Fracture detection and explainability in deep learning models

This thesis has been developed in the context of a collaboration project between health insurance company for work accidents Asepeyo and the Barcelona Supercomputing Center (BSC). The target of this project is the creation of a functional tool to support non-expert medical practitioners in the diagn...

Descripción completa

Detalles Bibliográficos
Autor: Giménez Abalos, Víctor|||0000-0003-4514-6145
Tipo de recurso: tesis de maestría
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/353720
Acceso en línea:https://hdl.handle.net/2117/353720
Access Level:acceso abierto
Palabra clave:Machine learning
Diagnosis
cnn
explicabilitat
gradcam
lrp
ciencies de la salut
radiografia
aprenentatge supervisat
aprenentatge profund
explainability
healthcare
radiography
supervised learning
deep learning
resnet
Aprenentatge automàtic
Diagnòstic
Àrees temàtiques de la UPC::Informàtica
id ES_e76ef463e95e45dfff0a0925c377f2f7
oai_identifier_str oai:upcommons.upc.edu:2117/353720
network_acronym_str ES
network_name_str España
repository_id_str
spelling Fracture detection and explainability in deep learning modelsGiménez Abalos, Víctor|||0000-0003-4514-6145Machine learningDiagnosiscnnexplicabilitatgradcamlrpciencies de la salutradiografiaaprenentatge supervisataprenentatge profundexplainabilityhealthcareradiographysupervised learningdeep learningresnetAprenentatge automàticDiagnòsticÀrees temàtiques de la UPC::InformàticaThis thesis has been developed in the context of a collaboration project between health insurance company for work accidents Asepeyo and the Barcelona Supercomputing Center (BSC). The target of this project is the creation of a functional tool to support non-expert medical practitioners in the diagnosis of radiology images. In this thesis, we focus the most common radiology diagnosed pathology in Spain: the wrist fracture. For this purpose, Asepeyo provided us with over 13,000 studies of real radiology data, as well as support from experts of the field for feedback. This thesis presents the problem and the analysis performed on it, as well as how we solve it using many AI methods both traditional and novel. Our main contributions include a complex preprocessing to deal with wrist images (as well as DICOM format images), training deep learning models in an environment with some degree of label uncertainty, obtaining models of reasonably high performance, and being able to unsupervisedly produce visual explanations on the radiologies that locate the fracture in the image - as this is a strong requirement for its potential use in practice. The results indicate that the model accuracy is enough to be deployed in a real world scenario, while the expainability outcomes illustrate the appropriate focus of the machine learning models on the fractures. Pending a few additional checks and bias validations, the outcome of this work could constitute a powerful and useful support tool for medical professionals non-experts in radiology. Lastly, we provide at the end a comprehensive list of the necessary requirements to be cleared before deploying the system into public healthcare.Universitat Politècnica de CatalunyaGarcia Gasulla, Dario20212021-06-2520212021-10-15master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/353720reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3537202026-05-27T15:37:01Z
dc.title.none.fl_str_mv Fracture detection and explainability in deep learning models
title Fracture detection and explainability in deep learning models
spellingShingle Fracture detection and explainability in deep learning models
Giménez Abalos, Víctor|||0000-0003-4514-6145
Machine learning
Diagnosis
cnn
explicabilitat
gradcam
lrp
ciencies de la salut
radiografia
aprenentatge supervisat
aprenentatge profund
explainability
healthcare
radiography
supervised learning
deep learning
resnet
Aprenentatge automàtic
Diagnòstic
Àrees temàtiques de la UPC::Informàtica
title_short Fracture detection and explainability in deep learning models
title_full Fracture detection and explainability in deep learning models
title_fullStr Fracture detection and explainability in deep learning models
title_full_unstemmed Fracture detection and explainability in deep learning models
title_sort Fracture detection and explainability in deep learning models
dc.creator.none.fl_str_mv Giménez Abalos, Víctor|||0000-0003-4514-6145
author Giménez Abalos, Víctor|||0000-0003-4514-6145
author_facet Giménez Abalos, Víctor|||0000-0003-4514-6145
author_role author
dc.contributor.none.fl_str_mv Garcia Gasulla, Dario
dc.subject.none.fl_str_mv Machine learning
Diagnosis
cnn
explicabilitat
gradcam
lrp
ciencies de la salut
radiografia
aprenentatge supervisat
aprenentatge profund
explainability
healthcare
radiography
supervised learning
deep learning
resnet
Aprenentatge automàtic
Diagnòstic
Àrees temàtiques de la UPC::Informàtica
topic Machine learning
Diagnosis
cnn
explicabilitat
gradcam
lrp
ciencies de la salut
radiografia
aprenentatge supervisat
aprenentatge profund
explainability
healthcare
radiography
supervised learning
deep learning
resnet
Aprenentatge automàtic
Diagnòstic
Àrees temàtiques de la UPC::Informàtica
description This thesis has been developed in the context of a collaboration project between health insurance company for work accidents Asepeyo and the Barcelona Supercomputing Center (BSC). The target of this project is the creation of a functional tool to support non-expert medical practitioners in the diagnosis of radiology images. In this thesis, we focus the most common radiology diagnosed pathology in Spain: the wrist fracture. For this purpose, Asepeyo provided us with over 13,000 studies of real radiology data, as well as support from experts of the field for feedback. This thesis presents the problem and the analysis performed on it, as well as how we solve it using many AI methods both traditional and novel. Our main contributions include a complex preprocessing to deal with wrist images (as well as DICOM format images), training deep learning models in an environment with some degree of label uncertainty, obtaining models of reasonably high performance, and being able to unsupervisedly produce visual explanations on the radiologies that locate the fracture in the image - as this is a strong requirement for its potential use in practice. The results indicate that the model accuracy is enough to be deployed in a real world scenario, while the expainability outcomes illustrate the appropriate focus of the machine learning models on the fractures. Pending a few additional checks and bias validations, the outcome of this work could constitute a powerful and useful support tool for medical professionals non-experts in radiology. Lastly, we provide at the end a comprehensive list of the necessary requirements to be cleared before deploying the system into public healthcare.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-06-25
2021
2021-10-15
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/353720
url https://hdl.handle.net/2117/353720
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422854766854144
score 15,300719