The Medical Imaging & Image Analysis Laboratory
Department of Biomedical Engineering, The George Washington University
GW Cancer Center Basic Sciences Retreat featured talks and posters by trainees (graduate students, postdocs, staff scientists, technicians, lab managers, and other full time staff) that took place on Friday, April 27, 2018 at GW Cancer Center. Our Master’s student, Apurva Singh, presented her project “Effectiveness of Radiation Therapy for the Treatment of Head and Neck Squamous Cell Carcinoma“.
The IEEE International Symposium on Biomedical Imaging (ISBI) is a scientific conference dedicated to mathematical, algorithmic, and computational aspects of biological and biomedical imaging, across all scales of observation. Our graduate students Shuyue Guan and Kristina Landino have presented their posters in the conference that took place on April 4-7th in Washington, DC.
Shuyue presented his work on mammographic detection based on the computer-aided diagnosis (CAD). Below is a summary of his work:
“Mammographic detection based on the computer-aided diagnosis (CAD) can improve treatment outcomes for breast cancer and longer survival times for the patients. For the breast cancer detection, the Convolutional Neural Network (CNN) can extract features from mammographic images automatically and then do classification. However, to train the CNN from scratch needs a huge number of labeled images, which is infeasible for some kinds of medical image data such as mammographic tumor images. A promising solution is to apply transfer learning in CNN. In this study, we applied the pre-trained VGG-16 model to extract features from input mammographic images and used these features to train a Neural Network (NN)-classifier. On the DDSM database, average validation accuracy converged at about 0.905 for abnormal vs. normal cases with 10-fold cross validation, and no obvious overfitting happened. Therefore, this study shows that applying transfer learning in CNN can detect female breast cancer from mammogram, and training a NN-classifier by feature extraction is a feasible method in transfer learning.”
Check the posters for more information here.
Our students have presented their projects in GW Research Days on April 9th. GW Research Days is an annual event held at the George Washington University, where graduate and undergraduate students from all schools present their research and projects.
Our undergraduate students Aidan Murray and Shannon Toole won the first place (tie) Undergraduate Presenters Award for their project titled “Symmetrical Cluster Analysis for Thermographic Breast Cancer Detection”.
From our graduate students Shuyue Guan presented on Breast Cancer detection using transfer learning in convolution neural networks, Kristina Landino presented on Silence in Videos, and Apurva Singh presented on the effectiveness of radiation therapy for the treatment of head and neck squamous cell carcinoma.
Zainab Mahmood and Nada Kamona, our undergraduate seniors, presented on “Automated Segmentation Algorithm for Thermal Breast Images” and “Reproducibility of Quantitative Image Texture Features in Identifying Tumor Regions in Thermal Breast Images” respectively.
Congratulations to our students on their accomplishments! Check their projects here and the photo gallery here.
For more information on GW Research Days, click here.
About the Program:
Technical studies of historical musical instruments remain relatively uncommon in the field of cultural heritage. This program features recent in-depth studies that serve as models of collaborations between curators, conservators, and cultural heritage scientists in the field of musical studies. As part of a National Endowment of the Humanities (NEH) Preservation and Access Grant-funded, collaborative research project involving the Library of Congress, the Catholic University of America, and George Washington University, Science meets Music: Technical Studies of Musical Instruments is the first of an annual series. These lectures highlight the NEH-supported study of glass flutes by Claude Laurent in the Library of Congress Dayton C. Miller Collection, along with invited talks that represent groundbreaking, collaborative research with broad appeal to cultural heritage curators, conservators, scientists, and musicians.
Webcast
Register for the live webcast by Monday, April 9 at noon. You will receive instructions for how to access the
live stream with the auto-confirm email upon registering and again on April 9 COB.
Tuesday, April 10, 2018
3:00 – 5:00 pm EDT
Library of Congress Thomas Jefferson Building
Whittall Pavilion, Room LJ WH
10 First St. SE
Washington, DC 20540
Carol Lynn Ward Bamford and Lynn Brostoff conducting non-invasive XRF analysis o f a Claude Laurent glass flute.
About the Speakers
Carol Lynn Ward-Bamford is a flutist and, since 1993, has worked as Music Specialist and Curator of Musical
Instruments at the Library of Congress Music Division, where she oversees the Library’s holdings of
approximately 2,000 musical instruments for study, performance, and exhibit. She holds degrees in music,
performance on the flute, and archives management from Tufts University.
Stephanie Zaleski, Ph.D., is a postdoctoral scientist at George Washington University, where her research
focuses on developing simple, non-invasive analytical tools to study 19th-century glass in historical
collections. She obtained her Ph.D. in chemistry from Northwestern University in 2016 and recently was a
postdoctoral fellow with the Department of Scientific Research at the Metropolitan Museum of Art from
2016-2017.
Isabelle Muller, Ph.D., is a project manager at the Vitreous State Laboratory at the Catholic University of
America in charge of research and development programs for the U.S. Department of Energy (glass
formulation for Hanford Site tank waste vitrification, long term water leaching of various waste glasses, and
development of predictive algorithms of the glass properties). She obtained her Ph.D. in physical chemistry
from Pierre et Marie Curie University, Paris VI, France and was a postdoctoral fellow in nuclear chemistry at
the Lawrence Berkeley Laboratory.
Lynn Brostoff, Ph.D., holds a Ph.D. in Chemistry, Masters Degrees in Polymer Materials Science and in Art
History, and an Advanced Certificate in Conservation of Historic and Artistic Works, with a specialty in Paper
Conservation. For the last 25 years, Lynn has worked as a conservation scientist at leading museums and
libraries, including the Metropolitan Museum of Art in New York, and the National Gallery of Art, the
Smithsonian’s Museum Conservation Institute, and the Library of Congress, where she is currently a Senior
Scientist and Analytical Service Liaison.
Jayme Kurland is a musicologist and independent researcher based in Northern Virginia. She is currently
working on a project with the musical instrument collection at the Library of Congress. Previously, she was
the Curatorial Research Fellow in Musical Instruments at the Museum of Fine Arts, Boston, and a curatorial
assistant at the Musical Instrument Museum in Phoenix.
Jean-Philippe Echard, Ph.D., is the curator of bowed string instruments at the French national collection at
the Musée de la musique in Paris. He studied musical acoustics at the Conservatoire National Supérieur de
Musique in Paris, was a Research Fellow at the National Gallery of Art in Washington, DC, and at the
Laboratoire de Recherche et de Restauration of the Musée de la musique, developed methodologies for the
observation and the analysis of materials of musical instruments. His Ph.D. (2010) research was on the
materials and techniques used to varnish musical instruments (15th-18th centuries).
Our students have participated and presented their projects in SEAS R&D Annual Showcase in February 2018. From our graduate students Shuyue Guan presented on Breast Cancer detection using transfer learning in convolution neural networks, Kristina Landino presented on Silence in Videos, and Apurva Singh presented on the effectiveness of radiation therapy for the treatment of head and neck squamous cell carcinoma. Apurva was awarded the $3,000 AccelerateGW I-Corps Site Program Grants, aimed to cover travel expenses related to client interviews and limited prototyping.
Zainab Mahmood and Nada Kamona, our undergraduate seniors, presented on “Automated Segmentation Algorithm for Thermal Breast Images” and “Reproducibility of Quantitative Image Texture Features in Identifying Tumor Regions in Thermal Breast Images” respectively.
Our undergraduate students Aidan Murray, Shannon Toole and Pannie Xu won the $2,000 Best Undergraduate Poster for their project titled “Symmetrical Cluster Analysis for Thermographic Breast Cancer Detection”.
Congratulations to our students on their accomplishments! Check their projects here and the photo gallery here.
The SEAS R&D Showcase is an annual event held at the School of Engineering and Applied Science, where graduate and undergraduate students from all different departments have the chance to present their research and projects. For more information, click here.
