Search

BACKGROUND: Image-based biomarkers could have translational implications by characterizing tumor behavior of lung cancers diagnosed during lung cancer screening. In this study, peritumoral and intratumoral radiomics and volume doubling time (VDT) were used to identify high-risk subsets of lung patients diagnosed in lung cancer screening that are associated with poor survival outcomes. METHODS: Data and images were acquired from the National Lung Screening Trial. VDT was calculated between two consequent screening intervals approximately 1 year apart; peritumoral and intratumoral radiomics were extracted from the baseline screen. Overall survival (OS) was the main endpoint. Classification and Regression Tree analyses identified the most predictive covariates to classify patient outcomes. RESULTS: Decision tree analysis stratified patients into three risk-groups (low, intermediate, and high) based on VDT and one radiomic feature (compactness). High-risk patients had extremely poor survival outcomes (hazard ratio [HR] = 8.15; 25% 5-year OS) versus low-risk patients (HR = 1.00; 83.3% 5-year OS). Among early-stage lung cancers, high-risk patients had poor survival outcomes (HR = 9.07; 44.4% 5-year OS) versus the low-risk group (HR = 1.00; 90.9% 5-year OS). For VDT, the decision tree analysis identified a novel cut-point of 279 days and using this cut-point VDT alone discriminated between aggressive (HR = 4.18; 45% 5-year OS) versus indolent/low-risk cancers (HR = 1.00; 82.8% 5-year OS). CONCLUSION: We utilized peritumoral and intratumoral radiomic features and VDT to generate a model that identify a high-risk group of screen-detected lung cancers associated with poor survival outcomes. These vulnerable subset of screen-detected lung cancers may be candidates for more aggressive surveillance/follow-up and treatment, such as adjuvant therapy.

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. In vivo, 200 mmol/L NaHCO3 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. Cancer Res; 77(9); 2242–54. ©2017 AACR.

Supplementary Table S1 from Gene expression profiling-based identification of cell-surface targets for developing multimeric ligands in pancreatic cancer

Simultaneous video of four simulations of tumor growth with accompanying phenotypic "flow" diagram, Top left: untreated; top right: low dose, early; bottom left: high dose, late; bottom right: low dose, late. The appearance of the white box in each of the treated windows indicates when the buffer treatment was applied (all vessels secrete buffer). In the phenotype flow plot, the cyan dot shows the median phenotype of all tumor cells, black points indicate distribution of phenotypes present in the tumor at each time point. The simulations show that the buffer therapy reverses the evolution towards the glycolytic, acid-resistant phenotype, with early or high dose having the stronger effect. A late, low dose does have an effect on the progression, but the invasive phenotype persists despite the therapy and will eventually dominate.

Supplemental material contains additional details of tumor imaging and mathematical models. Supplemental figures demonstrating results from experimental and computational studies referenced in the manuscript are included

Multimeric ligands are ligands that contain multiple binding domains that simultaneously target multiple cell-surface proteins. Due to cooperative binding, multimeric ligands can have high avidity for cells (tumor) expressing all targeting proteins and only show minimal binding to cells (normal tissues) expressing none or only some of the targets. Identifying combinations of targets that concurrently express in tumor cells but not in normal cells is a challenging task. Here, we describe a novel approach for identifying such combinations using genome-wide gene expression profiling followed by immunohistochemistry. We first generated a database of mRNA gene expression profiles for 28 pancreatic cancer specimens and 103 normal tissue samples representing 28 unique tissue/cell types using DNA microarrays. The expression data for genes that encode proteins with cell-surface epitopes were then extracted from the database and analyzed using a novel multivariate rule-based computational approach to identify gene combinations that are expressed at an efficient binding level in tumors but not in normal tissues. These combinations were further ranked according to the proportion of tumor samples that expressed the sets at efficient levels. Protein expression of the genes contained in the top ranked combinations was confirmed using immunohistochemistry on a pancreatic tumor tissue and normal tissue microarrays. Coexpression of targets was further validated by their combined expression in pancreatic cancer cell lines using immunocytochemistry. These validated gene combinations thus encompass a list of cell-surface targets that can be used to develop multimeric ligands for the imaging and treatment of pancreatic cancer. [Mol Cancer Ther 2008;7(9):3071–80]

PDF file - 287K, Figure S1: Photomicrographs of cells in this study. HMEC, HCT116/GFP and MDAmb231 cells were grown to 70-80% confluency. Samples were then viewed with an automated Zeiss Observer Z.1 inverted microscope through a 10x /0.3NA or 20x/0.4NA objective and a phase contrast ring. Images were produced using the AxioCam MRm CCD camera and Axiovision version 4.6 software suite. (Carl Zeiss Inc., Germany).

PDF file - 241K, Figure S7: Segmentation and analysis of vasculature In vivo. In vivo vessels and tumors were independently segmented and quantified within four ordinal quadrants emanating from the tumor centroid as described in Methods.

PDF file - 81K, Figure S10: Inhibition of tumor growth as a result of NaHCO3 treatment. Tumor area was measured at days 4 and 13 by fluorescent pixel number using Image-Pro Plus v6.2. The mean growth illustrated a significant increase in size of the control tumor over 2 weeks (p

PDF file - 43K, Figure S5: Relation between tumor growth and pH for all 5 mice. Data for all 5 mice were parsed as in figure 2D wherein the growth (in pixels) and pH were calculated every 22.5o of arc. These data show that growth increased with decreasing pH for all animals, and that there was a threshold of pH above which no growth occurred. Lines represent the trend below threshold for each mouse.

PDF file - 77K, Figure S4: Quantification of tumor growth. Images are shown for mouse tumor #23 on day 4 (green) and day 14 (red). Images were co-registered using the ring clip of the DWC as a fiducial. The centroid of the tumor on day 4 was calculated and radial lines were drawn every 22.5o of arc, beginning at the ring. Growth was calculated as the number of pixels that the day 14 tumor extended beyond the edge of the day 4 tumor using Definiens Developer XD�.

PDF file - 45K, Figure S2: Comparison of normal vs tumor cells by size. Using these phase contrast images, ROI were chosen and area of cells was determined by pixel number using Image-Pro Plus v6.2. Once area was measured, data analysis revealed statistical significance (p

PDF file - 50K, Figure S6: Ex vivo comparison of vessel density in stroma vs tumor tissue. Using the Image Scope v7.1 regions of viable tumor were manually selected. 200�m micrometers were placed around the circumference of the tumor region perpendicular to the tumor edge. A second manually selected region was drawn around the perimeter of the micrometers. This effectively segments the entire tissue section into three regions of interest; the tumor, the edge within 200�m of the tumor and the distant stromal region. The Aperio (Vista, CA, USA) microvessel algorithm v1.0 was used with the following parameters (smoothing 2; dark threshold160; light threshold 210; regioning 6; completion 7) to identify the vascular density which was defined as the vessel area divided by total area (�m2).

PDF file - 88K

PDF file - 45K, Figure S8: In vivo relation between vessel density and tumor growth. The data from Figure S5 were used to compare tumor growth (change in number of pixels from day 4 to day 13) to vessel density (on day 4) in each of the 4 quadrants.

PDF file - 46K, Figure S3: Growth of MDAmb231 tumor within the dorsal window chamber. Mean growth of MDAmb23/GFP tumors within the dorsal window chamber. Cells were embedded in a 0.8 mg/mL collagen type 1 matrix followed by inoculation into the window chamber. Tumor area was measured at days 2, 3, and 16 by counting the number of pixels. Tumor area measured by fluorescence pixel number obtained using Image-Pro Plus 6.2.

The Metabolic Tumor Volume (MTV) and Tumor Lesion Glycolysis (TLG) has been shown to be independent prognostic predictors for clinical outcome in Diffuse Large B-cell Lymphoma (DLBCL). However, definitions of these measurements have not been standardized, leading to many sources of variation, operator evaluation continues to be one major source. In this study, we propose a reader reproducibility study to evaluate computation of TMV (& TLG) metrics based on differences in lesion delineation. In the first approach, reader manually corrected regional boundaries after automated detection performed across the lesions in a body scan (Reader M using a manual process, or manual). The other reader used a semi-automated method of lesion identification, without any boundary modification (Reader A using a semi- automated process, or auto). Parameters for active lesion were kept the same, derived from standard uptake values (SUVs) over a 41% threshold. We systematically contrasted MTV & TLG differences between expert readers (Reader M & A). We find that MTVs computed by Readers M and A were both concordant between them (concordant correlation coefficient of 0.96) and independently prognostic with a P-value of 0.0001 and 0.0002 respectively for overall survival after treatment. Additionally, we find TLG for these reader approaches showed concordance (CCC of 0.96) and was prognostic for over -all survival (p ≤ 0.0001 for both). In conclusion, the semi-automated approach (Reader A) provides acceptable quantification & prognosis of tumor burden (MTV) and TLG in comparison to expert reader assisted measurement (Reader M) on PET/CT scans.

Prostate gland segmentation is the primary step to estimate gland volume, which aids in the prostate disease management. In this study, we present a 2D-3D convolutional neural network (CNN) ensemble that automatically segments the whole prostate gland along with the peripheral zone (PZ) (PPZ-SegNet) using a T2-weighted sequence (T2W) of Magnetic Resonance Imaging (MRI). The study used 4 different public data sets organized as Train #1 and Test #1 (independently derived from the same cohort), Test #2, Test #3 and Test #4. The prostate gland and the peripheral zone (PZ) anatomy were manually delineated with consensus read by a radiologist, except for Test #4 cohorts that had pre-marked glandular anatomy. A Bayesian hyperparameter optimization method was applied to construct the network model (PPZ-SegNet) with a training cohort (Train #1, n = 150) using a five-fold cross validation. The model evaluation was performed on an independent cohort of 283 T2W MRI prostate cases (Test #1 to #4) without any additional tuning. The data cohorts were derived from The Cancer Imaging Archives (TCIA): PROSTATEx Challenge, Prostatectomy, Repeatability studies and PROMISE12-Challenge. The segmentation performance was evaluated by computing the Dice similarity coefficient and Hausdorff distance between the estimated-deep-network identified regions and the radiologist-drawn annotations. The deep network architecture was able to segment the prostate gland anatomy with an average Dice score of 0.86 in Test #1 (n = 192), 0.79 in Test #2 (n = 26), 0.81 in Test #3 (n = 15), and 0.62 in Test #4 (n = 50). We also found the Dice coefficient improved with larger prostate volumes in 3 of the 4 test cohorts. The variation of the Dice scores from different cohorts of test images suggests the necessity of more diverse models that are inclusive of dependencies such as the gland sizes and others, which will enable us to develop a universal network for prostate and PZ segmentation. Our training and evaluation code can be accessed through the link: https://github.com/mariabaldeon/PPZ-SegNet.git.

BACKGROUND. Higher categories of background parenchymal enhancement (BPE) increase breast cancer risk. However, current clinical BPE categorization is subjective. OBJECTIVE. Using a semiautomated segmentation algorithm, we calculated quantitative BPE measures and investigated the utility of individual features and feature pairs in significantly predicting subsequent breast cancer risk compared with radiologist-assigned BPE category. METHODS. In this retrospective case-control study, we identified 95 women at high risk of breast cancer but without a personal history of breast cancer who underwent breast MRI. Of these women, 19 subsequently developed breast cancer and were included as cases. Each case was age matched to four control patients (76 control patients total). Sociodemographic characteristics were compared between the cases and matched control patients using the Mann-Whitney U test. From each dynamic contrast-enhanced MRI examination, quantitative fibroglandular tissue and BPE measures were computed by averaging enhancing voxels above enhancement ratio thresholds (0–100%), totaling the enhancing volume above thresholds (BPE volume in cm(3)), and estimating the percentage of enhancing tissue above thresholds relative to total breast volume (BPE%) on each gadolinium-enhanced phase. For the 91 imaging features generated, we compared predictive performance using conditional logistic regression with 80:20 holdout cross validation and ROC curve analysis. ROC AUC was the figure of merit. Sensitivity, specificity, PPV, and NPV were also computed. All feature pairs were exhaustively searched to identify those with the highest AUC and Youden index. A DeLong test was used to compare predictive performance (AUCs). RESULTS. Women subsequently diagnosed with breast cancer were more likely to have mild, moderate, or marked BPE (odds ratio, 3.0; 95% CI, 0.9–10.0; p = .07). According to ROC curve analysis, a BPE category threshold greater than minimal resulted in a maximized AUC (0.62) in distinguishing cases from control patients. Compared with BPE category, the first gadolinium-enhanced (phase 1) BPE% at the 30% and 40% enhancement ratio thresholds yielded significantly higher AUC values of 0.85 (p = .0007) and 0.84 (p = .0004), respectively. Feature combinations showed similar AUC values with improved sensitivity. CONCLUSION. Preliminary data indicate that quantitative BPE measures may outperform radiologist-assigned category in breast cancer risk prediction. CLINICAL IMPACT. Future risk prediction models that incorporate quantitative measures warrant additional investigation.

Histopathological classification in prostate cancer remains a challenge with high dependence on the expert practitioner. We develop a deep learning (DL) model to identify the most prominent Gleason pattern in a highly curated data cohort and validate it on an independent dataset. The histology images are partitioned in tiles (14,509) and are curated by an expert to identify individual glandular structures with assigned primary Gleason pattern grades. We use transfer learning and fine-tuning approaches to compare several deep neural network architectures that are trained on a corpus of camera images (ImageNet) and tuned with histology examples to be context appropriate for histopathological discrimination with small samples. In our study, the best DL network is able to discriminate cancer grade (GS3/4) from benign with an accuracy of 91%, F1-score of 0.91 and AUC 0.96 in a baseline test (52 patients), while the cancer grade discrimination of the GS3 from GS4 had an accuracy of 68% and AUC of 0.71 (40 patients).

Background: Lymphoma is a common primary malignancy consisting of a heterogeneous collection of lymphoid neoplasms. Diffuse large B-cell lymphoma (DLBCL) is the most common, aggressive disease form that accounts for 30% of all lymphoma cases. The disease spreads systemically to involve organs other than lymph nodes 40% of the time, with 5-year survival of about 38% for intermediate grade disease. Recent development in chimeric antigen receptor (CAR) T-cell therapy has shown tremendous promise in providing a cure to patients with relapsed/refractory (R/R) DLBCL. We propose to develop an image-based biomarker to identify patients that would respond to engineer edcell-based treatments. Methods: We identified a cohort of 58 patients with R/R DLBCL, whose largest lesions on the baseline positron emission tomography/computed tomography (PET/CT) imaging were identified along with their anatomical sites related to non-lymphatics. The lesion’s co-registered PET imaging was used to converge on a regional boundary to obtain the most active part of the lesion, applying Standardized Uptake Value definition with 41% regional threshold. The lesion regions were characterized using imaging metrics (radiomics) broadly categorized into: Size (n=38), Shape (n=9), Texture (n=259),followed by principal component (PC) analysis to reduce the dimensionality in each of the feature categories. These Radiomics metrics along with whole body metabolic tumor volume (MTV) were used both collectively and independently to assess risk to disease progression measured by overall survival using Cox-regression model. We also compared the Radiomic metrics to MTV to identify linear dependency measured by Coefficient of Determination (R2). Results: PET scans shape features (extra nodal) that describes compactness to sphericity, represented as a principal component across the samples had a 21% increased risk to disease progression compared to 15% using MTV, with a CI of [1.0487, 1.417] and [1.04, 1.30] respectively. Patients have a median follow up of 1 year after CAR-T treatment. Shape-PC (Non-Lymph) lesions were not related to MTV with a correlation coefficient of 41.8% (R2 of 0.0725). Most non lymphatic lesions (top three sites) in our cohort were from lung, bone and liver. Patients with no non- lymphatic lesions were not part of this cohort. Conclusion: We identified Non-Size based features that are prognostic to patient response to treatment. These metrics provide complementary information to MTV and may serve as a surrogate to treatment response. Our features would require a secondary validation in a larger cohort prior to clinical use. Citation Format: Yoganand Balagurunathan, Zhouping Wei, Jin Qi, Erin Dean, Zachary Thompson, Jung Choi, Frederick Locke. Shape features of extra-nodal lesions on positron emission tomography identifies responders to CAR-T-cell therapy. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5612.

Rationale and objectives Evaluate ability of radiological semantic traits assessed on multi-window computed tomography (CT) to predict lung cancer risk. Materials and methods A total of 199 participants were investigated, including 60 incident lung cancers and 139 benign positive controls. Twenty lung window features and 2 mediastinal window features were extracted and scored on a point scale in three screening rounds. Multivariate logistic regression analysis was used to explore the association of these radiological traits with the risk of developing lung cancer. The areas under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive predictive value (PPV) were computed to evaluate the best predictive model. Results Combining mediastinal window-specific features with the lung window features-based model significantly improves performance compared to individual window features. Model performance is consistent both at baseline and the first follow-up scan, with an AUROC increased from 0.822 to 0.871 (p = 0.009) and from 0.877 to 0.917 (p = 0.008), respectively, for single to multi-window feature models. We also find that the multi-window CT based model showed better specificity and PPV, with PPV at the second follow-up scan improved to 0.953. Conclusion We find combining window semantic features improves model performance in identifying cancerous nodules. We also find that lung window features are more informative compared to mediastinal features in predicting malignancy.

High metabolic tumor volume (MTV) predicts worse outcomes in lymphoma treated with chemotherapy. However, it is unknown if this holds for patients treated with axicabtagene ciloleucel (axi-cel), an anti-CD19 targeted chimeric antigen receptor T-cell therapy. The primary objective of this retrospective study was to investigate the relationship between MTV and survival (overall survival [OS] and progression-free survival [PFS]) in patients with relapsed/refractory large B-cell lymphoma (LBCL) treated with axi-cel. Secondary objectives included finding the association of MTV with response rates and toxicity. The MTV values on baseline positron emission tomography of 96 patients were calculated via manual methodology using commercial software. Based on a median MTV cutoff value of 147.5 mL in the first cohort (n = 48), patients were divided into high and low MTV groups. Median follow-up for survivors was 24.98 months (range, 10.59-51.02 months). Patients with low MTV had significantly superior OS (hazard ratio [HR], 0.25; 95% confidence interval [CI], 0.10-0.66) and PFS (HR, 0.40; 95% CI, 0.18-0.89). Results were successfully validated in a second cohort of 48 patients with a median follow-up for survivors of 12.03 months (range, 0.89-25.74 months). Patients with low MTV were found to have superior OS (HR, 0.14; 95% CI, 0.05-0.42) and PFS (HR, 0.29; 95% CI, 0.12-0.69). In conclusion, baseline MTV is associated with OS and PFS in axi-cel recipients with LBCL.

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.

BACKGROUND Intraductal papillary mucinous neoplasms (IPMNs) are non-invasive pancreatic precursor lesions that can potentially develop into invasive pancreatic ductal adenocarcinoma. Currently, the International Consensus Guidelines (ICG) for IPMNs provides the basis for evaluating suspected IPMNs on computed tomography (CT) imaging. Despite using the ICG, it remains challenging to accurately predict whether IPMNs harbor high grade or invasive disease which would warrant surgical resection. A supplementary quantitative radiological tool, radiomics, may improve diagnostic accuracy of radiological evaluation of IPMNs. We hypothesized that using CT whole lesion radiomics features in conjunction with the ICG could improve the diagnostic accuracy of predicting IPMN histology. AIM To evaluate whole lesion CT radiomic analysis of IPMNs for predicting malignant histology compared to International Consensus Guidelines. METHODS Fifty-one subjects who had pancreatic surgical resection at our institution with histology demonstrating IPMN and available preoperative CT imaging were included in this retrospective cohort. Whole lesion semi-automated segmentation was performed on each preoperative CT using Healthmyne software (Healthmyne, Madison, WI). Thirty-nine relevant radiomic features were extracted from each lesion on each available contrast phase. Univariate analysis of the 39 radiomics features was performed for each contrast phase and values were compared between malignant and benign IPMN groups using logistic regression. Conventional quantitative and qualitative CT measurements were also compared between groups, via χ2 (categorical) and Mann Whitney U (continuous) variables. RESULTS Twenty-nine subjects (15 males, age 71 ± 9 years) with high grade or invasive tumor histology comprised the "malignant" cohort, while 22 subjects (11 males, age 70 ± 7 years) with low grade tumor histology were included in the "benign" cohort. Radiomic analysis showed 18/39 precontrast, 19/39 arterial phase, and 21/39 venous phase features differentiated malignant from benign IPMNs (P < 0.05). Multivariate analysis including only ICG criteria yielded two significant variables: thickened and enhancing cyst wall and enhancing mural nodule < 5 mm with an AUC (95%CI) of 0.817 (0.709-0.926). Multivariable post contrast radiomics achieved an AUC (95%CI) of 0.87 (0.767-0.974) for a model including arterial phase radiomics features and 0.834 (0.716-0.953) for a model including venous phase radiomics features. Combined multivariable model including conventional variables and arterial phase radiomics features achieved an AUC (95%CI) of 0.93 (0.85-1.0) with a 5-fold cross validation AUC of 0.90. CONCLUSION Multi-phase CT radiomics evaluation could play a role in improving predictive capability in diagnosing malignancy in IPMNs. Future larger studies may help determine the clinical significance of our findings.

Lung cancer is the most common fatal malignancy in adults worldwide, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer diagnoses. Computed tomography (CT) is routinely used in clinical practice to determine lung cancer treatment and assess prognosis. Here, we developed LungNet, a shallow convolutional neural network for predicting outcomes of NSCLC patients. We trained and evaluated LungNet on four independent cohorts of NSCLC patients from four medical centers: Stanford Hospital (n = 129), H. Lee Moffitt Cancer Center and Research Institute (n = 185), MAASTRO Clinic (n = 311) and Charite - Universitatsmedizin (n=84). We show that outcomes from LungNet are predictive of overall survival in all four independent survival cohorts as measured by concordance indices of 0.62, 0.62, 0.62 and 0.58 on cohorts 1, 2, 3, and 4, respectively. Further, the survival model can be used, via transfer learning, for classifying benign vs malignant nodules on the Lung Image Database Consortium (n = 1010), with improved performance (AUC=0.85) versus training from scratch (AUC=0.82). LungNet can be used as a noninvasive predictor for prognosis in NSCLC patients and can facilitate interpretation of CT images for lung cancer stratification and prognostication.

Microvascular disease is frequently found in major pathologies affecting vital organs, such as the brain, heart, and kidneys. While imaging modalities, such as ultrasound, computed tomography, single photon emission computed tomography, and magnetic resonance imaging, are widely used to visualize vascular abnormalities, the ability to non-invasively assess an organ’s total vasculature, including microvasculature, is often limited or cumbersome. Previously, we have demonstrated proof of concept that non-invasive imaging of the total mouse vasculature can be achieved with 18F-fluorodeoxyglucose (18F-FDG)-labeled human erythrocytes and positron emission tomography/computerized tomography (PET/CT). In this work, we demonstrate that changes in the total vascular volume of the brain and left ventricular myocardium of normal rats can be seen after pharmacological vasodilation using 18F-FDG-labeled rat red blood cells (FDG RBCs) and microPET/CT imaging. FDG RBC PET imaging was also used to approximate the location of myocardial injury in a surgical myocardial infarction rat model. Finally, we show that FDG RBC PET imaging can detect relative differences in the degree of drug-induced intra-myocardial vasodilation between diabetic rats and normal controls. This FDG-labeled RBC PET imaging technique may thus be useful for assessing microvascular disease pathologies and characterizing pharmacological responses in the vascular bed of interest.

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

Rationale- Patients with indeterminate pulmonary nodules (IPNs) at risk of cancer undergo high rates of invasive, costly, and morbid procedures. Objectives: To train and externally validate a risk ...

Standard-of-care multiparameter magnetic resonance imaging (MRI) scans of the brain were used to objectively subdivide glioblastoma multiforme (GBM) tumors into regions that correspond to variations in blood flow, interstitial edema, and cellular density. We hypothesized that the distribution of these distinct tumor ecological “habitats” at the time of presentation will impact the course of the disease. We retrospectively analyzed initial MRI scans in 2 groups of patients diagnosed with GBM, a long-term survival group comprising subjects who survived &gt, 36 month postdiagnosis, and a short-term survival group comprising subjects who survived ≤19 month postdiagnosis. The single-institution discovery cohort contained 22 subjects in each group, while the multi-institution validation cohort contained 15 subjects per group. MRI voxel intensities were calibrated, and tumor voxels clustered on contrast-enhanced T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images into 6 distinct “habitats” based on low- to medium- to high-contrast enhancement and low–high signal on FLAIR scans. Habitat 6 (high signal on calibrated contrast-enhanced T1-weighted and FLAIR sequences) comprised a significantly higher volume fraction of tumors in the long-term survival group (discovery cohort, 35% ± 6.5%, validation cohort, 34% ± 4.8%) compared with tumors in the short-term survival group (discovery cohort, 17% ± 4.5%, p &lt, 0.03, validation cohort, 16 ± 4.0%, p &lt, 0.007). Of the 6 distinct MRI-defined habitats, the fractional tumor volume of habitat 6 at diagnosis was significantly predictive of long- or short-term survival. We discuss a possible mechanistic basis for this association and implications for habitat-driven adaptive therapy of GBM.

Lung cancer is the most common fatal malignancy in adults worldwide, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer diagnoses. Computed tomography (CT) is routinely used in clinical practice to determine lung cancer treatment and assess prognosis. Here, we developed LungNet, a shallow convolutional neural network for predicting outcomes of NSCLC patients. We trained and evaluated LungNet on four independent cohorts of NSCLC patients from four medical centers: Stanford Hospital (n = 129), H. Lee Moffitt Cancer Center and Research Institute (n = 185), MAASTRO Clinic (n = 311) and Charité – Universitätsmedizin (n=84). We show that outcomes from LungNet are predictive of overall survival in all four independent survival cohorts as measured by concordance indices of 0.62, 0.62, 0.62 and 0.58 on cohorts 1, 2, 3, and 4, respectively. Further, the survival model can be used, via transfer learning, for classifying benign vs malignant nodules on the Lung Image Database Consortium (n = 1010), with improved performance (AUC=0.85) versus training from scratch (AUC=0.82). LungNet can be used as a noninvasive predictor for prognosis in NSCLC patients and can facilitate interpretation of CT images for lung cancer stratification and prognostication.

[This corrects the article DOI: 10.1371/journal.pone.0118261.].

The digital information age has been a catalyst in creating a renewed interest in Artificial Intelligence (AI) approaches, especially the subclass of computer algorithms that are popularly grouped into Machine Learning (ML). These methods have allowed one to go beyond limited human cognitive ability into understanding the complexity in the high dimensional data. Medical sciences have seen a steady use of these methods but have been slow in adoption to improve patient care. There are some significant impediments that have diluted this effort, which include availability of curated diverse data sets for model building, reliable human-level interpretation of these models, and reliable reproducibility of these methods for routine clinical use. Each of these aspects has several limiting conditions that need to be balanced out, considering the data/model building efforts, clinical implementation, integration cost to translational effort with minimal patient level harm, which may directly impact future clinical adoption. In this review paper, we will assess each aspect of the problem in the context of reliable use of the ML methods in oncology, as a representative study case, with the goal to safeguard utility and improve patient care in medicine in general.

Radiomic features are being increasingly studied for clinical applications. We aimed to assess the agreement among radiomic features when computed by several groups by using different software packages under very tightly controlled conditions, which included standardized feature definitions and common image data sets. Ten sites (9 from the NCI's Quantitative Imaging Network] positron emission tomography–computed tomography working group plus one site from outside that group) participated in this project. Nine common quantitative imaging features were selected for comparison including features that describe morphology, intensity, shape, and texture. The common image data sets were: three 3D digital reference objects (DROs) and 10 patient image scans from the Lung Image Database Consortium data set using a specific lesion in each scan. Each object (DRO or lesion) was accompanied by an already-defined volume of interest, from which the features were calculated. Feature values for each object (DRO or lesion) were reported. The coefficient of variation (CV), expressed as a percentage, was calculated across software packages for each feature on each object. Thirteen sets of results were obtained for the DROs and patient data sets. Five of the 9 features showed excellent agreement with CV &lt, 1%, 1 feature had moderate agreement (CV &lt, 10%), and 3 features had larger variations (CV ≥ 10%) even after attempts at harmonization of feature calculations. This work highlights the value of feature definition standardization as well as the need to further clarify definitions for some features.

Prostate cancer diagnosis and treatment continues to be a major public health challenge. The heterogeneity of the disease is one of the major factors leading to imprecise diagnosis and suboptimal disease management. The improved resolution of functional multi-parametric magnetic resonance imaging (mpMRI) has shown promise to improve detection and characterization of the disease. Regions that subdivide the tumor based on Dynamic Contrast Enhancement (DCE) of mpMRI are referred to as DCE-Habitats in this study. The DCE defined perfusion curve patterns on the identified tumor habitat region are used to assess clinical significance. These perfusion curves were systematically quantified using seven features in association with the patient biopsy outcome and classifier models were built to find the best discriminating characteristics between clinically significant and insignificant prostate lesions defined by Gleason score (GS). Multivariable analysis was performed independently on one institution and validated on the other, using a multi-parametric feature model, based on DCE characteristics and ADC features. The models had an intra institution Area under the Receiver Operating Characteristic (AUC) of 0.82. Trained on Institution I and validated on the cohort from Institution II, the AUC was also 0.82 (sensitivity 0.68, specificity 0.95).

Purpose The purpose of this study was to investigate the potential of computed tomography (CT) based radiomic features of primary tumors to predict pathological nodal involvement in clinically node-negative (N0) peripheral lung adenocarcinomas. Methods A total of 187 patients with clinical N0 peripheral lung adenocarcinomas who underwent preoperative CT scan and subsequently received systematic lymph node dissection were retrospectively reviewed. 219 quantitative 3D radiomic features of primary lung tumor were extracted; meanwhile, nine radiological semantic features were evaluated. Univariate and multivariate logistic regression analysis were used to explore the role of these features in predicting pathological nodal involvement. The areas under the ROC curves (AUCs) were compared between multivariate logistic regression models. Results A total of 153 patients had pathological N0 status and 34 had pathological lymph node metastasis. On univariate analysis, fissure attachment and 17 radiomic features were significantly associated with pathological nodal involvement. Multivariate analysis revealed that semantic features of pleural retraction (P = 0.048) and fissure attachment (P = 0.023) were significant predictors of pathological nodal involvement (AUC = 0.659); and the radiomic feature F185 (Histogram SD Layer 1) (P = 0.0001) was an independent prognostic factor of pathological nodal involvement (AUC = 0.73). A logistic regression model produced from combining radiomic feature and semantic feature showed the highest AUC of 0.758 (95% CI: 0.685-0.831), and the AUC value computed by fivefold cross-validation method was 0.737 (95% CI: 0.73-0.744). Conclusions Features derived on primary lung tumor described by semantic and radiomic could provide information of pathological nodal involvement in clinical N0 peripheral lung adenocarcinomas.

We have identified a set of informative and relevant radiologic features that can be easily scored in the clinical setting to determine lung cancer risk among participants with small pulmonary nodules.

Purpose To investigate whether imaging features from pre-treatment planning CT scans are associated with overall survival (OS), recurrence-free survival (RFS), and loco-regional recurrence-free survival (LR-RFS) after stereotactic body radiotherapy (SBRT) among non-small-cell lung cancer (NSCLC) patients. Patients and methods A total of 92 patients (median age: 73 years) with stage I or IIA NSCLC were qualified for this study. A total dose of 50 Gy in 5 fractions was the standard treatment. Besides clinical characteristics, 24 “semantic” image features were manually scored based on a point scale (up to 5) and 219 computer-derived “radiomic” features were extracted based on whole tumor segmentation. Statistical analysis was performed using Cox proportional hazards model and Harrell's C-index, and the robustness of final prognostic model was assessed using ten-fold cross validation by dichotomizing patients according to the survival or recurrence status at 24 months. Results Two-year OS, RFS and LR-RFS were 69.95%, 41.3% and 51.85%, respectively. There was an improvement of Harrell's C-index when adding imaging features to a clinical model. The model for OS contained the Eastern Cooperative Oncology Group (ECOG) performance status (Hazard Ratio [HR] = 2.78, 95% Confidence Interval [CI]: 1.37 – 5.65), pleural retraction (HR = 0.27, 95% CI: 0.08 – 0.92), F2 (short axis × longest diameter, HR = 1.72, 95% CI: 1.21 – 2.44) and F186 (Hist-Energy-L1, HR = 1.27, 95% CI: 1.00 - 1.61); The prognostic model for RFS contained vessel attachment (HR = 2.13, 95% CI: 1.24 – 3.64) and F2 (HR = 1.69, 95% CI: 1.33 – 2.15); and the model for LR-RFS contained the ECOG performance status (HR = 2.01, 95% CI: 1.12 – 3.60) and F2 (HR = 1.67, 95% CI: 1.29 – 2.18). Conclusions Imaging features derived from planning CT demonstrate prognostic value for recurrence following SBRT treatment, and might be helpful in patient stratification. This article is protected by copyright. All rights reserved.

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. In vivo, 200 mmol/L NaHCO3 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. Cancer Res; 77(9); 2242–54. ©2017 AACR.

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

BackgroundIdentification of imaging traits to discriminate clinically significant prostate cancer is challenging due to the multi focal nature of the disease. The difficulty in obtaining a consensus by the Prostate Imaging and Data Systems (PI-RADS) scores coupled with disagreements in interpreting multi-parametric Magnetic Resonance Imaging (mpMRI) has resulted in increased variability in reporting findings and evaluating the utility of this imaging modality in detecting clinically significant prostate cancer. This study assess the ability of radiological traits (semantics) observed on multi-parametric Magnetic Resonance images (mpMRI) to discriminate clinically significant prostate cancer.MethodsWe obtained multi-parametric MRI studies from 103 prostate cancer patients with 167 targeted biopsies from a single institution. The study was approved by our Institutional Review Board (IRB) for retrospective analysis. The biopsy location had been identified and marked by a clinical radiologist for targeted biopsy based on initial study interpretation. Using the target locations, two study radiologists independently re-evaluated the scans and scored 16 semantic traits on a point scale (up to 5 levels) based on mpMRI images. The semantic traits describe size, shape, and border characteristics of the prostate lesion, as well as presence of disease around lymph nodes (lymphadenopathy). We built a linear classifier model on these semantic traits and related to pathological outcome to identify clinically significant tumors (Gleason Score ≥ 7). The discriminatory ability of the predictors was tested using cross validation method randomly repeated and ensemble values were reported. We then compared the performance of semantic predictors with the PI-RADS predictors.ResultsWe found several semantic features individually discriminated high grade Gleason score (ADC-intensity, Homogeneity, early-enhancement, T2-intensity and extraprostatic extention), these univariate predictors had an average area under the receiver operator characteristics (AUROC) ranging from 0.54 to 0.68. Multivariable semantic predictors with three features (ADC-intensity; T2-intensity, enhancement homogenicity) had an average AUROC of 0.7 [0.43, 0.94]. The PI-RADS based predictor had average AUROC of 0.6 [0.47, 0.75].ConclusionWe find semantics traits are related to pathological findings with relatively higher reproducibility between radiologists. Multivariable predictors formed on these traits shows higher discriminatory ability compared to PI-RADS scores.

Background: Multiparametric magnetic resonance imaging (mpMRI) has emerged as a non-invasive modality to diagnose and monitor prostate cancer. Quantitative metrics on the regions of abnormality have shown to be useful descriptors to discriminate clinically significant cancers. In this study, we evaluate the reproducibility of quantitative imaging features using repeated mpMRI on the same patients. Methods: We retrospectively obtained the deidentified records of patients, who underwent two mpMRI scans within 2 weeks of the first baseline scan. The patient records were obtained as deidentified data (including imaging), obtained through the TCIA (The Cancer Imaging Archive) repository and analyzed in our institution with an institutional review board-approved Health Insurance Portability and Accountability Act-compliant retrospective study protocol. Indicated biopsied regions were used as a marker for our study radiologists to delineate the regions of interest. We extracted 307 quantitative features in each mpMRI modality [T2-weighted MR sequence image (T2w) and apparent diffusion coefficient (ADC) with b values of 0 and 1,400 mm/s2] across the two sequential scans. Concordance correlation coefficients (CCCs) were computed on the features extracted from sequential scans. Redundant features were removed by computing the coefficient of determination (R 2) among them and replaced with a feature that had the highest dynamic range within intercorrelated groups. Results: We have assessed the reproducibility of quantitative imaging features among sequential scans and found that habitat region characterization improves repeatability in ADC maps. There were 19 T2w features and two ADC features in radiologist drawn regions (native raw image), compared to 18 T2w and 15 ADC features in habitat regions (sphere), which were reproducible (CCC ≥0.65) and non-redundant (R 2 ≥ 0.99). We also found that z-transformation of the images prior to feature extraction reduced the number of reproducible features with no detrimental effect. Conclusion: We have shown that there are quantitative imaging features that are reproducible across sequential prostate mpMRI acquisition at a preset level of filters. We also found that a habitat approach improves feature repeatability in ADC. A validated set of reproducible image features in mpMRI will allow us to develop clinically useful disease risk stratification, enabling the possibility of using imaging as a surrogate to invasive biopsies.

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

Prostate cancer diagnosis and treatment continues to be a major public health challenge. The heterogeneity of the disease is one of the major factors leading to imprecise diagnosis and suboptimal disease management. The improved resolution of functional multi-parametric magnetic resonance imaging (mpMRI) has shown promise to improve detection and characterization of the disease. Regions that subdivide the tumor based on Dynamic Contrast Enhancement (DCE) of mpMRI are referred to as DCE-Habitats in this study. The DCE defined perfusion curve patterns on the identified tumor habitat region are used to assess clinical significance. These perfusion curves were systematically quantified using seven features in association with the patient biopsy outcome and classifier models were built to find the best discriminating characteristics between clinically significant and insignificant prostate lesions defined by Gleason score (GS). Multivariable analysis was performed independently on one institution and validated on the other, using a multi-parametric feature model, based on DCE characteristics and ADC features. The models had an intra institution Area under the Receiver Operating Characteristic (AUC) of 0.82. Trained on Institution I and validated on the cohort from Institution II, the AUC was also 0.82 (sensitivity 0.68, specificity 0.95).

Prostate cancer identification and assessment of clinical significance continues to be a challenge. Routine multiparametric magnetic resonance imaging has shown to be useful in assessing disease progression. Although dynamic contrast-enhanced imaging (DCE) has the ability to characterize perfusion across time and has shown enormous utility, radiological assessment (Prostate Imaging-Reporting and Data System or PIRADS version 2) has limited its use owing to lack of consistency and nonquantitative nature. In our work, we propose a systematic methodology to quantify perfusion dynamics for the DCE imaging. Using these metrics, 7 different subregions or perfusion habitats of the targeted lesions are localized and related to clinical significance. We found that quantitative features describing the habitat based on the late area under the DCE time-activity curve was a good predictor of clinical significance disease. The best predictive feature in the habitat had an AUC of 0.82, CI [0.81–0.83].

Background The obesity epidemic has prompted the need to better understand the impact of adipose tissue on human pathophysiology. However, accurate, efficient, and replicable models of quantifying adiposity have yet to be developed and clinically implemented. We propose a novel semiautomated radiologic method of measuring the visceral fat area (VFA) using computed tomography scan analysis. Materials and methods We obtained a cohort of 100 patients with rectal adenocarcinoma, with a median age of 60.9 y (age range: 35-87 y) and an average body mass index of 28.8 kg/m2 ± 6.56 kg/m2. The semiautomated quantification method of adiposity was developed using a commercial imaging suite. The method was compared to two manual delineations performed using two different picture archiving communication systems. We quantified VFA, subcutaneous fat area (SFA), total fat area (TFA), and visceral-to-subcutaneous fat ratio (V/S ratio) on computed tomography axial slices that were at the L4-L5 intervertebral level. Results The semiautomated method was comparable to manual measurements for TFA, VFA, and SFA with intraclass correlation (ICC) of 0.99, 0.97, and 0.96, respectively. However, the ICC for the V/S ratio was only 0.44, which led to the identification of technical outliers that were identified using robust regression. After removal of these outliers, the ICC improved to 0.99 for TFA, VFA, and SFA and 0.97 for the V/S ratio. Measurements from the manual methodology highly correlated between the two picture archiving communication system platforms, with ICC of 0.98 for TFA, 0.98 for VFA, 0.96 for SFA, and 0.95 for the V/S ratio. Conclusions This semiautomated method is able to generate precise and reproducible results. In the future, this method may be applied on a larger scale to facilitate risk stratification of patients using measures of abdominal adiposity.

Objectives 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. Methods 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. Results 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. Conclusions The radiomics of lung cancer screening computed tomography scans at baseline can be used to assess risk for development of cancer.