A physician whose research produced promising results for using AI to improve the detection of tuberculosis (TB) was awarded the Alexander R. Margulis Award for Scientific Excellence during the annual RSNA conference in Chicago on Nov. 26.
"This award was so unexpected, and I am truly honored," Paras Lakhani, MD, a physician and assistant professor with the Thomas Jefferson University Hospital (TJUH) in Philadelphia, said in a statement. "Artificial intelligence is a hot area of research, and I have been focusing on this area for about two years. I don't plan to change direction any time soon."
The Margulis Award honors the best original scientific article published in the RSNA's Radiology journal. Lakhani and TJUH colleage Baskaran Sundaram, MD, used a deep convolutional neural network (DCNN) to identify TB from chest X-rays, according to an April 2017 article published in the journal.
Researchers collected more than 1,000 chest x-rays of patients with active TB. The X-rays were then split into training, validation and test datasets. The research showed that a combination of two DCNN models was 96 percent accurate.
The promising results indicate that deep learning can potentially be used to classify TB from chest X-rays and may be helpful with "screening and evaluation efforts in TB-prevalent areas with limited access to radiologists,” according to a press release.
"The authors evaluated a worldwide problem in public health—especially for areas with few radiologists," Radiology Editor David A. Bluemke, MD, PhD, said in a statement. "Importantly, Drs. Lakhani and Sundaram validated their results by studying chest X-rays from the United States, Belarus and China. This type of well-validated study is going to change the practice of radiology."
Danielle covers Clinical Innovation & Technology as a senior news writer for TriMed Media. Previously, she worked as a news reporter in northeast Missouri and earned a journalism degree from the University of Illinois at Urbana-Champaign. She's also a huge fan of the Chicago Cubs, Bears and Bulls.