Preliminary investigation into sources of uncertainty in quantitative imaging features
Introduction
Lung cancer is the leading cause of cancer deaths both globally and within the United States [1]. Non-small cell lung cancer (NSCLC) accounts for 85% of all lung cancer cases [2]. Survival rates in NSCLC have remained low despite progress in imaging and treatment techniques over the past forty years [1]. This problem is compounded by the substantial variability in outcomes among patients of the same stage or risk-group which can make choosing the optimal treatment strategy for any individual patient difficult. Because of these well-known statistics, a variety of research avenues have been explored to produce novel methods of predicting patient outcome or individualizing patient treatment. One method that has recently garnered a lot of attention is the use of image texture analysis to classify patients as high or low risk before they begin treatment.
Texture analysis is a computational method that assigns quantitative values to medical images of tumors. Textures are designed to assess the amount of heterogeneity or identify the patterns within a region of interest(ROI) [3], [4]. As a result, tumors with higher or lower values than a chosen threshold can be grouped and the results correlated to patient outcomes in order to predict survival. Several groups have demonstrated the usefulness of this technique in NSCLC [5], [6], [7], [8], [9], [10]. Taken together, these studies suggest image texture analysis may in future play a large role in the identification of patients with worse prognosis or high risk factors. This could substantially alter the way we select treatment regimens for NSCLC patients and potentially increase observed survival rates.
One obstacle to applying this technique in a clinical setting is the large level of uncertainty in whether features measured at different institutions can be fairly compared. Major sources of uncertainty for features measured from CT images of tumors encompass everything from imaging parameters (such as tube current, tube voltage, exposure, reconstruction algorithm, pixel dimensions, slice thickness, and CT manufacturer) to patient specific factors (such as motion artifacts and tumor size), to variations in feature measurement (such as ROI delineation, software, feature parameters, and pre-processing filters). Identifying the impact of each of these factors is nearly impossible due to the scale of the task and the fact that a ground truth does not exist for quantitative imaging features the way it might for histology or other imaging goals. However, a few of these factors could be controlled for if we knew that these factors have a substantial effect on extracted texture values. For example, while many studies have used textures measured from the entire tumor volume, certain studies used only the largest cross-sectional tumor slice [6], [11]. Whether the results from one technique can be applied to tumors delineated with the alternative technique is not known. Similarly, studies have not previously been conducted on the effect the choice of breathing phase for ROI delineation may have on an individual patient's measurement. It is also still not well understood how the choice of imaging parameters affects the values measured. Because imaging parameters are known to vary from institution to institution, current texture studies are limited to local patients imaged with the same technique. The only study attempting to probe this question found that tube voltage variations had a larger effect on measured values than changes in tube current when textures were measured from a water phantom [12]. However it is not known if this same relationship applies to heterogeneous images such as actual patient tumors.
Our study was designed in order to begin to investigate these specific issues and suggest guidelines for the comparison of texture values obtained under different or unknown conditions.
Section snippets
Patients
For this study, the 4D computed tomography (CT) thoracic scans of 20 patients with stage III NSCLC were obtained. These images are routinely collected as part of the radiation therapy treatment planning process. They are non-contrast images, as is routine in radiation therapy clinics. These images were selected because of the large number of published results demonstrating that image features calculated from non-contrast CT images may be used to predict patient outcomes [5], [6], [9], [11], [13]
Respiratory phase
Table 6 summarizes the results of the Wilcoxon signed rank tests after multiplicity correction comparing the texture values measured from the T50 phase images to the Tavg images and the other breathing phase images (T0–T90). Of the 28 total features, 12 were significantly different when they were measured from the Tavg versus the T50 phase images. The 12 significantly different features included at least one from every category but shape. Features measured from phases closer in time to T50 were
Respiratory phase
From our analysis, the choice of phase did not result in statistically significant differences in values. However, comparing texture values from the T50 and Tavg image sets did result in significant differences for half of the features, including one from each category except for shape. We suggest either the end-of-exhale (T50) or Tavg phase be used in future studies for consistency with already published results. Several features (standard deviation, kurtosis, skewness, all of the shape
Conclusion
Several studies have suggested that image texture analysis may be a useful tool for identifying non-small cell lung cancer (NSCLC) patients at high risk for poor survival. Before this technique can be clinically implemented, the effect of different approaches to measuring texture and of different imaging parameters must be analyzed to ensure features can be reliably and consistently evaluated. This paper investigated the susceptibility of texture features to four variables and may serve as a
Conflict of interest statement
We have no conflicts of interest to disclose.
Acknowledgment
Xenia Fave is a recipient of the AAPM and RSNA Doctoral Fellowship. Molly Cook is a recipient of the AAPM Summer Undergraduate Fellowship.
References (20)
- et al.
Non-small cell lung cancer: epidemiology, risk factors, treatment, and survivorship
Mayo Clin Proc
(2008) Texture analysis using gray level run lengths
Comput Graph Image Process
(1975)- et al.
Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image
Eur J Radiol
(2010) - et al.
Reproducibility and prognosis of quantitative features extracted from CT images
Transl Oncol
(2014) - et al.
CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma
Radiother Oncol
(2015) SEER stat fact sheets: lung and bronchus cancer
(2014)- et al.
Textural features for image classification
IEEE Trans Syst Man Cybern
(1973) - et al.
Texture analysis of non-small cell lung cancer on unenhanced computed tomography: initial evidence for a relationship with tumour glucose metabolism and stage
Cancer Imaging
(2010) - et al.
Tumour heterogeneity in non-small cell lung carcinoma assessed by CT texture analysis: a potential marker of survival
Eur Radiol
(2012) - et al.
Developing a classifier model for lung tumors in CT-scan images
Cited by (77)
The Promise and Future of Radiomics for Personalized Radiotherapy Dosing and Adaptation
2023, Seminars in Radiation OncologyInter-Reader Variability of Volumetric Subsolid Pulmonary Nodule Radiomic Features
2022, Academic RadiologyDosimetric Factors and Radiomics Features Within Different Regions of Interest in Planning CT Images for Improving the Prediction of Radiation Pneumonitis
2021, International Journal of Radiation Oncology Biology PhysicsRadiomics in breast cancer classification and prediction
2021, Seminars in Cancer BiologyRadiomics reproducibility challenge in computed tomography imaging as a nuisance to clinical generalization: a mini-review
2023, Egyptian Journal of Radiology and Nuclear Medicine