Joseph Y. Lo, PhD

Associate Professor of Radiology and Biomedical Engineering,
Duke University Medical Center
Faculty of Graduate Program in Medical Physics
Director of Biomedical Imaging and Medical Physics Third Year Study Program,
Duke University School of Medicine

Research Interests:
3D tomosynthesis imaging of the breast, prostate cancer radiation treatment planning, computer-aided diagnosis, image processing

Contact Information:
Carl E. Ravin Advanced Imaging Laboratories
2424 Erwin Rd (Hock Plaza), Ste 302
Durham, NC 27705, USA
Tel: (919) 684-7763
Fax: (919) 684-1491
joseph.lo@duke.edu

updated Apr 1, 2011

Research Summary:

My lab focuses on the diagnosis and treatment of cancer using advanced imaging techniques. We are working on 3 main projects: breast tomosynthesis, computer aided diagnosis, and radiation therapy treatment planning.

I have served as principal investigator (PI) of 22 grants from agencies such as the National Institutes of Health / National Cancer Institute, the DoD Breast Cancer Research Program, Siemens Healthcare, Susan G. Komen for the Cure, and others. I had the great pleasure of serving as the dissertation/thesis advisor for many students since the late 1990s, including 10 PhD, 7 MD, 3 MS, and 3 BSE.

3D Tomosynthesis Imaging of the Breast

While mammography remains the gold standard in breast cancer screening, it has many well known limitations. I lead a team from the Ravin Advanced Imaging Laboratories (RAI Labs) that collaborates closely with Siemens Healthcare to develop breast tomosynthesis, which is a form of limited-angle tomography using a modified digital mammography system. Tomosynthesis can acquire a 3D image quickly, easily, and at the same dose as a conventional mammogram. Tomosynthesis may improve sensitivity of breast cancer diagnosis by helping radiologists to detect subtle lesions which would otherwise be obscured. In addition, tomosynthesis may also improve specificity since radiologists can better characterize negative cases and thus avoid unnecessary follow-up imaging studies and procedures. For these reasons, tomosynthesis is the most exciting recent development in breast imaging, and the only technology that may actually replace mammography in the near future. My lab has worked closely with Siemens in developing their digital mammography and breast tomosynthesis systems. In collaboration with Jay Baker and other members of Duke Radiology Breast Imaging Division, we are now conducting clinical trials of the latest Siemens Mammomat Inspiration system (photo right). My lab has been working closely with Ehsan Samei, Jim Dobbins, and other members of RAILabs to study optimization and quantitation of breast tomosynthesis. This work has been supported by the NIH, Siemens Healthcare, and DoD.

Note to patients: This is an investigational prototype system. It is still being tested in research studies and is not yet approved by the U.S. Food and Drug Administration (FDA).

Here are some preliminary images from our on-going studies. This subject presented with a very subtle, indistinct mass as shown in the standard mammogram (left). Even with the magnification view, the mass is still very subtle (middle). The tomo scan easily reveals a spiculated mass which was later biopsied to reveal invasive ductal carcinoma.

Computer-aided Detection/Diagnosis

Since the mid 1990s, we have been a leader in computer aided diagnosis. We have developed automated detection algorithms which use computer vision techniques to localize suspicious mammographic lesions. We have also designed predictive models which use machine learning and statistical analysis in order to classify cases as benign versus malignant. During these studies, we compiled one of the largest multi-institution breast cancer databases with approximately 5,000 cases. In collaboration with RAILabs faculty members Georgia Tourassi and Maciej Mazurowski, we have been investigating computer aided diagnosis in mammography and tomosynthesis. This work has been supported by the NIH and DoD.

Optimization of Radiation Therapy

We are merging expertise from radiology and radiation oncology to address the problem of intensity modulated radiation therapy (IMRT), specifically to improve treatment planning for prostate cancer. Our goal is to improve the efficiency and safety of treatment plans using a knowledge-based approach. New cases are matched against a database of several hundred existing prostate cancer cases, and data from the best matching case is used to generate a new treatment plan. This approach takes advantage of the high quality information contained in our large database, and has the potential to improve not only the consistency and quality of radiation treatment planning, but also to streamline the efficiency of clinical workflow.

The figure on the left shows dose volume histograms for a sample prostate cancer case, with original clinical plan (solid lines) vs. our semi-automated, knowledge-base plan (dashed lines). Note our new plan offers comparable coverage of the planning target volume (red) and better dose sparing for rectum (brown) and bladder (blue).

The figure below shows the case matching algorithm in action. Using a database of 100 cases, we demonstrate that we can consistently rank the similarity of matching using our mutual information metric.


Rows correspond to 3 of 7 beam eye view projection images from CT contours of prostate cancer cases. Given query case at left, matched results are shown for #1, #2, #3, #49, and #99 out of 99, verifying trend of decreasing similarity.

This project has been supported by the Wallace H. Coulter Translational Partners Grant Program of Duke Biomedical Engineering as well as the Rennaisance Computing Institute at Duke.

Sample Publications

These are recent papers selected to cover a representative range of topics.

Resources and Environment

The Carl E. Ravin Advanced Imaging Labs (RAI Labs) is a group of over 30 faculty, staff and students devoted to research in advanced digital imaging techniques and applications for improved health care. It is part of the Duke Medical Phyiscs Program. Duke Hospital, one of the largest private hospitals in the United States, is licensed for over 1,000 beds. The Division of Breast Imaging in the Department of Radiology performs over 450,000 exams each year, approximately 1,000 of which are sent to biopsy each year. RAI Labs occupies over 7,000 square feet of laboratory and office space.