This study applied a Gaussian Mixture Model (GMM) to apparent diffusion coefficient (ADC) histograms to evaluate
glioblastoma multiforme (GBM) tumor treatment response using diffusion weighted (DW) MR images. ADC mapping,
calculated from DW images, has been shown to reveal changes in the tumor's microenvironment preceding
morphologic tumor changes. In this study, we investigated the effectiveness of features that represent changes from
pre- and post-treatment tumor ADC histograms to detect treatment response. The main contribution of this work is to
model the ADC histogram as the composition of two components, fitted by GMM with expectation maximization (EM)
algorithm. For both pre- and post-treatment scans taken 5-7 weeks apart, we obtained the tumor ADC histogram,
calculated the two-component features, as well as the other standard histogram-based features, and applied supervised
learning for classification. We evaluated our approach with data from 85 patients with GBM under chemotherapy, in
which 33 responded and 52 did not respond based on tumor size reduction. We compared AdaBoost and random
forests classification algorithms, using ten-fold cross validation, resulting in a best accuracy of 69.41%.
The purpose of this study is to test a new dynamic Perfusion-CT imaging protocol in an animal model and
investigate the feasibility of quantifying perfusion of lung parenchyma to perform functional analysis from
4D CT image data. A novel perfusion-CT protocol was designed with 25 scanning time points: the first at
baseline and 24 scans after a bolus injection of contrast material. Post-contrast CT scanning images were
acquired with a high sampling rate before the first blood recirculation and then a relatively low sampling
rate until 10 minutes after administrating contrast agent. Lower radiation techniques were used to keep the
radiation dose to an acceptable level. 2 Yorkshire swine with pulmonary emboli underwent this perfusion-
CT protocol at suspended end inspiration. The software tools were designed to measure the quantitative
perfusion parameters (perfusion, permeability, relative blood volume, blood flow, wash-in & wash-out
enhancement) of voxel or interesting area of lung. The perfusion values were calculated for further lung
functional analysis and presented visually as contrast enhancement maps for the volume being examined.
The results show increased CT temporal sampling rate provides the feasibility of quantifying lung function
and evaluating the pulmonary emboli. Differences between areas with known perfusion defects and those
without perfusion defects were observed. In conclusion, the techniques to calculate the lung perfusion on
animal model have potential application in human lung functional analysis such as evaluation of functional
effects of pulmonary embolism. With further study, these techniques might be applicable in human lung
parenchyma characterization and possibly for lung nodule characterization.
This study developed a methodology to extract the quantitative features of representing nodule 3D shape and investigate
the performance of these features in differentiating between benign and malignant solitary pulmonary nodules (SPNs).
36 cases with solitary lung nodules (15 Benign, 21 Malignant) were examined in this study. The CT helical scanning-parameters
were ⩽3 mm collimation, pitch 1-2, and 1.5-3 mm reconstruction interval. The nodule boundaries were
contoured by radiologists on 3D volume data. Using these boundaries, the nodule physical 3D surfaces were created and
several 3D nodule shape-features were computed, including: Compactness Factor (CF) of nodule, Shape Index (SI) and
curvedness of each pixel in the physical 3D nodule surface. The histogram characteristic features of SI and curvedness
were calculated. AdaBoost was performed to select the features and their statistically differences were analyzed. Logistic
Regression Analysis (LRA) and AdaBoost were used to evaluate the overall diagnostic accuracy. For 36 patients, CF is
the first feature selected by AdaBoost, which also has significant difference (t-test, P=0.6%) between Benign and
malignant nodules. However, histogram features of SI and curvedness are not all significantly different. The accuracy of
LRA is 75%, with accuracies of AdaBoost using all features is about 80% with cross validation. Generally, SI,
curvedness and CF may provide a comprehensive examination of the nodule shape, which can be used in differentiating
benign from malignant SPNs. However, other types' features (such as texture, angiogenesis) should be combined with
shape information to assist radiologists in characterizing SPNs more accurately.
The purpose of this paper was to investigate the effects of integrating nodule 3D morphological features, texture features and functional dynamic contrast-enhanced features in differentiating between benign and malignant solitary pulmonary nodules (SPNs). In this study, 42 cases with solitary lung nodules were examined in this study. The dynamic CT helical scans were acquired image at five time intervals: prior to contrast injection (baseline) and then at 45, 90, 180, 300 seconds after administrating the contrast agent. The nodule boundaries were contoured by radiologists on all series. Using these boundaries, several types of nodule features were computed, including: 3D morphology and Shape Index of the nodule contrast intensity surface; Dynamic contrast related features; 3D texture features. AdaBoost was performed to select the best features. Logistic Regression Analysis (LRA) and AdaBoost were used to analyze the diagnostic accuracy of features in each feature category. The performance when integrating all feature types was also evaluated. For 42 patients, when using only six SI and 3D structural features, the accuracy of AdaBoost was 81.4%, with accuracies of AdaBoost using functional contrast related features (include 8 features) and texture features(include 18 features) were 65.1% and 69.1% respectively. After combining all types' features together, the overall accuracy was improved to over 88%. In conclusion: Combining 3D structural, textural and functional contrast features can provide a more comprehensive examination of the SPNs by coupling dynamic CT scan techniques with image processing to quantify multiple properties that relate to tumor geometry and tumor angiogenesis. This integration may assist radiologists in characterizing SPNs more accurately.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.