Tabatabaei, Z.; Wang, Y.; Colomer, A.; Oliver Moll, J.; Zhao, Z.; Naranjo Ornedo, V. (2023). WWFedCBMIR: World-Wide Federated Content-Based Medical Image Retrieval. Bioengineering. 10(10). https://doi.org/10.3390/bioengineering10101144
Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10251/205646
Title:
|
WWFedCBMIR: World-Wide Federated Content-Based Medical Image Retrieval
|
Author:
|
Tabatabaei, Zahra
Wang, Yuandou
Colomer, Adrián
Oliver Moll, Javier
Zhao, Zhiming
Naranjo Ornedo, Valeriana
|
UPV Unit:
|
Universitat Politècnica de València. Escuela Técnica Superior de Ingenieros de Telecomunicación - Escola Tècnica Superior d'Enginyers de Telecomunicació
|
Issued date:
|
|
Abstract:
|
[EN] The paper proposes a federated content-based medical image retrieval (FedCBMIR) tool
that utilizes federated learning (FL) to address the challenges of acquiring a diverse medical data
set for training CBMIR models. ...[+]
[EN] The paper proposes a federated content-based medical image retrieval (FedCBMIR) tool
that utilizes federated learning (FL) to address the challenges of acquiring a diverse medical data
set for training CBMIR models. CBMIR is a tool to find the most similar cases in the data set to
assist pathologists. Training such a tool necessitates a pool of whole-slide images (WSIs) to train the
feature extractor (FE) to extract an optimal embedding vector. The strict regulations surrounding data
sharing in hospitals makes it difficult to collect a rich data set. FedCBMIR distributes an unsupervised
FE to collaborative centers for training without sharing the data set, resulting in shorter training times
and higher performance. FedCBMIR was evaluated by mimicking two experiments, including two
clients with two different breast cancer data sets, namely BreaKHis and Camelyon17 (CAM17), and
four clients with the BreaKHis data set at four different magnifications. FedCBMIR increases the F1
score (F1S) of each client from 96% to 98.1% in CAM17 and from 95% to 98.4% in BreaKHis, with
11.44 fewer hours in training time. FedCBMIR provides 98%, 96%, 94%, and 97% F1S in the BreaKHis
experiment with a generalized model and accomplishes this in 25.53 fewer hours of training.
[-]
|
Subjects:
|
Breast cancer
,
Content-based medical image retrieval (CBMIR)
,
Convolutional auto-encoder
(CAE)
,
Federated learning (FL)
,
Computer-aided diagnosis
,
Histopathological images
,
Digital pathology
,
Whole-slide images (WSIs)
|
Copyrigths:
|
Reconocimiento (by)
|
Source:
|
Bioengineering. (eissn:
2306-5354
)
|
DOI:
|
10.3390/bioengineering10101144
|
Publisher:
|
MDPI AG
|
Publisher version:
|
https://doi.org/10.3390/bioengineering10101144
|
Project ID:
|
info:eu-repo/grantAgreement/EC/H2020/860627/EU/CLoud ARtificial Intelligence For pathologY/
info:eu-repo/grantAgreement/UPV//PAID-PD-22/
|
Thanks:
|
This study is funded by European Union s Horizon 2020 research and innovation program under the Marie Skodowska-Curie grant agreement No. 860627 (CLARIFY Project). The work of Adrián Colomer has been supported by the ValgrAI ...[+]
This study is funded by European Union s Horizon 2020 research and innovation program under the Marie Skodowska-Curie grant agreement No. 860627 (CLARIFY Project). The work of Adrián Colomer has been supported by the ValgrAI Valencian Graduate School and Research Network for Artificial Intelligence and Generalitat Valenciana and Universitat Politècnica de València
(PAID-PD-22).
[-]
|
Type:
|
Artículo
|