Abstract
Convolutional Neural Networks (CNNs), which are currently state-of-the-art for most image analysis tasks, are ill suited to leveraging the key benefits of ultrasound imaging - specifically, ultrasound's portability and real-time capabilities. CNNs have large memory footprints, which obstructs their implementation on mobile devices, and require numerous floating point operations, which results in slow CPU inference times. In this paper, we propose three approaches to training efficient CNNs that can operate in real-time on a CPU (catering to the clinical setting), with a low memory footprint, for minimal compromise in accuracy. We first demonstrate the power of 'thin' CNNs, with very few feature channels, for fast medical image segmentation. We then leverage separable convolutions to further speed up inference, reduce parameter count and facilitate mobile deployment. Lastly, we propose a novel knowledge distillation technique to boost the accuracy of light-weight models, while maintaining inference speed-up. For a negligible sacrifice in test set Dice performance on the challenging ultrasound analysis task of nerve segmentation, our final proposed model processes images at 30fps on a CPU, which is 9Ă— faster than the standard U-Net, while requiring 420Ă— less space in memory.
Highlights
I N RECENT YEARS, convolutional neural networks (CNNs) have achieved state-of-the-art performance in most image analysis tasks
We propose the use of separable convolutions and a distillation technique tailored for segmentation, demonstrating real-time CPU inference for a negligible (0.7% mean) sacrifice in accuracy
We have tackled the problem of real-time ultrasound analysis on CPUs, thereby catering our CNN architectures to the clinical setting
Summary
I N RECENT YEARS, convolutional neural networks (CNNs) have achieved state-of-the-art performance in most image analysis tasks. After first being deployed for classification challenges [1], [2], CNNs have been adapted successfully for other tasks such as detection, registration, and segmentation [3]. In the context of segmentation (one of the most widely tackled problems in the medical imaging literature), the U-Net architecture has been extensively utilised and adapted for a number of scenarios [4]. Though CNNs achieve very high accuracies, their speed and memory requirements remain a significant limitation in their feasibility to real-world deployment. Date of publication February 14, 2020; date of current version April 6, 2020. (Corresponding author: Ana Namburete.)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
