The National Lung Screening Trial (NLST) demonstrated that screening with low-dose computed tomography (LDCT) is associated with a 20% reduction in lung cancer mortality. One potential limitation of ...LDCT screening is overdiagnosis of slow growing and indolent cancers. In this study, peritumoral and intratumoral radiomics was used to identify a vulnerable subset of lung patients associated with poor survival outcomes. Incident lung cancer patients from the NLST were split into training and test cohorts and an external cohort of non-screen detected adenocarcinomas was used for further validation. After removing redundant and non-reproducible radiomics features, backward elimination analyses identified a single model which was subjected to Classification and Regression Tree to stratify patients into three risk-groups based on two radiomics features (NGTDM Busyness and Statistical Root Mean Square RMS). The final model was validated in the test cohort and the cohort of non-screen detected adenocarcinomas. Using a radio-genomics dataset, Statistical RMS was significantly associated with FOXF2 gene by both correlation and two-group analyses. Our rigorous approach generated a novel radiomics model that identified a vulnerable high-risk group of early stage patients associated with poor outcomes. These patients may require aggressive follow-up and/or adjuvant therapy to mitigate their poor outcomes.
Purpose
Many radiomics features were originally developed for non‐medical imaging applications and therefore original assumptions may need to be reexamined. In this study, we investigated the impact ...of slice thickness and pixel spacing (or pixel size) on radiomics features extracted from Computed Tomography (CT) phantom images acquired with different scanners as well as different acquisition and reconstruction parameters. The dependence of CT texture features on gray‐level discretization was also evaluated.
Methods and materials
A texture phantom composed of 10 different cartridges of different materials was scanned on eight different CT scanners from three different manufacturers. The images were reconstructed for various slice thicknesses. For each slice thickness, the reconstruction Field Of View (FOV) was varied to render pixel sizes ranging from 0.39 to 0.98 mm. A fixed spherical region of interest (ROI) was contoured on the images of the shredded rubber cartridge and the 3D printed, 20% fill, acrylonitrile butadiene styrene plastic cartridge (ABS20) for all phantom imaging sets. Radiomic features were extracted from the ROIs using an in‐house program. Features categories were: shape (10), intensity (16), GLCM (24), GLZSM (11), GLRLM (11), and NGTDM (5), fractal dimensions (8) and first‐order wavelets (128), for a total of 213 features. Voxel‐size resampling was performed to investigate the usefulness of extracting features using a suitably chosen voxel size. Acquired phantom image sets were resampled to a voxel size of 1 × 1 × 2 mm3 using linear interpolation. Image features were therefore extracted from resampled and original datasets and the absolute value of the percent coefficient of variation (%COV) for each feature was calculated. Based on the %COV values, features were classified in 3 groups: (1) features with large variations before and after resampling (%COV >50); (2) features with diminished variation (%COV <30) after resampling; and (3) features that had originally moderate variation (%COV <50%) and were negligibly affected by resampling. Group 2 features were further studied by modifying feature definitions to include voxel size. Original and voxel‐size normalized features were used for interscanner comparisons. A subsequent analysis investigated feature dependency on gray‐level discretization by extracting 51 texture features from ROIs from each of the 10 different phantom cartridges using 16, 32, 64, 128, and 256 gray levels.
Results
Out of the 213 features extracted, 150 were reproducible across voxel sizes, 42 improved significantly (%COV <30, Group 2) after resampling, and 21 had large variations before and after resampling (Group 1). Ten features improved significantly after definition modification effectively removed their voxel‐size dependency. Interscanner comparison indicated that feature variability among scanners nearly vanished for 8 of these 10 features. Furthermore, 17 out of 51 texture features were found to be dependent on the number of gray levels. These features were redefined to include the number of gray levels which greatly reduced this dependency.
Conclusion
Voxel‐size resampling is an appropriate pre‐processing step for image datasets acquired with variable voxel sizes to obtain more reproducible CT features. We found that some of the radiomics features were voxel size and gray‐level discretization‐dependent. The introduction of normalizing factors in their definitions greatly reduced or removed these dependencies.
Tumours rapidly ferment glucose to lactic acid even in the presence of oxygen, and coupling high glycolysis with poor perfusion leads to extracellular acidification. We hypothesise that acidity, ...independent from lactate, can augment the pro-tumour phenotype of macrophages.
We analysed publicly available data of human prostate cancer for linear correlation between macrophage markers and glycolysis genes. We used zwitterionic buffers to adjust the pH in series of in vitro experiments. We then utilised subcutaneous and transgenic tumour models developed in C57BL/6 mice as well as computer simulations to correlate tumour progression with macrophage infiltration and to delineate role of acidity.
Activating macrophages at pH 6.8 in vitro enhanced an IL-4-driven phenotype as measured by gene expression, cytokine profiling, and functional assays. These results were recapitulated in vivo wherein neutralising intratumoural acidity reduced the pro-tumour phenotype of macrophages, while also decreasing tumour incidence and invasion in the TRAMP model of prostate cancer. These results were recapitulated using an in silico mathematical model that simulate macrophage responses to environmental signals. By turning off acid-induced cellular responses, our in silico mathematical modelling shows that acid-resistant macrophages can limit tumour progression.
This study suggests that tumour acidity contributes to prostate carcinogenesis by altering the state of macrophage activation.
The aim of this study was to determine whether quantitative analyses (“radiomics”) of low-dose computed tomography lung cancer screening images at baseline can predict subsequent emergence of cancer.
...Public data from the National Lung Screening Trial (ACRIN 6684) were assembled into two cohorts of 104 and 92 patients with screen-detected lung cancer and then matched with cohorts of 208 and 196 screening subjects with benign pulmonary nodules. Image features were extracted from each nodule and used to predict the subsequent emergence of cancer.
The best models used 23 stable features in a random forests classifier and could predict nodules that would become cancerous 1 and 2 years hence with accuracies of 80% (area under the curve 0.83) and 79% (area under the curve 0.75), respectively. Radiomics outperformed the Lung Imaging Reporting and Data System and volume-only approaches. The performance of the McWilliams risk assessment model was commensurate.
The radiomics of lung cancer screening computed tomography scans at baseline can be used to assess risk for development of cancer.
Pulmonary nodules are frequently detected radiological abnormalities in lung cancer screening. Nodules of the highest- and lowest-risk for cancer are often easily diagnosed by a trained radiologist ...there is still a high rate of indeterminate pulmonary nodules (IPN) of unknown risk. Here, we test the hypothesis that computer extracted quantitative features ("radiomics") can provide improved risk-assessment in the diagnostic setting. Nodules were segmented in 3D and 219 quantitative features are extracted from these volumes. Using these features novel malignancy risk predictors are formed with various stratifications based on size, shape and texture feature categories. We used images and data from the National Lung Screening Trial (NLST), curated a subset of 479 participants (244 for training and 235 for testing) that included incident lung cancers and nodule-positive controls. After removing redundant and non-reproducible features, optimal linear classifiers with area under the receiver operator characteristics (AUROC) curves were used with an exhaustive search approach to find a discriminant set of image features, which were validated in an independent test dataset. We identified several strong predictive models, using size and shape features the highest AUROC was 0.80. Using non-size based features the highest AUROC was 0.85. Combining features from all the categories, the highest AUROC were 0.83.
Two CT features were developed to quantitatively describe lung adenocarcinomas by scoring tumor shape complexity (feature 1: convexity) and intratumor density variation (feature 2: entropy ratio) in ...routinely obtained diagnostic CT scans. The developed quantitative features were analyzed in two independent cohorts (cohort 1: n = 61; cohort 2: n = 47) of patients diagnosed with primary lung adenocarcinoma, retrospectively curated to include imaging and clinical data. Preoperative chest CTs were segmented semi-automatically. Segmented tumor regions were further subdivided into core and boundary sub-regions, to quantify intensity variations across the tumor. Reproducibility of the features was evaluated in an independent test-retest dataset of 32 patients. The proposed metrics showed high degree of reproducibility in a repeated experiment (concordance, CCC≥0.897; dynamic range, DR≥0.92). Association with overall survival was evaluated by Cox proportional hazard regression, Kaplan-Meier survival curves, and the log-rank test. Both features were associated with overall survival (convexity: p = 0.008; entropy ratio: p = 0.04) in Cohort 1 but not in Cohort 2 (convexity: p = 0.7; entropy ratio: p = 0.8). In both cohorts, these features were found to be descriptive and demonstrated the link between imaging characteristics and patient survival in lung adenocarcinoma.
We propose a systematic methodology to quantify incidentally identified pulmonary nodules based on observed radiological traits (semantics) quantified on a point scale and a machine-learning method ...using these data to predict cancer status.
We investigated 172 patients who had low-dose CT images, with 102 and 70 patients grouped into training and validation cohorts, respectively. On the images, 24 radiological traits were systematically scored and a linear classifier was built to relate the traits to malignant status. The model was formed both with and without size descriptors to remove bias due to nodule size. The multivariate pairs formed on the training set were tested on an independent validation data set to evaluate their performance.
The best 4-feature set that included a size measurement (set 1), was short axis, contour, concavity, and texture, which had an area under the receiver operator characteristic curve (AUROC) of 0.88 (accuracy = 81%, sensitivity = 76.2%, specificity = 91.7%). If size measures were excluded, the four best features (set 2) were location, fissure attachment, lobulation, and spiculation, which had an AUROC of 0.83 (accuracy = 73.2%, sensitivity = 73.8%, specificity = 81.7%) in predicting malignancy in primary nodules. The validation test AUROC was 0.8 (accuracy = 74.3%, sensitivity = 66.7%, specificity = 75.6%) and 0.74 (accuracy = 71.4%, sensitivity = 61.9%, specificity = 75.5%) for sets 1 and 2, respectively.
Radiological image traits are useful in predicting malignancy in lung nodules. These semantic traits can be used in combination with size-based measures to enhance prediction accuracy and reduce false-positives.
.
Ongoing intratumoral evolution is apparent in molecular variations among cancer cells from different regions of the same tumor, but genetic data alone provide little insight into environmental ...selection forces and cellular phenotypic adaptations that govern the underlying Darwinian dynamics. In three spontaneous murine cancers (prostate cancers in TRAMP and PTEN mice, pancreatic cancer in KPC mice), we identified two subpopulations with distinct niche construction adaptive strategies that remained stable in culture: (i) invasive cells that produce an acidic environment via upregulated aerobic glycolysis; and (ii) noninvasive cells that were angiogenic and metabolically near-normal. Darwinian interactions of these subpopulations were investigated in TRAMP prostate cancers. Computer simulations demonstrated invasive, acid-producing (C2) cells maintain a fitness advantage over noninvasive, angiogenic (C3) cells by promoting invasion and reducing efficacy of immune response. Immunohistochemical analysis of untreated tumors confirmed that C2 cells were invariably more abundant than C3 cells. However, the C2 adaptive strategy phenotype incurred a significant cost due to inefficient energy production (i.e., aerobic glycolysis) and depletion of resources for adaptations to an acidic environment. Mathematical model simulations predicted that small perturbations of the microenvironmental extracellular pH (pHe) could invert the cost/benefit ratio of the C2 strategy and select for C3 cells.
, 200 mmol/L NaHCO
added to the drinking water of 4-week-old TRAMP mice increased the intraprostatic pHe by 0.2 units and promoted proliferation of noninvasive C3 cells, which remained confined within the ducts so that primary cancer did not develop. A 0.2 pHe increase in established tumors increased the fraction of C3 cells and signficantly diminished growth of primary and metastatic tumors. In an experimental tumor construct, MCF7 and MDA-MB-231 breast cancer cells were coinjected into the mammary fat pad of SCID mice. C2-like MDA-MB-231 cells dominated in untreated animals, but C3-like MCF7 cells were selected and tumor growth slowed when intratumoral pHe was increased. Overall, our data support the use of mathematical modeling of intratumoral Darwinian interactions of environmental selection forces and cancer cell adaptive strategies. These models allow the tumor to be steered into a less invasive pathway through the application of small but selective biological force.
.
Abstract We study the reproducibility of quantitative imaging features that are used to describe tumor shape, size, 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, 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 (CCCTreT ). 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 CCCTreT and DR ≥ 0.9 and R2Bet ≥ 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).