ULM-MbCNRT: In Vivo Ultrafast Ultrasound Localization Microscopy by Combining Multibranch CNN and Recursive Transformer.

Ultrasound localization microscopy (ULM) overcomes the acoustic diffraction limit by localizing tiny microbubbles (MBs), thus enabling the microvascular to be rendered at subwavelength resolution. Nevertheless, to obtain such superior spatial resolution, it is necessary to spend tens of seconds gathering numerous ultrasound (US) frames to accumulate the MB events required, resulting in ULM imaging still suffering from tradeoffs between imaging quality, data acquisition time, and data processing speed. In this article, we present a new deep learning (DL) framework combining multibranch convolutional neural network (CNN) and recursive transformer (RT), termed ULM-MbCNRT, that is capable of reconstructing a super-resolution (SR) image directly from a temporal mean low-resolution image generated by averaging much fewer raw US frames, i.e., implement an ultrafast ULM imaging. To evaluate the performance of ULM-MbCNRT, a series of numerical simulations and in vivo experiments are carried out. Numerical simulation results indicate that ULM-MbCNRT achieves high-quality ULM imaging with 10-fold reduction in data acquisition time and ~130-fold reduction in computation time compared to the previous DL method (e.g., the modified subpixel CNN, ULM-mSPCN). For the in vivo experiments, when comparing to the ULM-mSPCN, ULM-MbCNRT allows ~37-fold reduction in data acquisition time (0.8 s) and 2134-fold reduction in computation time (0.87 s) without sacrificing spatial resolution. It implies that ultrafast ULM imaging holds promise for observing rapid biological activity in vivo, potentially improving the diagnosis and monitoring of clinical conditions.