A novel federated deep learning scheme for glioma and its subtype classification

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: onr:"swepub:oai:research.chalmers.se:d815772e-5f99-4c97-8569-df402740abc3" > A novel federated d...

1 av 1
Föregående post
Nästa post
Till träfflistan

Ali, Muhaddisa Barat,1986Chalmers tekniska högskola,Chalmers University of Technology (författare)

A novel federated deep learning scheme for glioma and its subtype classification

Artikel/kapitelEngelska2023

Förlag, utgivningsår, omfång ...

2023
electronicrdacarrier

Nummerbeteckningar

LIBRIS-ID:oai:research.chalmers.se:d815772e-5f99-4c97-8569-df402740abc3
https://doi.org/10.3389/fnins.2023.1181703DOI
https://research.chalmers.se/publication/535849URI
https://gup.ub.gu.se/publication/326809URI

Kompletterande språkuppgifter

Språk:engelska
Sammanfattning på:engelska

Ingår i deldatabas

SwePubSwePub

Klassifikation

Ämneskategori:art swepub-publicationtype
Ämneskategori:ref swepub-contenttype

Anmärkningar

Background: Deep learning (DL) has shown promising results in molecular-based classification of glioma subtypes from MR images. DL requires a large number of training data for achieving good generalization performance. Since brain tumor datasets are usually small in size, combination of such datasets from different hospitals are needed. Data privacy issue from hospitals often poses a constraint on such a practice. Federated learning (FL) has gained much attention lately as it trains a central DL model without requiring data sharing from different hospitals. Method: We propose a novel 3D FL scheme for glioma and its molecular subtype classification. In the scheme, a slice-based DL classifier, EtFedDyn, is exploited which is an extension of FedDyn, with the key differences on using focal loss cost function to tackle severe class imbalances in the datasets, and on multi-stream network to exploit MRIs in different modalities. By combining EtFedDyn with domain mapping as the pre-processing and 3D scan-based post-processing, the proposed scheme makes 3D brain scan-based classification on datasets from different dataset owners. To examine whether the FL scheme could replace the central learning (CL) one, we then compare the classification performance between the proposed FL and the corresponding CL schemes. Furthermore, detailed empirical-based analysis were also conducted to exam the effect of using domain mapping, 3D scan-based post-processing, different cost functions and different FL schemes. Results: Experiments were done on two case studies: classification of glioma subtypes (IDH mutation and wild-type on TCGA and US datasets in case A) and glioma grades (high/low grade glioma HGG and LGG on MICCAI dataset in case B). The proposed FL scheme has obtained good performance on the test sets (85.46%, 75.56%) for IDH subtypes and (89.28%, 90.72%) for glioma LGG/HGG all averaged on five runs. Comparing with the corresponding CL scheme, the drop in test accuracy from the proposed FL scheme is small (−1.17%, −0.83%), indicating its good potential to replace the CL scheme. Furthermore, the empirically tests have shown that an increased classification test accuracy by applying: domain mapping (0.4%, 1.85%) in case A; focal loss function (1.66%, 3.25%) in case A and (1.19%, 1.85%) in case B; 3D post-processing (2.11%, 2.23%) in case A and (1.81%, 2.39%) in case B and EtFedDyn over FedAvg classifier (1.05%, 1.55%) in case A and (1.23%, 1.81%) in case B with fast convergence, which all contributed to the improvement of overall performance in the proposed FL scheme. Conclusion: The proposed FL scheme is shown to be effective in predicting glioma and its subtypes by using MR images from test sets, with great potential of replacing the conventional CL approaches for training deep networks. This could help hospitals to maintain their data privacy, while using a federated trained classifier with nearly similar performance as that from a centrally trained one. Further detailed experiments have shown that different parts in the proposed 3D FL scheme, such as domain mapping (make datasets more uniform) and post-processing (scan-based classification), are essential.

Ämnesord och genrebeteckningar

NATURVETENSKAP Data- och informationsvetenskap Annan data- och informationsvetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences Other Computer and Information Science hsv//eng
NATURVETENSKAP Data- och informationsvetenskap Människa-datorinteraktion hsv//swe
NATURAL SCIENCES Computer and Information Sciences Human Computer Interaction hsv//eng
MEDICIN OCH HÄLSOVETENSKAP Klinisk medicin Neurologi hsv//swe
MEDICAL AND HEALTH SCIENCES Clinical Medicine Neurology hsv//eng
NATURVETENSKAP Data- och informationsvetenskap Datavetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences Computer Sciences hsv//eng
MEDICIN OCH HÄLSOVETENSKAP Klinisk medicin Cancer och onkologi hsv//swe
MEDICAL AND HEALTH SCIENCES Clinical Medicine Cancer and Oncology hsv//eng
MEDICIN OCH HÄLSOVETENSKAP Klinisk medicin Kirurgi hsv//swe
MEDICAL AND HEALTH SCIENCES Clinical Medicine Surgery hsv//eng
MEDICIN OCH HÄLSOVETENSKAP Klinisk medicin Radiologi och bildbehandling hsv//swe
MEDICAL AND HEALTH SCIENCES Clinical Medicine Radiology, Nuclear Medicine and Medical Imaging hsv//eng
TEKNIK OCH TEKNOLOGIER Medicinteknik Medicinsk bildbehandling hsv//swe
ENGINEERING AND TECHNOLOGY Medical Engineering Medical Image Processing hsv//eng
domain mapping
multi-stream FL deep network
extended FedDyn
glioma subtype classification
IDH genotype
federated learning
deep learning

Biuppslag (personer, institutioner, konferenser, titlar ...)

Gu, Irene Yu-Hua,1953Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)irenegu (författare)
Berger, Mitchel S.University of California (författare)
Jakola, Asgeir StoreGothenburg University,Göteborgs universitet,Institutionen för neurovetenskap och fysiologi, sektionen för klinisk neurovetenskap,Institute of Neuroscience and Physiology, Department of Clinical Neuroscience(Swepub:gu)xjakas (författare)
Chalmers tekniska högskolaUniversity of California (creator_code:org_t)

Sammanhörande titlar

Ingår i:Frontiers in Neuroscience171662-45481662-453X

Internetlänk

Hitta via bibliotek

Frontiers in Neuroscience (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

1 av 1
Föregående post
Nästa post
Till träfflistan

Hitta mer i SwePub

Av författaren/redakt...: Ali, Muhaddisa B ...; Gu, Irene Yu-Hua ...; Berger, Mitchel ...; Jakola, Asgeir S ...

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Annan data och i ...

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Människa datorin ...

MEDICIN OCH HÄLSOVETENSKAP: MEDICIN OCH HÄLS ...; och Klinisk medicin; och Neurologi

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datavetenskap

MEDICIN OCH HÄLSOVETENSKAP: MEDICIN OCH HÄLS ...; och Klinisk medicin; och Cancer och onkol ...

MEDICIN OCH HÄLSOVETENSKAP: MEDICIN OCH HÄLS ...; och Klinisk medicin; och Kirurgi

visa fler...

MEDICIN OCH HÄLSOVETENSKAP: MEDICIN OCH HÄLS ...; och Klinisk medicin; och Radiologi och bi ...

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Medicinteknik; och Medicinsk bildbe ...

visa färre...

Artiklar i publikationen: Frontiers in Neu ...

Av lärosätet: Chalmers tekniska högskola; Göteborgs universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se