Joseph Lo, PhD

Professor in Radiology
Professor of Biomedical Engineering
Professor in the Department of Electrical and Computer Engineering
Member of the Duke Cancer Institute
Address: 2424 Erwin Road, Suite 302, Ravin Advanced Imaging Labs
Durham, NC 27705
Phone: (919) 684-7763

Research Interests

My research uses computer vision and machine learning to improve medical imaging, focusing on breast and CT imaging. There are three specific projects:

(1) We design deep learning models to diagnose breast cancer from mammograms. We perform single-shot lesion detection, multi-task segmentation/classification, and image synthesis. Our goal is to improve radiologist diagnostic performance and empower patients to make personalized treatment decisions. This work is funded by NIH, Dept of Defense, Cancer Research UK, and other agencies.

(2) We create "digital twin" anatomical models that are based on actual patient data and thus contain highly realistic anatomy. With customized 3D printing, these virtual phantoms can also be rendered into physical form to be scanned on actual imaging devices, which allows us to assess image quality in new ways that are clinically relevant.

(3) We are building a computer-aided triage platform to classify multiple diseases across multiple organs in chest-abdomen-pelvis CT scans. Our hospital-scale data sets have hundreds of thousands of patients. This work includes natural language processing to analyze radiology reports as well as deep learning models for organ segmentation and disease classification.


Tushar, Fakrul Islam, et al. “Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning.Radiol Artif Intell, vol. 4, no. 1, Jan. 2022, p. e210026. Pubmed, doi:10.1148/ryai.210026.

Grimm, Lars J., et al. “Mixed-Methods Study to Predict Upstaging of DCIS to Invasive Disease on Mammography.Ajr Am J Roentgenol, vol. 216, no. 4, Apr. 2021, pp. 903–11. Pubmed, doi:10.2214/AJR.20.23679.

Draelos, Rachel Lea, et al. “Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes.Med Image Anal, vol. 67, Jan. 2021, p. 101857. Pubmed, doi:10.1016/

Abadi, Ehsan, et al. “Virtual clinical trials in medical imaging: a review.J Med Imaging (Bellingham), vol. 7, no. 4, July 2020, p. 042805. Pubmed, doi:10.1117/1.JMI.7.4.042805.

Hou, Rui, et al. “Prediction of Upstaged Ductal Carcinoma In Situ Using Forced Labeling and Domain Adaptation.Ieee Trans Biomed Eng, vol. 67, no. 6, June 2020, pp. 1565–72. Pubmed, doi:10.1109/TBME.2019.2940195.

Georgian-Smith, Dianne, et al. “Can Digital Breast Tomosynthesis Replace Full-Field Digital Mammography? A Multireader, Multicase Study of Wide-Angle Tomosynthesis.Ajr. American Journal of Roentgenology, Apr. 2019, pp. 1–7. Epmc, doi:10.2214/ajr.18.20294.

Rossman, Andrea H., et al. “Three-dimensionally-printed anthropomorphic physical phantom for mammography and digital breast tomosynthesis with custom materials, lesions, and uniform quality control region.J Med Imaging (Bellingham), vol. 6, no. 2, Apr. 2019, p. 021604. Pubmed, doi:10.1117/1.JMI.6.2.021604.

Sturgeon, Gregory M., et al. “Synthetic breast phantoms from patient based eigenbreasts.Med Phys, vol. 44, no. 12, Dec. 2017, pp. 6270–79. Pubmed, doi:10.1002/mp.12579.