Dataset Information

Multi-window CT based Radiomic signatures in differentiating indolent versus aggressive lung cancers in the National Lung Screening Trial: a retrospective study.

ABSTRACT: BACKGROUND:We retrospectively evaluated the capability of radiomic features to predict tumor growth in lung cancer screening and compared the performance of multi-window radiomic features and single window radiomic features. METHODS:One hundred fifty lung nodules among 114 screen-detected, incident lung cancer patients from the National Lung Screening Trial (NLST) were investigated. Volume double time (VDT) was calculated as the difference between continuous two scans and used to define indolent and aggressive lung cancers. Lung nodules were semi-automatically segmented using lung and mediastinal windows separately, and subtracting the mediastinal window region from the lung window region generated the difference region. 364 radiomic features were separately exacted from nodules using the lung window, the mediastinal window and the difference region. Multivariable models were conducted to identify the most predictive features in predicting tumor growth. Clinical information was also obtained from the database. RESULTS:Based on our definition, 26% of the cases were indolent lung cancer. The tumor growth pattern could be predicted by radiomic models constructed using features obtained in the lung window, the difference region, and by combining features obtained in both the lung window and difference regions with areas under the receiver operator characteristic (AUROCs) of 0.799, 0.819, and 0.846, respectively. The multi-window feature model showed better performance compared to single window features (P < 0.001). Incorporating clinical factors into the multi-window feature models showed improvement, yielding an accuracy of 84.67% and AUROC of 0.855 for distinguishing indolent from aggressive disease. CONCLUSIONS:Multi-window CT based radiomics features are valuable predictors of indolent lung cancers and out performed single CT window setting. Combining clinical information improved predicting performance.

SUBMITTER: Lu H

PROVIDER: S-EPMC6599273 | biostudies-other | 2019 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Multi-window CT based Radiomic signatures in differentiating indolent versus aggressive lung cancers in the National Lung Screening Trial: a retrospective study.

Lu Hong H Mu Wei W Balagurunathan Yoganand Y Qi Jin J Abdalah Mahmoud A MA Garcia Alberto L AL Ye Zhaoxiang Z Gillies Robert J RJ Schabath Matthew B MB

Cancer imaging : the official publication of the International Cancer Imaging Society 20190628 1

<h4>Background</h4>We retrospectively evaluated the capability of radiomic features to predict tumor growth in lung cancer screening and compared the performance of multi-window radiomic features and single window radiomic features.<h4>Methods</h4>One hundred fifty lung nodules among 114 screen-detected, incident lung cancer patients from the National Lung Screening Trial (NLST) were investigated. Volume double time (VDT) was calculated as the difference between continuous two scans and used to ...[more]

PMID: 31253194

Similar Datasets

Project description:It is currently not known whether most lung cancers detected by computerized tomography (CT) screening are aggressive and likely to be fatal if left untreated, or if a sizable fraction are indolent and unlikely to cause death during the natural lifetime of the individual. We developed a longitudinal biologically-based model of the relationship between individual smoking histories and the probability for lung cancer incidence, CT screen detection, lung cancer mortality, and other-cause mortality. The longitudinal model relates these different outcomes to an underlying lung cancer disease pathway and an effective other-cause mortality pathway, which are both influenced by the individual smoking history. The longitudinal analysis provides additional information over that available if these outcomes were analyzed separately, including testing if the number of CT detected and histologically-confirmed lung cancers is consistent with the expected number of lung cancers "in the pipeline". We assume indolent nodules undergo Gompertz growth and are detectable by CT, but do not grow large enough to contribute significantly to symptom-based lung cancer incidence or mortality. Likelihood-based model calibration was done jointly to data from 6878 heavy smokers without asbestos exposure in the control (placebo) arm of the Carotene and Retinol Efficacy Trial (CARET); and to 3,642 heavy smokers with comparable smoking histories in the Pittsburgh Lung Screening Study (PLuSS), a single-arm prospective trial of low-dose spiral CT screening for diagnosis of lung cancer. Model calibration was checked using data from two other single-arm prospective CT screening trials, the New York University Lung Cancer Biomarker Center (NYU) (n=1,021), and Moffitt Cancer Center (Moffitt) cohorts (n=677). In the PLuSS cohort, we estimate that at the end of year 2, after the baseline and first annual CT exam, that 33.0 (26.9, 36.9)% of diagnosed lung cancers among females and 7.0 (4.9,11.7)% among males were overdiagnosed due to being indolent cancers. At the end of the PLuSS study, with maximum follow-up of 5.8 years, we estimate that due to early detection by CT and limited follow-up, an additional 2.2 (2.0,2.4)% of all diagnosed cancers among females and 7.1 (6.7,8.0)% among males would not have been diagnosed in the absence of CT screening. We also find a higher apparent cure rate for lung cancer among CARET females than males, consistent with the larger indolent fraction of CT detected and histologically confirmed lung cancers among PLuSS females. This suggests that there are significant gender differences in the aggressiveness of lung cancer. Females may have an inherently higher proportion of indolent lung cancers than males, or aggressive lung cancers may be brought into check by the immune system more frequently among females than males.

Project description:BackgroundDistinguishing men with aggressive from indolent prostate cancer is critical to decisions in the management of clinically localized prostate cancer. Molecular signatures of aggressive disease could help men overcome this major clinical challenge by reducing unnecessary treatment and allowing more appropriate treatment of aggressive disease.MethodsWe performed a mass spectrometry-based proteomic analysis of normal and malignant prostate tissues from 22 men who underwent surgery for prostate cancer. Prostate cancer samples included Grade Groups (3-5), with 8 patients experiencing recurrence and 14 without evidence of recurrence with a mean of 6.8 years of follow-up. To better understand the biological pathways underlying prostate cancer aggressiveness, we performed a systems biology analysis and gene enrichment analysis. Proteins that distinguished recurrent from nonrecurrent cancer were chosen for validation by immunohistochemical analysis on tissue microarrays containing samples from a larger cohort of patients with recurrent and nonrecurrent prostate cancer.ResultsIn all, 24,037 unique peptides (false discovery rate < 1%) corresponding to 3,313 distinct proteins were identified with absolute abundance ranges spanning seven orders of magnitude. Of these proteins, 115 showed significantly (p < 0.01) different levels in tissues from recurrent versus nonrecurrent cancers. Analysis of all differentially expressed proteins in recurrent and nonrecurrent cases identified several protein networks, most prominently one in which approximately 24% of the proteins in the network were regulated by the YY1 transcription factor (adjusted p < 0.001). Strong immunohistochemical staining levels of three differentially expressed proteins, POSTN, CALR, and CTSD, on a tissue microarray validated their association with shorter patient survival.ConclusionsThe protein signatures identified could improve understanding of the molecular drivers of aggressive prostate cancer and be used as candidate prognostic biomarkers.

Project description:Lung cancer can be classified into two main categories: small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC), which are different in treatment strategy and survival probability. The lung CT images of SCLC and NSCLC are similar such that their subtle differences are hardly visually discernible by the human eye through conventional imaging evaluation. We hypothesize that SCLC/NSCLC differentiation could be achieved via computerized image feature analysis and classification in feature space, as termed a radiomic model. The purpose of this study was to use CT radiomics to differentiate SCLC from NSCLC adenocarcinoma. Patients with primary lung cancer, either SCLC or NSCLC adenocarcinoma, were retrospectively identified. The post-diagnosis pre-treatment lung CT images were used to segment the lung cancers. Radiomic features were extracted from histogram-based statistics, textural analysis of tumor images and their wavelet transforms. A minimal-redundancy-maximal-relevance method was used for feature selection. The predictive model was constructed with a multilayer artificial neural network. The performance of the SCLC/NSCLC adenocarcinoma classifier was evaluated by the area under the receiver operating characteristic curve (AUC). Our study cohort consisted of 69 primary lung cancer patients with SCLC (n = 35; age mean ± SD = 66.91± 9.75 years), and NSCLC adenocarcinoma (n = 34; age mean ± SD = 58.55 ± 11.94 years). The SCLC group had more male patients and smokers than the NSCLC group (P < 0.05). Our SCLC/NSCLC classifier achieved an overall performance of AUC of 0.93 (95% confidence interval = [0.85, 0.97]), sensitivity = 0.85, and specificity = 0.85). Adding clinical data such as smoking history could improve the performance slightly. The top ranking radiomic features were mostly textural features. Our results showed that CT radiomics could quantitatively represent tumor heterogeneity and therefore could be used to differentiate primary lung cancer subtypes with satisfying results. CT image processing with the wavelet transformation technique enhanced the radiomic features for SCLC/NSCLC classification. Our pilot study should motivate further investigation of radiomics as a non-invasive approach for early diagnosis and treatment of lung cancer.

Project description:Background:A majority of prostate cancers (PCas) are indolent and cause no harm even without treatment. However, a significant proportion of patients with PCa have aggressive tumors that progress rapidly to metastatic disease and are often lethal. PCa develops through somatic mutagenesis, but emerging evidence suggests that germline genetic variation can markedly contribute to tumorigenesis. However, the causal association between genetic susceptibility and tumorigenesis has not been well characterized. The objective of this study was to map the germline and somatic mutation interaction landscape in indolent and aggressive tumors and to discover signatures of mutated genes associated with each type and distinguishing the two types of PCa. Materials and Methods:We integrated germline mutation information from genome-wide association studies (GWAS) with somatic mutation information from The Cancer Genome Atlas (TCGA) using gene expression data from TCGA on indolent and aggressive PCas as the intermediate phenotypes. Germline and somatic mutated genes associated with each type of PCa were functionally characterized using network and pathway analysis. Results:We discovered gene signatures containing germline and somatic mutations associated with each type and distinguishing the two types of PCa. We discovered multiple gene regulatory networks and signaling pathways enriched with germline and somatic mutations including axon guidance, RAR, WINT, MSP-RON, STAT3, PI3K, TR/RxR, and molecular mechanisms of cancer, NF-kB, prostate cancer, GP6, androgen, and VEGF signaling pathways for indolent PCa and MSP-RON, axon guidance, RAR, adipogenesis, and molecular mechanisms of cancer and NF-kB signaling pathways for aggressive PCa. Conclusion:The investigation revealed germline and somatic mutated genes associated with indolent and aggressive PCas and distinguishing the two types of PCa. The study revealed multiple gene regulatory networks and signaling pathways dysregulated by germline and somatic alterations. Integrative analysis combining germline and somatic mutations is a powerful approach to mapping germline and somatic mutation interaction landscape.

Project description:BackgroundInterstitial lung disease (ILD) defines a group of parenchymal lung disorders, characterized by fibrosis as their common final pathophysiological stage. To improve diagnosis and treatment of ILD, there is a need for repetitive non-invasive characterization of lung tissue by quantitative parameters. In this study, we investigated whether CT image patterns found in mice with bleomycin induced lung fibrosis can be translated as prognostic factors to human patients diagnosed with ILD.MethodsBleomycin was used to induce lung fibrosis in mice (n_control = 36, n_experimental = 55). The patient cohort consisted of 98 systemic sclerosis (SSc) patients (n_ILD = 65). Radiomic features (n_histogram = 17, n_texture = 137) were extracted from microCT (mice) and HRCT (patients) images. Predictive performance of the models was evaluated with the area under the receiver-operating characteristic curve (AUC). First, predictive performance of individual features was examined and compared between murine and patient data sets. Second, multivariate models predicting ILD were trained on murine data and tested on patient data. Additionally, the models were reoptimized on patient data to reduce the influence of the domain shift on the performance scores.ResultsPredictive power of individual features in terms of AUC was highly correlated between mice and patients (r = 0.86). A model based only on mean image intensity in the lung scored AUC = 0.921 ± 0.048 in mice and AUC = 0.774 (CI95% 0.677-0.859) in patients. The best radiomic model based on three radiomic features scored AUC = 0.994 ± 0.013 in mice and validated with AUC = 0.832 (CI95% 0.745-0.907) in patients. However, reoptimization of the model weights in the patient cohort allowed to increase the model's performance to AUC = 0.912 ± 0.058.ConclusionRadiomic signatures of experimental ILD derived from microCT scans translated to HRCT of humans with SSc-ILD. We showed that the experimental model of BLM-induced ILD is a promising system to test radiomic models for later application and validation in human cohorts.

Dataset Information

Multi-window CT based Radiomic signatures in differentiating indolent versus aggressive lung cancers in the National Lung Screening Trial: a retrospective study.

Publications

Multi-window CT based Radiomic signatures in differentiating indolent versus aggressive lung cancers in the National Lung Screening Trial: a retrospective study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets