High Gray-level Run Emphasis Research Articles

Individualized treatment decision model for inoperable elderly esophageal squamous cell carcinoma based on multi-modal data fusion

BackgroundThis research aimed to develop a model for individualized treatment decision-making in inoperable elderly patients with esophageal squamous cell carcinoma (ESCC) using machine learning methods and multi-modal data.MethodsA total of 189 inoperable elderly ESCC patients aged 65 or older who underwent concurrent chemoradiotherapy (CCRT) or radiotherapy (RT) were included. Multi-task learning models were created using machine learning techniques to analyze multi-modal data, including pre-treatment CT images, clinical information, and blood test results. Nomograms were constructed to predict the objective response rate (ORR) and progression-free survival (PFS) for different treatment strategies. Optimal treatment plans were recommended based on the nomograms. Patients were stratified into high-risk and low-risk groups using the nomograms, and survival analysis was performed using Kaplan–Meier curves.ResultsThe identified risk factors influencing ORR were histologic grade (HG), T stage and three radiomic features including original shape elongation, first-order skewness and original shape flatness, while risk factors influencing PFS included BMI, HG and three radiomic features including high gray-level run emphasis, first-order minimum and first-order skewness. These risk factors were incorporated into the nomograms as independent predictive factors. PFS was substantially different between the low-risk group (total score ≤ 110) and the high-risk group (total score > 110) according to Kaplan–Meier curves (P < 0.05).ConclusionsThe developed predictive models for ORR and PFS in inoperable elderly ESCC patients provide valuable insights for predicting treatment efficacy and prognosis. The nomograms enable personalized treatment decision-making and can guide optimal treatment plans for inoperable elderly ESCC patients.

Prediction of MYCN Gene Amplification in Pediatric Neuroblastomas: Development of a Deep Learning-Based Tool for Automatic Tumor Segmentation and Comparative Analysis of Computed Tomography-Based Radiomics Features Harmonization.

MYCN oncogene amplification is closely linked to high-grade neuroblastoma with poor prognosis. Accurate quantification is essential for risk assessment, which guides clinical decision making and disease management. This study proposes an end-to-end deep-learning framework for automatic tumor segmentation of pediatric neuroblastomas and radiomics features-based classification of MYCN gene amplification. Data from pretreatment contrast-enhanced computed tomography scans and MYCN status from 47 cases of pediatric neuroblastomas treated at a tertiary children's hospital from 2009 to 2020 were reviewed. Automated tumor segmentation and grading pipeline includes (1) a modified U-Net for tumor segmentation; (2) extraction of radiomic textural features; (3) feature-based ComBat harmonization for removal of variabilities across scanners; (4) feature selection using 2 approaches, namely, (a) an ensemble approach and (b) stepwise forward-and-backward selection method using logistic regression classifier; and (5) radiomics features-based classification of MYCN gene amplification using machine learning classifiers. Median train/test Dice score for modified U-Net was 0.728/0.680. The top 3 features from the ensemble approach were neighborhood gray-tone difference matrix (NGTDM) busyness, NGTDM strength, and gray-level run-length matrix (GLRLM) low gray-level run emphasis, whereas those from the stepwise approach were GLRLM low gray-level run emphasis, GLRLM high gray-level run emphasis, and NGTDM coarseness. The top-performing tumor classification algorithm achieved a weighted F1 score of 97%, an area under the receiver operating characteristic curve of 96.9%, an accuracy of 96.97%, and a negative predictive value of 100%. Harmonization-based tumor classification improved the accuracy by 2% to 3% for all classifiers. The proposed end-to-end framework achieved high accuracy for MYCN gene amplification status classification.

Integrative Risk Predictors of Temporomandibular Joint Osteoarthritis Progression.

In this paper we propose feature selection and machine learning approaches to identify a combination of features for risk prediction of Temporomandibular Joint (TMJ) disease progression. In a sample of 32 TMJ osteoarthritis and 38 controls, feature selection of 5 clinical comorbidities, 43 quantitative imaging, 28 biological features and was performed using Maximum Relevance Minimum Redundancy, Chi-Square and Least Absolute Shrinkage and Selection Operator (LASSO) and Recursive Feature Elimination. We compared the performance of learning using concave and convex kernels (LUCCK), Support Vector Machine (SVM) and Random Forest (RF) approaches to predict disease cure/improvement or persistence/worsening. We show that the SVM model using LASSO achieves area under the curve (AUC), sensitivity and precision of 0.92±0.08, 0.85±0.19 and 0.76 ±0.18, respectively. Baseline levels of headaches, lower back pain, restless sleep, muscle soreness, articular fossa bone surface/bone volume and trabecular separation, condylar High Gray Level Run Emphasis and Short Run High Gray Level Emphasis, saliva levels of 6Ckine, Osteoprotegerin (OPG) and Angiogenin, and serum levels of 6ckine and Brain Derived Neurotrophic Factor (BDNF) were the most frequently occurring features to predict more severe TMJ osteoarthritis prognosis.

Beads phantom for evaluating heterogeneity of SUV on 18F-FDG PET images.

This study aimed to develop a dedicated phantom using acrylic beads for texture analysis and to represent heterogeneous 18F-fluorodeoxyglucose (FDG) distributions in various acquisition periods. Images of acrylic spherical beads with or without diameters of 5- and 10-mm representing heterogeneous and homogeneous 18F-FDG distribution in phantoms, respectively, were collected for 20min in list mode. Phantom data were reconstructed using three-dimensional ordered subset expectation maximization with attenuation and scatter corrections, and the time-of-flight algorithm. The beads phantom images were acquired twice to evaluate the robustness of texture features. Thirty-one texture features were extracted, and the robustness of texture feature values was evaluated by calculating the percentage of coefficient of variation (%COV) and intraclass coefficient of correlation (ICC). Cross-correlation coefficients among texture feature values were clustered to classify the characteristics of these features. Heterogeneous 18F-FDG distribution was represented by the beads phantom images. The agreements of %COV between two measurements were acceptable (ICC ≥ 0.71). All texture features were classified into four groups. Among 31 texture features, 24 exhibited significant different values between phantoms with and without beads in 1-, 2-, 3-, 4-, 5-, 20-min image acquisitions. Whereas, the homogeneous and heterogeneous 18F-FDG distribution could not be discriminated by seven texture features: low gray-level run emphasis, high gray-level run emphasis, short-run low gray-level emphasis, low gray-level zone emphasis, high gray-level zone emphasis, short-zone low gray-level emphasis, and coarseness. We have developed the acrylic beads phantom for texture analysis that could represent heterogeneous 18F-FDG distributions in various acquisition periods. Most texture features could discriminate homogeneous and heterogeneous 18F-FDG distributions in the beads phantom images.

DWI-related texture analysis for prostate cancer: differences in correlation with histological aggressiveness and data repeatability between peripheral and transition zones

BackgroundWe investigated the correlation between texture features extracted from apparent diffusion coefficient (ADC) maps or diffusion-weighted images (DWIs), and grade group (GG) in the prostate peripheral zone (PZ) and transition zone (TZ), and assessed reliability in repeated examinations.MethodsPatients underwent 3-T pelvic magnetic resonance imaging (MRI) before radical prostatectomy with repeated DWI using b-values of 0, 100, 1,000, and 1,500 s/mm2. Region of interest (ROI) for cancer was assigned to the first and second DWI acquisition separately. Texture features of ROIs were extracted from comma-separated values (CSV) data of ADC maps generated from several sets of two b-value combinations and DWIs, and correlation with GG, discrimination ability between GG of 1–2 versus 3–5, and data repeatability were evaluated in PZ and TZ.ResultsForty-four patients with 49 prostate cancers met the eligibility criteria. In PZ, ADC 10% and 25% based on ADC map of two b-value combinations of 100 and 1,500 s/mm2 and 10% based on ADC map with b-value of 0 and 1,500 s/mm2 showed significant correlation with GG, acceptable discrimination ability, and good repeatability. In TZ, higher-order texture feature of busyness extracted from ADC map of 100 and 1,500 s/mm2, and high gray-level run emphasis, short-run high gray-level emphasis, and high gray-level zone emphasis from DWI with b-value of 100 s/mm2 demonstrated significant correlation, excellent discrimination ability, but moderate repeatability.ConclusionsSome DWI-related features showed significant correlation with GG, acceptable to excellent discrimination ability, and moderate to good data repeatability in prostate cancer, and differed between PZ and TZ.

CT texture analysis of mediastinal lymphadenopathy: Combining with US-based elastographic parameter and discrimination between sarcoidosis and lymph node metastasis from small cell lung cancer.

ObjectivesTo investigate the potential of computed tomography (CT)-based texture analysis and elastographic data provided by endobronchial ultrasonography (EBUS) for differentiating the mediastinal lymphadenopathy by sarcoidosis and small cell lung cancer (SCLC) metastasis.MethodsSixteen patients with sarcoidosis and 14 with SCLC were enrolled. On CT images showing the largest mediastinal lymph node, a fixed region of interest was drawn on the node, and texture features were automatically measured. Among the 30 patients, 19 (12 sarcoidosis and 7 SCLC) underwent endobronchial ultrasound transbronchial needle aspiration, and the fat-to-lesion strain ratio (FLR) was recorded. Texture features and FLRs were compared between the 2 patient groups. Logistic regression analysis was performed to evaluate the diagnostic accuracy of these measurements.ResultsOf the 31 texture features, the differences between 11 texture features of CT ROIs in the patients with sarcoidosis versus patients with SCLC were significant. Among them, the grey-level run length matrix with high gray-level run emphasis (GLRLM-HGRE) showed the greatest difference (P<0.01). Differences between FLRs were significant (P<0.05). Logistic regression analysis together with receiver operating characteristic curve analysis demonstrated that the FLR combined with the GLRLM-HGRE showed a high diagnostic accuracy (100% sensitivity, 92% specificity, 0.988 area under the curve) for discriminating between sarcoidosis and SCLC.ConclusionTexture analysis, particularly combined with the FLR, is useful for discriminating between mediastinal lymphadenopathy caused by sarcoidosis from that caused by metastasis from SCLC.

A Non-invasive Method to Diagnose Lung Adenocarcinoma.

Purpose: To find out the CT radiomics features of differentiating lung adenocarcinoma from another lung cancer histological type.Methods: This was a historical cohort study, three independent lung cancer cohorts included. One cohort was used to evaluate the stability of radiomics features, one cohort was used to feature selection, and the last was used to construct and evaluate classification models. The research is divided into four steps: region of interest segmentation, feature extraction, feature selection, and model building and validation. The feature selection methods included the intraclass correlation coefficient, ReliefF coefficient, and Partition-Membership filter. The performance metrics of the classification model included accuracy (Acc), precision (Pre), area under curve (AUC), and kappa statistics.Results: The 10 features (First order shape features: Sphericity and Compacity, Gray-Level Run Length Matrix: Short-Run Emphasis, Low Gray-level Run Emphasis, and High Gray-level Run Emphasis, Gray Level Co-occurrence Matrix: Homogeneity, Energy, Contrast, Correlation, and Dissimilarity) showed the most stable and classification capability. The 6 classifiers, Logistic regression classifier (LR), Sequence Minimum Optimization algorithm, Random Forest, KStar, Naive Bayes and Random Committee, have great performance both on the train and the test sets, and especially LR has the best performance on the test set (Acc = 98.72, Pre = 0.988, AUC = 1, and kappa = 0.974).Conclusion: Lung adenocarcinoma can be identified based on CT radiomics features. We can diagnose lung adenocarcinoma with CT non-invasively.

Using texture analysis as a predictive factor of subtype, grade and stage of renal cell carcinoma.

The aim of this study was to evaluate the correlation between the tissue texture analysis and the histological subtypes, grade and stage of the disease in patients with renal cell carcinoma (RCC). Seventy-seven patients who underwent computed tomography due to renal mass and diagnosed with RCC as a result of pathological examination were retrospectively analyzed. In these analyses, the demographic characteristics, pathological and radiological findings of the patients were evaluated. The masses were introduced to the Radiomics extension of the software and the first- and second-order texture analysis parameters were obtained. The correlation of these parameters with histological subtype, Fuhrman grade and TNM stage was investigated. In the comparison of the Radiomics values by stages, "minimum", "Long Run Low Gray-level Emphasis" values were higher in the stage 1-2 group, while "Energy", "Total energy", "Range", "Joint Average", "Sum Average", "Gray-Level Non-Uniformity", "Short-Run High Gray-level Emphasis ", "Run Length Non-Uniformity "and "High Gray-Level Run Emphasis "values were higher in the stage 3-4 group. Of these parameters, only "Gray-Level Non-Uniformity" and "Run Length Non-Uniformity'' values were significantly lower in tumors with low Fuhrman grade (1-2) and low TNM stage (1-2). There was no statistically significant correlation between the parameters found to be significant in histological subtype differentiation and Fuhrman grade and TNM stage. This study demonstrates that "Gray-Level Non-Uniformity" and "Run Length Non-Uniformity "parameters in the texture analysis method can be used to evaluate the prognosis in patients with RCC.

Amide Proton Transfer Imaging in Predicting Isocitrate Dehydrogenase 1 Mutation Status of Grade II/III Gliomas Based on Support Vector Machine.

BackgroundTo compare the efficacies of univariate and radiomics analyses of amide proton transfer weighted (APTW) imaging in predicting isocitrate dehydrogenase 1 (IDH1) mutation of grade II/III gliomas.MethodsFifty-nine grade II/III glioma patients with known IDH1 mutation status were prospectively included (IDH1 wild type, 16; IDH1 mutation, 43). A total of 1044 quantitative radiomics features were extracted from APTW images. The efficacies of univariate and radiomics analyses in predicting IDH1 mutation were compared. Feature values were compared between two groups with independent t-test and receiver operating characteristic (ROC) analysis was applied to evaluate the predicting efficacy of each feature. Cases were randomly assigned to either the training (n = 49) or test cohort (n = 10) for the radiomics analysis. Support vector machine with recursive feature elimination (SVM-RFE) was adopted to select the optimal feature subset. The adverse impact of the imbalance dataset in the training cohort was solved by synthetic minority oversampling technique (SMOTE). Subsequently, the performance of SVM model was assessed on both training and test cohort.ResultsAs for univariate analysis, 18 features were significantly different between IDH1 wild-type and mutant groups (P < 0.05). Among these parameters, High Gray Level Run Emphasis All Direction offset 8 SD achieved the biggest area under the curve (AUC) (0.769) with the accuracy of 0.799. As for radiomics analysis, SVM model was established using 19 features selected with SVM-RFE. The AUC and accuracy for IDH1 mutation on training set were 0.892 and 0.952, while on the testing set were 0.7 and 0.84, respectively.ConclusionRadiomics strategy based on APT image features is potentially useful for preoperative estimating IDH1 mutation status.

Textural features of cervical cancers on FDG-PET/CT associate with survival and local relapse in patients treated with definitive chemoradiotherapy

We retrospectively reviewed the records of 142 patients with stage IB–IIIB cervical cancer who underwent 18F-FDG-PET/CT before external beam radiotherapy plus intracavitary brachytherapy and concurrent chemotherapy. The patients were divided into training and validation cohorts to confirm the reliability of predictors for recurrence. Kaplan–Meier analysis was performed and a Cox regression model was used to examine the effects of variables on overall survival (OS), progression-free survival (PFS), distant metastasis-free survival (DMFS), and pelvic relapse-free survival (PRFS). High gray-level run emphasis (HGRE) derived from gray-level run-length matrix most accurately and consistently predicted the presence of pelvic residual or recurrent tumors for both cohorts. In multivariate analysis, stages IIIA–IIIB (P = 0.001, hazard ratio [HR] = 4.07) and a low HGRE (P < 0.0001, HR = 4.34) were prognostic factors for low OS, whereas a low HGRE (P = 0.001, HR = 2.86) and nonsquamous cell histology (P = 0.003, HR = 2.76) were prognostic factors for inferior PFS. The nonsquamous cell histology (P < 0.0001, HR = 9.19) and a low HGRE (P = 0.001, HR = 4.69) were predictors for low PRFS. In cervical cancer patients receiving definitive chemoradiotherapy, pretreatment textural features on 18F-FDG-PET/CT can supplement the prognostic information.

Intratumoral heterogeneity in 18F-FDG PET/CT by textural analysis in breast cancer as a predictive and prognostic subrogate.

To assess the predictive and prognostic value of textural parameters in locally advanced breast cancer (LABC) obtained by 18F-FDG PET/CT. Prospective study including 68 patients with LABC, neoadjuvant chemotherapy (NC) indication and a baseline 18F-FDG PET/CT. Breast specimens were grouped into molecular phenotypes and classified as responders or non-responders after completion of NC. Patients underwent standard follow-up to obtain the disease-free survival (DFS) and overall survival (OS). After breast tumor segmentation, three-dimensional (3D) textural measures were computed based on run-length matrices (RLM) and co-occurrence matrices (CM). Relations between textural features with risk categories attending to molecular phenotypes were explored. Kaplan-Meier analysis and univariate and multivariate Cox proportional hazard analysis were used to study the potential of textural variables, molecular phenotypes and histologic response to predict DFS and OS. Receiver operating characteristic (ROC) analysis was used to obtain the best cut-off value, the area under the curve (AUC) and sensitivity and specificity considering OS and DFS. Eighteen patients were classified as responders. Mean ± SD of DFS and OS was 70.87 ± 21.85 and 76.77 ± 18.80months, respectively. Long run emphasis (LRE) and long run high gray-level emphasis (LRHGE) showed a relation with risk categories. Low gray-level run emphasis (LGRE), LRHGE and run-length non-uniformity (RLNU) showed association with the NC response. Textural variables were significantly associated with OS and DFS in univariate analysis. Regarding the multivariate Cox regression analysis, PET stage with short run high gray-level emphasis (SRHGE) was significantly associated with OS, and PET stage and high gray-level run emphasis (HGRE) with DFS. Textural variables obtained with 18F-FDG PET/CT were predictors of neoadjuvant chemotherapy response and prognosis, being as relevant as PET stage at diagnosis for OS and DFS prediction.

MR textural analysis on T2 FLAIR images for the prediction of true oligodendroglioma by the 2016 WHO genetic classification.

The genetic status of 1p/19q is important for differentiating oligodendroglioma, isocitrate-dehydrogenase (IDH)-mutant, and 1p/19q-codeleted from diffuse astrocytoma, IDH-mutant according to the 2016 World Health Organization (WHO) criteria. To assess the value of magnetic resonance textural analysis (MRTA) on T2 fluid-attenuated inversion recovery (FLAIR) images for making a genetically integrated diagnosis of true oligodendroglioma by WHO guidelines. Retrospective case control. In all, there were 54 patients with a histopathological diagnosis of diffuse glioma (grade II). All were tested for IDH and 1p/19q. 3.0T, including T2 FLAIR sequence, axial T1 -weighted, and T2 -weighted sequence. MRTA on a representative tumor region of interest (ROI) was made on preoperative T2 FLAIR images around the area that had the largest diameter of solid tumor using Omni Kinetics software. Differences between IDH-mutant and 1p/19q-codeleted and IDH-mutant and 1p/19q-intact gliomas were analyzed by the Mann-Whitney rank sum test. Receiver operating characteristic curves (ROC) were created to assess MRTA diagnostic performance. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated with a cutoff value according to the Youden Index. Comparisons demonstrated significant differences in kurtosis (P = 0.007), energy (0.008), entropy (0.008), mean deviation (MD) (<0.001), and high gray-level run emphasis (HGLRE) (0.002), cluster shade (0.025), and sum average (0.002). First-order features comprising entropy (area under the curve [AUC] = 0.718, sensitivity = 97.1%) and energy (0.719, 94.1%) had the highest sensitivity but lower specificity (both 45%). Second-order features such as HGLRE (AUC = 0.750, sensitivity = 73.5%, specificity = 80.0%) and sum average (0.751, 70.6%, 80.0%) had relatively higher specificity, and all had AUC >0.7. MD had the highest diagnostic performance, with AUC = 0.878, sensitivity = 94.1%, specificity = 75.0%, PPV = 86.5%, and NPV = 88.2%. MRTA on T2 FLAIR images may be helpful in identifying oligodendroglioma, IDH-mutant, and 1p/19q-codeleted. 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017.

Predicting Overall Survival of Local Advanced Rectal Cancer Patients Treated With Neoadjuvant Chemoradiation Therapy by Radiomic Features Extracted From Planning CTs

To investigate the feasibility of predicting the prognosis of local advanced rectal cancer patients using a variety of radiomic features extracted from planning Computed Tomography (CT). We hypothesize that informative radiomic features will allow us to predict patient survival. A total of 93 local advanced rectal cancer patients treated with neoadjuvant chemo-radiotherapy (CRT) were enrolled in this study. In these patients, 52 of them were stage 3, 22 of them were stage 2, others were stage 1 or stage 4. All patients underwent planning CT scans before CRT. The Gross Tumor Volume (GTV) on the CT images were applied to define the area of primary lesion in this research. The CT images were filtered by Laplacian of Gaussian (LoG) filters to reduce image noise. A total of 170 radiomics features were extracted from the filtered images, including 3 geometry features, 12 histogram features, 100 GLCM (Gray-Level Co-Occurrence Matrix) texture features, and 55 GLRLM (Gray Level Run Length Matrix) texture features. A univariate Cox regression analysis were preformed upon all features to select the most predictive features. The first 4 features with the lowest p-value in univariate analysis were used to build a Cox regression model for predicting overall survival of these patients. The model was bootstrapped for 200 times to validate the accuracy of its result. A training C-index and a validation C-index of the Cox model were calculated to evaluate the performance of the prediction. 17 of 93 patients were deceased over a median follow-up time of 3 years. The 4 features most frequently selected in the univariate Cox regression analysis were Entropy of the histogram features, Maximal Correlation Coefficient and Homogeneity of the GLCM texture features, and High Gray Level Run Emphasis of the GLRLMS texture features. The final Cox regression model had a training C-index of 0.69 (0.55-0.79) and a validation C-index of 0.59 (0.39-0.65). Our results demonstrate that radiomic features extracted from planning CT scans are related to overall survival of rectal cancer patients. The Cox regression model built upon the informative radiomic features has promising performance for predicting overall survival of rectal cancer patients.

Influence of gray level and space discretization on brain tumor heterogeneity measures obtained from magnetic resonance images

PurposeTumor heterogeneity in medical imaging is a current research trend due to its potential relationship with tumor malignancy. The aim of this study is to analyze the effect of dynamic range and matrix size changes on the results of different heterogeneity measures. Materials and methodsFour patients harboring three glioblastomas and one metastasis were considered. Sixteen textural heterogeneity measures were computed for each patient, with a configuration including co-occurrence matrices (CM) features (local heterogeneity) and run-length matrices (RLM) features (regional heterogeneity). The coefficient of variation measured agreement between the textural measures in two types of experiments: (i) fixing the matrix size and changing the dynamic range and (ii) fixing the dynamic range and changing the matrix size. ResultsNone of the measures considered were robust under dynamic range changes. The CM Entropy and the RLM high gray-level run emphasis (HGRE) were the outstanding textural features due to their robustness under matrix size changes. Also, the RLM low gray-level run emphasis (LGRE) provided robust results when the dynamic range considered was sufficiently high (more than 8 levels). All of the remaining textural features were not robust. ConclusionTumor texture studies based on images with different characteristics (e.g. multi-center studies) should first fix the dynamic range to be considered. For studies involving images of different resolutions either (i) only robust measures should be used (in our study CM entropy, RLM HGRE and/or RLM LGRE) or (ii) images should be resampled to match those of the lowest resolution before computing the textural features.

Impact of Image Reconstruction Settings on Texture Features in 18F-FDG PET.

Evaluation of tumor heterogeneity based on texture parameters has recently attracted much interest in the PET imaging community. However, the impact of reconstruction settings on texture parameters is unclear, especially relating to time-of-flight and point-spread function modeling. Their effects on 55 texture features (TFs) and 6 features based on first-order statistics (FOS) were investigated. Standardized uptake value (SUV) measures were also evaluated as peak SUV (SUVpeak), maximum SUV, and mean SUV (SUVmean). This study retrospectively recruited 20 patients with lesions in the lung who underwent whole-body (18)F-FDG PET/CT. The coefficient of variation (COV) of each feature across different reconstructions was calculated. SUVpeak, SUVmean, 18 TFs, and 1 FOS were the most robust (COV ≤ 5%) whereas skewness, cluster shade, and zone percentage were the least robust (COV > 20%) with respect to reconstruction algorithms using default settings. Heterogeneity parameters had different sensitivities to iteration number. Twenty-four parameters including SUVpeak and SUVmean exhibited variation with a COV less than 5%; 28 parameters, including maximum SUV, showed variation with a COV in the range of 5%-10%. In addition, skewness, cluster shade, and zone percentage were the most sensitive to iteration number. In terms of sensitivity to full width at half maximum (FWHM), 15 TFs and 1 FOS had the best performance with a COV less than 5%, whereas SUVpeak and SUVmean had a COV between 5% and 10%. Grid size had the largest impact on image features, which was demonstrated by only 11 features, including SUVpeak and SUVmean, having a COV less than 10%. Different image features have different sensitivities to reconstruction settings. Iteration number and FWHM of the gaussian filter have a similar impact on the image features. Grid size has a larger impact on the features than iteration number and FWHM. The features that exhibited large variations such as skewness in FOS, cluster shade, and zone percentage should be used with caution. The entropy in FOS, difference entropy, inverse difference normalized, inverse difference moment normalized, low gray-level run emphasis, high gray-level run emphasis, and low gray-level zone emphasis are the most robust features.

Relationship between tumor heterogeneity measured on FDG-PET/CT and pathological prognostic factors in invasive breast cancer.

BackgroundThere is currently little support to understand which pathological factors led to differences in tumor texture as measured from FDG PET/CT images. We studied whether tumor heterogeneity measured using texture analysis in FDG-PET/CT images is correlated with pathological prognostic factors in invasive breast cancer.MethodsFifty-four patients with locally advanced breast cancer who had an initial FDG-PET/CT were retrospectively included. In addition to SUVmax, three robust textural indices extracted from 3D matrices: High-Gray-level Run Emphasis (HGRE), Entropy and Homogeneity were studied. Univariate and multivariate logistic regression was used to identify PET parameters associated with poor prognosis pathological factors: hormone receptor negativity, presence of HER-2 and triple negative phenotype. Receiver operating characteristic (ROC) curves and the (AUC) analysis, and reclassification measures, were performed in order to evaluate the performance of combining texture analysis and SUVmax for characterizing breast tumors.ResultsTumor heterogeneity, measured with HGRE, was higher in negative estrogen receptor (p = 0.039) and negative progesterone receptor tumors (p = 0.036), and in Scarff-Bloom-Richardson grade 3 tumors (p = 0.047). None of the PET indices could identify HER-2 positive tumors. Only SUVmax was positively correlated with Ki-67 (p<0.0004). Triple negative breast cancer (TNBC) exhibited higher SUVmax (Odd Ratio = 1.22, 95%CI [1.06–1.39],p = 0.004), lower Homogeneity (OR = 3.57[0.98–12.5],p = 0.05) and higher HGRE (OR = 8.06[1.88–34.51],p = 0.005) than non-TNBC. Multivariate analysis showed that HGRE remained associated with TNBC (OR = 5.27[1.12–1.38],p = 0.03) after adjustment for SUVmax. Combining SUVmax and HGRE yielded in higher area under the ROC curves (AUC) than SUVmax for identifying TNBC: AUC = 0.83 and 0.77, respectively. Probability of correct classification also increased in 77% (10/13) of TNBC and 71% (29/41) of non-TNBC (p = 0.003), when combining SUVmax and HGRE.ConclusionsTumor heterogeneity measured on FDG-PET/CT was higher in invasive breast cancer with poor prognosis pathological factors. Texture analysis might be used, in addition to SUVmax, as a new tool to assess invasive breast cancer aggressiveness.

Use of gray value distribution of run lengths for texture analysis

Most of the texture measures based on run lengths use only the lengths of the runs and their distribution. We propose to use the gray value distribution of the runs to define two new features, viz., low gray level run emphasis ( LGRE) and high gray level run emphasis ( HGRE).