Effect of Slice Thickness on Texture-Based Classification of Liver Dynamic CT Scans [chapter]

Dorota Duda, Marek Kretowski, Johanne Bezy-Wendling
<span title="">2013</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
This paper assesses the impact of slice thickness on texture parameters. Experiments are performed on liver dynamic CT scans, with two slice thicknesses. Three acquisition moments are considered: without contrast, in arterial and in portal phase. In total, 155 texture parameters, extracted with 9 methods, are tested. Classification of normal and cirrhotic liver is performed using a boosting algorithm. Experiments reveal that slice thickness does not considerably influence the stability of the
more &raquo; ... rameters. They also enable to assess the rate of parameter dependency on slice thickness. Finally, they show that applying different slice thicknesses for training and testing the CAD system requires slice thickness-independent parameters. Effect of Slice Thickness on Texture-Based Classification of Liver CTs 97 for the recognition of several classes of tissue, representing different pathologies. The second stage is the applicationof the system for the (semi)automatic recognition of new cases, not yet diagnosed. Due to the constant changes of image acquisition protocols, the question arises whether the protocols for new recognized images can be different from those that were used during the system training. The question seems all the more important given the fact that there is still no universal consensus on image acquisition protocols, so the images obtained from different machines could be of different properties and qualities. The aim of our study is to examine the effect of slice thickness on texture parameters characterizing hepatic tissue on dynamic (contrast-enhanced) CT images. Our choice was dictated by the fact that the image database that we have been creating for about 10 years includes images of several slice thicknesses: from the oldest ones, of 10 mm, to the most recent ones, of 1.3 mm. So far, we have not found any research concerning the impact of slice thickness on texture-based classification of liver CT images with different contrast product concentrations. In this study, we first assess the influence of slice thickness on parameter stability. Secondly, we study the possibility of tissue differentiation, with the most known parameters and different combinations of slice thicknesses used for system training and testing. Then, the parameter dependency on slice thickness is evaluated. Finally, the classification of two types of liver tissue, characterized by parameters which are least dependent on slice thickness is performed. The next section includes a short description of related works. In Sect. 3 the system for classification of multiphasic textures is presented. Then, the methods for assessing the effect of slice thickness on the system performance are proposed. An experimental validation is described in Sect. 4. Conclusions and future work are presented in the last section.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-40925-7_10">doi:10.1007/978-3-642-40925-7_10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wpiwja5elnernlxuota36fvyt4">fatcat:wpiwja5elnernlxuota36fvyt4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706013343/http://aragorn.pb.bialystok.pl/%7Emkret/docs/cisim2013.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/93/d09332d4ad014717eb8f4be783a8f45b210b8360.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-40925-7_10"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>