The broader impact/commercial potential of this I-Corps project is the development of software that will serve as an aid to the pathologist to provide more accurate diagnoses using histopathology images. The software will be deployed on the cloud so that it can be used anywhere, anytime through a web portal using a desktop, laptop, tablet, or a smart-phone. The software has the potential to dramatically speed up the disease diagnosis process with increased accuracy, which in turn will result in improved quality of care and better patient outcomes.
This I-Corps project is based on the development of novel deep learning techniques for whole-slide image analysis to aid pathologists in making a better diagnosis for diseases such as tuberculosis. Pathologists make a diagnosis based on recognizing patterns in histopathology images. Recognizing pathology patterns takes many years of training. After training, pathologists spend significant amount of time doing pattern recognition for the rest of their life. With the potential to save time and effort for pathologists, and inspired by the recent success of deep learning on natural images, there is a need to develop artificial intelligence models to recognize patterns in histopathology images. In addition to tuberculosis, the proposed techniques and software prototype could be extended to the diagnosis of other diseases in the future.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
