Hybrid Speckle Noise Reduction Method for Abdominal Circumference Segmentation of Fetal Ultrasound Images

Abstract

Fetal biometric size such as abdominal circumference (AC) is used to predict fetal weight or gestational age in ultrasound images. The automatic biometric measurement can improve efficiency in the ultrasonography examination workflow. The unclear boundaries of the abdomen image and the speckle noise presence are the challenges for the automated AC measurement techniques. The main problem to improve the accuracy of the automatic AC segmentation is how to remove noise while retaining the boundary features of objects. In this paper, we proposed a hybrid ultrasound image denoising framework which was a combination of spatial-based filtering method and multiresolution based method. In this technique, an ultrasound image was decomposed into subbands using wavelet transform. A thresholding technique and the anisotropic diffusion method were applied to the detail subbands, at the same time the bilateral filtering modified the approximation subband. The proposed denoising approach had the best performance in the edge preservation level and could improve the accuracy of the abdominal circumference segmentation.

Combination of Aggregated Channel Features (ACF) Detector and Faster R-CNN to Improve Object Detection Performance in Fetal Ultrasound Images

“…Preprocessing step aims to remove the speckle noise on the ultrasound image. We implement the hybrid speckle reduction method that is proposed in [25]. The speckle reduction approach combines the spatial filtering, i.e.…”

“…In this study, we propose a method that combines the ACF detector and Faster R-CNN to detect a crosssectional area of the fetal limb in an ultrasound image. Firstly, we apply a preprocessing step to reduce the speckle noise in the ultrasound image using the method proposed by Hermawati et al [25]. Then, we implement ACF detector to process the training images with annotation bounding box.…”

Median Filter For Transition Region Refinement In Image Segmentation

“…The value of ft is obtained by summing the number of adjacent transitional pixels horizontally of each row in image. The value of ft is then compared with the value of fm to determine the value of pa using Equation (5). Median filter process will be performed to the image if the value of pa is greater than or equal to the normal proximity threshold nt.…”

“…It is usually used for further processing such as biomedical image analysis, character identification and object recognition [1]. In general, the method of image segmentation can be categorized into several types of approaches: thresholding based approach [2][3][4][5], boundary based approach [6], region-based approach [7] and hybrid approach [8][9][10][11].…”

Soft Weighted Median Filter Method for Improved Image Segmentation with Noise

“…Adapun metode-metode yang lain yang juga dapat menangani FVN N maupun RVN dan sering digunakan seperti: Median Filter, Mean Filter, Wiener Filter, dan Gaussian Filter [6]. Disamping itu denoising dapat dilakukan dengan menggunakan altenatif metode seperti transformasi wavelet [7] [8], dan Singular Spectrum Analysis (SSA) [9]. Semua metode tersebut tentunya mempunyai kelebihan dan kekurangannya.…”