The first step in treating patients with brain tumor is to remove as much of the mass as possible through surgery. A sample of tumor mass examined during surgery not only helps to precisely diagnose the tumor, but also aid in defining the margins between healthy and tumor brain tissue. The intraoperative diagnosis is essential for providing safe and effective care during cancer surgery. Nonetheless, intraoperative pathology analysis takes time, including sample processing, staining, and analysis by a pathologist, and during this time the surgeon and patient both have to wait for the results. A new study shows that a process that combines an advanced imaging technology and artificial intelligence (AI) can precisely identify brain tumors in less than 3 minutes during the surgery. The approach is able to accurately distinguish tumor tissue from healthy tissues. Optical imaging and AI are making brain tumor diagnosis quicker and more accurate. Computers are trained to “see” the patterns of disease hidden in cells and tissues. The remarkable use of computer-generated AI is quickly providing neurosurgeons with valuable, real-time information about the type of brain tumor, while the patient is still on the operating table. In operating room, faster also means more affordable. The researchers are also using an AI algorithm called a deep convolutional neural network to learn the characteristics of the 10 most common types of brain cancer and predict diagnosis. Thus, today neurosurgeons can leave the operation theatre with assertiveness than before about their patient’s brain tumor diagnosis because this application of AI allow them to quickly see diagnostic tissue and tumor margins in near-real time. This means neuropathologists can review the images without the need for a pathology lab, eliminating the long wait time.
The Challenge:
How can Artificial Intelligence Speeds Brain Tumor Diagnosis?
International Center for Chemical and Biological Sciences (ICCBS)
Pakistan