Researchers at the Athinoula A. Martinos Center for Biomedical Imaging at Massachusetts General Hospital (MGH) in the US have developed a new technique that uses artificial intelligence (AI) and machine learning to acquire high-quality medical images from limited data.
High quality images are crucial for radiologists to make accurate diagnoses. However, as the researchers describe in their paper published in the journal Nature, acquiring sufficient data to generate the best quality imaging comes at a cost. For example, increased radiation dose for computed tomography CT and positron emission tomography (PET) or uncomfortably long scan times for magnetic resonance imaging (MRI).
“An essential part of the clinical imaging pipeline is image reconstruction, which transforms the raw data coming off the scanner into images for radiologists to evaluate,” said a Research Fellow in the MGH Martinos Center and first author of the Nature paper, Bo Zhu, PhD.
“The conventional approach to image reconstruction uses a chain of handcrafted signal processing modules that require expert manual parameter tuning and often are unable to handle imperfections of the raw data, such as noise. We introduce a new paradigm in which the correct image reconstruction algorithm is automatically determined by deep learning AI,” continued Zhu.
The new technique Zhu and his team have developed has been dubbed AUTOMAP (automated transform by manifold approximation).
“With AUTOMAP, we’ve taught imaging systems to ‘see’ the way humans learn to see after birth, not through directly programming the brain but by promoting neural connections to adapt organically through repeated training on real-world examples,” said Zhu.
“This approach allows our imaging systems to automatically find the best computational strategies to produce clear, accurate images in a wide variety of imaging scenarios,” continued Zhu.
According to Zhu and his team, the speed at which AUTOMAP creates high-quality images could help radiologists make real-time decisions about imaging protocols while the patient is in the scanner.
“Since AUTOMAP is implemented as a feedforward neural network, the speed of image reconstruction is almost instantaneous – just tens of milliseconds,” said senior author and Director of the Low-field MRI and Hyperpolarized Media Laboratory and Co-director of the Center for Machine Learning at the MGH Martinos Center, Matt Rosen, PhD.
“Some types of scans currently require time-consuming computational processing to reconstruct the images. In those cases, immediate feedback is not available during initial imaging, and a repeat study may be required to better identify a suspected abnormality. AUTOMAP would provide instant image reconstruction to inform the decision-making process during scanning and could prevent the need for additional visits,” concluded Rosen.
The development of AUTOMAP was funded in part by the National Institute of Biomedical Imaging and Bioengineering. A patent application related to AUTOMAP has been filed.