOPOULOS, Marek DOSTÁL, Miloš KEŘKOVSKÝ, Michal KOZUBEK a Luigi SERIO. Brain MRI Screening Tool with Federated Learning. Online. In \textit{2024 IEEE International Symposium on Biomedical Imaging}. Athens, Greece: IEEE, 2024, s.~1-5. ISBN~979-8-3503-1333-8. Dostupné z: https://dx.doi.org/10.1109/ISBI56570.2024.10635396.

Podrobný výpis o publikaci