ACU2E-Net: A novel predict-refine attention network for segmentation of soft-tissue structures in ultrasound images.

Sharanya Balachandran¹, Xuebin Qin², Chen Jiang³, Ehsan Seyed Blouri⁴, Amir Forouzandeh⁵, Masood Dehghan⁶, Dornoosh Zonoobi⁷, Jeevesh Kapur⁸, Jacob Jaremko⁹, Kumaradevan Punithakumar¹⁰

¹Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, AB, Canada. Electronic address: balachan@ualberta.ca.

²Department of Computing Science, University of Alberta, Edmonton, AB, Canada. Electronic address: xuebin@ualberta.ca.

³Department of Computing Science, University of Alberta, Edmonton, AB, Canada. Electronic address: cjiang2@ualberta.ca.

⁴Exo Imaging Inc., Edmonton, AB, Canada. Electronic address: ebolouri@exo.inc.

⁵Exo Imaging Inc., Edmonton, AB, Canada. Electronic address: aforouzandeh@exo.inc.

⁶Exo Imaging Inc., Edmonton, AB, Canada. Electronic address: mdehghan@exo.inc.

⁷Exo Imaging Inc., Edmonton, AB, Canada. Electronic address: dornoosh@exo.inc.

⁸Department of Diagnostic Imaging, National University of Singapore, Singapore. Electronic address: jeevesh@nus.edu.sg.

⁹Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, AB, Canada. Electronic address: jjaremko@ualberta.ca.

¹⁰Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, AB, Canada. Electronic address: punithak@ualberta.ca.

PubMed DOI

Abstract

Segmentation of anatomical structures in ultrasound images is a challenging task due to existence of artifacts inherit to the modality such as speckle noise, attenuation, shadowing, uneven textures and blurred boundaries. This paper presents a novel attention-based predict-refine network, called ACU2E-Net, for segmentation of soft-tissue structures in ultrasound images. The network consists of two…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.