Search

BackgroundRelapsed and refractory Diffuse large B cell lymphoma (DLBCL) can be successfully treated with axicabtagene ciloleucel (axi-cel), a CD19-directed autologous chimeric antigen receptor T cell (CAR-T) therapy. Diagnostic image-based features could help identify the patients who would clinically respond to this advanced immunotherapy.PurposeThe aim of this study was to establish a radiomic image feature-based signature derived from positron emission tomography/computed tomography (PET/CT), including metabolic tumor burden, which can predict a durable response to CAR-T therapy in refractory/relapsed DLBCL.MethodsWe conducted a retrospective review of 155 patients with relapsed/refractory DLBCL treated with axi-cel CAR-T therapy. The patients’ disease involvement was evaluated based on nodal or extranodal sites. A sub-cohort of these patients with at least one nodal lesion (n=124) was assessed, while an overlapping sub-cohort (n=94) had at least one extranodal lesion. The lesion regions were characterized using 306 quantitative imaging metrics for PET images and CT images independently. Principal component (PC) analysis was performed to reduce the dimensionality in feature-based functional categories: size (n=38), shape (n=9), and texture (n=259). The selected features were used to build prediction models for survival at 1 year and tested for prognosis to overall/progression-free survival (OS/PFS) using a Kaplan-Meier (KM) plot.ResultsThe Shape-based PC features of the largest extranodal lesion on PET were predictive of 1-year survival (AUC 0.68 [0.43,0.94]) and prognostic of OS/PFS (p

For multicenter clinical studies, characterizing the robustness of image-derived radiomics features is essential. Features calculated on PET images have been shown to be very sensitive to image noise. The purpose of this work was to investigate the efficacy of a relatively simple harmonization strategy on feature robustness and agreement. A purpose-built texture pattern phantom was scanned on 10 different PET scanners in 7 institutions with various different image acquisition and reconstruction protocols. An image harmonization technique based on equalizing a contrast-to-noise ratio was employed to generate a “harmonized” alongside a “standard” dataset for a reproducibility study. In addition, a repeatability study was performed with images from a single PET scanner of variable image noise, varying the binning time of the reconstruction. Feature agreement was measured using the intraclass correlation coefficient (ICC). In the repeatability study, 81/93 features had a lower ICC on the images with the highest image noise as compared to the images with the lowest image noise. Using the harmonized dataset significantly improved the feature agreement for five of the six investigated feature classes over the standard dataset. For three feature classes, high feature agreement corresponded with higher sensitivity to the different patterns, suggesting a way to select suitable features for predictive models.

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.

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.

Abstract Background Identification 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. Methods We 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. Results We 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]. Conclusion We 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.

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

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

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 (R2) 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 (R2 ≥ 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.

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.

Abstract Background Predicting recurrence after stereotactic body radiotherapy (SBRT) in non-small cell lung cancer (NSCLC) patients is problematic, but critical for the decision of following treatment. This study aims to investigate the association of imaging features derived from the first follow-up computed tomography (CT) on lung cancer patient outcomes following SBRT, and identify patients at high risk of recurrence. Methods Fifty nine biopsy-proven non-small cell lung cancer patients were qualified for this study. The first follow-up CTs were performed about 3 months after SBRT (median time: 91 days). Imaging features included 34 manually scored radiological features (semantics) describing the lesion, lung and thorax and 219 quantitative imaging features (radiomics) extracted automatically after delineation of the lesion. Cox proportional hazard models and Harrel’s C-index were used to explore predictors of overall survival (OS), recurrence-free survival (RFS), and loco-regional recurrence-free survival (LR-RFS). Five-fold cross validation was performed on the final prognostic model. Results The median follow-up time was 42 months. The model for OS contained Eastern Cooperative Oncology Group (ECOG) performance status (HR = 3.13, 95% CI: 1.17–8.41), vascular involvement (HR = 3.21, 95% CI: 1.29–8.03), lymphadenopathy (HR = 3.59, 95% CI: 1.58–8.16) and the 1st principle component of radiomic features (HR = 1.24, 95% CI: 1.02–1.51). The model for RFS contained vascular involvement (HR = 3.06, 95% CI: 1.40–6.70), vessel attachment (HR = 3.46, 95% CI: 1.65–7.25), pleural retraction (HR = 3.24, 95% CI: 1.41–7.42), lymphadenopathy (HR = 6.41, 95% CI: 2.58–15.90) and relative enhancement (HR = 1.40, 95% CI: 1.00–1.96). The model for LR-RFS contained vascular involvement (HR = 4.96, 95% CI: 2.23–11.03), lymphadenopathy (HR = 2.64, 95% CI: 1.19–5.82), circularity (F13, HR = 1.60, 95% CI: 1.10–2.32) and 3D Laws feature (F92, HR = 1.96, 95% CI: 1.35–2.83). Five-fold cross-validated the areas under the receiver operating characteristic curves (AUC) of these three models were all above 0.8. Conclusions Our analysis reveals disease progression could be prognosticated as early as 3 months after SBRT using CT imaging features, and these features would be helpful in clinical decision-making.

Objective: Intra-abdominal fat is a risk factor for pancreatic cancer (PC), but little is known about its contribution to PC precursors known as intraductal papillary mucinous neoplasms (IPMNs). Our goal was to evaluate quantitative radiologic measures of abdominal/visceral obesity as possible diagnostic markers of IPMN severity/pathology.Methods: In a cohort of 34 surgically-resected, pathologically-confirmed IPMNs (17 benign; 17 malignant) with preoperative abdominal computed tomography (CT) images, we calculated body mass index (BMI) and four radiologic measures of obesity: total abdominal fat (TAF) area, visceral fat area (VFA), subcutaneous fat area (SFA), and visceral to subcutaneous fat ratio (V/S). Measures were compared between groups using Wilcoxon two-sample exact tests and other metrics.Results: Mean BMI for individuals with malignant IPMNs (28.9 kg/m2) was higher than mean BMI for those with benign IPMNs (25.8 kg/m2) (P=0.045). Mean VFA was higher for patients with malignant IPMNs (199.3 cm2) compared to benign IPMNs (120.4 cm2), P=0.092. V/S was significantly higher (P=0.013) for patients with malignant versus benign IPMNs (1.25 vs. 0.69 cm2), especially among females. The accuracy, sensitivity, specificity, and positive and negative predictive value of V/S in predicting malignant IPMN pathology were 74%, 71%, 76%, 75%, and 72%, respectively.Conclusions: Preliminary findings suggest measures of visceral fat from routine medical images may help predict IPMN pathology, acting as potential noninvasive diagnostic adjuncts for management and targets for intervention that may be more biologically-relevant than BMI. Further investigation of gender-specific associations in larger, prospective IPMN cohorts is warranted to validate and expand upon these observations.

Nonsmall cell lung cancer is a prevalent disease. It is diagnosed and treated with the help of computed tomography (CT) scans. In this paper, we apply radiomics to select 3-D features from CT images of the lung toward providing prognostic information. Focusing on cases of the adenocarcinoma nonsmall cell lung cancer tumor subtype from a larger data set, we show that classifiers can be built to predict survival time. This is the first known result to make such predictions from CT scans of lung cancer. We compare classifiers and feature selection approaches. The best accuracy when predicting survival was 77.5% using a decision tree in a leave-one-out cross validation and was obtained after selecting five features per fold from 219.

Lung cancer screening identifies cancers with heterogeneous behaviors. Some lung cancers will be identified among patients who had prior negative CT screens and upon follow-up scans develop a de novo nodule that was determined to be cancerous. Other lung cancers will be identified among patients who had one or more prior stable positive scans that were not determined to be lung cancer (indeterminate pulmonary nodules), but in follow-up scans was diagnosed with an incidence lung cancer. Using data from the CT arm of the National Lung Screening Trial, this analysis investigated differences in patient characteristics and survival endpoints between prevalence-, interval-, and screen-detected lung cancers, characterized based on sequence of screening results. Lung cancers immediately following a positive baseline (T0), and prior to the T1 screen, formed the prevalence cohort. Interval cancers were diagnosed following a negative screen at any time point prior to the next screening round. Two cohorts of screen-detected lung cancers (SDLC) were identified that had a baseline positive screen that was that was not determined to be lung cancer (i.e., an indeterminate pulmonary nodule), but in follow-up scans was diagnosed with an incidence lung cancer 12 (SDLC1) or 24 (SDLC2) months later. Two other incidence cohorts had screen-detected lung cancers that had baseline negative screen and upon follow-up scans developed a de novo nodule determined to be cancerous at 12 (SDLC3) or 24 (SDLC4) months later. Differences in patient characteristics, progression-free survival (PFS), and overall survival (OS) were assessed. The lung cancer-specific death rate was higher for SDLC3/SDLC4 compared to SDLC1/SDLC2 lung cancers (136.6/1,000 person-years vs. 71.3/1,000 person-years, P < 0.001). Moreover, PFS and OS were significantly lower for SDLC3/SDLC4 compared to SDLC1/SDLC2 (P < 0.004; P < 0.002, respectively). The findings were consistent when stratified by stage and histology. Multivariable Cox proportional models revealed that the SDLC3/SDLC4 case groups were associated with significantly poorer PFS (HR = 1.89; 95% CI 1.31-2.74) and OS (HR = 1.80; 95% CI 1.21-2.67) compared to SDLC1/SDLC2 lung cancers (HR = 1.00). Lung cancer patients who develop a de novo nodule that determined to be cancerous (i.e., at least one negative CT screen prior to cancer diagnosis) had poorer survival outcomes compared to patients who had at least one positive screen prior to cancer diagnosis. As such, the observation that de novo screen-detected are associated with poorer survival could be attributed to faster growing, more aggressive cancers that arose from a lung environment previously lacking focal abnormalities.

Sediments are routinely analyzed in terms of the sizing characteristics of the grains of which they are composed. Via sieving methods, the grains are separated and a weight-based size distribution constructed. Various moment parameters are computed from the size distribution and these serve as sediment characteristics. This paper examines the feasibility of a fully electronic granularity analysis using digital image processing. The study uses a random model of three-dimensional grains in conjunction with the morphological method of granulometric size distributions. The random model is constructed to simulate sand, silt, and clay particle distributions. Owing to the impossibility of perfectly sifting small grains so that they do not touch, the model is used in both disjoint and non-disjoint modes, and watershed segmentation is applied in the non-disjoint model. The image-based granulometric size distributions are transformed so that they take into account the necessity to view sediment fractions at different magnifications and in different frames. Gray-scale granulometric moments are then computed using both ordinary and reconstructive granulometries. The resulting moments are then compared to moments found from real grains in seven different sediments using standard weight-based size distributions.

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.

Hypoxia in tumors correlates with greater risk of metastases, increased invasiveness, and resistance to systemic and radiation therapy. The evolutionary dynamics that links specific adaptations to hypoxia with these observed tumor properties have not been well investigated. While some tumor populations may experience fixed hypoxia, cyclical and stochastic transitions from normoxia to hypoxia are commonly observed in vivo. Although some phenotypic adaptations to this cyclic hypoxia are likely reversible, we hypothesize that some adaptations may become fixed through mutations promoted by hypoxia-induced genomic instability. Here we seek to identify genetic alterations and corresponding stable phenotypes that emerge following cyclic hypoxia. Although these changes may originate as adaptations to this specific environmental stress, their fixation in the tumor genome may result in their observation in tumors from regions of normoxia, a condition known as pseudohypoxia. We exposed several epithelial cell lines to 50 cycles of hypoxia-normoxia, followed by culture in normoxia over a period of several months. Molecular analyses demonstrated permanent changes in expression of several oncogenes and tumor-suppressors, including p53, E-cadherin, and Hif-1α. These changes were associated with increased resistance to multiple cytotoxins, increased survival in hypoxia and increased anchorage-independent growth. These results suggest cycles of hypoxia encountered in early cancers can select for specific and stable genotypic and phenotypic properties that persist even in normoxic conditions, which may promote tumor progression and resistance to therapy.

Many studies have shown that the acidity of solid tumors contributes to local invasion and metastasis. Oral pH buffers can specifically neutralize the acidic pH of tumors and reduce the incidence of local invasion and metastatic formation in multiple murine models. However, this effect is not universal as we have previously observed that metastasis is not inhibited by buffers in some tumor models, regardless of buffer used. B16-F10 (murine melanoma), LL/2 (murine lung) and HCT116 (human colon) tumors are resistant to treatment with lysine buffer therapy, whereas metastasis is potently inhibited by lysine buffers in MDA-MB-231 (human breast) and PC3M (human prostate) tumors. In the current work, we confirmed that sensitive cells utilized a pH-dependent mechanism for successful metastasis supported by a highly glycolytic phenotype that acidifies the local tumor microenvironment resulting in morphological changes. In contrast, buffer-resistant cell lines exhibited a pH-independent metastatic mechanism involving constitutive secretion of matrix degrading proteases without elevated glycolysis. These results have identified two distinct mechanisms of experimental metastasis, one of which is pH-dependent (buffer therapy sensitive cells) and one which is pH-independent (buffer therapy resistant cells). Further characterization of these models has potential for therapeutic benefit.