Purpose: Investigate the ability of using complementary information provided by the fusion of PET/CT images to predict immunotherapy response in non-small cell lung cancer (NSCLC) patients. Materials and methods: We collected 64 patients diagnosed with primary NSCLC treated with anti PD-1 checkpoint blockade. Using PET/CT images, fused images were created following multiple methodologies, resulting in up to 7 different images for the tumor region. Quantitative image features were extracted from the primary image (PET/CT) and the fused images, which included 195 from primary images and 1235 features from the fusion images. Three clinical characteristics were also analyzed. We then used support vector machine (SVM) classification models to identify discriminant features that predict immunotherapy response at baseline. Results: A SVM built with 87 fusion features and 13 primary PET/CT features on validation dataset had an accuracy and area under the ROC curve (AUROC) of 87.5% and 0.82, respectively, compared to a model built with 113 original PET/CT features on validation dataset 78.12% and 0.68. Conclusion: The fusion features shows better ability to predict immunotherapy response prediction compared to individual image features.
Pulmonary nodules are effectively diagnosed in CT scans, but determining their malignancy has been a challenge. The rate of change of the volume of a pulmonary nodule is known to be a prognostic factor for cancer development. In this study, we propose that other changes in imaging characteristics are similarly informative. We examined the combination of image features across multiple CT scans, taken from the National Lung Screening Trial, with individual scans of the same patient separated by approximately one year. By subtracting the values of existing features in multiple scans for the same patient, we were able to improve the ability of existing classification algorithms to determine whether a nodule will become malignant. We trained each classifier on 83 nodules determined to be malignant by biopsy and 172 nodules determined to be benign by their clinical stability through two years of no change; classifiers were tested on 77 malignant and 144 benign nodules, using a set of features that in a test-retest experiment were shown to be stable. An accuracy of 83.71% and AUC of 0.814 were achieved with the Random Forests classifier on a subset of features determined to be stable via test-retest reproducibility analysis, further reduced with the Correlation-based Feature Selection algorithm.
Background: Lung-RADS is the new oncology classification guideline proposed by American College of Radiology (ACR), which provides recommendation for further follow up in lung cancer screening. However, only two features (solidity and size) are included in this system. We hypothesize that additional sematic features can be used to better characterize lung nodules and diagnose cancer. Objective: We propose to develop and characterize a systematic methodology based on semantic image traits to more accurately predict occurrence of cancerous nodules. Methods: 24 radiological image traits were systematically scored on a point scale (up to 5) by a trained radiologist, and lung-RADS was independently scored. A linear discriminant model was used on the semantic features to access their performance in predicting cancer status. The semantic predictors were then compared to lung-RADS classification in 199 patients (60 cancers, 139 normal controls) obtained from the National Lung Screening Trial. Result: There were different combinations of semantic features that were strong predictors of cancer status. Of these, contour, border definition, size, solidity, focal emphysema, focal fibrosis and location emerged as top candidates. The performance of two semantic features (short axial diameter and contour) had an AUC of 0.945, and was comparable to that of lung-RADS (AUC: 0.871). Conclusion: We propose that a semantics-based discrimination approach may act as a complement to the lung-RADS to predict cancer status.
Background: We propose a systematic methodology to quantify incidentally identified lung nodules based on observed radiological traits on a point scale. These quantitative traits classification model was used to predict cancer status. Materials and Methods: We used 102 patients’ low dose computed tomography (LDCT) images for this study, 24 semantic traits were systematically scored from each image. We built a machine learning classifier in cross validation setting to find best predictive imaging features to differentiate malignant from benign lung nodules. Results: The best feature triplet to discriminate malignancy was based on long axis, concavity and lymphadenopathy with average AUC of 0.897 (Accuracy of 76.8%, Sensitivity of 64.3%, Specificity of 90%). A similar semantic triplet optimized on Sensitivity/Specificity (Youden’s J index) included long axis, vascular convergence and lymphadenopathy which had an average AUC of 0.875 (Accuracy of 81.7%, Sensitivity of 76.2%, Specificity of 95%). Conclusions: Quantitative radiological image traits can differentiate malignant from benign lung nodules. These semantic features along with size measurement enhance the prediction accuracy.
A microarray-image model is used that takes into account many factors, including spot morphology, signal strength, background fluorescent noise, and shape and surface degradation. The model yields synthetic images whose appearance and quality reflect that of real microarray images. The model is used to link noise factors to the fidelity of signal extraction with respect to a standard image-extraction algorithm. Of particular interest is the identification of the noise factors and their interactions that significantly degrade the ability to accurately detect the true gene-expression signal. This study uses statistical criteria in conjunction with the simulation of various noise conditions to better understand the noise influence on signal extraction for cDNA microarray images. It proposes a paradigm that is implemented in software. It specifically considers certain kinds of noise in the noise model and sets these at certain levels; however, one can choose other types of noise or use different noise levels. In sum, it develops a statistical package that can work in conjunction with the existing image simulation toolbox.
Morphological granulometries and their moment features are used as shape descriptors. These features find application in classification, segmentation and estimation. Design of classifiers has been a primary goal of most pattern recognition problems. Small sample design is often a constraint when designing classifiers. We use a recently proposed small sample design method in which the sample observations are spread with a probability mass and the classifiers designed on the spread mass. The designed classifiers are more reliability for relative to the population. Two issues are addressed: design of granulometric classifiers using a small sample, and granulometric classification based on a very small number of features.
Granulometric features have been widely used for classification, segmentation and recently in estimation of parameters in shape models. In this paper we study the inference of clustering based on granulometric features for a collection of structuring probes in the context of random models. We use random Boolean models to represent grains of different shapes and structure. It is known that granulometric features are excellent descriptors of shape and structure of grains. Inference based on clustering these features helps to analyze the consistency of these features and clustering algorithms. This greatly aids in classifier design and feature selection. Features and the order of their addition play a role in reducing the inference errors. We study four different types of feature addition methods and the effect of replication in reducing the inference errors.
The images resulting from cDNA microarrays are highly random. There are many aspects to this randomness, including spot size, shape, intensity, uniformity, and circularity, as well as both foreground and background noise. This paper presents a random model for the generation of microarray images. The model is complicated and contains over 20 parameters. It can be used to test microarray imaging algorithms and to simulate the effects of various dependencies within the image formation process.
Morphological granulometries have been used to successfully discriminate textures in the context of classical feature-based classification. The features are typically the granulometric moments resulting from the pattern spectrum of the random image. This paper takes a different approach and uses the granulometric moments as inputs to a linear system that has been derived by classical optimization techniques for linear filters. The output of the system in a set of estimators that estimate the parameters of the model governing the distribution of the random set. These model parameters are assumed to be random variables possessing a prior distribution, so that the linear filter estimates these random variables based on granulometric moments. The methodology is applied to estimating the primary grain and intensity of a random Boolean model.
Morphological granulometric moments have proven useful for quantification and classification of image texture. This paper considers their use as measures of surface roughness. The analysis is based on simulations in the framework of a modified Boolean random function model for surfaces. Four granulometric features are considered: the pattern-spectrum mean and pattern-spectrum variance for both opening and closing granulometries generated by flat structuring elements. The expectations of these granulometric moments are compared with the expectations of the classical average and root-mean-square roughness across a range of Boolean models.
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.