Content-based image retrieval for pulmonary computed tomography nodule images

Abstract

Research studies have shown that advances in computed tomography (CT) technology allow better detection of pulmonary nodules by generating higher-resolution images. However, the new technology also generates many more individual transversal reconstructions, which as a result may affect the efficiency and accuracy of the radiologists interpreting these images.The goal of our research study is to build a content-based image retrieval (CBIR) system for pulmonary CT nodules. Currently, texture is used to quantify the image content, but any other image feature could be incorporated into the proposed system. Unfortunately, there is no texture model or similarity measure known to work best for encoding nodule texture properties or retrieving most similar nodules. Therefore, we investigated and evaluated several texture models and similarity measures with respect to nodule size, number of retrieved nodules, and radiologist agreement on the nodules' texture characteristic.The results were generated on 90 thoracic CT scans collected by the Lung Image Database Consortium (LIDC). Every case was annotated by up to four radiologists marking the contour of nodules and assigning nine characteristics (including texture) to each identified nodule. We found that Gabor texture descriptors produce the best retrieval results regardless of the nodule size, number of retrieved items or similarity metric. Furthermore, when analyzing the radiologists' agreement on the texture characteristic, we found that when just two radiologists agreed, the average precision increased from 88% to 96% for both Gabor and Markov texture features. Moreover, once three or four radiologists agreed the precision increased to nearly 100%.

Correlated Networks for Content Based Image Retrieval

“…The Gabor filter is then convolved with different parameters; and it will generate the response images. As per the work done by Michael Lama et.al [7] we are using only the odd component of the Gabor filter which does not produce imaginary output:…”

“…Gabor filter is a sinusoid function modulated by a Gaussian and extracts feature information from an image in the form of a response images by applying varying parameters [7]. Such filters after convolution generate the set of response images which are based on different frequencies and orientations; and from these response images we generate the representative feature vectors based on salient points.…”

“…In [7] Michael Lama et.al, proposed a content based image retrieval system for computed tomography nodule images. Their system generates feature vector through GLCM, Gabor filters, and Markov random fields.…”

“…As far as the scope of features is concerned, features can be divided into two main categories: global features and local features. Global feature category includes color histogram [3,4], texture histogram [7], color layout [5] of the whole image, and features selected from multidimensional discriminant analysis of a collection of images [23]. While local feature category includes color, texture [9], and shape features for sub images, segmented regions [2,6], or interest points.…”

“…Such filters after convolution generate the set of response images which are based on different frequencies and orientations; and from these response images we generate the representative feature vectors based on salient points. In our implementation the filters we used are defined by the following equation [7]:…”