Comparative assessment of texture features for the identification of cancer in ultrasound images: a review

Abstract

In this paper, we review the use of texture features for cancer detection in Ultrasound (US) images of breast, prostate, thyroid, ovaries and liver for Computer-Aided Diagnosis (CAD) systems. This paper shows that texture features are a valuable tool to extract diagnostically relevant information from US images. This information helps practitioners to discriminate normal from abnormal tissues. A drawback of some classes of texture features comes from their sensitivity to both changes in image resolution and grayscale levels. These limitations pose a considerable challenge to CAD systems, because the information content of a specific texture feature depends on the US imaging system and its setup. Our review shows that single classes of texture features are insufficient, if considered alone, to create robust CAD systems, which can help to solve practical problems, such as cancer screening. Therefore, we recommend that the CAD system design involves testing a wide range of texture features along with features obtained with other image processing methods. Having such a competitive testing phase helps the designer to select the best feature combination for a particular problem. This approach will lead to practical US based cancer detection systems which deliver real benefits to patients by improving the diagnosis accuracy while reducing health care cost.

The Diagnostic Efficiency of Ultrasound Computer–Aided Diagnosis in Differentiating Thyroid Nodules: A Systematic Review and Narrative Synthesis

“…Because the scope of this review was limited to human populations with thyroid nodules, two studies were excluded with one being a mouse model study [30] and the other a human cell line study [31]. Two review articles and an editorial letter were excluded as they did not meet the publication inclusion criteria of original research articles [17,19,32]. A full-text review was conducted for the remaining 43 papers which resulted in the exclusion of 29 articles that did not meet the inclusion criteria.…”

“…Presently, few studies have investigated the diagnostic performance of various thyroid ultrasound CAD methods as applied in the clinical context and shown variable results. Existing systematic reviews have been based on analyzing different textural techniques and machine learning algorithms and classifiers more on a biomedical engineering perspective rather than clinical applicability [13,17,18,19]. A recent systematic review and meta-analysis study focused on the diagnostic performance of mainly the Samsung S-Detect CAD software in comparison with that of radiologists for the differentiation of thyroid nodules in clinical settings [20].…”

Shape and Texture Aware Facial Expression Recognition Using Spatial Pyramid Zernike Moments and Law’s Textures Feature Set

“…These features are invariant to changes in rotation, contrast and luminance. These measures find applications in various domains [46,47,48].…”

A Multiscale Topographical Analysis Based on Morphological Information: The HEVC Multiscale Decomposition

“…He also gave drawbacks and presented examples of applications for each method. Texture analysis is widely used for various applications like medical imaging [32], remote sensing [33], or industrial automation [34]. Hence, intra-prediction results should constitute a good candidate for texture feature extraction.…”