Gray Level Size Zone Matrix Research Articles

Can texture analysis based on single unenhanced CT accurately predict the WHO/ISUP grading of localized clear cell renal cell carcinoma?

The purpose was to investigate the value of texture analysis in predicting the World Health Organization (WHO)/International Society of Urological Pathology (ISUP) grading of localized clear cell renal cell carcinoma (ccRCC) based on unenhanced CT (UECT). Pathologically confirmed subjects (n = 104) with localized ccRCC who received UECT scanning were collected retrospectively for this study. All cases were classified into low grade (n = 53) and high grade (n = 51) according to the WHO/ISUP grading and were randomly divided into training set and test set as a ratio of 7:3. Using 3D-ROI segmentation on UECT images and extracted ninety-three texture features (first-order, gray-level co-occurrence matrix [GLCM], gray-level run length matrix [GLRLM], gray-level size zone matrix [GLSZM], neighboring gray tone difference matrix [NGTDM] and gray-level dependence matrix [GLDM] features). Univariate analysis and the least absolute shrinkage selection operator (LASSO) regression were used for feature dimension reduction, and logistic regression classifier was used to develop the prediction model. Using receiver operating characteristic (ROC) curve, bar chart and calibration curve to evaluate the performance of the prediction model. Dimension reduction screened out eight optimal texture features (maximum, median, dependence variance [DV], long run emphasis [LRE], run entropy [RE], gray-level non-uniformity [GLN], gray-level variance [GLV] and large area low gray-level emphasis [LALGLE]), and then the prediction model was developed according to the linear combination of these features. The accuracy, sensitivity, specificity, and AUC of the model in training set were 86.1%, 91.4%, 81.1%, and 0.937, respectively. The accuracy, sensitivity, specificity, and AUC of the model in test set were 81.2%, 81.2%, 81.2%, and 0.844, respectively. The calibration curves showed good calibration both in training set and test set (P > 0.05). This study has demonstrated that the radiomics model based on UECT texture analysis could accurately evaluate the WHO/ISUP grading of localized ccRCC.

Prediction of Microvascular Invasion in Hepatocellular Carcinoma With a Multi-Disciplinary Team-Like Radiomics Fusion Model on Dynamic Contrast-Enhanced Computed Tomography.

ObjectiveTo investigate microvascular invasion (MVI) of HCC through a noninvasive multi-disciplinary team (MDT)-like radiomics fusion model on dynamic contrast enhanced (DCE) computed tomography (CT).MethodsThis retrospective study included 111 patients with pathologically proven hepatocellular carcinoma, which comprised 57 MVI-positive and 54 MVI-negative patients. Target volume of interest (VOI) was delineated on four DCE CT phases. The volume of tumor core (Vtc) and seven peripheral tumor regions (Vpt, with varying distances of 2, 4, 6, 8, 10, 12, and 14 mm to tumor margin) were obtained. Radiomics features extracted from different combinations of phase(s) and VOI(s) were cross-validated by 150 classification models. The best phase and VOI (or combinations) were determined. The top predictive models were ranked and screened by cross-validation on the training/validation set. The model fusion, a procedure analogous to multidisciplinary consultation, was performed on the top-3 models to generate a final model, which was validated on an independent testing set.ResultsImage features extracted from Vtc+Vpt(12mm) in the portal venous phase (PVP) showed dominant predictive performances. The top ranked features from Vtc+Vpt(12mm) in PVP included one gray level size zone matrix (GLSZM)-based feature and four first-order based features. Model fusion outperformed a single model in MVI prediction. The weighted fusion method achieved the best predictive performance with an AUC of 0.81, accuracy of 78.3%, sensitivity of 81.8%, and specificity of 75% on the independent testing set.ConclusionImage features extracted from the PVP with Vtc+Vpt(12mm) are the most reliable features indicative of MVI. The MDT-like radiomics fusion model is a promising tool to generate accurate and reproducible results in MVI status prediction in HCC.

Repeatability of CBCT radiomic features and their correlation with CT radiomic features for prostate cancer.

Radiomic features of cone-beam CT (CBCT) images have potential as biomarkers to predict treatment response and prognosis for patients of prostate cancer. Previous studies of radiomic feature analysis for prostate cancer were assessed in a variety of imaging modalities, including MRI, PET, and CT, but usually limited to a pretreatment setting. However, CBCT images may provide an opportunity to capture early morphological changes to the tumor during treatment that could lead to timely treatment adaptation. This work investigated the quality of CBCT-based radiomic features and their relationship with reconstruction methods applied to the CBCT projections and the preprocessing methods used in feature extraction. Moreover, CBCT features were correlated with planning CT (pCT) features to further assess the viability of CBCT radiomic features. The quality of 42 CBCT-based radiomic features was assessed according to their repeatability and reproducibility. Repeatability was quantified by correlating radiomic features between 20 CBCT scans that also had repeated scans within 15minutes. Reproducibility was quantified by correlating radiomic features between the planning CT (pCT) and the first fraction CBCT for 20 patients. Concordance correlation coefficients (CCC) of radiomic features were used to estimate the repeatability and reproducibility of radiomic features. The same patient dataset was assessed using different reconstruction methods applied to the CBCT projections. CBCT images were generated using 18 reconstruction methods using iterative (iCBCT) and standard (sCBCT) reconstructions, three convolution filters, and five noise suppression filters. Eighteen preprocessing settings were also considered. Overall, CBCT radiomic features were more repeatable than reproducible. Five radiomic features are repeatable in>97% of the reconstruction and preprocessing methods, and come from the gray-level size zone matrix (GLSZM), neighborhood gray-tone difference matrix (NGTDM), and gray-level-run length matrix (GLRLM) radiomic feature classes. These radiomic features were reproducible in>9.8% of the reconstruction and preprocessing methods. Noise suppression and convolution filter smoothing increased radiomic features repeatability, but decreased reproducibility. The top-repeatable iCBCT method (iCBCT-Sharp-VeryHigh) is more repeatable than the top-repeatable sCBCT method (sCBCT-Smooth) in 64% of the radiomic features. Methods for reconstruction and preprocessing that improve CBCT radiomic feature repeatability often decrease reproducibility. The best approach may be to use methods that strike a balance repeatability and reproducibility such as iCBCT-Sharp-VeryLow-1-Lloyd-256 that has 17 repeatable and eight reproducible radiomic features. Previous radiomic studies that only used pCT radiomic features have generated prognostic models of prostate cancer outcome. Since our study indicates that CBCT radiomic features correlated well with a subset of pCT radiomic features, one may expect CBCT radiomics to also generate prognostic models for prostate cancer.

Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach

Purpose Preoperative prediction of isocitrate dehydrogenase 1 (IDH1) mutation in lower-grade gliomas (LGGs) is crucial for clinical decision-making. This study aimed to examine the predictive value of a machine learning approach using qualitative and quantitative MRI features to identify the IDH1 mutation in LGGs. Materials and Methods A total of 102 LGG patients were allocated to training (n = 67) and validation (n = 35) cohorts and were subject to Visually Accessible Rembrandt Images (VASARI) feature extraction (23 features) from conventional multimodal MRI and radiomics feature extraction (56 features) from apparent diffusion coefficient maps. Feature selection was conducted using the maximum Relevance Minimum Redundancy method and 0.632+ bootstrap method. A machine learning model to predict IDH1 mutation was then established using a random forest classifier. The predictive performance was evaluated using receiver operating characteristic (ROC) curves. Results After feature selection, the top 5 VASARI features were enhancement quality, deep white matter invasion, tumor location, proportion of necrosis, and T1/FLAIR ratio, and the top 10 radiomics features included 3 histogram features, 3 gray-level run-length matrix features, and 3 gray-level size zone matrix features and one shape feature. Using the optimal VASARI or radiomics feature sets for IDH1 prediction, the trained model achieved an area under the ROC curve (AUC) of 0.779 ± 0.001 or 0.849 ± 0.008 on the validation cohort, respectively. The fusion model that integrated outputs of both optimal VASARI and radiomics models improved the AUC to 0.879. Conclusion The proposed machine learning approach using VASARI and radiomics features can predict IDH1 mutation in LGGs.

Preoperative classification of primary and metastatic liver cancer via machine learning-based ultrasound radiomics.

To investigate the application of machine learning-based ultrasound radiomics in preoperative classification of primary and metastatic liver cancer. Data of 114 consecutive histopathologically confirmed patients with liver cancer from January 2018 to November 2019 were retrospectively analyzed. All patients underwent liver ultrasonography within 1week before hepatectomy or fine-needle biopsy. The liver lesions were manually segmented by two experts using ITK-SNAP software. Seven categories of radiomics features, including first-order, two-dimensional shape, gray-level co-occurrence matrices, gray-level run-length matrix, gray-level size-zone matrix, neighboring gray tone difference matrix, and gray-level dependence matrix, were extracted on the Pyradiomics platform. Fourteen filters were applied to the original images, and derived images were obtained. Then, the dimensions of radiomics features were reduced by least absolute shrinkage and selection operator (Lasso) method. Finally, k-nearest neighbor (KNN), logistic regression (LR), multilayer perceptron (MLP), random forest (RF), and support vector machine (SVM) were employed to distinguish primary liver cancer from metastatic liver cancer by a fivefold cross-validation strategy. The performance of the established model was mainly evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy. One thousand four hundred nine radiomics features were extracted from the original images and/or derived images for each patient. The mentioned five machine learning classifiers were able to differentiate primary liver cancer from metastatic liver cancer. LR outperformed other classifiers, with the accuracy of 0.843 ± 0.078 (AUC, 0.816 ± 0.088; sensitivity, 0.768 ± 0.232; specificity, 0.880 ± 0.117). Machine learning-based ultrasound radiomics features are able to non-invasively distinguish primary liver tumors from metastatic liver tumors. • Ultrasound-based radiomics was initially used for preoperative classification of primary versus metastatic liver cancer. • Multiple machine learning-based algorithms with cross-validation strategy were applied to extract machine learning-based ultrasound radiomics features. • Distinction between primary and metastatic tumors was obtained with a sensitivity of 0.768 and a specificity of 0.880.

Radiomics Signature: A potential biomarker for the prediction of survival in Advanced Hepatocellular Carcinoma.

Objectives: To develop and validate radiomics nomograms for the pretreatment predictions of overall survival (OS) and time to progression (TTP) in the patients with advanced hepatocellular carcinoma (HCC) treated with apatinib plus transarterial chemoembolization (TACE), and to assess the incremental value of the clinical-radiomics nomograms for estimating individual OS and TTP.Methods: A total of 60 patients with advanced HCC (BCLC stage C) treated with apatinib plus TACE were divided into a training set (n=48) and a validation set (n=12). The predictors identified from the clinical variables and the radiomics signature constructed from the computed tomography images, such as ɑ-fetoprotein level (AFP), formfactor, the grey level co-occurrence matrix, the gray level size zone matrix, and the gray level run-length matrix, were used to build the clinical-radiomics nomograms and the radiomics nomograms for the prediction of OS and TTP.Results: Apatinib plus TACE benefited the patients with advanced HCC, with a 579-day median OS and a 270-day median TTP. The nomograms were built with the radiomics signature and AFP, and achieved favorable prediction efficacy with acceptable calibration curves. Decision curve analyses demonstrated that the clinical-radiomics nomograms outperformed the radiomics nomograms for the predictions of OS and TTP.Conclusions: Apatinib plus TACE may improve OS and prolonged TTP in the patients with advanced HCC. The clinical-radiomics nomograms, a noninvasive pretreatment prediction tool that incorporate radiomics signature and AFP, demonstrated good prediction accuracy for OS and TTP in these patients. These results indicate that the clinical-radiomics nomograms may provide novel insight for precise personalized medicine approaches in the patients with advanced HCC.

Interpretable Machine Learning Model for Locoregional Relapse Prediction in Oropharyngeal Cancers.

Simple SummaryMachine learning may be used to personalize cancer care. However, physicians need interpretability to understand and use a predictive model powered by machine learning. We present a radiomics based model, interpretable for each patient, trained on an American multicentric cohort that yielded a 92% predictive value for relapse at 18 months in oropharyngeal cancers when tested on an external multicentric prospective French cohort.Background: There is no evidence to support surgery or radiotherapy as the best treatment for resectable oropharyngeal cancers with a negative HPV status. Predictive algorithms may help to decide which strategy to choose, but they will only be accepted by caregivers and European authorities if they are interpretable. As a proof of concept, we developed a predictive and interpretable algorithm to predict locoregional relapse at 18 months for oropharyngeal cancers as a first step towards that goal. Methods: The model was based on clinical and Pyradiomics features extracted from the dosimetric CT scan. Intraclass correlation was used to filter out features dependant on delineation. Correlated redundant features were also removed. An XGBoost model was cross-validated and optimised on the HN1 cohort (79 patients), and performances were assessed on the ART ORL cohort (45 patients). The Shapley Values were used to provide an overall and local explanation of the model. Results: On the ART ORL cohort, the model trained on HN1 yielded a precision—or predictive positive value—of 0.92, a recall of 0.42, an area under the curve of the receiver operating characteristic of 0.68 and an accuracy of 0.64. The most contributory features were shape Voxel Volume, grey level size zone matrix Small Area Emphasis (glszmSAE), gldm Dependence Non Uniformity Normalized (gldmDNUN), Sex and Age. Conclusions: We developed an interpretable and generalizable model that could yield a good precision—positive predictive value—for relapse at 18 months on a different test cohort.

IMG-10. MRI-BASED RADIOMIC PROGNOSTIC MARKERS OF DIFFUSE MIDLINE GLIOMA

BACKGROUNDDiffuse midline gliomas (DMG) are lethal pediatric brain tumors with dismal prognoses. Presently, MRI is the mainstay of disease diagnosis and surveillance. We aimed to identify prognostic image-based radiomics markers of DMG and compare its performance to clinical variables at presentation.METHODS104 treatment-naïve DMG MRIs from five centers were used (median age=6.5yrs; 18 males, median OS=11mos). We isolated tumor volumes of T1-post-contrast (T1gad) and T2-weighted (T2) MRI for PyRadiomics high-dimensional feature extraction. 900 features were extracted on each image, including first order statistics, 2D/3D Shape, Gray Level Co-occurrence Matrix, Gray Level Run Length Matrix, Gray Level Size Zone Matrix, Neighboring Gray tone Difference Matrix, and Gray Level Dependence Matrix, as defined by Imaging Biomarker Standardization Initiative. Overall survival (OS) served as outcome. 10-fold cross-validation of LASSO Cox regression was used to predict OS. We analyzed model performance using clinical variable (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variable. Concordance metric was used to assess the Cox model.RESULTSNine radiomic features were selected from T1gad (2 texture wavelet) and T2 (5 first-order features (1 original, 4 wavelet), 2 texture features (1 wavelet, 1 log-sigma). This model demonstrated significantly higher performance than a clinical model alone (C: 0.68 vs 0.59, p<0.001). Adding clinical features to radiomic features slightly improved prediction, but was not significant (C=0.70, p=0.06).CONCLUSIONOur pilot study shows a potential role for MRI-based radiomics and machine learning for DMG risk stratification and as image-based biomarkers for clinical therapy trials.

Prediction of burden and management of renal calculi from whole kidney radiomics: a multicenter study.

PurposeTo assess if autosegmentation-assisted radiomics can predict disease burden, hydronephrosis, and treatment strategies in patients with renal calculi.MethodsThe local ethical committee-approved, retrospective study included 202 adult patients (mean age: 53 ± 17 years; male: 103; female: 99) who underwent clinically indicated, non-contrast abdomen-pelvis CT for suspected or known renal calculi. All CT examinations were reviewed to determine the presence (n = 123 patients) or absence (n = 79) of renal calculi. On CT images with renal calculi, each kidney stone was annotated and measured (maximum dimension, Hounsfield unit (HU), and combined and dominant stone volumes) using a HU threshold-based segmentation. We recorded the presence of hydronephrosis, number of renal calculi, and treatment strategies. Deidentified CT images were processed with the radiomics prototype (Radiomics, Frontier, Siemens Healthineers), which automatically segmented each kidney to obtain 1690 first-, shape-, and higher-order radiomics. Data were analyzed using multiple logistic regression analysis with areas under the curve (AUC) as output.ResultsAmong 202 patients, only 28 patients (18%) needed procedural treatment (lithotripsy or ureteroscopic stone extraction). Gray-level co-occurrence matrix (GLCM) and gray-level run length matrix (GLRLM) differentiated patients with and without procedural treatment (AUC 0.91, 95% CI 0.85–0.92). Higher-order radiomics (gray-level size zone matrix – GLSZM) differentiated kidneys with and without hydronephrosis (AUC: 0.99, p < 0.001) as well those with different stone volumes (AUC up to 0.89, 95% CI 0.89–0.92).ConclusionAutomated segmentation and radiomics of entire kidneys can assess hydronephrosis presence, stone burden, and treatment strategies for renal calculi with AUCs > 0.85.

A Paradigm Shift in Nuclear Chromatin Interpretation: From Qualitative Intuitive Recognition to Quantitative Texture Analysis of Breast Cancer Cell Nuclei.

Assessing the pattern of nuclear chromatin is essential for pathological investigations. However, the interpretation of nuclear pattern is subjective. In this study, we performed the texture analysis of nuclear chromatin in breast cancer samples to determine the nuclear pleomorphism score thereof. We used three different algorithms for extracting high‐level texture features: the gray‐level co‐occurrence matrix (GLCM), gray‐level run length matrix (GLRLM), and gray‐level size zone matrix (GLSZM). Using these algorithms, 12 GLCM, 11 GLRLM, and 16 GLSZM features were extracted from three scores of breast carcinoma (Scores 1–3). Classification accuracy was assessed using the support vector machine (SVM) and k‐nearest neighbor (KNN) classification models. Three features of GLCM, 11 of GLRLM, and 12 of GLSZM were consistent across the three nuclear pleomorphism scores of breast cancer. Comparing Scores 1 and 3, the GLSZM feature large zone high gray‐level emphasis showed the largest difference among breast cancer nuclear scores among all features of the three algorithms. The SVM and KNN classifiers showed favorable results for all three algorithms. A multiclass classification was performed to compare and distinguish between the scores of breast cancer. Texture features of nuclear chromatin can provide useful information for nuclear scoring. However, further validation of the correlations of histopathologic features, and standardization of the texture analysis process, are required to achieve better classification results. © 2021 The Authors. Cytometry Part A published by Wiley Periodicals LLC on behalf of International Society for Advancement of Cytometry.

Radiomic Features Predict Rib Fracture after Stereotactic Body Radiotherapy for Early Stage Non-Small Cell Lung Cancer

Dose to the chest wall is a well-established predictor of rib fracture after stereotactic body radiation therapy (SBRT), but even with a high dose to the chest wall most patients will not develop a fracture. Discovering other predictors that are independent from dose will improve our ability to predict which patients will develop a rib fracture. Radiomic analysis of the chest wall can provide an opportunity to find such features on imaging. A retrospective analysis was conducted of 73 patients with early stage NSCLC who were treated with SBRT. Quantitative radiomic feature extraction using PyRadiomics was performed on the 4D treatment planning scans of all patients. A total of 236 radiomic features were extracted, all of which were based on a Boolean overlap of the 20 Gy isodose volume and the chest wall. A 10-fold cross validation based Elastic Net Cox regression was completed for variable selection and used to identify the lambda (regularization parameter) value that produced the lowest cross-validated error. Variables that remained in the final model were then evaluated independently with univariate Cox regression hazard ratios and in a multivariate model built with and without the radiomic features and compared based on concordance indexes that were averaged across a Monte Carlo cross-validation scheme with 10 resamples. Correlation between predictors was evaluated using Pearson’s correlation coefficient. Twenty-nine patients with radiation induced rib fractures were identified retrospectively and compared to 44 patients with no rib fracture. The Elastic Net Cox regression model with the lowest cross-validated error included 6 predictors: three clinical and three radiomic. The clinical variables included volume of overlap between the PTV and chest wall (HR 2.49, p < 0.01), volume of chest wall receiving 50 Gy (HR 2.23, p < 0.01) and volume of rib receiving 50 Gy (HR 2.14, p < 0.01). Radiomic variables included shape elongation (HR 0.64, p = 0.03), Gray Level Size Zone Matrix (GLSZM) Large Area Low Gray Level Emphasis (LALGLE; HR 2.24, p < 0.01) and Neighboring Gray Tone Difference Matrix (NGTDM) busyness (HR 2.36, p < 0.01). A multivariate model that included only the clinical variables had a concordance index of 0.69 (95% CI 0.61-0.77) while inclusion of the radiomic variables increased the concordance index to 0.79 (95% CI 0.76 to 0.82). Of the 3 identified radiomic features, shape elongation was the least correlated with the clinical variables. The Pearson correlation coefficient comparing shape elongation to chest wall V50 was 0.03 (95% CI -0.20 to 0.25, p = 0.824). Radiomic feature extraction from the chest wall can provide insight into a patient’s risk of a rib fracture after SBRT. Of the radiomic features found to persist in the final multivariate model, shape elongation was the only variable not correlated with chest wall dose. This provides evidence for a predictor of rib fracture after SBRT that is independent of chest wall dose.

Makine Öğrenimi Tekniklerini Kullanarak SAR Görüntülemesinden Otomatik Hedef Tanıma (OHT)

Automatic Target Recognition (ATR) in Synthetic aperture radar (SAR) images becomes a very challenging problem owing to containing high level noise. In this study, a machine learning-based method is proposed to detect different moving and stationary targets using SAR images. First Order Statistical (FOS) features were obtained from Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) on gray level SAR images. Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM) and Gray Level Size Zone Matrix (GLSZM) algorithms are also used. These features are provided as input for the training and testing stage Support Vector Machine (SVM) model with Gaussian kernels. 4-fold cross-validations were implemented in performance evaluation. Obtained results showed that GLCM + SVM algorithm is the best model with 95.26% accuracy. This proposed method shows that moving and stationary targets in MSTAR database could be recognized with high performance.

Exploring MRI based radiomics analysis of intratumoral spatial heterogeneity in locally advanced nasopharyngeal carcinoma treated with intensity modulated radiotherapy.

BackgroundWe hypothesized that spatial heterogeneity exists between recurrent and non-recurrent regions within a tumor. The aim of this study was to determine if there is a difference between radiomics features derived from recurrent versus non recurrent regions within the tumor based on pre-treatment MRI.MethodsA total of 14 T4NxM0 NPC patients with histologically proven “in field” recurrence in the post nasal space following curative intent IMRT were included in this study. Pretreatment MRI were co-registered with MRI at the time of recurrence for the delineation of gross tumor volume at diagnosis(GTV) and at recurrence(GTVr). A total of 7 histogram features and 40 texture features were computed from the recurrent(GTVr) and non-recurrent region(GTV-GTVr). Paired t-tests and Wilcoxon signed-rank tests were carried out on the 47 quantified radiomics features.ResultsA total of 7 features were significantly different between recurrent and non-recurrent regions. Other than the variance from intensity-based histogram, the remaining six significant features were either from the gray-level size zone matrix (GLSZM) or the neighbourhood gray-tone difference matrix (NGTDM).ConclusionsThe radiomic features extracted from pre-treatment MRI can potentially reflect the difference between recurrent and non-recurrent regions within a tumor and has a potential role in pre-treatment identification of intra-tumoral radio-resistance for selective dose escalation.

Radiomics for Gleason Score Detection through Deep Learning.

Prostate cancer is classified into different stages, each stage is related to a different Gleason score. The labeling of a diagnosed prostate cancer is a task usually performed by radiologists. In this paper we propose a deep architecture, based on several convolutional layers, aimed to automatically assign the Gleason score to Magnetic Resonance Imaging (MRI) under analysis. We exploit a set of 71 radiomic features belonging to five categories: First Order, Shape, Gray Level Co-occurrence Matrix, Gray Level Run Length Matrix and Gray Level Size Zone Matrix. The radiomic features are gathered directly from segmented MRIs using two free-available dataset for research purpose obtained from different institutions. The results, obtained in terms of accuracy, are promising: they are ranging between 0.96 and 0.98 for Gleason score prediction.

Automated design for recognition of blood cells diseases from hematopathology using classical features selection and ELM.

In the human immune system, the white blood cells (WBC) creates bone and lymphoid masses. These cells defend the human body toward several infections, such as fungi and bacteria. The popular WBC types are Eosinophils, Lymphocytes, Neutrophils, and Monocytes, which are manually diagnosis by the experts. The manual diagnosis process is complicated and time-consuming; therefore, an automated system is required to classify these WBC. In this article, a new method is presented for WBC classification using feature selection and extreme learning machine (ELM). At the very first step, data augmentation is performed to increases the number of images and then implement a new contrast stretching technique name pixel stretch (PS). In the next step, color and gray level size zone matrix (GLSZM) features are calculated from PS images and fused in one vector based on the level of high similarity. However, few redundant features are also included that affect the classification performance. For handling this problem, a maximum relevance probability (MRP) based feature selection technique is implemented. The best-selected features computed from a fitness function are ELM in this work. All maximum relevance features are put to ELM, and this process is continued until the error rate is minimized. In the end, the final selected features are classified through Cubic SVM. For validation of the proposed method, LISC and Dhruv datasets are used, and it achieved the highest accuracy of 96.60%. From the results, it is clearly shown that the proposed method results are improved as compared to other implemented techniques.

Optimal co-clinical radiomics: Sensitivity of radiomic features to tumour volume, image noise and resolution in co-clinical T1-weighted and T2-weighted magnetic resonance imaging.

BackgroundRadiomics analyses has been proposed to interrogate the biology of tumour as well as to predict/assess response to therapy in vivo. The objective of this work was to assess the sensitivity of radiomics features to noise, resolution, and tumour volume in the context of a co-clinical trial.MethodsTriple negative breast cancer (TNBC) patients were recruited into an ongoing co-clinical imaging trial. Sub-typed matched TNBC patient-derived tumour xenografts (PDX) were generated to investigate optimal co-clinical MR radiomic features. The MR imaging protocol included T1-weighed and T2-weighted imaging. To test the sensitivity of radiomics to resolution, PDX were imaged at three different resolutions. Multiple sets of images with varying signal-to-noise ratio (SNR) were generated, and an image independent patch-based method was implemented to measure the noise levels. Forty-eight radiomic features were extracted from manually segmented 2D and 3D segmented tumours and normal tissues of T1- and T2- weighted co-clinical MR images.FindingsSixteen radiomics features were identified as volume dependent and corrected for volume-dependency following normalization. Features from grey-level run-length matrix (GLRLM), grey-level size zone matrix (GLSZM) were identified as most sensitive to noise. Radiomic features Kurtosis and Run-length variance (RLV) from GLSZM were most sensitive to changes in resolution in both T1w and T2w MRI. In general, 3D radiomic features were more robust compared to 2D (single slice) measures, although the former exhibited higher variability between subjects.InterpretationTumour volume, noise characteristics, and image resolution significantly impact radiomic analysis in co-clinical studies.

On Representative Elementary Volumes of Grayscale Micro‐CT Images of Porous Media

AbstractThe concept of linking pore‐scale data to continuum‐scale characteristics of porous media relies on the existence of a representative elementary volume (REV). The current techniques for estimating REVs require access to segmented micro‐computed tomographic (micro‐CT) images and computations of petrophysical properties which are computationally intensive and time‐consuming. Herein, a texture characterization method called the Gray‐Level Size Zone Matrix (GLSZM) is applied directly to raw grayscale micro‐CT images. GLSZM representations of 3D micro‐CT images capture information regarding the connectivity of gray‐level intensities, termed as “size‐zones.” Statistical descriptors of pore space are calculated based on GLSZM to understand the connectivity of low gray‐level intensities. These GLSZM statistics capture microstructural fluctuations and offer insights into the impact of grayscale heterogeneity on REV size. This approach allows REV sizes to be estimated directly using grayscale micro‐CT images, in a reproducible, less time‐consuming and computationally efficient manner.

Quantitative accuracy of radiomic features of low-dose 18F-FDG PET imaging.

Background18F-FDG PET based radiomics is promising for precision oncology imaging. This work aims to explore quantitative accuracies of radiomic features (RFs) for low-dose 18F-FDG PET imaging.MethodsTwenty lung cancer patients were prospectively enrolled and underwent 18F-FDG PET/CT scans. Low-dose PET situations (true counts: 20×106, 15×106, 10×106, 7.5×106, 5×106, 2×106, 1×106, 0.5×106, 0.25×106) were simulated by randomly discarding counts from the acquired list-mode data. Each PET image was created using the scanner default reconstruction parameters. Each lesion volume of interest (VOI) was obtained via an adaptive contouring method with a threshold of 50% peak standardized uptake value (SUVpeak) in the PET images with full count data and VOIs were copied to the PET images at the reduced count level. Conventional SUV measures, features calculated from first-order statistics (FOS) and texture features (TFs) were calculated. Texture based RF include features calculated from gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), neighboring gray-level dependence matrix (NGLDM) and neighbor gray-tone difference matrix (NGTDM). Bias percentage (BP) at different count levels for each RF was calculated.ResultsFifty-seven lesions with a volume greater than 1.5 cm3 were found (mean volume, 25.7 cm3, volume range, 1.5–245.4 cm3). In comparison with normal total counts, mean SUV (SUVmean) in the lesions, normal lungs and livers, Entropy and sum entropy from GLCM, busyness from NGTDM and run-length non-uniformity from GLRLM were the most robust features, with a BP of 5% at the count level of 1×106 (equivalent to an effective dose of 0.04 mSv) RF including cluster shade from GLCM, long-run low grey-level emphasis, high grey-level run emphasis and short-run low grey-level emphasis from GLRM exhibited the worst performance with 50% of bias with 20×106 counts (equivalent to an effective dose of 0.8 mSv).ConclusionsIn terms of the lesions included in this study, SUVmean, entropy and sum entropy from GLCM, busyness from NGTDM and run-length non-uniformity from GLRLM were the least sensitive features to lowering count.

Radiomics Based on Thyroid Ultrasound Can Predict Distant Metastasis of Follicular Thyroid Carcinoma

We aimed to evaluate whether radiomics analysis based on gray-scale ultrasound (US) can predict distant metastasis of follicular thyroid cancer (FTC). We retrospectively included 35 consecutive FTCs with distant metastases and 134 FTCs without distant metastasis. We extracted a total of 60 radiomics features derived from the first order, shape, gray-level cooccurrence matrix, and gray-level size zone matrix features using US imaging. A radiomics signature was generated using the least absolute shrinkage and selection operator and was used to train a support vector machine (SVM) classifier in five-fold cross-validation. The SVM classifier showed an area under the curve (AUC) of 0.90 on average on the test folds. Age, size, widely invasive histology, extrathyroidal extension, lymph node metastases on pathology, nodule-in-nodule appearance, marked hypoechogenicity, and rim calcification on the US were significantly more frequent among FTCs with distant metastasis compared to those without metastasis (p < 0.05). Radiomics signature and widely invasive histology were significantly associated with distant metastasis on multivariate analysis (p < 0.01 and p = 0.003). The classifier using the results of the multivariate analysis showed an AUC of 0.93. The radiomics signature from thyroid ultrasound is an independent biomarker for noninvasively predicting distant metastasis of FTC.

Baseline radiomics features (RF) in metastatic colorectal cancer (mCRC): Correlation with m site and clinical-pathological characteristics.

e15589 Background: R is an emerging field of research based on the extraction of a large amount of F from biomedical images and on computed analysis algorithms of tumour architecture. Few data regarding mCRC are available, in particular no correlation of baseline RF both with m sites and clinical-pathological characteristics was so far investigated. Methods: Baseline chest-abdomen CT scans of mCRC patients (pts) were retrospectively analysed. RF were extracted from Regions of Interest (ROI) delineated on CT scan from each m sites, including primary tumor, when on site. The association of specific F and disease site (liver, lung, nodes, peritoneum and on-site primary tumor) was investigated. Sites similarity was assessed with Principal Component Analysis, an unsupervised learning technique to identify patterns and clusters. Then RFs were tested individually for correlation with clinical-pathological covariates of interest (gender, CEA level, synchronous disease, RAS/BRAF status, mucinous histology, grading, number of m site, primary tumor site). Wilcoxon-Mann-Whitney test was used for this purpose (significance level set at 0.05). Results: After RF extraction from the different ROIs, the dataset was composed of 433 observations of 236 variables. Observations referred to the number (N) of pts = 89 and the N of ROIs = 18. RF classes were divided in statistical F (grey-level histogram) (N of F = 10); morphological F (N = 14); texture F GLCM (grey level co-occurrence matrix) (N = 100); texture F GLRLM (grey level run length matrix) (N = 66); texture F GLSZM (grey level size zone matrix) (N = 32). Regarding the association of RF with m sites, an homogenous distribution with liver, nodes, peritoneum and primary tumor was detected, while lung metastases showed a different pattern for all the RF classes. A significant correlation of specific RF with clinical-pathologic characteristics was shown, in particular with gender, CEA level, synchronous disease, mucinous histology, RAS/BRAF status. Conclusions: Despite its retrospective nature and the limited number of pts, this is the first experience demonstrating I) a different pattern of RF for lung m versus an homogeneous RF distribution for the other m sites; and II) a significant association of specific RF with few clinical-pathologic characteristics. Our results, if confirmed in a prospective validation set, may represent an hypothesis generator regarding the different behaviour of lung metastases and a possible R signature able to identify different prognostic subgroups of pts.