ABSTRACT
Mammograms contain information that predicts breast cancer risk. We developed two novel mammogram-based breast cancer risk measures based on image brightness (Cirrocumulus) and texture (Cirrus). Their risk prediction when fitted together, and with an established measure of conventional mammographic density (Cumulus), is not known. We used three studies consisting of: 168 interval cases and 498 matched controls; 422 screen-detected cases and 1,197 matched controls; and 354 younger-diagnosis cases and 944 controls frequency-matched for age at mammogram. We conducted conditional and unconditional logistic regression analyses of individually- and frequency-matched studies, respectively. We estimated measure-specific risk gradients as the change in odds per standard deviation of controls after adjusting for age and body mass index (OPERA) and calculated the area under the receiver operating characteristic curve (AUC). For interval, screen-detected and younger-diagnosis cancer risks, the best fitting models (measure-specific OPERAs [95% confidence intervals]) involved: Cumulus (1.81 [1.41 to 2.31]) and Cirrus (1.72 [1.38 to 2.14]); Cirrus (1.49 [1.32 to 1.67]) and Cirrocumulus (1.16 [1.03 to 1.31]); and Cirrus (1.70 [1.48 to 1.94]) and Cirrocumulus (1.46 [1.27 to 1.68]), respectively. The AUCs were: 0.73 [0.68 to 0.77], 0.63 [0.60 to 0.66], and 0.72 [0.69 to 0.75], respectively. Combined, our new mammogram-based measures doubled the risk gradient for screen-detected and younger-diagnosis breast cancer (P<10−12), have at least the same discriminatory power as the current polygenic risk score, and are more correlated with causal factors than conventional mammographic density. Discovering more information about breast cancer risk from mammograms could help enable risk-based personalised breast screening.
What’s new?We developed two novel mammogram-based breast cancer risk measures based on image brightness (Cirrocumulus) and texture (Cirrus). We estimated their risk prediction when fitted with conventional mammographic density (Cumulus), for interval, screen-detected, and younger age at diagnosis breast cancer. Our new measures substantially improved risk prediction. There is more risk information in a woman’s mammogram than in her genome. Discovering new ways of extracting risk information from a mammogram could enable risk-based personalised breast screening.
Competing Interest Statement
GSD receives funding from Genetic Technologies Ltd for work unrelated to this study.
Funding Statement
This research was supported by the National Health and Medical Research Council (251533, 209057, and 504711), the Victorian Health Promotion Foundation, Cancer Council Victoria, Cancer Council NSW, Cancer Australia, and the National Breast Cancer Foundation. It has also been supported by the Breast Cancer Network Australia, the National Breast Cancer Foundation, Victoria Breast Cancer Research Consortium and was further supported by infrastructure provided by the Cancer Council Victoria and the University of Melbourne. We thank the Victorian Cancer Registry, BreastScreen Victoria, the Australian Mammographic Density Research Facility. TLN has been supported by Cure Cancer Australia Foundation through Cancer Australia Priority-Driven Collaborative Cancer Research Scheme (1159399). TLN and SL have been supported by Victorian Cancer Council Post-Doctoral Fellowships and grants from the Picchi Foundation, Victorian Comprehensive Cancer Centre. JLH is a NHMRC Senior Principal Research Fellow. MAJ and MCS are NHMRC Senior Research Fellows.
Author Declarations
I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.
Yes
The details of the IRB/oversight body that provided approval or exemption for the research described are given below:
This study was approved by the ethical committee of the University of Melbourne
All necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived.
Yes
I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).
Yes
I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.
Yes
Data Availability
For data accessment, please contact the corresponding author.
Abbreviations
- AUC
- Area under the receiver operating characteristic curve;
- BMI
- Body mass index;
- CI
- Confidence interval;
- CC
- Cranio-caudal;
- LL
- log likelihood;
- OPERA
- odds per adjusted standard deviation.