Subjective and objective evaluations of feature selected multi output filter for speckle reduction on ultrasound images

Abstract

Ultrasonographic examination, either as visual inspection or quantitative analysis, is the most widely diagnostic resource. However, speckle noise is one of the drawbacks that makes it less effective than other medical imaging systems. Several speckle reduction methods often offer effective speckle reduction but generally suffer from oversmoothing, a blurring effect and a man-made appearance. In this paper, we propose a multi-output filter based on the multiplicative multiresolution decomposition (MOF-MMD). This multi-scale based method enables the enhancement of the original image and provides three enhanced outputs: global, edge and texture images. The multi-output filter aims at offering an enhanced image according to the features desired by radiologists. The different structures, textures and edges are filtered according to the contour image obtained by morphological operators. Three radiologists with different years of experience, have subjectively evaluated the speckle reduction methods according to enhanced features. The results of objective metrics and subjective evaluation showed that the proposed method reduces speckle and could help radiologists, according to their years of experience, in the diagnostic task. Finally, the correlation between three objective metrics and the perceived quality of contrast, diagnostic, texture and edges show that an objective metric is suitable for assessing quality of ultrasound images.

Deep-Based Quality Assessment of Medical Images Through Domain Adaptation

“…We compared the performance of our model to some blind state-ofthe-art metrics: BRISQUE [21], NIQE [10], bliinds [22] and BIQAA [23]. We also considered a metric, so-called NIQEK [9], that was developed specifically for such kind of medical images. In addition to those methods, we finally considered 2 metrics dedicated to the blur (i.e.…”

“…For each image, the corresponding MOS value is given. • MD72 dataset: The medical dataset proposed in [9] has been here used. The latter, denoted here as MD72, is composed of 72 liver Ultrasound images with the corresponding MOS.…”

“…Interesting metrics were already proposed in the literature. In [9], the authors proposed to extend the well-known NIQE method [10] for medical images. The metric, called NIQE-k, is based on a signal analysis in frequency domain.…”

Comparative study of the methodologies used for subjective medical image quality assessment

“…More recently, in 2018, Outtas et al worked on despeckeling of liver ultrasound images (Outtas et al 2018). The studied methods, as well as the proposed one, were subjectively and objectively tested on a parenchymal organ.…”

Label-free Medical Image Quality Evaluation by Semantics-aware Contrastive Learning in IoMT

“…In addition, we synthesise low-illumination and blurred skin images based on good quality skin images from ISIC dataset to create SkinQ dataset. • To carry out a comprehensive evaluation, we compare our method with other state-of-the-art (SOTA) methods on three distinct medical image datasets, including EyeQ [11], LiverQ [12], and SkinQ [13] datasets, to show its effectiveness in domain generalisation.…”