liu.seSök publikationer i DiVA
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Automatic detection of breast masses using deep learning with YOLO approach
Univ Cent Marta Abreu de las Villas, Cuba.
Univ Cent Marta Abreu de las Villas, Cuba.
Hosp Clin Quirurg Docente Dr Celestino Hernandez R, Cuba.
Linköpings universitet, Institutionen för systemteknik, Kommunikationssystem. Linköpings universitet, Tekniska fakulteten.ORCID-id: 0009-0004-1846-9496
Visa övriga samt affilieringar
2023 (Engelska)Ingår i: Health and Technology, ISSN 2190-7188, E-ISSN 2190-7196, Vol. 13, nr 6, s. 915-923Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

IntroductionBreast cancer is the most common malignant tumor among women. Mammography is the specific type of X-ray recommended to examine the breasts. However, they are difficult to interpret due to the size of the lesions, shape, indefinite borders, and low contrast of the masses with respect to healthy tissue, mainly in very dense breasts. Computer-aided detection (CAD) systems increase the efficiency of diagnoses and reduce the workload of specialists.PurposeA CAD system that uses artificial intelligence (AI) based on "You Only Look Once" (YOLO), with two models YOLOv5x and YOLOv5s, is tested for the detection of breast nodules from mammography.MethodTransfer learning and data augmentation techniques were applied. Image sets for training and validation were created from an international database (Vindr-Mammo). The network was trained and validated, and for the best model obtained, an external test was performed from a second database belonguing to "The Mammographic Image Analysis Society" (MIAS Database).ResultsThe best model was obtained with YOLOv5x. This reached a maximum sensitivity of 80% in internal validation and 72% with external test data.ConclusionYOLOv5x and YOLOv5s models showed potential for the task of detecting masses from mammographies.

Ort, förlag, år, upplaga, sidor
SPRINGER HEIDELBERG , 2023. Vol. 13, nr 6, s. 915-923
Nyckelord [en]
Mammography; Masses; Artificial intelligence; Deep learning; You Only Look Once
Nationell ämneskategori
Folkhälsovetenskap, global hälsa, socialmedicin och epidemiologi
Identifikatorer
URN: urn:nbn:se:liu:diva-198963DOI: 10.1007/s12553-023-00783-xISI: 001084223500001OAI: oai:DiVA.org:liu-198963DiVA, id: diva2:1809970
Anmärkning

Funding Agencies|Agence Universitaire de la Francophonie in the Caribbean [04.06.42.22]; Agency for Nuclear Energy and Advanced Technology of Cuba (AENTA) [PS211LH02]

Tillgänglig från: 2023-11-06 Skapad: 2023-11-06 Senast uppdaterad: 2024-03-07

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Sök vidare i DiVA

Av författaren/redaktören
Rodríguez Linares, Deijany
Av organisationen
KommunikationssystemTekniska fakulteten
I samma tidskrift
Health and Technology
Folkhälsovetenskap, global hälsa, socialmedicin och epidemiologi

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 47 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf