Joseph Yuan-Chieh Lo
Professor of Radiology
My research focuses on computer vision and machine learning in medical imaging, with a focus on mammography and CT imaging. There are three specific projects:
First, we have a long track record of creating machine learning models to detect and diagnose breast cancer from mammograms. These algorithms are based on computer vision and deep learning, with the long term goal to incorporate the contribution of imaging data with proteomic/genomic markers. Specific projects include predicting which cases of DCIS are likely to contain hidden invasive cancer, thus informing women to take advantage of personalized treatment decisions. This work is funded by NIH, Dept of Defense, Cancer Research UK, and other agencies.
Second, we design virtual breast models that are based on actual patient data and thus contain highly realistic breast anatomy with voxel-level ground truth. We can transform these virtual models into physical form using several forms of 3D printing technology. In work funded by NIH, we are translating this work to produce a new generation of realistic phantoms for CT. Such physical phantoms can be scanned on actual imaging devices, allowing us to assess image quality in new ways that are not only quantitative but also clinically relevant.
Third, we are developing a broad, machine learning platform to segment multiple organs and classify multiple diseases in chest-abdomen-pelvis CT scans. The goal is to provide automated labeling of hospital-scale data sets (potentially hundreds of thousands of studies) to produce sufficient data for deep learning studies. This work includes natural language processing to analyze radiology reports, and deep learning models for the segmentation and classification tasks.
Appointments and Affiliations
- Professor of Radiology
- Professor in the Department of Electrical and Computer Engineering
- Member of the Duke Cancer Institute
- Office Location: Ravin Advanced Imaging Labs, 2424 Erwin Road, Suite 302, Durham, NC 27705
- Office Phone: (919) 684-7763
- Email Address: firstname.lastname@example.org
- Duke University, 1995
- Ph.D. Duke University, 1993
- B.S.E.E. Duke University, 1988
Computer vision and machine learning for medical imaging diagnosis; radiogenomics for improved management of breast cancer; computational and physical breast models for virtual clinical trials
- BME 394: Projects in Biomedical Engineering (GE)
- BME 493: Projects in Biomedical Engineering (GE)
- BME 494: Projects in Biomedical Engineering (GE)
- ECE 891: Internship
- RROMP 301B: Radiology, Radiation Oncology & Medical Physics
- Shi, B; Grimm, LJ; Mazurowski, MA; Baker, JA; Marks, JR; King, LM; Maley, CC; Hwang, ES; Lo, JY, Prediction of Occult Invasive Disease in Ductal Carcinoma in Situ Using Deep Learning Features., Journal of the American College of Radiology : Jacr, vol 15 no. 3 Pt B (2018), pp. 527-534 [10.1016/j.jacr.2017.11.036] [abs].
- Sturgeon, GM; Park, S; Segars, WP; Lo, JY, Synthetic breast phantoms from patient based eigenbreasts., Med Phys, vol 44 no. 12 (2017), pp. 6270-6279 [10.1002/mp.12579] [abs].
- Shi, B; Grimm, LJ; Mazurowski, MA; Baker, JA; Marks, JR; King, LM; Maley, CC; Hwang, ES; Lo, JY, Can Occult Invasive Disease in Ductal Carcinoma In Situ Be Predicted Using Computer-extracted Mammographic Features?, Acad Radiol, vol 24 no. 9 (2017), pp. 1139-1147 [10.1016/j.acra.2017.03.013] [abs].
- Ikejimba, LC; Glick, SJ; Choudhury, KR; Samei, E; Lo, JY, Assessing task performance in FFDM, DBT, and synthetic mammography using uniform and anthropomorphic physical phantoms., Med Phys, vol 43 no. 10 (2016) [10.1118/1.4962475] [abs].
- Ikejimba, L; Lo, JY; Chen, Y; Oberhofer, N; Kiarashi, N; Samei, E, A quantitative metrology for performance characterization of five breast tomosynthesis systems based on an anthropomorphic phantom., Med Phys, vol 43 no. 4 (2016) [10.1118/1.4943373] [abs].
- Erickson, DW; Wells, JR; Sturgeon, GM; Samei, E; Dobbins, JT; Segars, WP; Lo, JY, Population of 224 realistic human subject-based computational breast phantoms., Med Phys, vol 43 no. 1 (2016) [10.1118/1.4937597] [abs].