Technical Note: Identification of CT Texture Features Robust to Tumor Size Variations for Normal Lung Texture Analysis (original) (raw)
Related papers
How to use CT texture analysis for prognostication of non-small cell lung cancer
Cancer Imaging
Patients with non-small cell lung cancer frequently demonstrate differing clinical courses, even when they express the same tumour stage. Additional markers of prognostic significance could allow further stratification of treatment for these patients. By generating quantitative information about tumour heterogeneity as reflected by the distribution of pixel values within the tumour, CT texture analysis (CTTA) can provide prognostic information for patients with NSCLC. In addition to describing the practical application of CTTA to NSCLC, this article discusses a range of issues that need to be addressed when CTTA is included as part of routine clinical care as opposed to its use in a research setting. The use of quantitative imaging to provide prognostic information is a new and exciting development within cancer imaging that can expand the imaging specialist's existing role in tumour evaluation. Derivation of prognostic information through the application of image processing techniques such as CTTA, to images acquired as part of routine care can help imaging specialists make best use of the technologies they deploy for the benefit of patients with cancer.
Physics in Medicine and Biology, 2014
This study examines the correlation between the radiologist-defined severity of normal tissue damage following radiation therapy (RT) for lung cancer treatment and a set of mathematical descriptors of computed tomography (CT) scan texture ("texture features"). A pre-therapy CT scan and a post-therapy (median: 33 days) CT scan were retrospectively collected under IRB approval for each of 25 patients who underwent definitive RT (median dose: 66 Gy). Sixty regions of interest (ROIs) were automatically identified in the non-cancerous lung tissue of each posttherapy scan. A radiologist compared post-therapy scan ROIs with pre-therapy scans and categorized each as containing no abnormality, mild abnormality, moderate abnormality, or severe abnormality. Twenty texture features that characterize gray-level intensity, region morphology, and gray-level distribution were calculated in post-therapy scan ROIs and compared with anatomically matched ROIs in the pre-therapy scan. Linear regression and receiver operating characteristic (ROC) analysis were used to compare the percent feature value change (ΔFV) between ROIs at each category of visible radiation damage. Most ROIs contained no (65%) or mild abnormality (30%). ROIs with moderate (3%) or severe (2%) abnormalities were observed in 9 patients. For 19 of 20 features, ΔFV was significantly different among severity levels. For 12 features, significant differences were observed at every level. Compared with regions with no abnormalities, ΔFV for these 12 features increased, on average, by 1.5%, 12%, and 30%, respectively, for mild, moderate, and severe abnormalitites. Area under the ROC curve was largest when comparing ΔFV in the highest severity level with the remaining three categories (mean AUC across features: 0.84). In conclusion, 19 features that characterized the severity of radiologic changes from pre-therapy scans were identified. These features may be used in future studies to quantify acute normal lung tissue damage following RT.
Reproducibility and Prognosis of Quantitative Features Extracted from CT Images
2014
We study the reproducibility of quantitative imaging features that are used to describe tumor shape, size, and texture from computed tomography (CT) scans of non-small cell lung cancer (NSCLC). CT images are dependent on various scanning factors. We focus on characterizing image features that are reproducible in the presence of variations due to patient factors and segmentation methods. Thirty-two NSCLC nonenhanced lung CT scans were obtained from the Reference Image Database to Evaluate Response data set. The tumors were segmented using both manual (radiologist expert) and ensemble (software-automated) methods. A set of features (219 threedimensional and 110 two-dimensional) was computed, and quantitative image features were statistically filtered to identify a subset of reproducible and nonredundant features. The variability in the repeated experiment was measured by the test-retest concordance correlation coefficient (CCC TreT). The natural range in the features, normalized to variance, was measured by the dynamic range (DR). In this study, there were 29 features across segmentation methods found with CCC TreT and DR ≥ 0.9 and R 2 Bet ≥ 0.95. These reproducible features were tested for predicting radiologist prognostic score; some texture features (run-length and Laws kernels) had an area under the curve of 0.9. The representative features were tested for their prognostic capabilities using an independent NSCLC data set (59 lung adenocarcinomas), where one of the texture features, run-length gray-level nonuniformity, was statistically significant in separating the samples into survival groups (P ≤ .046).
2021
Computer-assisted analysis of three-dimensional imaging data (radiomics) has received a lot of research attention as a possible means to improve the management of patients with lung cancer. Building robust predictive models for clinical decision making requires the imaging features to be stable enough to changes in the acquisition and extraction settings. Experimenting on 517 lung lesions from a cohort of 207 patients, we assessed the stability of 88 texture features from the following classes: first-order (13 features), Grey-level Co-Occurrence Matrix (24), Grey-level Difference Matrix (14), Grey-level Run-length Matrix (16), Grey-level Size Zone Matrix (16) and Neighbouring Grey-tone Difference Matrix (five). The analysis was based on a public dataset of lung nodules and open-access routines for feature extraction, which makes the study fully reproducible. Our results identified 30 features that had good or excellent stability relative to lesion delineation, 28 to intensity quanti...
2017
Standard computed tomography (CT) scan is performed on lung cancer patients for progression and lesion classification. However, low-dose CT (LDCT) is commonly used in lung cancer screening for high-risk people. Extensive studies have shown that computer-aided diagnosis (CAD) using standard CT could greatly improve the diagnostic accuracy of early lung cancer. Unlike standard CT imaging, the application of radiological texture features extracted by radiologists on LDCT imaging is not well established due to lower resolution and higher variations. The purpose of this study is to investigate possible diagnosis value of texture features by comparing the classification performance of radiologic reading with radiologic reading combined with computer-aided texture features. A total of 186 biopsy-confirmed control and lung cancer cases were obtained from the National Lung Screening Trial (NLST). Cases were matched by various clinical parameters including age, gender, smoking status, chronic obstructive pulmonary disease (COPD) status, body mass index (BMI) and image appearances. We compared the subjective diagnosis of benign/malignant with the consensus readings of three radiologists. We then developed a CAD framework that imports radiologic reading features and extracts CAD features for heterogeneity quantification and data analysis. A total of 1342 CAD features were extracted. After eliminating highly correlated and redundant features, the remaining 458 features were given to a random forest algorithm, and a predicted probability of malignancy score (Pm) was calculated. Patients were grouped into 140 training (70 biopsypositive for cancer and 70 negatives) and 46 testing (20 positives and 26 negatives) sets, and a threshold value over Pm (0.5) was then used to classify the test set into cancer and non-cancer. Clinical accuracy [sensitivity, specificity, positive predictive value (PPV), and negative predictive value (PV)] were [0.95, 0.88, 0.86, 0.96] and [0.70, 0.69, 0.64, 0.75] for the CAD and radiologic reading, respectively. The CAD framework incorporating the clinical reading with the texture features extracted from LDCT increased the PPV and reduced the false positive (FP) rate in the early diagnosis of lung cancer. This approach shows promise for improving the accuracy of lung cancer diagnosis in the clinical environment, especially in patients with well-established risk factors.
In 13-37% of cases, lung cancer patients treated with radiotherapy suffer from radiation induced lung disease, such as radiation induced pneumonitis. Three dimensional (3D) texture analysis, combined with patient-specific clinical parameters, were used to compute unique features (n=2138). Principal component analysis (PCA) was used to remove highly correlated features and a series of support vector machines (SVM) were used for classification in a leave one out scheme. On radiotherapy planning CT data of 57 patients, (14 symptomatic, 43 asymptomatic), the classifier obtained an area under the receiver operating curve of 0.873 with sensitivity, specificity and accuracy of 92%, 72% and 87% respectively. The combination of texture and clinical features demonstrates a statistically significant performance increase over the use of the clinical features alone. With further development the approach has the potential to be used to predict the likelihood of patients developing radiation induced pneumonitis in a clinical environment.
Quantitative imaging in medicine and surgery, 2017
The prediction of local recurrence (LR) of stage I non-small cell lung cancer (NSCLC) after definitive stereotactic body radiotherapy (SBRT) remains elusive. The purpose of this study was to assess whether quantitative imaging features on pre-treatment computed tomography (CT) can predict LR beyond 18 (F) fluorodeoxyglucose (F-FDG) positron emission tomography (PET)/CT maximum standard uptake value (SUV). This retrospective study evaluated 36 patients with 37 stage I NSCLC who had local tumor control (LC; n=19) and (LR; n=18). Textural features were extracted on pre-treatment CT. Mann-Whitney U tests were used to compare LC and LR groups. Receiver-operating characteristic (ROC) curves were constructed and the area under the curve (AUC) calculated with LR as outcome. Gray-level correlation and sum variance were greater in the LR group, compared with the LC group (P=0.02 and P=0.04, respectively). Gray-level difference variance was lower in the LR group (P=0.004). The logistic regress...
2013
Purpose: For nonsmall cell lung cancer (NSCLC) patients, quantitative image features extracted from computed tomography (CT) images can be used to improve tumor diagnosis, staging, and response assessment. For these findings to be clinically applied, image features need to have high intra and intermachine reproducibility. The objective of this study is to identify CT image features that are reproducible, nonredundant, and informative across multiple machines. Methods: Noncontrast-enhanced, test-retest CT image pairs were obtained from 56 NSCLC patients imaged on three CT machines from two institutions. Two machines (“M1” and “M2”) used cine 4D-CT and one machine (“M3”) used breath-hold helical 3D-CT. Gross tumor volumes (GTVs) were semiautonomously segmented then pruned by removing voxels with CT numbers less than a prescribed Hounsfield unit (HU) cutoff. Three hundred and twenty eight quantitative image features were extracted from each pruned GTV based on its geometry, intensity histogram, absolute gradient image, co-occurrence matrix, and run-length matrix. For each machine, features with concordance correlation coefficient values greater than 0.90 were considered reproducible. The Dice similarity coefficient (DSC) and the Jaccard index (JI) were used to quantify reproducible feature set agreement between machines. Multimachine reproducible feature sets were created by taking the intersection of individual machine reproducible feature sets. Redundant features were removed through hierarchical clustering based on the average correlation between features across multiple machines. Results: For all image types, GTV pruning was found to negatively affect reproducibility (reported results use no HU cutoff). The reproducible feature percentage was highest for average images (M1 = 90.5%, M2 = 94.5%, M1∩M2 = 86.3%), intermediate for end-exhale images (M1 = 75.0%, M2 = 71.0%, M1∩M2 = 52.1%), and lowest for breath-hold images (M3 = 61.0%). Between M1 and M2, the reproducible feature sets generated from end-exhale images were relatively machine-sensitive (DSC = 0.71, JI = 0.55), and the reproducible feature sets generated from average images were relatively machine-insensitive (DSC = 0.90, JI = 0.87). Histograms of feature pair correlation distances indicated that feature redundancy was machine-sensitive and image type sensitive. After hierarchical clustering, 38 features, 28 features, and 33 features were found to be reproducible and nonredundant for M1∩M2 (average images), M1∩M2 (end-exhale images), and M3, respectively. When blinded to the presence of test-retest images, hierarchical clustering showed that the selected features were informative by correctly pairing 55 out of 56 test-retest images using only their reproducible, nonredundant feature set values. Conclusions: Image feature reproducibility and redundancy depended on both the CT machine and the CT image type. For each image type, the authors found a set of cross-machine reproducible, nonredundant, and informative image features that would be useful for future image-based models. Compared to end-exhale 4D-CT and breath-hold 3D-CT, average 4D-CT derived image features showed superior multimachine reproducibility and are the best candidates for clinical correlation.
Non–Small Cell Lung Cancer: Histopathologic Correlates for Texture Parameters at CT
Radiology, 2013
Standard deviation (SD) of the histogram and mean value of the positive pixels (MPP) quantified from medium texture scale (1.8 to 3.0 mm in width) to coarse texture scale (3.6 mm in width) on CE-CT showed significant associations with tumor staining by Pimonidazole (coarse texture, SD, slope=0.003, p=0.0003). 2. Uniformity of the distribution of the positive pixels (UPP) for image features (medium to coarse texture) on non-CE CT showed a significant inverse association with tumor GLUT-1 expression (coarse texture, slope=-115.13, p=0.0008). 3. MPP quantified from medium to coarse texture on both non-CE and CE-CT showed significant inverse associations with tumor CD34 expression (non-CE CT: medium texture, slope=-0.0008, p=0.003 and CE-CT: medium texture, slope=-0.0006, p=0.004).
Cancer Imaging, 2010
The aim was to undertake an initial study of the relationship between texture features in computed tomography (CT) images of non-small cell lung cancer (NSCLC) and tumour glucose metabolism and stage. This retrospective pilot study comprised 17 patients with 18 pathologically confirmed NSCLC. Non-contrast-enhanced CT images of the primary pulmonary lesions underwent texture analysis in 2 stages as follows: (a) image filtration using Laplacian of Gaussian filter to differentially highlight fine to coarse textures, followed by (b) texture quantification using mean grey intensity (MGI), entropy (E) and uniformity (U) parameters. Texture parameters were compared with tumour fluorodeoxyglucose (FDG) uptake (standardised uptake value (SUV)) and stage as determined by the clinical report of the CT and FDG-positron emission tomography imaging. Tumour SUVs ranged between 2.8 and 10.4. The number of NSCLC with tumour stages I, II, III and IV were 4, 4, 4 and 6, respectively. Coarse texture features correlated with tumour SUV (E: r ¼ 0.51, p ¼ 0.03; U: r ¼ À0.52, p ¼ 0.03), whereas fine texture features correlated with tumour stage (MGI: r s ¼ 0.71, p ¼ 0.001; E: r s ¼ 0.55, p ¼ 0.02; U: r s ¼ À0.49, p ¼ 0.04). Fine texture predicted tumour stage with a kappa of 0.7, demonstrating 100% sensitivity and 87.5% specificity for detecting tumours above stage II ( p ¼ 0.0001). This study provides initial evidence for a relationship between texture features in NSCLC on non-contrast-enhanced CT and tumour metabolism and stage. Texture analysis warrants further investigation as a potential method for obtaining prognostic information for patients with NSCLC undergoing CT.