Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images
Refereed conference paper presented and published in conference proceedings

Altmetrics Information

Other information
AbstractAccurate detection and segmentation of anatomical structures from ultrasound images are crucial for clinical diagnosis and biometric measurements. Although ultrasound imaging has been widely used with superiorities such as low cost and portability, the fuzzy border definition and existence of abounding artifacts pose great challenges for automatically detecting and segmenting the complex anatomical structures. In this paper, we propose a multi-domain regularized deep learning method to address this challenging problem. By leveraging the transfer learning from cross domains, the feature representations are effectively enhanced. The results are further improved by the iterative refinement. Moreover, our method is quite efficient by taking advantage of a fully convolutional network, which is formulated as an end-to-end learning framework of detection and segmentation. Extensive experimental results on a large-scale database corroborated that our method achieved a superior detection and segmentation accuracy, outperforming other methods by a significant margin and demonstrating competitive capability even compared to human performance.
Acceptance Date17/10/2016
All Author(s) ListHao Chen, Yefeng Zheng, Jin-Hyeong Park, Pheng-Ann Heng, S. Kevin Zhou
Name of Conference19th International Conference on Medical Image Computing and Computer-Assisted Intervention, Proceedings, Part II
Start Date of Conference17/10/2017
End Date of Conference21/10/2017
Place of ConferenceAthens
Country/Region of ConferenceGreece
Proceedings TitleMedical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Part II
Series TitleLecture Notes in Computer Science book series (LNCS)
Volume Number9901
PublisherSpringer International Publishing
Place of PublicationGreece
Pages487 - 495
LanguagesEnglish-United States
KeywordsMedical image segmentation, Ultrasound imaging, Regularized deep learning, Convolutional neural networks

Last updated on 2021-29-11 at 00:01