DeepSynthBody: The beginning of the end for data deficiency in medicine
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
DeepSynthBody : The beginning of the end for data deficiency in medicine. / Thambawita, Vajira; Hicks, Steven A.; Isaksen, Jonas; Stensen, Mette Haug; Haugen, Trine B.; Kanters, Jorgen; Parasa, Sravanthi; De Lange, Thomas; Johansen, Havard D.; Johansen, Dag; Hammer, Hugo L.; Halvorsen, Pal; Riegler, Michael A.
2021 International Conference on Applied Artificial Intelligence, ICAPAI 2021. IEEE, 2021. s. 1-8.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - DeepSynthBody
T2 - 2021 International Conference on Applied Artificial Intelligence, ICAPAI 2021
AU - Thambawita, Vajira
AU - Hicks, Steven A.
AU - Isaksen, Jonas
AU - Stensen, Mette Haug
AU - Haugen, Trine B.
AU - Kanters, Jorgen
AU - Parasa, Sravanthi
AU - De Lange, Thomas
AU - Johansen, Havard D.
AU - Johansen, Dag
AU - Hammer, Hugo L.
AU - Halvorsen, Pal
AU - Riegler, Michael A.
PY - 2021
Y1 - 2021
N2 - Limited access to medical data is a barrier on developing new and efficient machine learning solutions in medicine such as computer-aided diagnosis, risk assessments, predicting optimal treatments and home-based personal healthcare systems. This paper presents DeepSynthBody: a novel framework that overcomes some of the inherent restrictions and limitations of medical data by using deep generative adversarial networks to produce synthetic data with characteristics similar to the real data, so-called DeepSynth (deep synthetic) data. We show that DeepSynthBody can address two key issues commonly associated with medical data, namely privacy concerns (as a result of data protection rules and regulations) and the high costs of annotations. To demonstrate the full pipeline of applying DeepSynthBody concepts and user-friendly functionalities, we also describe a synthetic medical dataset generated and published using our framework. DeepSynthBody opens a new era of machine learning applications in medicine with a synthetic model of the human body.
AB - Limited access to medical data is a barrier on developing new and efficient machine learning solutions in medicine such as computer-aided diagnosis, risk assessments, predicting optimal treatments and home-based personal healthcare systems. This paper presents DeepSynthBody: a novel framework that overcomes some of the inherent restrictions and limitations of medical data by using deep generative adversarial networks to produce synthetic data with characteristics similar to the real data, so-called DeepSynth (deep synthetic) data. We show that DeepSynthBody can address two key issues commonly associated with medical data, namely privacy concerns (as a result of data protection rules and regulations) and the high costs of annotations. To demonstrate the full pipeline of applying DeepSynthBody concepts and user-friendly functionalities, we also describe a synthetic medical dataset generated and published using our framework. DeepSynthBody opens a new era of machine learning applications in medicine with a synthetic model of the human body.
KW - deep synthetic human body
KW - DeepSynth augmentation
KW - DeepSynth explainable AI
KW - DeepSynthBody
KW - explainable DeepSynth
KW - GAN
KW - medical data privacy
KW - multi-model DeepSynth
KW - privacy issue
KW - synthetic data
KW - synthetic medical data
UR - http://www.scopus.com/inward/record.url?scp=85113768320&partnerID=8YFLogxK
U2 - 10.1109/ICAPAI49758.2021.9462062
DO - 10.1109/ICAPAI49758.2021.9462062
M3 - Article in proceedings
AN - SCOPUS:85113768320
SP - 1
EP - 8
BT - 2021 International Conference on Applied Artificial Intelligence, ICAPAI 2021
PB - IEEE
Y2 - 19 May 2021 through 21 May 2021
ER -
ID: 298378496