MRI Texture Research Articles

Cardiac MRI Texture Analysis of T1 and T2 Maps in Patients with Infarctlike Acute Myocarditis.

Purpose To assess the diagnostic potential of texture analysis applied to T1 and T2 maps obtained with cardiac MRI for the diagnosis of acute infarctlike myocarditis. Materials and Methods This prospective study from August 2012 to May 2015 included 39 participants (overall mean age ± standard deviation, 34.7 years ± 12.2 [range, 18-63 years]; mean age of women, 46.1 years ± 10.8 [range, 24-63 years]; mean age of men, 29.8 years ± 9.2 [range, 18-56 years]) from the Magnetic Resonance Imaging in Myocarditis (MyoRacer) trial with clinical suspicion of acute myocarditis and infarctlike presentation. Participants underwent biventricular endomyocardial biopsy, cardiac catheterization, and cardiac MRI at 1.5 T, in which native T1 and T2 mapping as well as Lake Louise criteria (LLC) were assessed. Texture analysis was applied on T1 and T2 maps by using a freely available software package. Stepwise dimension reduction and texture feature selection was performed for selecting features enabling the diagnosis of myocarditis by using endomyocardial biopsy as the reference standard. Results Endomyocardial biopsy confirmed the diagnosis of acute myocarditis in 26 patients, whereas 13 participants had no signs of acute inflammation. Mean T1 and T2 values and LLC showed a low diagnostic performance, with area under the curve in receiver operating curve analyses as follows: 0.65 (95% confidence interval [CI]: 0.45, 0.85) for T1, 0.67 (95% CI: 0.49, 0.85) for T2, and 0.62 (95% CI: 0.42, 0.79) for LLC. Combining the texture features T2 run-length nonuniformity and gray-level nonuniformity resulted in higher diagnostic performance with an area under the curve of 0.88 (95% CI: 0.73, 1.00) (P < .001) and a sensitivity and specificity of 89% [95% CI: 81%, 93%] and 92% [95% CI: 77%, 93%], respectively. Conclusion Texture analysis of T2 maps shows high sensitivity and specificity for the diagnosis of acute infarctlike myocarditis. © RSNA, 2018 Online supplemental material is available for this article.

MRI texture analysis as a predictor of tumor recurrence or progression in patients with clinically non-functioning pituitary adenomas.

There are limited predictors of prognosis in patients with clinically non-functioning pituitary adenomas (NFPAs). We hypothesized that MRI texture analysis may predict tumor recurrence or progression in patients with NFPAs undergoing transsphenoidal pituitary surgery (TSS). To characterize texture parameters on preoperative MRI examinations in patients with NFPAs in relation to prognosis. Retrospective study of patients with NFPAs who underwent TSS at our institution between 2009 and 2010. Clinical, radiological and histopathological data were extracted from electronic medical records. MRI texture analysis was performed on coronal T1-weighted non-enhanced MR images using ImageJ (NIH). MRI texture parameters were used to predict tumor recurrence or progression. Both logistic regression and Cox proportional hazard analyses were conducted to adjust for potential confounders. Data on 78 patients were analyzed. On both crude and multivariable-adjusted analyses, mean, median, mode, minimum and maximum pixel intensity were associated with the risk of pituitary tumor recurrence or progression after TSS. Patients whose tumor mean pixel intensity was above the median for the population had a hazard ratio of 0.44 (95% CI: 0.21-0.94, P = 0.034) for recurrence or progression in comparison with tumors below the median. Our data suggest that MRI texture analysis can predict the risk of tumor recurrence or progression in patients with NFPAs.

MRI texture features and outcomes to immune checkpoint inhibitors in melanoma brain metastases.

2069Background: Brain metastases (BM) in patients (pts) with melanoma historically portend a dismal prognosis, but immune checkpoint inhibitors (ICI) are associated with durable responses in a subs...

Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study.

To examine the capability of MRI texture analysis to differentiate the primary site of origin of brain metastases following a radiomics approach. Sixty-seven untreated brain metastases (BM) were found in 3D T1-weighted MRI of 38 patients with cancer: 27 from lung cancer, 23 from melanoma and 17 from breast cancer. These lesions were segmented in 2D and 3D to compare the discriminative power of 2D and 3D texture features. The images were quantized using different number of gray-levels to test the influence of quantization. Forty-three rotation-invariant texture features were examined. Feature selection and random forest classification were implemented within a nested cross-validation structure. Classification was evaluated with the area under receiver operating characteristic curve (AUC) considering two strategies: multiclass and one-versus-one. In the multiclass approach, 3D texture features were more discriminative than 2D features. The best results were achieved for images quantized with 32 gray-levels (AUC = 0.873 ± 0.064) using the top four features provided by the feature selection method based on the p-value. In the one-versus-one approach, high accuracy was obtained when differentiating lung cancer BM from breast cancer BM (four features, AUC = 0.963 ± 0.054) and melanoma BM (eight features, AUC = 0.936 ± 0.070) using the optimal dataset (3D features, 32 gray-levels). Classification of breast cancer and melanoma BM was unsatisfactory (AUC = 0.607 ± 0.180). Volumetric MRI texture features can be useful to differentiate brain metastases from different primary cancers after quantizing the images with the proper number of gray-levels. • Texture analysis is a promising source of biomarkers for classifying brain neoplasms. • MRI texture features of brain metastases could help identifying the primary cancer. • Volumetric texture features are more discriminative than traditional 2D texture features.

Dynamic contrast-enhanced MRI texture analysis predicts microvascular invasion in hepatocellular carcinoma before operation

Objective To investigate the prognostic value of the texture analysis contrast-enhanced MR imaging (DCE-MRI) in predicting microvascular invasion in hepatocellular carcinoma (HCC) before operation. Methods Sixty patients with HCC confirmed by pathology in the Chinese Academy Medical Sciences from January 2014 to December 2016, were enrolled in our study retrospectively. According to the post-operative pathology, the patients were divided into positive microvascular invation[MVI(+)]group including 30 patients, and negative MVI[MVI(-)] group including 30 patients. All patients underwent normal MR and DCE-MRI before surgery. Sixty seven texture features were extracted from the original data of arterial phase (AP) and portal venous phase (PVP) of DCE-MRI. All data were calculated by using Omni-Kinetics (OK) software of the United States. The difference between MVI(+) group and MVI(-) group was statistically significant using the independent sample t test. The identified methods of the DCE-MR texture features in predicting MVI adopted the principal component analysis (PCA) and the establishing prediction model including dimensionality reduction, modeling, prediction and verification. The model was established by logistic regression method. According to the histopathology, 80% data of AP and PVP were used as training group [48 cases, MVI(+) and MVI(-) group 24 cases respectively], 20% as validation group[12 cases, MVI(+) and MVI(-) group 6 cases respectively]. The DCE-MRI images of AP and PVP were modeled and cross-referenced respectively, and the diagnostic efficiency of ROC evaluation model was adopted. Results There were 15 significant different texture features of the AP and three significant different texture features of the PVP between MVI(+) group and MVI(-) group respectively. The PCA method extracted the important DCE-MRI texture features and analyzed the 15 features of AP. The UPP and energy showed a good correlation (r>0.90), therefore the UPP were removed. Fourteen texture features were analyzed using the PCA method. There were four important texture features including the GLCM Correlation, Hara Variance, GLCM sum Variance and GLCM sum Entropy in the AP. Moreover, there were three important texture features including GLCM difference Entropy, Long Run Low Grey Level Emphasis and GLCM difference Variance in the PVP. Through the prediction model was established and crossly validated. There were three significant different texture features in the AP of DCE-MRI, including GLCM Correlation, GLCM Contrast and GLCM sum Entropy. And there were two significant different texture features in the PVP of DCE-MRI, including GLCM difference Variance and Long Run Low Grey Level Emphasis. In the training and validation group, the areas under the ROC of the AP model and PVP model were 0.774, 0.681, 0.889 and 0.611 respectively. The diagnosed accuracy rate of the AP model (83.30%, 10/12) was higher than that of the PVP model (42.00%, 5/12). Conclusion The DCE-MRI texture analysis technique could predict the MVI of HCC before operation, and the predictive accuracy of the AP texture feature was higher. Key words: Carcinoma,hepatocellular; Microvascular invasion; Texture analysis; Magnetic resonance imaging

Abstract PD2-09: Association of quantitative MRI features with tumor infiltrating lymphocytes and treatment response prediction in HER2 positive subtype of breast cancer

Abstract Objectives: To evaluate associations between qualitative and quantitative MRI features and tumor infiltrating lymphocytes (TIL) levels in HER2+ subtype of breast cancer, as potential prognostic non-invasive imaging markers for treatment response prediction. Materials and Methods: Retrospective review of breast cancer patients who had MRI at staging, neoadjuvant chemotherapy and surgery from January 1, 2008 through December 31, 2015 was performed. BI-RADS lexicon was used for lesion evaluation. Demographic, imaging, and pathologic data including TIL levels were documented. Quantitative MRI texture analysis was performed using 3 types of textural features (TF): local binary patterns (LBP), gray-level co-occurrence matrix (GLCM), and threshold adjacency statistics (TAS). Associations between MRI quantitative TF, TIL levels, and pathologic complete response (pCR) were evaluated by Pearson correlation and logistic regression. Results: There were 50 HER2+ patients (median age 51 years, range 29-59) with pretreatment MRI and TIL status for analysis; 27 patients had pCR at surgery. Qualitative MRI analysis showed that mass rim-enhancement (p&amp;lt;0. 05) and fast early enhancement kinetics (p&amp;lt;0.01) were associated with higher TIL levels. No association between qualitative MRI features and pCR was found. Nine TF significantly correlated with pCR (p&amp;lt;0.05): angular 2nd moment (GLCM), 75 percentile (LBP), standard deviation (GLCM), adjacency 0-5 (TAS). This is indicative of association of tumor heterogeneity with pCR. Three TF were significantly associated with high TIL levels (p&amp;lt;0.05): standard deviation, adjacency 1 and 2. Additional four TF had high association with TIL (p&amp;lt;0.1): sum entropy, adjacency 0, 3 and 4. These findings showed that increased heterogeneity, complexity and entropy were associated with high TIL level. Three TF were significantly associated with both, pCR and TIL (p&amp;lt;0.05): 75 percentile, standard deviation, adjacency 8. Conclusion: Quantitative tumor texture analysis based on statistical modeling showed specific nine TF indicative of tumor heterogeneity associated with pCR; and seven TF indicative of increased heterogeneity, complexity, and entropy associated with high TIL levels in HER2+ breast cancer. Analysis of associations of MRI quantitative TF with pCR and TIL in HER2+ breast cancer may help to develop prognostic non-invasive imaging markers for treatment response prediction. Citation Format: Rauch GM, Zhu H, Li H, Adrada BE, Santiago L, Candelaria RP, Wang H, Leung J, Litton J, Wu Y, Murthy R, Mittendorf EA, Yang W. Association of quantitative MRI features with tumor infiltrating lymphocytes and treatment response prediction in HER2 positive subtype of breast cancer [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr PD2-09.

MRI features predictive of negative surgical margins in patients with HER2 overexpressing breast cancer undergoing breast conservation

Here we develop a tool to predict resectability of HER2+ breast cancer at breast conservation surgery (BCS) utilizing features identified on preoperative breast MRI. We identified patients with HER2+ breast cancer who obtained pre-operative breast MRI and underwent BCS between 2002–2013. From the contoured tumor on pre-operative MRI, shape, histogram, and co-occurrence and size zone matrix texture features were extracted. In univariate analysis, Spearman’s correlation coefficient (Rs) was used to assess the correlation between each image feature and an endpoint (surgical re-excision). For multivariate modeling, we employed a support vector machine (SVM) method in a manner of leave-one-out cross-validation (LOOCV). Of 109 patients with HER2+breast cancer who underwent BCS, 39% underwent surgical re-excision. 62% had residual cancer at re-excision. In univariate analysis, solidity (Rs = −0.32, p = 0.009) and extent (Rs = −0.29, p = 0.019) were significantly associated with re-excision. Skewness in post-contrast 1, 2, and 3 (Rs = 0.25, p = 0.045; Rs = 0.30, p = 0.015; Rs = 0.28, p = 0.026) and kurtosis in post-contrast 1 (Rs = 0.26, p = 0.035) were also statistically significant. LOOCV-based SVM test achieved 74.4% specificity and 71.4% sensitivity when 21 features were used. Thus, tumor texture, histogram and morphological MRI features may assist surgical planning, encouraging wide margins or mastectomy in patients who may otherwise go on to re-excision.

Alzheimer's disease: 3-Dimensional MRI texture for prediction of conversion from mild cognitive impairment

IntroductionCurrently, there are no tools that can accurately predict which patients with mild cognitive impairment (MCI) will progress to Alzheimer's disease (AD). Texture analysis uses image processing and statistical methods to identify patterns in voxel intensities that cannot be appreciated by visual inspection. Our main objective was to determine whether MRI texture could be used to predict conversion of MCI to AD. MethodsA method of 3-dimensional, whole-brain texture analysis was used to compute texture features from T1-weighted MR images. To assess predictive value, texture changes were compared between MCI converters and nonconverters over a 3-year observation period. A predictive model using texture and clinical factors was used to predict conversion of patients with MCI to AD. This model was then tested on ten randomly selected test groups from the data set. ResultsTexture features were found to be significantly different between normal controls (n = 225), patients with MCI (n = 382), and patients with AD (n = 183). A subset of the patients with MCI were used to compare between MCI converters (n = 98) and nonconverters (n = 106). A composite model including texture features, APOE-ε4 genotype, Mini-Mental Status Examination score, sex, and hippocampal occupancy resulted in an area under curve of 0.905. Application of the composite model to ten randomly selected test groups (nonconverters = 26, converters = 24) predicted MCI conversion with a mean accuracy of 76.2%. DiscussionEarly texture changes are detected in patients with MCI who eventually progress to AD dementia. Therefore, whole-brain 3D texture analysis has the potential to predict progression of patients with MCI to AD.

The association between MRI texture analysis and chemoradiotherapy outcomes in glioblastoma cases

Aim: Texture analysis can provide additional information regarding tumor heterogeneity and treatment response. The aim of this study was to evaluate whether MRI texture analysis can predict radiotherapy response and survival in glioblastoma patients.Material and Methods: A total of 26 patients with pathologically confirmed glioblastoma who had received curative chemoradiotherapy (60 Gy radiotherapy + temozolomide) underwent contrast-enhanced cranial MRI texture analysis before and after chemoradiotherapy. The region of interest was determined as the active tumor area in post-contrast axial T1 sections. The gray level intensity, standard deviation of histogram, entropy, uniformity, skewness, and kurtosis values were determined by texture analysis.Results: Comparison of the pre- and post-radiotherapy values showed an increase in entropy (6.97±0.37 vs. 7.20±0.30, p = 0.014) and a decrease in uniformity (0.21±0.12 vs.0.16±0.08, p = 0.049). Therefore, radiation therapy was determined to have caused increased heterogeneity in the active tumor region of glioblastoma. The median follow-up was 7.5 [95% confidence interval (1.8-21.63)] months, while the median overall survival was 12.5 [95% confidence interval (4.24-20.81)] months. Young age, high performance statusand low entropy value after radiotherapywere associated with longer survival according to the Kaplan-Meier analysis (p = 0.014, p = 0.031, p = 0.034, respectively).Conclusion: Based on these results,entropy measurements can be recommended for use as a new prognostic factor for glioblastoma.Keywords: Glioblastoma; Entropy; Radiotherapy; Survival; Texture Analysis.

To distinguish flexible and rigid lumbar curve from MRI texture analysis in adolescent idiopathic scoliosis: A feasibility study.

Imaging in side bending, supine, traction, fulcrum, and push prone are examples of methods used to evaluate the curve reduction of scoliotic spine. However, being able to determine spine curve flexibility from MRI would eliminate the need of additional X-ray radiation related to radiograph acquisition in side-bending. To find specific texture features of lumbar postural muscles on MRI that can distinguish flexible from rigid lumbar scoliotic curves. We hypothesized that the changes occurring in postural muscles with scoliosis can be seen with MRI. Retrospective study case control. With Institutional Review Board approval and informed consent, 15 adolescents with idiopathic scoliosis and scheduled for surgery were involved. T1 -weighted MR images were performed on a 1.5T system using a spin echo sequence in the axial direction. The spinal erector, quadratus lumborum and psoas major muscles were analyzed using textural features. Principal component analysis (PCA) and agglomerative hierarchical clustering (AHC) were used to classify the lumbar postural muscles and calculate performance metrics. The lumbar flexibility index, measured from suspension tests, was used as ground truth measurement. The five discriminant features (out of 34 tested features) obtained from PCA were able to keep over 90% of the variability of the dataset. The right and left spinal erector and the left psoas major had the highest performance metrics to classify the spinal curve flexibility, with an accuracy over 0.80, a sensitivity over 0.82, a specificity over 0.68, and a Matthews correlation coefficient over 0.57. This study analyzed MRI using texture information of muscle to distinguish flexible from rigid scoliotic curves. Some postural muscle such as the spinal erector and the psoas major are more likely to reflect the curve flexibility of a scoliotic participant. 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2017.

MRI texture analysis in predicting treatment response to neoadjuvant chemoradiotherapy in rectal cancer.

To evaluate the importance of MRI texture analysis in prediction and early assessment of treatment response before and early neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC). This retrospective study comprised of 59 patients. The tumoral texture parameters were compared between pre- and early nCRT. Area Under receiver operating characteristic (ROC) Curves [AUCs] were used to compare the diagnostic performance of statistically significant difference parameters and logistic regression analysis predicted probabilities for discriminating responders and nonresponders. The Standard Deviation (SD), kurtosis and uniformity were statistically significantly difference between pre- and early nCRT (p = 0.0012, 0.0001, and < 0.0001, respectively). In pathological complete response (pCR) group, pre-uniformity and pre-Energy were significantly higher than that of nonresponders (p = 0.03 and p < 0.01, respectively), while the pre-entropy in nonresponder was reverse (p = 0.01). The diagnostic performance of pre-kurtosis and pre-Energy were higher in tumor regression grade (TRG) and pCR group (AUC = 0.67, 0.73, respectively). Logistic regression analysis showed that diagnostic performance for prediction responder and nonresponder did not significantly improve compared with to pre-uniformity, energy and entropy in pCR group (AUC = 0.76, p = 0.2794, 0.4222 and 0.3512, respectively). Texture parameters as imaging biomarkers have the potential to prediction and early assessment of tumoral treatment response to neoadjuvant chemoradiotherapy in patients with LARC.

A glioma grading method based on radiomics

Objective To explore the classification of gliomas according to the theory and method of radiomics. Methods In this study, 161 pathologically confirmed glioma patients were retrospectively selected from 2012 to 2016 including 52 low-grade gliomas and 109 high-grade gliomas. Three hundred and forty-six quantization features were extracted from the MRI images, including shape, density, texture and wavelet imaging features. Mutual information and logistic regression model were used to select feature reduction and prediction model. The predictive ability of the model was validated using 10-fold cross-validation. Results Nineteen radiomics features were chosen from 346 quantization features. The sensitivity of the model was 96.3% (105/109), the specificity was 78.8% (41/52), the area under the curve(AUC) was 0.952 7, and the accuracy was 90.7%(146/161). Conclusion The solution proposed in this paper showed that radiomics can non-invasively and quickly provide an adjunct to the clinical grade of glioma with high accuracy. Key words: Glioma; Radiomics; Artificial intelligence

MRI texture analysis in prediction of treatment response to neoadjuvant chemoradiotherapy in patients with locally advanced rectal cancer

Objective To evaluate the value of MRI texture analysis (TA) in prediction of treatment response neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer patients. Methods Fifty nine histopathologically-proven rectal adenocarcinoma patients through biopsy treated with nCRT before total mesorectal excision were enrolled in this retrospective study. The first MRI examination (pre-nCRT MRI) was performed before nCRT, and the second one (early nCRT MRI) was performed at the third week of nCRT. The texture parameters values were measured, including mean value, standard deviation, skewness, kurtosis, uniformity, energy, and entropy. Tumoral downstaging was determined by comparing the pre-nCRT clinical T stage(cT stage) with the ypT stage. The patients were divided into downstaging and non downstaging group based on postoperative T staging. Parameters were compared between pre-and early nCRT in terms of averages using Wilcoxon signed-rank test. Downstaging and non downstaging groups were analyzed using Mann-Whitney U test. Multivariate logistic regression analysis was performed using the statistically significant parameters between the two groups as independent variables. ROC analysis was performed on the new independent variables obtained by multi-parameter logistic regression analysis and the single parameter independent variables. The diagnostic efficiency of the parameters were evaluated. Results T-downstaging were found in 28 patients after nCRT. The stdDeviation, kurtosis, and uniformity were significantly different between pre-and early nCRT (P 0.05). The pre-nCRT, uniformity, energy, entropy and the early nCRT mean value, entropy were significantly different in patients with downstaging vs. non downstaging (P<0.05). For the pre-nCRT stdDeviation, uniformity, energy, entropy and the early nCRT mean value, entropy, ROC analysis showed an area under curve(AUC) of 0.69, 0.76, 0.68, 0.67 and 0.65, 0.68, respectively. The multivariate logistic regression analysis for the four pre-nCRT independent variables (stdDeviation, uniformity, energy, entropy) achieved logical variable 1, and the logical variable 1 achieved an AUC of 0.78 to discriminate patients with T-downstaging from patients with non downstaging. The multivariate logistic regression analysis for the two early nCRT independent variables (mean value, entropy) achieved logical variable 2, and the logical variable 2 achieved an AUC of 0.69 to predict T-downstaging. Conclusion Pre-and early nCRT MRI TA in rectal cancer have the efficacy to predict treatment response. Key words: Rectal neoplasms; Magnetic resonance imaging; Treatment outcome; Texture analysis

Clinical Application of Biparametric MRI Texture Analysis for Detection and Evaluation of High-Grade Prostate Cancer in Zone-Specific Regions.

The purpose of this study was to investigate the performance of biparametric MRI texture analysis (TA) in detecting and evaluating high-grade prostate cancer in zone-specific regions. A retrospective study included 184 consecutively registered biopsy-naive patients in whom prostate cancer was suspected who were undergoing multiparametric prostate MRI. MR images were scored and evaluated by two readers using the Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) and biparametric MRI TA in separate sessions. Interobserver agreement on PI-RADSv2 score and textural parameters of biparametric MRI was evaluated. The logistic regression model based on TA was built for different zones of the prostate. ROC analysis was used to compare the TA-based model with other parameters alone. The correlation of each parameter with Gleason score of high-grade prostate cancer was also assessed. Reader reliability ranged from moderate to good for PI-RADSv2 (Cohen κ = 0.525-0.616) and from good to excellent for textural metrics (intraclass correlation coefficient, 0.745-0.925). Diagnostic performance was significantly improved by use of the TA-based model (transition zone AUC, 0.87; peripheral zone AUC, 0.89) in comparison with PI-RADSv2 and other texture parameters alone. For the transition zone, entropy had moderate to good correlation with the Gleason score of high-grade prostate cancer (r = 0.562, p = 0.004). In the peripheral zone, entropy (r = 0.614, p = 0.003) and inertia (r = 0.663, p = 0.002) had moderate to good correlations with Gleason score. The results of this clinical study indicate that a TA-based model that includes biparametric MRI can be used for identifying high-grade prostate cancer and that specific parameters extracted from TA may be additional tools for assessing tumor aggressiveness.

MRI texture analysis in differentiating luminal A and luminal B breast cancer molecular subtypes - a feasibility study

BackgroundThe aim of this study was to use texture analysis (TA) of breast magnetic resonance (MR) images to assist in differentiating estrogen receptor (ER) positive breast cancer molecular subtypes.MethodsTwenty-seven patients with histopathologically proven invasive ductal breast cancer were selected in preliminary study. Tumors were classified into molecular subtypes: luminal A (ER-positive and/or progesterone receptor (PR)-positive, human epidermal growth factor receptor type 2 (HER2) -negative, proliferation marker Ki-67 < 20 and low grade (I)) and luminal B (ER-positive and/or PR-positive, HER2-positive or HER2-negative with high Ki-67 ≥ 20 and higher grade (II or III)). Co-occurrence matrix -based texture features were extracted from each tumor on T1-weighted non fat saturated pre- and postcontrast MR images using TA software MaZda. Texture parameters and tumour volumes were correlated with tumour prognostic factors.ResultsTextural differences were observed mainly in precontrast images. The two most discriminative texture parameters to differentiate luminal A and luminal B subtypes were sum entropy and sum variance (p = 0.003). The AUCs were 0.828 for sum entropy (p = 0.004), and 0.833 for sum variance (p = 0.003), and 0.878 for the model combining texture features sum entropy, sum variance (p = 0.001). In the LOOCV, the AUC for model combining features sum entropy and sum variance was 0.876. Sum entropy and sum variance showed positive correlation with higher Ki-67 index. Luminal B types were larger in volume and moderate correlation between larger tumour volume and higher Ki-67 index was also observed (r = 0.499, p = 0.008).ConclusionsTexture features which measure randomness, heterogeneity or smoothness and homogeneity may either directly or indirectly reflect underlying growth patterns of breast tumours. TA and volumetric analysis may provide a way to evaluate the biologic aggressiveness of breast tumours and provide aid in decisions regarding therapeutic efficacy.

Quantitative MRI Texture Analysis in Differentiating Enhancing and Non-enhancing T1-hypointense Lesions without Application of Contrast Agent in Multiple Sclerosis

Quantitative MRI Texture Analysis in Differentiating Enhancing and Non-enhancing T1-hypointense Lesions without Application of Contrast Agent in Multiple Sclerosis

Integrated radiomic framework for breast cancer and tumor biology using advanced machine learning and multiparametric MRI

Radiomics deals with the high throughput extraction of quantitative textural information from radiological images that not visually perceivable by radiologists. However, the biological correlation between radiomic features and different tissues of interest has not been established. To that end, we present the radiomic feature mapping framework to generate radiomic MRI texture image representations called the radiomic feature maps (RFM) and correlate the RFMs with quantitative texture values, breast tissue biology using quantitative MRI and classify benign from malignant tumors. We tested our radiomic feature mapping framework on a retrospective cohort of 124 patients (26 benign and 98 malignant) who underwent multiparametric breast MR imaging at 3 T. The MRI parameters used were T1-weighted imaging, T2-weighted imaging, dynamic contrast enhanced MRI (DCE-MRI) and diffusion weighted imaging (DWI). The RFMs were computed by convolving MRI images with statistical filters based on first order statistics and gray level co-occurrence matrix features. Malignant lesions demonstrated significantly higher entropy on both post contrast DCE-MRI (Benign-DCE entropy: 5.72 ± 0.12, Malignant-DCE entropy: 6.29 ± 0.06, p = 0.0002) and apparent diffusion coefficient (ADC) maps as compared to benign lesions (Benign-ADC entropy: 5.65 ± 0.15, Malignant ADC entropy: 6.20 ± 0.07, p = 0.002). There was no significant difference between glandular tissue entropy values in the two groups. Furthermore, the RFMs from DCE-MRI and DWI demonstrated significantly different RFM curves for benign and malignant lesions indicating their correlation to tumor vascular and cellular heterogeneity respectively. There were significant differences in the quantitative MRI metrics of ADC and perfusion. The multiview IsoSVM model classified benign and malignant breast tumors with sensitivity and specificity of 93 and 85%, respectively, with an AUC of 0.91.

Radiomics in paediatric neuro-oncology: A multicentre study on MRI texture analysis.

Brain tumours are the most common solid cancers in children in the UK and are the most common cause of cancer deaths in this age group. Despite current advances in MRI, non-invasive diagnosis of paediatric brain tumours has yet to find its way into routine clinical practice. Radiomics, the high-throughput extraction and analysis of quantitative image features (e.g. texture), offers potential solutions for tumour characterization and decision support. In the search for diagnostic oncological markers, the primary aim of this work was to study the application of MRI texture analysis (TA) for the classification of paediatric brain tumours. A multicentre study was carried out, within a supervised classification framework, on clinical MR images, and a support vector machine (SVM) was trained with 3D textural attributes obtained from conventional MRI. To determine the cross-centre transferability of TA, an assessment of how SVM performs on unseen datasets was carried out through rigorous pairwise testing. The study also investigated the nature of features that are most likely to train classifiers that can generalize well with the data. Finally, the issue of class imbalance, which arises due to some tumour types being more common than others, was explored. For each of the tests carried out through pairwise testing, the optimal area under the receiver operating characteristic curve ranged between 76% and 86%, suggesting that the model was able to capture transferable tumour information. Feature selection results suggest that similar aspects of tumour texture are enhanced by MR images obtained at different hospitals. Our results also suggest that the availability of equally represented classes has enabled SVM to better characterize the data points. The findings of the study presented here support the use of 3D TA on conventional MR images to aid diagnostic classification of paediatric brain tumours.

MRI Texture Analysis Reflects Histopathology Parameters in Thyroid Cancer – A First Preliminary Study

OBJECT: Thyroid cancer represents the most frequent malignancy of the endocrine system with an increasing incidence worldwide. Novel imaging techniques are able to further characterize tumors and even predict histopathology features. Texture analysis is an emergent imaging technique to extract extensive data from an radiology images. The present study was therefore conducted to identify possible associations between texture analysis and histopathology parameters in thyroid cancer. METHODS: The radiological database was retrospectively reviewed for thyroid carcinoma. Overall, 13 patients (3 females, 23.1%) with a mean age of 61.6 years were identified. The MaZda program was used for texture analysis. The T1-precontrast and T2-weighted images were analyzed and overall 279 texture feature for each sequence was investigated. For every patient cell count, Ki67-index and p53 count were investigated. RESULTS: Several significant correlations between texture features and histopathology were identified. Regarding T1-weighted images, S(0;1)Sum Averg correlated the most with cell count (r=0.82). An inverse correlations with S(5;0)AngScMom, S(5;0)DifVarnc S(5;0), DiffEntrp and GrNonZeros (r=−0.69, −0.66, −0.69 and −0.63, respectively) was also identified. For T2-weighted images, Variance with r=0.63 was the highest coefficient, WavEnLL_S3 correlated inversely with cell count (r=−0.57). WavEnLL_S2 derived from T1-weighted images was the highest coefficient r=−0.80, S(0;5)SumVarnc was positively with r=0.74. Regarding T2-weighted images WavEnHL_s-1 was inverse correlated with Ki67 index (r=−0.77). S(1;0)Correlat was with r=0.75 the best correlation with Ki67 index. For T1-weighed images S(5;0)SumofSqs was the best with r=0.65 with p53 count. For T2-weighted images S(1;−1)SumEntrp was the inverse correlation with r=−0.72, whereas S(0;4)AngScMom correlated positively with r=0.63. CONCLUSIONS: MRI texture analysis derived from conventional sequences reflects histopathology features in thyroid cancer. This technique might be a novel noninvasive modality to further characterize thyroid cancer in clinical oncology.

Diagnostic value of MRI-based 3D texture analysis for tissue characterisation and discrimination of low-grade chondrosarcoma from enchondroma: a pilot study.

To explore the diagnostic value of MRI-based 3D texture analysis to identify texture features that can be used for discrimination of low-grade chondrosarcoma from enchondroma. Eleven patients with low-grade chondrosarcoma and 11 patients with enchondroma were retrospectively evaluated. Texture analysis was performed using mint Lesion: Kurtosis, entropy, skewness, mean of positive pixels (MPP) and uniformity of positive pixel distribution (UPP) were obtained in four MRI sequences and correlated with histopathology. The Mann-Whitney U-test and receiver operating characteristic (ROC) analysis were performed to identify most discriminative texture features. Sensitivity, specificity, accuracy and optimal cut-off values were calculated. Significant differences were found in four of 20 texture parameters with regard to the different MRI sequences (p<0.01). The area under the ROC curve values to discriminate chondrosarcoma from enchondroma were 0.876 and 0.826 for kurtosis and skewness in contrast-enhanced T1 (ceT1w), respectively; in non-contrast T1, values were 0.851 and 0.822 for entropy and UPP, respectively. The highest discriminatory power had kurtosis in ceT1w with a cut-off ≥3.15 to identify low-grade chondrosarcoma (82 % sensitivity, 91 % specificity, accuracy 86 %). MRI-based 3D texture analysis might be able to discriminate low-grade chondrosarcoma from enchondroma by a variety of texture parameters. • MRI texture analysis may assist in differentiating low-grade chondrosarcoma from enchondroma. • Kurtosis in the contrast-enhanced T1w has the highest power of discrimination. • Tools provide insight into tumour characterisation as a non-invasive imaging biomarker.