Show simple item record

dc.contributor.authorYeung, Michael
dc.contributor.authorSala, Evis
dc.contributor.authorSchönlieb, Carola-Bibiane
dc.contributor.authorRundo, Leonardo
dc.date.accessioned2021-12-08T00:30:26Z
dc.date.available2021-12-08T00:30:26Z
dc.date.issued2022-01
dc.identifier.issn0895-6111
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/331262
dc.description.abstractAutomatic segmentation methods are an important advancement in medical image analysis. Machine learning techniques, and deep neural networks in particular, are the state-of-the-art for most medical image segmentation tasks. Issues with class imbalance pose a significant challenge in medical datasets, with lesions often occupying a considerably smaller volume relative to the background. Loss functions used in the training of deep learning algorithms differ in their robustness to class imbalance, with direct consequences for model convergence. The most commonly used loss functions for segmentation are based on either the cross entropy loss, Dice loss or a combination of the two. We propose the Unified Focal loss, a new hierarchical framework that generalises Dice and cross entropy-based losses for handling class imbalance. We evaluate our proposed loss function on five publicly available, class imbalanced medical imaging datasets: CVC-ClinicDB, Digital Retinal Images for Vessel Extraction (DRIVE), Breast Ultrasound 2017 (BUS2017), Brain Tumour Segmentation 2020 (BraTS20) and Kidney Tumour Segmentation 2019 (KiTS19). We compare our loss function performance against six Dice or cross entropy-based loss functions, across 2D binary, 3D binary and 3D multiclass segmentation tasks, demonstrating that our proposed loss function is robust to class imbalance and consistently outperforms the other loss functions. Source code is available at: https://github.com/mlyg/unified-focal-loss.
dc.description.sponsorshipThis work was partially supported by The Mark Foundation for Cancer Research and Cancer Research UK Cambridge Centre [C9685/A25177], the CRUK National Cancer Imaging Translational Accelerator (NCITA) [C42780/A27066] and the Wellcome Trust Innovator Award, UK [215733/Z/19/Z]. Additional support was also provided by the National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre [BRC-1215-20014] and the Cambridge Mathematics of Information in Healthcare (CMIH) [funded by the EPSRC grant EP/T017961/1]. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR, or the Department of Health and Social Care. CBS in addition acknowledges support from the Leverhulme Trust project on ‘Breaking the non-convexity barrier’, the Philip Leverhulme Prize, the Royal Society Wolfson Fellowship, the EPSRC grants EP/S026045/1, EP/N014588/1, European Union Horizon 2020 research and innovation programmes under the Marie Skodowska-Curie grant agreement No. 777826 NoMADS and No. 691070 CHiPS, the Cantab Capital Institute for the Mathematics of Information and the Alan Turing Institute. This work was performed using resources provided by the Cambridge Service for Data Driven Discovery (CSD3) operated by the University of Cambridge Research Computing Service (www.csd3.cam.ac.uk), provided by Dell EMC and Intel using Tier-2 funding from the Engineering and Physical Sciences Research Council (capital grant EP/P020259/1), and DiRAC funding from the Science and Technology Facilities Council (www.dirac.ac.uk).
dc.publisherElsevier BV
dc.rightsAll Rights Reserved
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserved
dc.titleUnified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation.
dc.typeArticle
dc.publisher.departmentSchool of Clinical Medicine
dc.date.updated2021-12-06T12:26:44Z
prism.publicationNameComput Med Imaging Graph
dc.identifier.doi10.17863/CAM.78708
dcterms.dateAccepted2021-12-04
rioxxterms.versionofrecord10.1016/j.compmedimag.2021.102026
rioxxterms.versionAM
dc.contributor.orcidSala, Evis [0000-0002-5518-9360]
dc.identifier.eissn1879-0771
rioxxterms.typeJournal Article/Review
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/N014588/1)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (691070)
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/P020259/1)
pubs.funder-project-idCancer Research UK (C96/A25177)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (777826)
pubs.funder-project-idEPSRC (EP/S026045/1)
pubs.funder-project-idEPSRC (EP/T017961/1)
pubs.funder-project-idNational Institute for Health Research (NIHRDH-IS-BRC-1215-20014)
cam.orpheus.successTue Feb 01 19:02:24 GMT 2022 - Embargo updated
cam.depositDate2021-12-06
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2023-01-31


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record