Abstract
Currently, placental maturity is performed using subjective evaluation, which can be unreliable as it is highly dependent on the observations and experiences of clinicians. To address this problem, this paper proposes a method to automatically stage placenta maturity from B-mode ultrasound (US) images based on dense sampling and novel feature descriptors. Specifically, our proposed method first densely extracts features with a regular grid based on dense sampling instead of a few unreliable interest points. Followed by, these features are clustered using generative Gaussian mixture model (GMM) to obtain high order statistics of the features. The clustering representatives (i.e., cluster means) are encoded by Fisher vector (FV) for staging accuracy enhancement. Differing from the previous studies, a multi-layer FV is investigated to exploit the spatial information rather than the single layer FV. Experimental results show that the proposed method with the dense FV has achieved an area under the receiver of characteristics (AUC) of 96.77%, sensitivity and specificity of 98.04% and 93.75% for the placental maturity staging, respectively. Our experimental results also demonstrate that the dense feature outperforms the traditional sparse feature for placental maturity staging.
Highlights
Over the past decade, ultrasound (US) imaging has been extensively applied in prenatal diagnosis and prognosis since it is radiation-free, direct-use, and low-cost[1,2,3,4,5,6,7]
The routine examination is performed by one radiologist at one time, but there are a total of three radiologists rather than one radiologist involved to provide the ground truth of the total 443 placental images in our study for placental staging, and 443 placental images are utilized in our study
The feature extraction time for an image is six seconds using a computer with a configuration of 32GBs RAM, double quad-core multi-threaded server with a single CPU, and the whole processing time for the testing step requires less than 1 second
Summary
Ultrasound (US) imaging has been extensively applied in prenatal diagnosis and prognosis since it is radiation-free, direct-use, and low-cost[1,2,3,4,5,6,7]. This method makes diagnosis and prognosis decision based on the doctor’s subjective diagnosis experience, and decision scores from the developed learned models via training, which can obtain a more accurate US image interpretation for the placental function evaluation than the traditional methods[2,15,16,17,18]. In 1979, the first placental maturity staging method[14] was proposed by Grannum et al to divide the chorionic, substance, and basal plates of the placenta into four stages This method relied on visual observation of placental US images to determine the calcification degree, which was highly dependent on the subjective judgment of the operator. The placental function evaluation is based on dense sampled visual discriminative features
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.
