A Review on Ultrasound Image Pre-Processing, Segmentation and Compression for Enhanced Image Storage and Transmission

Abstract

Imaging is one of the key medical diagnostic tools to observe internal organs and soft tissues. One such tool is ultrasound scanning, which is highly utilized in gynecology and echo cardiogram. This is due to the number of advantages of ultrasound scanning, such as being non-invasive, free of radiation, economical and real-time. However, access to ultrasound scanning facilities remain limited due to the scarcity of human and physical resources. Therefore, developing technologies to remotely perform ultrasound scans using mobile devices to extend medical imaging facilities to rural and less accessible areas is becoming an interesting research area. This requires efficient compression of ultrasound scan footage in order to facilitate real-time transmission over a mobile network. Careful selection of the Region of Interest (ROI) is essential to compress ultrasound footage efficiently. Yet, it is a challenge due to distributions of various intensities depending on the imaging conditions, boundary ambiguities and speckle noise. This review paper highlights state-of-the-art technologies for the careful selection of ROI of ultrasound images to facilitate ultrasound image pre-processing, segmentation and compression. Furthermore, the paper proposes directions for future research to develop existing methods. It is envisaged that these technologies will pave the path to develop new technologies that would enable better patient care in the future.