Contact Info:

Office Location:	Duke Advanced Imaging Labs (DAI Labs)
Email Address:
Web Page:	http://dailabs.duhs.duke.edu/person.php?id=2249

Teaching (Fall 2008):

• MEDPHY 251.02, SEMINARS IN MEDICAL PHYSICS

  Hock Plaza AUDITORIUM, Th 02:50 PM-04:05 PM

• BIMP 301B.16, RESEARCH IN BIMP

• BIMP 301B.16-S, RESEARCH IN BIMP

Education:

Ph.D., Duke University, 1993

Specialties:

Medical Imaging

Research Interests: Breast cancer imaging and diagnosis

We seek to define the future of breast cancer imaging and diagnosis. To accomplish this lofty goal, we are pursuing two main projects, breast tomosynthesis and computer aided diagnosis. First, while mammography remains the gold standard in breast cancer screening, it has many well known limitations. Dr. Lo leads a team from the Duke Advanced Imaging Laboratories (see website above) which collaborates closely with Siemens Medical Solutions to evaluate and commercialize the Siemens full field digital mammography system. This system has now been approved by the FDA. Dr. Lo’s team is now focusing on digital tomosynthesis of the breast, 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 will improve sensitivity of breast cancer diagnosis by helping radiologists to detect subtle lesions which would otherwise be obscured. In addition, tomosynthesis will also improve specificity since radiologists can better characterize benign cases and thus avoid unnecessary follow-up imaging studies and surgical procedures. For these reasons, tomosynthesis is the most exciting recent development in breast imaging, and the only technology that can actually replace mammography in the near future. Duke is now conducting clinical trials using the first ever Siemens breast tomosynthesis prototype. Second, for over a decade, we have been a leader in computer aided diagnosis (CAD), which is an interdisciplinary field combining elements of medical physics, engineering, statistics, and bioinformatics. 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 mammograms or sonograms as benign versus malignant. During these studies, we compiled one of the largest multi-institution breast cancer databases with approximately 5000 cases. In on-going research, we are building CAD detection systems for tomosynthesis, which will be necessary to help radiologists process the huge volume of 3D data. We are also studying a multi-modality decision fusion approach to breast cancer diagnosis which utilizes information from radiologist findings, clinical and history data, computer vision features, and proteomics/genomics.

Curriculum Vitae

Representative Publications   (More Publications)

1. JA Baker, EL Rosen, MM Crockett, JY Lo, Accuracy of segmentation of a commercial computer-aided detection system for mammography., Radiology, United States, vol. 235 no. 2 (May, 2005), pp. 385-90  [abs].
2. Lo JY, Gavrielides MA, Markey MK, and Jesneck JL, “Computer-aided classification of breast microcalcification clusters: Merging of features from image processing and radiologists,” Medical Imaging 2003: Image Processing, Hanson KM, Ed., SPIE Medical Imaging 2003: Image Processing, San Diego, CA, Proc. SPIE: (2003). .
3. AO Bilska-Wolak, CE Floyd, JY Lo, JA Baker, Computer aid for decision to biopsy breast masses on mammography: validation on new cases., Academic radiology, United States, vol. 12 no. 6 (June, 2005), pp. 671-80  [abs].
4. RS Saunders, E Samei, JL Jesneck, JY Lo, Physical characterization of a prototype selenium-based full field digital mammography detector., Medical physics, United States, vol. 32 no. 2 (February, 2005), pp. 588-99  [abs].
5. MK Markey, JY Lo, GD Tourassi, CE Floyd, Self-organizing map for cluster analysis of a breast cancer database., Artificial intelligence in medicine, Netherlands, vol. 27 no. 2 (February, 2003), pp. 113-27  [abs].
6. JY Lo, MK Markey, JA Baker, CE Floyd, Cross-institutional evaluation of BI-RADS predictive model for mammographic diagnosis of breast cancer., AJR. American journal of roentgenology, United States, vol. 178 no. 2 (February, 2002), pp. 457-63  [abs].
7. MA Gavrielides, JY Lo, CE Floyd, Parameter optimization of a computer-aided diagnosis scheme for the segmentation of microcalcification clusters in mammograms., Medical physics, United States, vol. 29 no. 4 (April, 2002), pp. 475-83  [abs].