Breast cancer patient characterisation and visualisation using deep learning and fisher information networks

Information

• Publication Type: Journal Paper (without talk)
• Workgroup(s)/Project(s):
  • Visualization Group
• Date: August 2022
• DOI: 10.1038/s41598-022-17894-6
• ISSN: 2045-2322
• Journal: Scientific Reports
• Open Access: yes
• Pages: 14
• Volume: 12
• Publisher: Nature Publishing
• Keywords: Breast, Female, Humans, Information Services, Mammography, Breast Neoplasms, Deep Learning

Abstract

Breast cancer is the most commonly diagnosed female malignancy globally, with better survival rates if diagnosed early. Mammography is the gold standard in screening programmes for breast cancer, but despite technological advances, high error rates are still reported. Machine learning techniques, and in particular deep learning (DL), have been successfully used for breast cancer detection and classification. However, the added complexity that makes DL models so successful reduces their ability to explain which features are relevant to the model, or whether the model is biased. The main aim of this study is to propose a novel visualisation to help characterise breast cancer patients using Fisher Information Networks on features extracted from mammograms using a DL model. In the proposed visualisation, patients are mapped out according to their similarities and can be used to study new patients as a 'patient-like-me' approach. When applied to the CBIS-DDSM dataset, it was shown that it is a competitive methodology that can (i) facilitate the analysis and decision-making process in breast cancer diagnosis with the assistance of the FIN visualisations and 'patient-like-me' analysis, and (ii) help improve diagnostic accuracy and reduce overdiagnosis by identifying the most likely diagnosis based on clinical similarities with neighbouring patients.

Additional Files and Images

Weblinks

• Entry in reposiTUm (TU Wien Publication Database)
• DOI: 10.1038/s41598-022-17894-6

BibTeX

@article{martorell2022,
  title =      "Breast cancer patient characterisation and visualisation
               using deep learning and fisher information networks",
  author =     "Sandra Ortega-Martorell and Patrick Riley and I Olier and
               Renata Raidou and R Casana-Eslava and M Rea and L  Shen and
               P.J. Lisboa and C Palmieri",
  year =       "2022",
  abstract =   "Breast cancer is the most commonly diagnosed female
               malignancy globally, with better survival rates if diagnosed
               early. Mammography is the gold standard in screening
               programmes for breast cancer, but despite technological
               advances, high error rates are still reported. Machine
               learning techniques, and in particular deep learning (DL),
               have been successfully used for breast cancer detection and
               classification. However, the added complexity that makes DL
               models so successful reduces their ability to explain which
               features are relevant to the model, or whether the model is
               biased. The main aim of this study is to propose a novel
               visualisation to help characterise breast cancer patients
               using Fisher Information Networks on features extracted from
               mammograms using a DL model. In the proposed visualisation,
               patients are mapped out according to their similarities and
               can be used to study new patients as a 'patient-like-me'
               approach. When applied to the CBIS-DDSM dataset, it was
               shown that it is a competitive methodology that can (i)
               facilitate the analysis and decision-making process in
               breast cancer diagnosis with the assistance of the FIN
               visualisations and 'patient-like-me' analysis, and (ii) help
               improve diagnostic accuracy and reduce overdiagnosis by
               identifying the most likely diagnosis based on clinical
               similarities with neighbouring patients.",
  month =      aug,
  doi =        "10.1038/s41598-022-17894-6",
  issn =       "2045-2322",
  journal =    "Scientific Reports",
  pages =      "14",
  volume =     "12",
  publisher =  "Nature Publishing",
  keywords =   "Breast, Female, Humans, Information Services, Mammography,
               Breast Neoplasms, Deep Learning",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2022/martorell2022/",
}