Show simple item record

dc.contributor.authorRodríguez Bazaga, Adrián
dc.contributor.authorRoldán Molina, Mónica
dc.contributor.authorBadosa Gallego, Maria del Carmen
dc.contributor.authorJiménez Mallebrera, Cecilia
dc.contributor.authorPorta Pleite, Josep Maria
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Òptica i Optometria
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2020-01-17T13:28:07Z
dc.date.available2021-12-01T01:32:21Z
dc.date.issued2019-12-01
dc.identifier.citationRodríguez-Bazaga, A. [et al.]. A Convolutional Neural Network for the automatic diagnosis of collagen VI-related muscular dystrophies. "Applied soft computing", 1 Desembre 2019, vol. 85, p. 105772:1-105772:9.
dc.identifier.issn1568-4946
dc.identifier.urihttp://hdl.handle.net/2117/175193
dc.description.abstractThe development of machine learning systems for the diagnosis of rare diseases is challenging, mainly due to the lack of data to study them. This paper surmounts this obstacle and presents the first Computer-Aided Diagnosis (CAD) system for low-prevalence collagen VI-related congenital muscular dystrophies. The proposed CAD system works on images of fibroblast cultures obtained with a confocal microscope and relies on a Convolutional Neural Network (CNN) to classify patches of such images in two classes: samples from healthy persons and samples from persons affected by a collagen VI-related muscular distrophy. This fine-grained classification is then used to generate an overall diagnosis on the query image using a majority voting scheme. The proposed system is advantageous, as it overcomes the lack of training data, points to the possibly problematic areas in the query images, and provides a global quantitative evaluation of the condition of the patients, which is fundamental to monitor the effectiveness of potential therapies. The system achieves a high classification performance, with 95% of accuracy and 92% of precision on randomly selected independent test images, outperforming alternative approaches by a significant margin.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subjectÀrees temàtiques de la UPC::Ciències de la visió
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshMachine learning
dc.subject.lcshRare diseases
dc.subject.lcshComputer-aided design
dc.subject.otherConvolutional neural networks
dc.subject.otherDeep learning
dc.subject.otherClassification
dc.subject.otherComputer aided diagnosis
dc.subject.otherConfocal microscopy images
dc.titleA Convolutional Neural Network for the automatic diagnosis of collagen VI-related muscular dystrophies
dc.typeArticle
dc.subject.lemacXarxes neuronals (Informàtica) -- Aplicacions
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacMalalties rares
dc.subject.lemacDisseny assistit per ordinador
dc.contributor.groupUniversitat Politècnica de Catalunya. KRD - Cinemàtica i Disseny de Robots
dc.identifier.doi10.1016/j.asoc.2019.105772
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.sciencedirect.com/science/article/abs/pii/S1568494619305538
dc.rights.accessOpen Access
local.identifier.drac25892515
dc.description.versionPostprint (author's final draft)
local.citation.authorRodríguez-Bazaga, A.; Roldan, M.; Badosa, M.; Jiménez, C.; Porta, J.
local.citation.publicationNameApplied soft computing
local.citation.volume85
local.citation.startingPage105772:1
local.citation.endingPage105772:9


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record