Brain MRI Screening Tool with Federated Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F65269705%3A_____%2F24%3A00080465" target="_blank" >RIV/65269705:_____/24:00080465 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216224:14330/24:00136280

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10635396" target="_blank" >https://ieeexplore.ieee.org/document/10635396</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ISBI56570.2024.10635396" target="_blank" >10.1109/ISBI56570.2024.10635396</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Brain MRI Screening Tool with Federated Learning

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Brain MRI Screening Tool with Federated Learning

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

30224 - Radiology, nuclear medicine and medical imaging

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings - International Symposium on Biomedical Imaging

ISBN

979-8-3503-1333-8

ISSN

1945-7928

e-ISSN

—

Počet stran výsledku

5

Strana od-do

202064

Název nakladatele

IEEE

Místo vydání

New York

Místo konání akce

Athens

Datum konání akce

27. 5. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001305705101121