Synthetic Data as a Tool to Combat Racial Bias in Medical AI:
Utilizing Generative Models for Optimizing Early Detection of
Melanoma in Fitzpatrick Skin Types IV–VI

D 2023

Synthetic Data as a Tool to Combat Racial Bias in Medical AI: Utilizing Generative Models for Optimizing Early Detection of Melanoma in Fitzpatrick Skin Types IV–VI

KVAK, Daniel; Eva BŘEZINOVÁ; Marek BIROŠ a Robert HRUBÝ

Základní údaje

Originální název

Synthetic Data as a Tool to Combat Racial Bias in Medical AI: Utilizing Generative Models for Optimizing Early Detection of Melanoma in Fitzpatrick Skin Types IV–VI

Autoři

KVAK, Daniel; Eva BŘEZINOVÁ; Marek BIROŠ a Robert HRUBÝ

Vydání

1. vyd. Singapore, Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022), od s. 317-330, 584 s. 2023

Nakladatel

Springer Publishing

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Stát vydavatele

Singapur

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

URL

ISBN

978-981-16-6774-9

ISSN

DOI

http://dx.doi.org/10.1007/978-981-16-6775-6_26

Klíčová slova anglicky

Autoregressive Models, Computer-Aided Diagnosis, Deep Learning, Generative Adversarial Networks, Melanoma, Synthetic Data, Zero-Shot Learning.

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 20. 12. 2023 21:58, Mgr. Daniel Kvak

Anotace

V originále

Assistive tools to aid in skin cancer detection are experiencing an unprecedented rise with the accessibility of robust and accurate deep learning models. However, in the present applications, only a negligible number of dermatology images come from patients with Fitzpatrick skin types IV–VI, representing brown, dark brown or black skin, respectively. In this study, we demonstrate the utilization of Zero-Shot Text-to-Image autoregressive models to generate synthetic medical data for improved balance in training CAD classification models with minimized racial bias. Synthetically generated images of skin lesions were assessed by an experienced dermatologist using the ABCD rule and differential diagnostics, and subsequently validated using a pre-trained ResNet50V2 multi-class classification model.

Návaznosti

MUNI/A/1551/2023, interní kód MU

Název: Rozvoj vědeckých aspektů simulačního vzdělávání na LF MU I.

Investor: Masarykova univerzita, Rozvoj vědeckých aspektů simulačního vzdělávání na LF MU I.

Citovat

KVAK, Daniel; Eva BŘEZINOVÁ; Marek BIROŠ a Robert HRUBÝ. Synthetic Data as a Tool to Combat Racial Bias in Medical AI: Utilizing Generative Models for Optimizing Early Detection of Melanoma in Fitzpatrick Skin Types IV–VI. In Ruidan Su, Yudong Zhang, Han Liu, Alejandro F Frangi. Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022). 1. vyd. Singapore: Springer Publishing, 2023, s. 317-330, 584 s. ISBN 978-981-16-6774-9. Dostupné z: https://dx.doi.org/10.1007/978-981-16-6775-6_26.

@inproceedings{2241105,
   author = {Kvak, Daniel and Březinová, Eva and Biroš, Marek and Hrubý, Robert},
   address = {Singapore},
   booktitle = {Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022)},
   doi = {http://dx.doi.org/10.1007/978-981-16-6775-6_26},
   edition = {1},
   editor = {Ruidan Su, Yudong Zhang, Han Liu, Alejandro F Frangi},
   keywords = {Autoregressive Models, Computer-Aided Diagnosis, Deep Learning, Generative Adversarial Networks, Melanoma, Synthetic Data, Zero-Shot Learning.},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Singapore},
   isbn = {978-981-16-6774-9},
   pages = {317-330},
   publisher = {Springer Publishing},
   title = {Synthetic Data as a Tool to Combat Racial Bias in Medical AI: Utilizing Generative Models for Optimizing Early Detection of Melanoma in Fitzpatrick Skin Types IV–VI},
   url = {https://link.springer.com/chapter/10.1007/978-981-16-6775-6_26},
   year = {2023}
}

TY  - CONF
ID  - 2241105
AU  - Kvak, Daniel - Březinová, Eva - Biroš, Marek - Hrubý, Robert
PY  - 2023
TI  - Synthetic Data as a Tool to Combat Racial Bias in Medical AI: Utilizing Generative Models for Optimizing Early Detection of Melanoma in Fitzpatrick Skin Types IV–VI
PB  - Springer Publishing
CY  - Singapore
SN  - 9789811667749
KW  - Autoregressive Models, Computer-Aided Diagnosis, Deep Learning, Generative Adversarial Networks, Melanoma, Synthetic Data, Zero-Shot Learning.
UR  - https://link.springer.com/chapter/10.1007/978-981-16-6775-6_26
N2  - Assistive tools to aid in skin cancer detection are experiencing an unprecedented rise with the accessibility of robust and accurate deep learning models. However, in the present applications, only a negligible number of dermatology images come from patients with Fitzpatrick skin types IV–VI, representing brown, dark brown or black skin, respectively. In this study, we demonstrate the utilization of Zero-Shot Text-to-Image autoregressive models to generate synthetic medical data for improved balance in training CAD classification models with minimized racial bias. Synthetically generated images of skin lesions were assessed by an experienced dermatologist using the ABCD rule and differential diagnostics, and subsequently validated using a pre-trained ResNet50V2 multi-class classification model.
ER  -

KVAK, Daniel; Eva BŘEZINOVÁ; Marek BIROŠ a Robert HRUBÝ. Synthetic Data as a Tool to Combat Racial Bias in Medical AI: Utilizing Generative Models for Optimizing Early Detection of Melanoma in Fitzpatrick Skin Types IV–VI. In Ruidan Su, Yudong Zhang, Han Liu, Alejandro F Frangi. \textit{Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022)}. 1. vyd. Singapore: Springer Publishing, 2023, s.~317-330, 584 s. ISBN~978-981-16-6774-9. Dostupné z: https://dx.doi.org/10.1007/978-981-16-6775-6\_{}26.

Přehled o publikaci