Matching of Mammographic Lesions in Different Breast Projections

Detalhes bibliográficos
Autor(a) principal: Simão Pedro Ribeiro Quintans
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://hdl.handle.net/10216/136026
Resumo: Of all cancer diseases, breast cancer is the most lethal among women. It has been shown that breast cancer screening programs can decrease mortality, since early detection increases the chances of survival. Usually, a pair of radiologists interpret the screening mammograms, however the process is long and exhausting. This has encouraged the development of computer aided diagnosis (CADx) systems to replace the second radiologist, making a better use of human-experts' time. But CADx systems are associated with high false positive rates, since most of them only use one view (craniocaudal or mediolateral oblique) of the screening mammogram. Radiologist, on the other hand, use both views; frequently reasoning about the diagnosis by noticeable differences between the two views. When considering both projections of a mammogram, lesion matching is a necessary step to perform diagnosis. However this is a complex task, since there might be various lesion candidates on both projections to match. In this work, a matching system is proposed. The system is a cascade of three blocks: candidates detector, feature extraction and lesion matching. The first is a replication of Ribli et al.'s Faster R-CNN and its purpose is to find possible lesion candidates. The second is the feature vector extraction of each candidate, either by using the candidates detector's backbone, handcrafted features or a siamese network model trained for distinguish lesions. The third is the calculus of the distance between feature vector, also using some heuristics to restrain possible non-lesion pairs, and the ranking of the distances to match the lesions. This work provides several options of possible feature extractors and heuristics to be incorporated into a CADx system based on object detectors. The fact that the triplet loss trained models obtained competitive results with the other features extractors is valuable, since it offers some independence between the detection and matching tasks. "Hard" heuristics and "soft" heurisitcs are introduced as methods to restrain matching. The system is able to detect matches satisfactorily, since its accuracy (70%85%) is significantly higher than chance level (30%40%). "Hard" heuristics proposals achieved encouraging results on precision@k, due to its match and candidates exclusion methods, which rejects a significant number of false positives generated by the object detector.
id RCAP_be9ffb08e7e618b6b90fe6bf39403b54
oai_identifier_str oai:repositorio-aberto.up.pt:10216/136026
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Matching of Mammographic Lesions in Different Breast ProjectionsEngenharia electrotécnica, electrónica e informáticaElectrical engineering, Electronic engineering, Information engineeringOf all cancer diseases, breast cancer is the most lethal among women. It has been shown that breast cancer screening programs can decrease mortality, since early detection increases the chances of survival. Usually, a pair of radiologists interpret the screening mammograms, however the process is long and exhausting. This has encouraged the development of computer aided diagnosis (CADx) systems to replace the second radiologist, making a better use of human-experts' time. But CADx systems are associated with high false positive rates, since most of them only use one view (craniocaudal or mediolateral oblique) of the screening mammogram. Radiologist, on the other hand, use both views; frequently reasoning about the diagnosis by noticeable differences between the two views. When considering both projections of a mammogram, lesion matching is a necessary step to perform diagnosis. However this is a complex task, since there might be various lesion candidates on both projections to match. In this work, a matching system is proposed. The system is a cascade of three blocks: candidates detector, feature extraction and lesion matching. The first is a replication of Ribli et al.'s Faster R-CNN and its purpose is to find possible lesion candidates. The second is the feature vector extraction of each candidate, either by using the candidates detector's backbone, handcrafted features or a siamese network model trained for distinguish lesions. The third is the calculus of the distance between feature vector, also using some heuristics to restrain possible non-lesion pairs, and the ranking of the distances to match the lesions. This work provides several options of possible feature extractors and heuristics to be incorporated into a CADx system based on object detectors. The fact that the triplet loss trained models obtained competitive results with the other features extractors is valuable, since it offers some independence between the detection and matching tasks. "Hard" heuristics and "soft" heurisitcs are introduced as methods to restrain matching. The system is able to detect matches satisfactorily, since its accuracy (70%85%) is significantly higher than chance level (30%40%). "Hard" heuristics proposals achieved encouraging results on precision@k, due to its match and candidates exclusion methods, which rejects a significant number of false positives generated by the object detector.2021-07-162021-07-16T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/10216/136026TID:202825680engSimão Pedro Ribeiro Quintansinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-29T14:30:52Zoai:repositorio-aberto.up.pt:10216/136026Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:02:53.499180Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Matching of Mammographic Lesions in Different Breast Projections
title Matching of Mammographic Lesions in Different Breast Projections
spellingShingle Matching of Mammographic Lesions in Different Breast Projections
Simão Pedro Ribeiro Quintans
Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electronic engineering, Information engineering
title_short Matching of Mammographic Lesions in Different Breast Projections
title_full Matching of Mammographic Lesions in Different Breast Projections
title_fullStr Matching of Mammographic Lesions in Different Breast Projections
title_full_unstemmed Matching of Mammographic Lesions in Different Breast Projections
title_sort Matching of Mammographic Lesions in Different Breast Projections
author Simão Pedro Ribeiro Quintans
author_facet Simão Pedro Ribeiro Quintans
author_role author
dc.contributor.author.fl_str_mv Simão Pedro Ribeiro Quintans
dc.subject.por.fl_str_mv Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electronic engineering, Information engineering
topic Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electronic engineering, Information engineering
description Of all cancer diseases, breast cancer is the most lethal among women. It has been shown that breast cancer screening programs can decrease mortality, since early detection increases the chances of survival. Usually, a pair of radiologists interpret the screening mammograms, however the process is long and exhausting. This has encouraged the development of computer aided diagnosis (CADx) systems to replace the second radiologist, making a better use of human-experts' time. But CADx systems are associated with high false positive rates, since most of them only use one view (craniocaudal or mediolateral oblique) of the screening mammogram. Radiologist, on the other hand, use both views; frequently reasoning about the diagnosis by noticeable differences between the two views. When considering both projections of a mammogram, lesion matching is a necessary step to perform diagnosis. However this is a complex task, since there might be various lesion candidates on both projections to match. In this work, a matching system is proposed. The system is a cascade of three blocks: candidates detector, feature extraction and lesion matching. The first is a replication of Ribli et al.'s Faster R-CNN and its purpose is to find possible lesion candidates. The second is the feature vector extraction of each candidate, either by using the candidates detector's backbone, handcrafted features or a siamese network model trained for distinguish lesions. The third is the calculus of the distance between feature vector, also using some heuristics to restrain possible non-lesion pairs, and the ranking of the distances to match the lesions. This work provides several options of possible feature extractors and heuristics to be incorporated into a CADx system based on object detectors. The fact that the triplet loss trained models obtained competitive results with the other features extractors is valuable, since it offers some independence between the detection and matching tasks. "Hard" heuristics and "soft" heurisitcs are introduced as methods to restrain matching. The system is able to detect matches satisfactorily, since its accuracy (70%85%) is significantly higher than chance level (30%40%). "Hard" heuristics proposals achieved encouraging results on precision@k, due to its match and candidates exclusion methods, which rejects a significant number of false positives generated by the object detector.
publishDate 2021
dc.date.none.fl_str_mv 2021-07-16
2021-07-16T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10216/136026
TID:202825680
url https://hdl.handle.net/10216/136026
identifier_str_mv TID:202825680
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799135953420288000