Deep Learning in Image-based Breast and Cervical Cancer Detection: a Systematic Review and Meta-analysis

Overview

Journal NPJ Digit Med

Specialty Medical Informatics

Date 2022 Feb 16

PMID 35169217

Authors

Peng Xue

Jiaxu Wang

Dongxu Qin

Huijiao Yan

Yimin Qu

Samuel Seery

Yu Jiang

Youlin Qiao

Affiliations

Soon will be listed here.

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.

Citing Articles

CerviFusionNet: A multi-modal, hybrid CNN-transformer-GRU model for enhanced cervical lesion multi-classification.

Sha Y, Zhang Q, Zhai X, Hou M, Lu J, Meng W iScience. 2024; 27(12):111313.

PMID: 39634563 PMC: 11615576. DOI: 10.1016/j.isci.2024.111313.

Impact of human and artificial intelligence collaboration on workload reduction in medical image interpretation.

Chen M, Wang Y, Wang Q, Shi J, Wang H, Ye Z NPJ Digit Med. 2024; 7(1):349.

PMID: 39616244 PMC: 11608314. DOI: 10.1038/s41746-024-01328-w.

Non-invasive prediction of human embryonic ploidy using artificial intelligence: a systematic review and meta-analysis.

Xin X, Wu S, Xu H, Ma Y, Bao N, Gao M EClinicalMedicine. 2024; 77:102897.

PMID: 39513188 PMC: 11541425. DOI: 10.1016/j.eclinm.2024.102897.

Looking Back, Moving Forward: Challenges and Opportunities for Global Cervical Cancer Prevention and Control.

Castle P Viruses. 2024; 16(9).

PMID: 39339834 PMC: 11435674. DOI: 10.3390/v16091357.

Chinese colposcopists' attitudes toward the colposcopic artificial intelligence auxiliary diagnostic system (CAIADS): A nation-wide, multi-center survey.

Wang H, Ye Z, Zhang P, Cui X, Chen M, Wu A Digit Health. 2024; 10:20552076241279952.

PMID: 39247091 PMC: 11378189. DOI: 10.1177/20552076241279952.

References

Arbyn M, Weiderpass E, Bruni L, de Sanjose S, Saraiya M, Ferlay J . Estimates of incidence and mortality of cervical cancer in 2018: a worldwide analysis. Lancet Glob Health. 2019; 8(2):e191-e203. PMC: 7025157. DOI: 10.1016/S2214-109X(19)30482-6. View

Li N, Deng Y, Zhou L, Tian T, Yang S, Wu Y . Global burden of breast cancer and attributable risk factors in 195 countries and territories, from 1990 to 2017: results from the Global Burden of Disease Study 2017. J Hematol Oncol. 2019; 12(1):140. PMC: 6925497. DOI: 10.1186/s13045-019-0828-0. View

Sung H, Ferlay J, Siegel R, Laversanne M, Soerjomataram I, Jemal A . Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3):209-249. DOI: 10.3322/caac.21660. View

Ginsburg O, Badwe R, Boyle P, Derricks G, Dare A, Evans T . Changing global policy to deliver safe, equitable, and affordable care for women's cancers. Lancet. 2016; 389(10071):871-880. DOI: 10.1016/S0140-6736(16)31393-9. View

Allemani C, Matsuda T, Di Carlo V, Harewood R, Matz M, Niksic M . Global surveillance of trends in cancer survival 2000-14 (CONCORD-3): analysis of individual records for 37 513 025 patients diagnosed with one of 18 cancers from 322 population-based registries in 71 countries. Lancet. 2018; 391(10125):1023-1075. PMC: 5879496. DOI: 10.1016/S0140-6736(17)33326-3. View

Viswabandya A, Shah S, Mukhopadhyay A, Nagarkar R, Batra S, Lopez-Lazaro L . Randomized, Double-Blind, Pharmacokinetic Equivalence Trial Comparing DRL-Rituximab With MabThera in Patients With Diffuse Large B-Cell Lymphoma. J Glob Oncol. 2019; 5:1-13. PMC: 6939748. DOI: 10.1200/JGO.19.00248. View

Wentzensen N, Chirenje Z, Prendiville W . Treatment approaches for women with positive cervical screening results in low-and middle-income countries. Prev Med. 2021; 144:106439. DOI: 10.1016/j.ypmed.2021.106439. View

Britt K, Cuzick J, Phillips K . Key steps for effective breast cancer prevention. Nat Rev Cancer. 2020; 20(8):417-436. DOI: 10.1038/s41568-020-0266-x. View

Brisson M, Kim J, Canfell K, Drolet M, Gingras G, Burger E . Impact of HPV vaccination and cervical screening on cervical cancer elimination: a comparative modelling analysis in 78 low-income and lower-middle-income countries. Lancet. 2020; 395(10224):575-590. PMC: 7043009. DOI: 10.1016/S0140-6736(20)30068-4. View

10.

Yang L, Wang S, Zhang L, Sheng C, Song F, Wang P . Performance of ultrasonography screening for breast cancer: a systematic review and meta-analysis. BMC Cancer. 2020; 20(1):499. PMC: 7268243. DOI: 10.1186/s12885-020-06992-1. View

11.

Conti A, Duggento A, Indovina I, Guerrisi M, Toschi N . Radiomics in breast cancer classification and prediction. Semin Cancer Biol. 2020; 72:238-250. DOI: 10.1016/j.semcancer.2020.04.002. View

12.

Xue P, Alexander Ng M, Qiao Y . The challenges of colposcopy for cervical cancer screening in LMICs and solutions by artificial intelligence. BMC Med. 2020; 18(1):169. PMC: 7271416. DOI: 10.1186/s12916-020-01613-x. View

13.

Muse E, Topol E . Guiding ultrasound image capture with artificial intelligence. Lancet. 2020; 396(10253):749. DOI: 10.1016/S0140-6736(20)31875-4. View

14.

Mandal R, Basu P . Cancer screening and early diagnosis in low and middle income countries : Current situation and future perspectives. Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz. 2018; 61(12):1505-1512. DOI: 10.1007/s00103-018-2833-9. View

15.

Torode J, Kithaka B, Chowdhury R, Simelela N, Cruz J, Tsu V . National action towards a world free of cervical cancer for all women. Prev Med. 2021; 144:106313. PMC: 8201602. DOI: 10.1016/j.ypmed.2020.106313. View

16.

Coiera E . The fate of medicine in the time of AI. Lancet. 2018; 392(10162):2331-2332. DOI: 10.1016/S0140-6736(18)31925-1. View

17.

Kleppe A, Skrede O, de Raedt S, Liestol K, Kerr D, Danielsen H . Designing deep learning studies in cancer diagnostics. Nat Rev Cancer. 2021; 21(3):199-211. DOI: 10.1038/s41568-020-00327-9. View

18.

Nagendran M, Chen Y, Lovejoy C, Gordon A, Komorowski M, Harvey H . Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 2020; 368:m689. PMC: 7190037. DOI: 10.1136/bmj.m689. View

19.

Benjamens S, Dhunnoo P, Mesko B . The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database. NPJ Digit Med. 2020; 3:118. PMC: 7486909. DOI: 10.1038/s41746-020-00324-0. View

20.

Liu X, Cruz Rivera S, Moher D, Calvert M, Denniston A . Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension. BMJ. 2020; 370:m3164. PMC: 7490784. DOI: 10.1136/bmj.m3164. View