Research team Fredrik Strand
Exploring the use of image-based artificial intelligence in precision screening and treatment optimization for breast cancer
We are living in exciting times. The use of Artificial Intelligence is on the rise. The true limits to what can be achieved are not yet known. Our focus are the more than 600,000 women who die of breast cancer each year in the world.
Image-based AI for Precision Screening
Early detection is the most important measure, until now achieved by population-wide mammography screening every 1 to 3 years for women in a certain age group. Nevertheless, around 30 percent of the cancers diagnosed for women who participate in screening are clinically detected in the interval between two screenings; and nearly 15 percent of screen-detected cancers are 2 cm or larger. Employing AI to tailor and improve the screening could bring the benefit of early detection to more women keeping in mind the scarcity of radiological resources - image-based AI for precision screening.
Image-based AI for Precision Treatment
Oncological treatment options have become more diverse and have contributed to prolonged survival. However, each cancer resides in its own microenvironment of evolutionary pressure, which means no two cancers are alike. The use of preoperative, neoadjuvant, medical treatment has increased since it offers an opportunity to study how the cancer reacts to a certain medication while it remains in the breast. The need to predict which treatment is likely best for each patient, and the need to study how the cancer reacts over time, puts increasing demands on the precision of imaging and on cross-disciplinary analysis between radiology (non-invasive imaging of the whole breast, and the whole cancer) and pathology (invasive sample of the cancer). In addition, surgery has become more precise and less extensive. Employing AI on medical images could improve mapping of the tumor extent, predicting the best therapy, and continuously assessing the response - image-based AI for precision treatment.
Our studies are cross-disciplinary. Since 2016 we have built a strong collaboration with computer science researchers at the Royal School of Engineering (KTH) in Stockholm. We have jointly developed deep neural networks that can be used to assess for each woman: the risk of getting breast cancer in the future, and how difficult it would be to visualize an early cancer in the mammogram. In addition, we have examined and compared commercially available AI algorithms for cancer detection. The research has until recently been retrospective, and now it is time to add a prospective clinical study with two sub-studies: ScreenTrust CAD (exploring the use of AI as an independent reader of screening mammograms) and ScreenTrust MRI (exploring the use of AI as selection method to offer supplemental MRI to some women in mammography screening). We also collaborate with international research groups, including MIT in Boston, USA.
Exploring the use of AI and novel imaging methods in precision treatment, we work with breast oncology researchers at Karolinska University Hospital. The aim is to combine images from all radiological modalities (mammography, ultrasound and MRI) as well as pathology images.
Our main funders are currently Medtechlabs, Region Stockholm and the Swedish Breast Cancer Association.
Core Team members
Fredrik Strand, MD, PhD, Radiologist, Team Leader
Karin Dembrower, MD, PhD student, Radiologist
Mattie Salim, MD, PhD student, Radiologist in training
Vanda Svjatoha, BSc, MRI technologist
Yanlu Wang, MD, PhD, MRI physicist
Athanasios Zouzos, MD, PhD student, Radiologist
Collaborative Team members
Hossein Azizpour, MSc, PhD, Computer scientist
Martin Eklund, MSc, PhD, Biostatistician
Theodoros Foukakis, MD, PhD, Oncologist
Hanna Fredholm, MD, PhD, Surgeon
Irma Fredriksson, MD, PhD, Surgeon
Johan Hartman, MD, PhD, Pathologist
Yue Liu, MSc, PhD student in Computer science
Mattias Rantalainen, MSc, PhD, Biostatistician
Kevin Smith, MSc, PhD, Computer scientist
Moein Sorkhei, MSc in Computer science
Toward robust mammography-based models for breast cancer risk.
Yala A, Mikhael PG, Strand F, Lin G, Smith K, Wan YL, Lamb L, Hughes K, Lehman C, Barzilay R
Sci Transl Med 2021 Jan;13(578):
External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms.
Salim M, Wåhlin E, Dembrower K, Azavedo E, Foukakis T, Liu Y, Smith K, Eklund M, Strand F
JAMA Oncol 2020 10;6(10):1581-1588
Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study.
Dembrower K, Wåhlin E, Liu Y, Salim M, Smith K, Lindholm P, Eklund M, Strand F
Lancet Digit Health 2020 09;2(9):e468-e474
A Multi-million Mammography Image Dataset and Population-Based Screening Cohort for the Training and Evaluation of Deep Neural Networks-the Cohort of Screen-Aged Women (CSAW).
Dembrower K, Lindholm P, Strand F
J Digit Imaging 2020 04;33(2):408-413
Comparison of a Deep Learning Risk Score and Standard Mammographic Density Score for Breast Cancer Risk Prediction.
Dembrower K, Liu Y, Azizpour H, Eklund M, Smith K, Lindholm P, et al
Radiology 2020 02;294(2):265-272
Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms.
Schaffter T, Buist DSM, Lee CI, Nikulin Y, Ribli D, Guan Y, et al
JAMA Netw Open 2020 03;3(3):e200265
The association between breast cancer risk factors and background parenchymal enhancement at dynamic contrast-enhanced breast MRI.
Hellgren R, Saracco A, Strand F, Eriksson M, Sundbom A, Hall P, et al
Acta Radiol 2020 Dec;61(12):1600-1607
Breast cancer imaging - A rapidly evolving discipline.
Strand F, Zackrisson S
Breast 2019 Aug;46():58-63
Derived mammographic masking measures based on simulated lesions predict the risk of interval cancer after controlling for known risk factors: a case-case analysis.
Hinton B, Ma L, Mahmoudzadeh AP, Malkov S, Fan B, Greenwood H, et al
Med Phys 2019 Mar;46(3):1309-1316
Discontinuation of adjuvant hormone therapy among breast cancer patients not previously attending mammography screening.
He W, Eriksson L, Törnberg S, Strand F, Hall P, Czene K
BMC Med 2019 01;17(1):24
Localized mammographic density is associated with interval cancer and large breast cancer: a nested case-control study.
Strand F, Azavedo E, Hellgren R, Humphreys K, Eriksson M, Shepherd J, et al
Breast Cancer Res 2019 01;21(1):8
The future of breast cancer screening: what do participants in a breast cancer screening program think about automation using artificial intelligence?
Jonmarker O, Strand F, Brandberg Y, Lindholm P
Acta Radiol Open 2019 Dec;8(12):2058460119880315
Long-term prognostic implications of risk factors associated with tumor size: a case study of women regularly attending screening.
Strand F, Humphreys K, Holm J, Eriksson M, Törnberg S, Hall P, et al
Breast Cancer Res 2018 04;20(1):31
Longitudinal fluctuation in mammographic percent density differentiates between interval and screen-detected breast cancer.
Strand F, Humphreys K, Eriksson M, Li J, Andersson TM, Törnberg S, et al
Int J Cancer 2017 Jan;140(1):34-40
Novel mammographic image features differentiate between interval and screen-detected breast cancer: a case-case study.
Strand F, Humphreys K, Cheddad A, Törnberg S, Azavedo E, Shepherd J, et al
Breast Cancer Res 2016 10;18(1):100