Home > Research > Publications & Outputs > Deep learning in image-based breast and cervica...

Links

Text available via DOI:

View graph of relations

Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis. / Xue, Peng; Wang, Jiaxu; Qin, Dongxu et al.
In: npj Digital Medicine, Vol. 5, No. 1, 19, 15.02.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Xue, P, Wang, J, Qin, D, Yan, H, Qu, Y, Seery, S, Jiang, Y & Qiao, Y 2022, 'Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis', npj Digital Medicine, vol. 5, no. 1, 19. https://doi.org/10.1038/s41746-022-00559-z

APA

Xue, P., Wang, J., Qin, D., Yan, H., Qu, Y., Seery, S., Jiang, Y., & Qiao, Y. (2022). Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis. npj Digital Medicine, 5(1), Article 19. https://doi.org/10.1038/s41746-022-00559-z

Vancouver

Xue P, Wang J, Qin D, Yan H, Qu Y, Seery S et al. Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis. npj Digital Medicine. 2022 Feb 15;5(1):19. doi: 10.1038/s41746-022-00559-z

Author

Xue, Peng ; Wang, Jiaxu ; Qin, Dongxu et al. / Deep learning in image-based breast and cervical cancer detection : a systematic review and meta-analysis. In: npj Digital Medicine. 2022 ; Vol. 5, No. 1.

Bibtex

@article{aae973aab7384e17a2fbffcd45750775,
title = "Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis",
abstract = "Accurate early detection of breast and cervical cancer is vital for treatment success. Here, we conduct a meta-analysis to assess the diagnostic performance of deep learning (DL) algorithms for early breast and cervical cancer identification. Four subgroups are also investigated: cancer type (breast or cervical), validation type (internal or external), imaging modalities (mammography, ultrasound, cytology, or colposcopy), and DL algorithms versus clinicians. Thirty-five studies are deemed eligible for systematic review, 20 of which are meta-analyzed, with a pooled sensitivity of 88% (95% CI 85–90%), specificity of 84% (79–87%), and AUC of 0.92 (0.90–0.94). Acceptable diagnostic performance with analogous DL algorithms was highlighted across all subgroups. Therefore, DL algorithms could be useful for detecting breast and cervical cancer using medical imaging, having equivalent performance to human clinicians. However, this tentative assertion is based on studies with relatively poor designs and reporting, which likely caused bias and overestimated algorithm performance. Evidence-based, standardized guidelines around study methods and reporting are required to improve the quality of DL research.",
keywords = "Article, /692/699/67/2195, /692/700/139, article",
author = "Peng Xue and Jiaxu Wang and Dongxu Qin and Huijiao Yan and Yimin Qu and Samuel Seery and Yu Jiang and Youlin Qiao",
year = "2022",
month = feb,
day = "15",
doi = "10.1038/s41746-022-00559-z",
language = "English",
volume = "5",
journal = "npj Digital Medicine",
issn = "2398-6352",
publisher = "Nature Publishing Group UK",
number = "1",

}

RIS

TY - JOUR

T1 - Deep learning in image-based breast and cervical cancer detection

T2 - a systematic review and meta-analysis

AU - Xue, Peng

AU - Wang, Jiaxu

AU - Qin, Dongxu

AU - Yan, Huijiao

AU - Qu, Yimin

AU - Seery, Samuel

AU - Jiang, Yu

AU - Qiao, Youlin

PY - 2022/2/15

Y1 - 2022/2/15

N2 - Accurate early detection of breast and cervical cancer is vital for treatment success. Here, we conduct a meta-analysis to assess the diagnostic performance of deep learning (DL) algorithms for early breast and cervical cancer identification. Four subgroups are also investigated: cancer type (breast or cervical), validation type (internal or external), imaging modalities (mammography, ultrasound, cytology, or colposcopy), and DL algorithms versus clinicians. Thirty-five studies are deemed eligible for systematic review, 20 of which are meta-analyzed, with a pooled sensitivity of 88% (95% CI 85–90%), specificity of 84% (79–87%), and AUC of 0.92 (0.90–0.94). Acceptable diagnostic performance with analogous DL algorithms was highlighted across all subgroups. Therefore, DL algorithms could be useful for detecting breast and cervical cancer using medical imaging, having equivalent performance to human clinicians. However, this tentative assertion is based on studies with relatively poor designs and reporting, which likely caused bias and overestimated algorithm performance. Evidence-based, standardized guidelines around study methods and reporting are required to improve the quality of DL research.

AB - Accurate early detection of breast and cervical cancer is vital for treatment success. Here, we conduct a meta-analysis to assess the diagnostic performance of deep learning (DL) algorithms for early breast and cervical cancer identification. Four subgroups are also investigated: cancer type (breast or cervical), validation type (internal or external), imaging modalities (mammography, ultrasound, cytology, or colposcopy), and DL algorithms versus clinicians. Thirty-five studies are deemed eligible for systematic review, 20 of which are meta-analyzed, with a pooled sensitivity of 88% (95% CI 85–90%), specificity of 84% (79–87%), and AUC of 0.92 (0.90–0.94). Acceptable diagnostic performance with analogous DL algorithms was highlighted across all subgroups. Therefore, DL algorithms could be useful for detecting breast and cervical cancer using medical imaging, having equivalent performance to human clinicians. However, this tentative assertion is based on studies with relatively poor designs and reporting, which likely caused bias and overestimated algorithm performance. Evidence-based, standardized guidelines around study methods and reporting are required to improve the quality of DL research.

KW - Article

KW - /692/699/67/2195

KW - /692/700/139

KW - article

U2 - 10.1038/s41746-022-00559-z

DO - 10.1038/s41746-022-00559-z

M3 - Journal article

VL - 5

JO - npj Digital Medicine

JF - npj Digital Medicine

SN - 2398-6352

IS - 1

M1 - 19

ER -