Scale-aware Auto-context-guided Fetal US Segmentation with Structured Random Forests
Accurate measurement of fetal biometrics in ultrasound at different trimesters is essential in assisting clinicians to conduct pregnancy diagnosis. However, the accuracy of manual segmentation for measurement is highly user-dependent. Here, we design a general framework for automatically segmenting fetal anatomical structures in two-dimensional (2D) ultrasound (US) images and thus make objective biometric measurements available. We first introduce structured random forests (SRFs) as the core discriminative predictor to recognize the region of fetal anatomical structures with a primary classification map. The patch-wise joint labeling presented by SRFs has inherent advantages in identifying an ambiguous/fuzzy boundary and reconstructing incomplete anatomical boundary in US. Then, to get a more accurate and smooth classification map, a scale-aware auto-context model is injected to enhance the contour details of the classification map from various visual levels. Final segmentation can be obtained from the converged classification map with thresholding. Our framework is validated on two important biometric measurements, which are fetal head circumference (HC) and abdominal circumference (AC). The final results illustrate that our proposed method outperforms state-of-the-art methods in terms of segmentation accuracy.
Document Type: Original Article
Affiliations: 1: National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China 2: National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China 3: Department of Electronic Engineering, the Chinese University of Hong Kong, Hong Kong, China
Publication date: December 16, 2020
This article was made available online on September 29, 2020 as a Fast Track article with title: "Scale-aware Auto-context-guided Fetal US Segmentation with Structured Random Forests".
- BIO Integration will specifically focus on original, cutting-edge, interdisciplinary contents in the field of biosciences, including medicine, biochemistry, biophysics, bioengineering, biotechnology, etc., which generate hypotheses and questions relevant to the patient and disease and guide the investigations of cellular and molecular medicine. BIO Integration covers new methods, important applications, and new interpretations and treatments of existing data, as well as conventional studies in medicine that can be applied to future theranostic applications.
- Editorial Board
- Information for Authors
- Submit a Paper
- Information for Advertisers
- BIO Integration Aims and Scope
- BIO Integration Journal Information
- BIO Integration Contact Us
- Ingenta Connect is not responsible for the content or availability of external websites