Search

One of the most promising areas of diagnosis and prognosis of diseases is radiomics, a science combining radiology, mathematical modeling, and deep machine learning. The main concept of radiomics is image biomarkers (IBMs), the parameters characterizing various pathological changes and calculated based on the analysis of digital image texture. IBMs are used for quantitative assessment of digital imaging results (CT, MRI, ultrasound, PET). The use of IBMs in the form of “virtual biopsy” is of particular relevance in oncology. The article provides the basic concepts of radiomics identifying the main stages of obtaining IBMs: data collection and preprocessing, tumor segmentation, data detection and extraction, modeling, statistical processing, and data validation. The authors have analyzed the possibilities of using IBMs in oncology, describing the currently known features and advantages of using radiomics and image texture analysis in the diagnosis and prognosis of cancer. The limitations and problems associated with the use of radiomics data are considered. Although the novel effective tool for performing virtual biopsy of human tissue is at the development stage, quite a few projects have already been implemented, and medical software packages for radiomics analysis of digital images have been created.

Recurrence after resection of colorectal liver metastases (CRLMs) occurs in up to 75% of patients. Preoperative prediction of hepatic recurrence may inform therapeutic strategies at the time of initial resection. Texture analysis (TA) is an established technique that quantifies pixel intensity variations (heterogeneity) on cross-sectional imaging. We hypothesized that tumoral and parenchymal changes that are predictive of overall survival (OS) and recurrence in the future liver remnant (FLR) can be detected using TA on preoperative computed tomography (CT) images.Patients who underwent resection for CRLM between 2003 and 2007 with appropriate preoperative CT scans were included (n = 198) in this retrospective study. Texture features extracted from the tumor and FLR, and clinicopathologic variables, were incorporated into a multivariable survival model.Quantitative imaging features of the FLR were an independent predictor of both OS and hepatic disease-free survival (HDFS). Tumor texture showed significant association with OS. TA of the FLR allowed patient stratification into two groups, with significantly different risks of hepatic recurrence (hazard ratio 2.09, 95% confidence interval 1.33-3.28; p = 0.001). Patients with homogeneous parenchyma had approximately twice the risk of hepatic recurrence (41 vs. 20%).TA of the tumor and FLR are independently associated with OS, and TA of the FLR is independently associated with HDFS. Patients with homogeneous parenchyma had a significantly higher risk of hepatic recurrence. Preoperative TA of the liver represents a potential biomarker to identify patients at risk of liver recurrence after resection for CRLM.

Reports have suggested that tumor textures presented on T2-weighted images correlate with the genetic status of glioma. Therefore, development of an image analyzing framework that is capable of objective and high throughput image texture analysis for large scale image data collection is needed. The current study aimed to address the development of such a framework by introducing two novel parameters for image textures on T2-weighted images, i.e., Shannon entropy and Prewitt filtering. Twenty-two WHO grade 2 and 28 grade 3 glioma patients were collected whose pre-surgical MRI and IDH1 mutation status were available. Heterogeneous lesions showed statistically higher Shannon entropy than homogenous lesions (p = 0.006) and ROC curve analysis proved that Shannon entropy on T2WI was a reliable indicator for discrimination of homogenous and heterogeneous lesions (p = 0.015, AUC = 0.73). Lesions with well-defined borders exhibited statistically higher Edge mean and Edge median values using Prewitt filtering than those with vague lesion borders (p = 0.0003 and p = 0.0005 respectively). ROC curve analysis also proved that both Edge mean and median values were promising indicators for discrimination of lesions with vague and well defined borders and both Edge mean and median values performed in a comparable manner (p = 0.0002, AUC = 0.81 and p < 0.0001, AUC = 0.83, respectively). Finally, IDH1 wild type gliomas showed statistically lower Shannon entropy on T2WI than IDH1 mutated gliomas (p = 0.007) but no difference was observed between IDH1 wild type and mutated gliomas in Edge median values using Prewitt filtering. The current study introduced two image metrics that reflect lesion texture described on T2WI. These two metrics were validated by readings of a neuro-radiologist who was blinded to the results. This observation will facilitate further use of this technique in future large scale image analysis of glioma.

Oncotype DX (ODX) is a 21 panel gene-expression based assay for predicting whether patients with estrogen receptor-positive (ER+) breast cancer (BCa) are candidates for adjuvant chemotherapy. However, the time and expense associated with genomic assays suggests the need for a non-invasive, imaging-based, pre-therapeutic tool for assessment of disease risk and selection of an appropriate treatment regimen. The objective of this research was to determine whether (a) computer extracted image features on T2-weighted (T2w) MRI and H&E stained histopathology are independently able to distinguish ER+ BCa with low and high ODX recurrence scores (RS) and (b) to determine whether there is a correlation between MRI and histologic features identified as being predictive of low and high ODX risk categories. A total of 11 ER+ BCa patients were considered in this study, based on availability of in vivo 1.5 Tesla T2w MRI. For each study, the corresponding formalin-fixed paraffin-embedded H&E stained tissue specimens were digitized at 20x (0.5 μm/pixel) using a whole-slide scanner. Of the 11 patients, 8 were identified in the low ODX (RS < 18) and 3 in the high ODX (RS > 30) risk categories. Each dataset was accompanied by expert annotations of (a) the lesion ROI on MRI and (b) boundaries of epithelial nuclei from a representative field-of-view on the digitized histology slide. For each MRI study, a multi-scale, multi-orientation Gabor filter bank was convolved with the annotated lesion area providing a set of 192 texture features (FMRI). For each corresponding histology image, 471 features (FHIST) were extracted describing both nuclear morphology (NM) and Laws texture (LT) within the nuclear regions. Independent 2-sample t-tests were used to identify salient features in FMRI and FHIST that are able to distinguish low and high ODX risk categories. We found that, for the MRI dataset, Gabor texture features at several scales and orientations yielded salient features (p < 0.05) while on histopathology, nuclear texture and convexity (shape) features were identified as the top discriminative features (p < 0.01). Relationships between significant features were evaluated via Spearman's rank correlation test (see table), where high correlations were observed between lesion texture on T2w MRI and nuclear texture and shape on histology. Correlation of histologic and MRI features able to distinguish low and high ODX RSHistologic feature correlated with ODXMRI feature correlated with ODXCorrelation coefficient (ρ)p-valueLT: 70 Mean HSVGF: Scale 2: Orientation 3: min/max-0.85450.0008NM: ConvexityGF: Scale 5: Orientation 6: mean-0.85450.0008LT: 70 Mean HSVGF: Scale 2: Orientation 3: min/max-0.83640.0013LT: 70 Mean HSVGF: Scale 3: Orientation 8: mean-0.83640.0013LT: 70 Mean HSVGF: Scale 3: Orientation 2: mean-0.81820.0021 Our results suggest that quantitative features extracted on both T2w MRI and histopathology can independently distinguish between low and high risk ODX classes. Moreover, some of these MRI and histologic features appear to be significantly correlated, suggesting that information regarding tumor biology is reflected in both MRI and histologic image features. Citation Information: Cancer Res 2013;73(24 Suppl): Abstract nr P2-03-01.

Background Non-invasive characterization of a tumor's molecular features could enhance treatment management. Quantitative computed tomography (CT) based texture analysis (QTA) has been used to derive tumor heterogeneity information, and the appearance of the tumors has been shown to relate to patient outcome in non-small cell lung cancer (NSCLC) and other cancers. In this study, we examined the potential of tumoral QTA to differentiate K-ras mutant from pan-wildtype tumors and its prognostic potential using baseline pre-treatment non-contrast CT imaging in NSCLC. Methods Tumor DNA from patients with early-stage NSCLC was analyzed on the LungCarta Panel. Cases with a K-ras mutation or pan-wildtype for 26 oncogenes and tumor suppressor genes were selected for QTA. QTA was applied to regions of interest in the primary tumor. Non-parametric Mann Whitney test assessed the ability of the QTA, clinical and patient characteristics to differentiate between K-ras mutation from pan-wildtype. A recursive decision tree was developed to determine whether the differentiation of K-ras mutant from pan-wildtype tumors could be improved by sequential application of QTA parameters. Kaplan-Meier survival analysis assessed the ability of these markers to predict survival. Results QTA was applied to 48 cases identified, 27 had a K-ras mutation and 21 cases were pan-wildtype. Positive skewness and lower kurtosis were significantly associated with the presence of a K-ras mutation. A five node decision tree had sensitivity, specificity, and accuracy values (95% CI) of 96.3% (78.1–100), 81.0% (50.5–97.4), and 89.6% (72.9–97.0); respectively. Kurtosis was a significant predictor of OS and DFS, with a lower kurtosis value linked with poorer survival. Conclusions Lower kurtosis and positive skewness are significantly associated with K-ras mutations. A QTA feature such as kurtosis is prognostic for OS and DFS. Non-invasive QTA can differentiate the presence of K-ras mutation from pan-wildtype NSCLC and is associated with patient survival.

Discrimination of tumor from radiation injured (RI) tissues and differentiation of tumor types using noninvasive imaging is essential for guiding surgical and radiotherapy treatments are some of the challenges that clinicians face in the course of treatment of brain tumors. The first objective in this thesis was to develop a method to discriminate between glioblastoma tumor recurrences and radiation injury using multiparametric characterization of the tissue incorporating conventional magnetic resonance imaging signal intensities and diffusion tensor imaging parameters. Our results show significant correlations in the RI that was missing in the tumor regions. These correlations may aid in differentiating between tumor recurrence and RI. The second objective of was to investigate whether texture based image analysis of routine MR images would provide quantitative information that could be used to differentiate between glioblastoma and metastasis. Our results demonstrate that first-order texture feature of standard deviation and second-order texture features of entropy, inertia, homogeneity, and energy show significant differences between the two groups. The third objective was to investigate whether quantitative measurements of tumor size and appearance on MRI scans acquired prior to helical tomotherapy (HT) type whole brain radiotherapy with simultaneous infield boost treatment could be used to differentiate responder and non-responder patient groups. Our results demonstrated that smaller size lesions may respond better to this type of radiation therapy. Measures of appearance provided limited added value over measures of size for response prediction. Quantitative measurements of rim enhancement and core necrosis performed separately did not provide additional predictive value.

Introduction: Non-invasive methods that can characterize a tumor's molecular features could enhance treatment management. Recently, researchers have investigated tumor heterogeneity on imaging to assess how grainy or coarse a tumor seems to be in the search for oncologic prognostic markers and mechanisms. Quantitative computed tomography (CT) based texture analysis (qCTTA) has been used to derive tumor heterogeneity information, and the appearance of the tumors has been shown to relate to patient outcome in esophageal, colorectal, lung and head and neck cancer and treatment response in metastatic renal cell cancer. Furthermore histological assessment has demonstrated an association between qCTTA and hypoxia and angiogenesis in lung cancer and very recently qCTTA in combination with CT blood-flow and PET glucose-uptake identified an imaging signature for K-ras mutation status in colorectal cancer. In this study, we examined the predictive potential of tumoral qCTTA to differentiate K-ras mutant and K-ras wildtype tumors and its prognostic potential using non-contrast CT imaging in non-small cell lung cancer (NSCLC). Methods: Formalin-fixed, paraffin-embedded (FFPE) lung tumor tissues from patients with stage I and II NSCLC, diagnosed between 2001 and 2007 and undergoing definitive surgical resection were obtained. Tumor DNA was extracted and analyzed on the LungCarta Panel that interrogates 213 somatic mutations in 26 oncogenes and/or tumor suppressor genes. Cases with a K-ras mutation or pan-wildtype for all 26 oncogenes and tumor suppressor genes were selected for imaging analysis. Baseline pre-treatment non-contrast CT images that were performed as part of standard of care were retrieved for qCTTA. qCTTA was applied to regions of interest in the primary tumor and comprised an image filtration-histogram technique; where the filtration technique enhanced features of different sizes based on the spatial scale filter (SSF) value varying from fine (2mm in radius), medium (3-5mm in radius) and coarse (6mm in radius) followed by quantification of the histogram parameters – kurtosis (a measure of peakedness and tailedness) and skewness (a measure of asymmetry of the histogram). Non-parametric Mann Whitney test assessed the ability of the qCTTA, clinical and patient characteristics to differentiate between K-ras mutation from pan-wildtype whereas Kaplan-Meier survival analysis assessed the ability of these markers including K-ras mutation to predict survival. Results: 48 cases were identified and qCTTA was applied to pre-treatment non-contrast CT. The median age was 70.4 years (range 45.1-85.1), 29 were men, and 46 had a smoking history. There were 33 adenocarcinomas, 10 squamous cell carcinomas, and 5 other NSCLC. Stages IA, IB, IIA, and IIB were 16, 21, 6, and 5; respectively. At least 33 patients did not receive adjuvant chemotherapy. There were 27 cases with K-ras mutation and 21 cases that were pan-wildtype. As of the last follow-up, 18 had confirmed disease relapse, including 5 with brain metastasis, and 22 were deceased. The median disease-free survival (DFS) was 39.7 months and median overall survival (OS) was 45.0 months. Positive skewness (p=0.031) and lower kurtosis (p=0.009) were significantly associated with the presence of a K-ras mutation (n=27 vs. 21 pan-wildtype). Kurtosis was a significant predictor of OS (p=0.009) and DFS (p=0.04) with a lower kurtosis value linked with poorer survival. As expected, patients with disease relapse and older age had significantly inferior OS and DFS, whereas adenocarcinomas (n=30) had inferior DFS vs. non-adenocarcinomas (n=14)(p=0.031). In line with other published data in early-stage NSCLC, K-ras was not associated with OS or DFS. Conclusions: The outcomes in this dataset are in sync with published poor clinical prognostic features in early-stage NSCLC. Lower kurtosis (which may reflect increased number of highlighted features and intensity variation in highlighted features) and positive skewness (which may reflect bright highlighted features surrounded by darker background or lower density areas) are significantly associated with K-ras mutations. These features may suggest more tumoral necrosis and these may be due to the hostile microenvironment within a K-ras driven tumor. A qCTTA feature such as lower kurtosis is prognostic for poorer OS and DFS. Non-invasive qCTTA can differentiate the presence of K-ras mutation from pan-wildtype NSCLC and is associated with patient survival. Citation Format: Glen J. Weiss, Balaji Ganeshan, Kenneth A. Miles, David A. Campbell, Philip Y. Cheung, Samuel Frank, Ronald L. Korn. Noninvasive image texture analysis differentiates K-ras mutation from pan-wildtype NSCLC and is prognostic. [abstract]. In: Proceedings of the AACR-IASLC Joint Conference on Molecular Origins of Lung Cancer; 2014 Jan 6-9; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2014;20(2Suppl):Abstract nr A34.

Purpose When physicians interpret 18F‐FDG PET/CT scans, they rely on their subjective visual impression of the presence of small lesions, the criteria for which may vary among readers. Our investigation used physical phantom scans to evaluate whether image texture analysis metrics reliably correspond to visual criteria used to identify lesions and accurately differentiate background regions from sub‐centimeter simulated lesions. Methods Routinely collected quality assurance test data were processed retrospectively for 65 different 18F‐FDG PET scans performed of standardized phantoms on eight different PET/CT systems. Phantoms included 8‐, 12‐, 16‐, and 25‐mm diameter cylinders embedded in a cylindrical water bath, prepared with 2.5:1 activity‐to‐background ratio emulating typical whole‐body PET protocols. Voxel values in cylinder regions and background regions were sampled to compute several classes of image metrics. Two experienced physicists, blinded to quantified image metrics and to each other's readings, independently graded cylinder visibility on a 5‐level scale (0 = definitely not visible to 4 = definitely visible). Results The three largest cylinders were visible in 100% of cases with a mean visibility score of 3.3 ± 1.2, while the smallest 8‐mm cylinder was visible in 58% of cases with a significantly lower mean visibility score of 1.5±1.1 (P

Purpose：The purpose of this study was to explore the correlation between CT texture features and the pathological grading of Pancreatic Neuroendocrine tumors. Materials and methods: A retrospective study was conducted on 54 patients (32 males and 22 females; average age (55.3 +11.1 years) with Pancreatic Neuroendocrine tumors (from March 2011 to May 2018) All patients had definite pathological diagnosis and grading results. The texture parameters of tumors were extracted from enhanced CT images taken before treatment. All parameters were analyzed by ROC curve, and the parameters with the largest AUC and P < 0.05 under each texture parameter category were selected. The selected parameters are modeled by binary logistic regression, and three models are constructed: image model, texture model and combined model. ROC was used to test the diagnostic capacity of these models. Result：We get the most discriminating image-based parameter (maxvalue, AUC: 0.678, p=0.037) and 5 most discriminating texture parameters (SHAPE_Volume (# vx), GLCM_Correlation, GLRLM_RLNU, NGLDM_Coarseness and GLZLM_ZLNU, AUC: 0.703,0.706, 0.715, 0.676, 0.702, p< 0.05) were selected by ROC analysis. Among them, maxvalue, SHAPE_Volume (# vx), GLCM_Correlation, GLRLM_RLNU and GLZLM_ZLNU tends to indicate pathological high-grade. NGLDM_Coarseness tends to indicate pathological low-grade. The AUC of image-based model is 0.678, with sensitivity of 81.1%, specificity of 52.9%. The AUC of texture model is 0.749, with sensitivity of 51.4%, specificity of 94.1%. The AUC of combined model is 0.766, with sensitivity of 56.8%, specificity of 94.1%. Conclusion: The preoperative enhanced CT image texture analysis to predict the pathological grade of pancreatic neuroendocrine tumors has a potential application.

Chemotherapy response and metastasis prediction play important roles in the treatment of pediatric osteosarcoma, which is prone to metastasis and has a high mortality rate. This study aimed to estimate the prediction model using gene expression and image texture features. 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) images of 52 pediatric osteosarcoma patients were used to estimate the machine learning algorithm. An appropriate algorithm was selected by estimating the machine learning accuracy. 18F-FDG PET/CT images of 21 patients were selected for prediction model development based on simultaneous KI67 and EZRIN expression. The prediction model for chemotherapy response and metastasis was estimated using area under the curve (AUC) maximum image texture features (AUC_max) and gene expression. The machine learning algorithm with the highest test accuracy in chemotherapy response and metastasis was selected using the random forest algorithm. The chemotherapy response and metastasis test accuracy with image texture features was 0.83 and 0.76, respectively. The highest test accuracy and AUC of chemotherapy response with AUC_max, KI67, and EZRIN were estimated to be 0.85 and 0.89, respectively. The highest test accuracy and AUC of metastasis with AUC_max, KI67, and EZRIN were estimated to be 0.85 and 0.8, respectively. The metastasis prediction accuracy increased by 10% using radiogenomics data.

Breast cancer is a known heterogeneous disease. Current clinically utilized histopathologic biomarkers may undersample tumor heterogeneity, resulting in higher rates of misdiagnosis for breast cancer. MRI can provide a whole-tumor sampling of disease burden and is widely utilized in clinical care. Texture analysis can provide a localized description of breast cancer, with particular emphasis on quantifying breast lesion heterogeneity. The object of this review is to provide an overview of texture analysis applications towards breast cancer diagnosis, prognosis, and treatment response evaluation and review the role of image-based texture features as noninvasive prognostic and predictive biomarkers. Level of Evidence: 5 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:927-938.

// Xin Zhang 1, * , Lin-Feng Yan 1, * , Yu-Chuan Hu 1 , Gang Li 2 , Yang Yang 1 , Yu Han 1 , Ying-Zhi Sun 1 , Zhi-Cheng Liu 1 , Qiang Tian 1 , Zi-Yang Han 3 , Le-De Liu 3 , Bin-Quan Hu 3 , Zi-Yu Qiu 3 , Wen Wang 1 and Guang-Bin Cui 1 1 Department of Radiology, Tangdu Hospital, The Fourth Military Medical University, Xi’an 710038, Shaanxi, P.R. China 2 Department of Neurosurgery, Tangdu Hospital, The Fourth Military Medical University, Xi’an 710038, Shaanxi, P.R. China 3 Student Brigade, The Fourth Military Medical University, Xi’an 710032, Shaanxi, P.R. China * These authors have contributed equally to this work Correspondence to: Guang-Bin Cui, email: cgbtd@126.com Wen Wang, email: wangwen@fmmu.edu.cn Keywords: glioma grading, MRI, machine learning, attribute selection, support vector machine (SVM) Received: March 17, 2017 Accepted: April 19, 2017 Published: May 18, 2017 ABSTRACT Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type , c , gama , K , etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

Background: To stratify risks of pancreatic adenocarcinoma (PA) patients using pre- and post-radiotherapy (RT) PET/CT images, and to assess the prognostic value of texture variations in predicting therapy response of patients. Methods: Twenty-six PA patients treated with RT from 2011–2013 with pre- and post-treatment 18F-FDG-PET/CT scans were identified. Tumor locoregional texture was calculated using 3D kernel-based approach, and texture variations were identified by fitting discrepancies of texture maps of pre- and post-treatment images. A total of 48 texture and clinical variables were identified and evaluated for association with overall survival (OS). The prognostic heterogeneity features were selected using lasso/elastic net regression, and further were evaluated by multivariate Cox analysis. Results: Median age was 69 y (range, 46–86 y). The texture map and temporal variations between pre- and post-treatment were well characterized by histograms and statistical fitting. The lasso analysis identified seven predictors (age, node stage, post-RT SUVmax, variations of homogeneity, variance, sum mean, and cluster tendency). The multivariate Cox analysis identified five significant variables: age, node stage, variations of homogeneity, variance, and cluster tendency (with P=0.020, 0.040, 0.065, 0.078, and 0.081, respectively). The patients were stratified into two groups based on the risk score of multivariate analysis with log-rank P=0.001: a low risk group (n=11) with a longer mean OS (29.3 months) and higher texture variation (>30%), and a high risk group (n=15) with a shorter mean OS (17.7 months) and lower texture variation ( Conclusions: Locoregional metabolic texture response provides a feasible approach for evaluating and predicting clinical outcomes following treatment of PA with RT. The proposed method can be used to stratify patient risk and help select appropriate treatment strategies for individual patients toward implementing response-driven adaptive RT.

To assess the changes in computed tomography (CT) tumor heterogeneity following neoadjuvant chemotherapy in esophageal cancer. Thirty-one consecutive patients who received neoadjuvant chemotherapy for esophageal cancer were identified. Analysis of primary tumor heterogeneity (texture) was performed on staging and post-chemotherapy CT scans. Image texture parameters (mean grey-level intensity, entropy, uniformity, kurtosis, skewness, standard deviation of histogram) were derived for different levels of image filtration (0-2.5). Proportional changes in each parameter following treatment were obtained. Comparison between pathological tumor response and texture parameters was analyzed using Mann-Whitney U-test. The relationship between CT texture and overall survival) was estimated using the Kaplan-Meier method. Tumor texture became more homogeneous after treatment with a significant decrease in entropy and increase in uniformity (filter 1.0 and 2.5). Pretreatment (filter 1.5, P = 0.006) and posttreatment standard deviation of histogram (filter 1.0, P = 0.009) showed a borderline association with pathological tumor response. A proportional change in skewness

Purpose: Imaging biomarker research focuses on discovering relationships between radiological features and histological findings. In glioblastoma patients, methylation of the O6-methylguanine methyltransferase (MGMT) gene promoter is positively correlated with an increased effectiveness of current standard of care. In this paper, the authors investigate texture features as potential imaging biomarkers for capturing the MGMT methylation status of glioblastoma multiforme (GBM) tumors when combined with supervised classification schemes. Methods: A retrospective study of 155 GBM patients with known MGMT methylation status was conducted. Co-occurrence and run length texture features were calculated, and both support vector machines (SVMs) and random forest classifiers were used to predict MGMT methylation status. Results: The best classification system (an SVM-based classifier) had a maximum area under the receiver-operating characteristic (ROC) curve of 0.85 (95% CI: 0.78–0.91) using four texture features (correlation, energy, entropy, and local intensity) originating from the T2-weighted images, yielding at the optimal threshold of the ROC curve, a sensitivity of 0.803 and a specificity of 0.813. Conclusions: Results show that supervised machine learning of MRI texture features can predict MGMT methylation status in preoperative GBM tumors, thus providing a new noninvasive imaging biomarker.

Purpose: A new approach to spectroscopic imaging was developed to detect and discriminate microscopic pathologies in resected breast tissues; diagnostic performance of the prototype system was tested in 27 tissues procured during breast conservative surgery. Experimental Design: A custom-built, scanning in situ spectroscopy platform sampled broadband reflectance from a 150-μm-diameter spot over a 1 × 1 cm2 field using a dark field geometry and telecentric lens; the system was designed to balance sensitivity to cellular morphology and imaging the inherent diversity within tissue subtypes. Nearly 300,000 broadband spectra were parameterized using light scattering models and spatially dependent spectral signatures were interpreted using a cooccurrence matrix representation of image texture. Results: Local scattering changes distinguished benign from malignant pathologies with 94% accuracy, 93% sensitivity, 95% specificity, and 93% positive and 95% negative predictive values using a threshold-based classifier. Texture and shape features were important to optimally discriminate benign from malignant tissues, including pixel-to-pixel correlation, contrast and homogeneity, and the shape features of fractal dimension and Euler number. Analysis of the region-based diagnostic performance showed that spectroscopic image features from 1 × 1 mm2 areas were diagnostically discriminant and enabled quantification of within-class tissue heterogeneities. Conclusions: Localized scatter-imaging signatures detected by the scanning spectroscopy platform readily distinguished benign from malignant pathologies in surgical tissues and showed new spectral-spatial signatures of clinical breast pathologies. Clin Cancer Res; 18(22); 6315–25. ©2012 AACR.

The purpose of this study was to investigate the correlation between image features extracted from PET images and the accuracy of manually drawn lesion contours in the lung. Such correlations are interesting in that they could potentially be used in predictive models to help guide physician contouring. In this work, 26 synthetic PET datasets were created using an anthropomorphic phantom and Monte Carlo simulation. Manual contours of simulated lesions were provided by 10 physicians. Contour accuracy was quantified using five commonly used similarity metrics which were then correlated with several features extracted from the images. Features were sub-divided into three groups using intensity, geometry, and texture as categorical descriptors. When averaged among the participants, the results showed relatively strong correlations with complexity and contrast I ( r ≥0.65, p r ≥0.5, p

Introduction The new BTS Pulmonary Nodule Guidelines 2015 recommend the use of composite prediction models to assess the pre-test probability of malignancy in patients presenting with pulmonary nodules (PNs). These models were not developed for use in patients with a history of malignancy within five years of presentation with a PN. In order to assist in the diagnosis of PNs, CT texture analysis has been proposed as a potential biomarker in tumour characterisation. 1 Image texture refers to the statistical analysis of spatial intensity variations of the pixels within an image to produce a CT texture score. 2 Aims and objectives To evaluate four existing models for the probability of malignancy in the target population. To create and validate prediction models for probability of malignancy for patients undergoing oncology follow-up for an indeterminate PN. Methods Retrospective data on clinical and radiological characteristics were collected from the medical records of 61 patients with a PN (mean diameter 7 mm, SD 4 mm) that had an active or previous history (within 5 years) of primary lung or extra-thoracic malignancy. The gold standard diagnosis of the nodules was established by histology or 2-year stable follow-up. Three multivariable logistic regression models were evaluated using a leave-one-out cross-validation strategy: Model 1: Age, Sex, Smoking status, Emphysema, Nodule diameter. Model 2: Age, Sex, Smoking status, Emphysema, CT Texture score. Model 3: CT Texture score only. The models’ performance, measured using the area under the ROC curve (AUC), were reported and further compared to existing clinical models. Results The highest AUC, 0.86, was obtained from Model 3 (texture score only). Utilising clinical parameters (Model 2) did not improve performance. In comparison, AUCs for previously published clinical models were 0.76(Mayo), 0.84(Herder), 0.66(VA) and 0.70(McWilliams) (Figure.1). Conclusion This texture feature model is successful at discriminating benign from malignant nodules in a population of patients undergoing oncology follow-up. While not significantly better than the Herder model (which incorporates PET avidity), this model offers improved risk stratification for PNs in the absence of PET in this patient group. References 1 RSNA 2014, SSC03-05 2 IEEE International Conference doi: 10.1109/SMC.2013.663

In this paper, we review the different studies that developed Computer Aided Diagnostic (CAD) for automated classification of thyroid cancer into benign and malignant types. Specifically, we discuss the different types of features that are used to study and analyze the differences between benign and malignant thyroid nodules. These features can be broadly categorized into (a) the sonographic features from the ultrasound images, and (b) the non-clinical features extracted from the ultrasound images using statistical and data mining techniques. We also present a brief description of the commonly used classifiers in ultrasound based CAD systems. We then review the studies that used features based on the ultrasound images for thyroid nodule classification and highlight the limitations of such studies. We also discuss and review the techniques used in studies that used the non-clinical features for thyroid nodule classification and report the classification accuracies obtained in these studies.

Background: Some patients with low-grade glioma have extraordinarily long survival times; current, early treatment does not prolong their lives. For this reason, therapies that sometimes have neurologic side effects are often deferred intentionally. Methods: In a study of oligodendrogliomas, we used a quantitative method of MR analysis based on the S-transform to investigate whether codeletion of chromosomes 1p and 19q, a marker of good prognosis, could be predicted accurately by measuring image texture. Results: Differences in texture were seen between tumors with codeletion of chromosomes 1p and 19q and those with intact 1p and 19q alleles on contrast-enhanced T1-weighted and T2-weighted MR images. Quantitative MR texture on T2 images predicted codeletion of chromosomes 1p and 19q with high sensitivity and specificity. Conclusions: This new method of MR image interpretation may have the potential to augment the diagnostic assessment of patients with suspected low-grade glioma.

The objective of this study was to classify hysteroscopy images of the endometrium based on texture analysis for the early detection of gynaecological cancer. A total of 418 Regions of Interest (ROIs) were extracted (209 normal and 209 abnormal) from 40 subjects. Images were gamma corrected and were converted to gray scale. The following texture features were extracted: (i) Statistical Features, (ii) Spatial Gray Level Dependence Matrices (SGLDM), and (iii) Gray level difference statistics (GLDS). The PNN and SVM neural network classifiers were also investigated for classifying normal and abnormal ROIs. Results show that there is significant difference (using Wilcoxon Rank Sum Test at a=0.05) between the texture features of normal and abnormal ROIs for both the gamma corrected and uncorrected images. Abnormal ROIs had lower gray scale median and homogeneity values, and higher entropy and contrast values when compared to the normal ROIs. The highest percentage of correct classifications score was 77% and was achieved for the SVM models trained with the SF and GLDS features. Concluding, texture features provide useful information differentiating between normal and abnormal ROIs of the endometrium. © 2006 IEEE. 3005 3008 Conference code: 69200 Cited By :6

Objective: To build an association map between medical images (CT/PET) and gene expression microarrays for Non-Small Cell Lung Cancer (NSCLC) from which to derive relationships between imaging features and gene expression. Methods: We studied 26 cases of NSCLC using CT and PET images and microarray data from excised tumors. An experienced thoracic radiologist annotated the CT image using “semantic features” from a controlled vocabulary, a nuclear medicine physician extracted the Standard Uptake Value (SUV) from the PET scan, and we developed and applied algorithms to extract “computational features” that characterized the lesion's image texture using Gabor and other texture features, the sharpness of lesion boundaries and the lesion boundary shape, including notions of compactness, roughness, and other shape signatures. We preprocessed the microarray data using log transformation and quantile normalization, obtained 100 co-expressed gene clusters using k-means clustering, and computed a metagene for each cluster using its first principal component. We performed (a) univariate and (b) multivariate analyses to integrate imaging features and metagenes using (a) Significance Analysis of Microarrays (SAM) with False Discovery Rate (FDR) multiple testing correction, and (b) Sparse Canonical Correlation Analysis (SCCA), respectively. Results: Image features included 44 semantic terms, 107 computational features, and SUV for each tumor. In a univariate analysis, 60 CT-features and SUV were significantly associated with at least one metagene, and on average 3.8 metagenes (FDR Conclusion: The integration of medical image features and gene expression promises to reveal molecular characteristics underlying medical image features. For translational purposes, this work highlights the potential use of medical image features as predictive markers for molecularly-targeted therapeutics. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr 4148. doi:10.1158/1538-7445.AM2011-4148

Purpose Methods and materials Results Conclusion Personal information and conflict of interest References, Purpose: Recently, new deep-learning reconstruction (DLR) algorithms have been developed. They allow the reduction of the noise magnitude but do not alter the image texture, which is very promising for the visualization of low-contrast liver lesions. Studies...

Yang Liu,1,* Feng-Jiao Zhang,2,* Xi-Xi Zhao,3,* Yuan Yang,4 Chun-Yi Liang,3 Li-Li Feng,5 Xiang-Bo Wan,5 Yi Ding,1 Yao-Wei Zhang1 1Department of Radiation Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, People’s Republic of China; 2Shanghai Concord Medical Cancer Center, Shanghai, 200001, People’s Republic of China; 3Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, People’s Republic of China; 4Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong, 510515, People’s Republic of China; 5Department of Radiation Oncology, The Sixth Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, 510655, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yi Ding; Yao-Wei Zhang Tel +86 20-62786616Email dingyi197980@126.com; weiyaozhang2@163.comPurpose: Neoadjuvant chemoradiotherapy (nCRT) has become the standard treatment for locally advanced rectal cancer (LARC). However, the accuracy of traditional clinical indicators in predicting tumor response is poor. Recently, radiomics based on magnetic resonance imaging (MRI) has been regarded as a promising noninvasive assessment method. The present study was conducted to develop a model to predict the pathological response by analyzing the quantitative features of MRI and clinical risk factors, which might predict the therapeutic effects in patients with LARC as accurately as possible before treatment.Patients and Methods: A total of 82 patients with LARC were enrolled as the training cohort and internal validation cohort. The pre-CRT MRI after pretreatment was acquired to extract texture features, which was finally selected through the minimum redundancy maximum relevance (mRMR) algorithm. A support vector machine (SVM) was used as a classifier to classify different tumor responses. A joint radiomics model combined with clinical risk factors was then developed and evaluated by receiver operating characteristic (ROC) curves. External validation was performed with 107 patients from another center to evaluate the applicability of the model.Results: Twenty top image texture features were extracted from 6192 extracted-radiomic features. The radiomics model based on high-spatial-resolution T2-weighted imaging (HR-T2WI) and contrast-enhanced T1-weighted imaging (T1+C) demonstrated an area under the curve (AUC) of 0.8910 (0.8114– 0.9706) and 0.8938 (0.8084– 0.9792), respectively. The AUC value rose to 0.9371 (0.8751– 0.9997) and 0.9113 (0.8449– 0.9776), respectively, when the circumferential resection margin (CRM) and carbohydrate antigen 19-9 (CA19-9) levels were incorporated. Clinical usefulness was confirmed in an external validation cohort as well (AUC, 0.6413 and 0.6818).Conclusion: Our study indicated that the joint radiomics prediction model combined with clinical risk factors showed good predictive ability regarding the treatment response of tumors as accurately as possible before treatment.Keywords: rectal cancer, neoadjuvant chemoradiotherapy, magnetic resonance imaging, tumor response

Background and purposeSemantic imaging features have been used for molecular subclassification of high-grade gliomas. Radiomics-based prediction of molecular subgroups has the potential to strategize and individualize therapy. Using MRI texture features, we propose to distinguish between IDH wild type and IDH mutant type high grade gliomas.MethodsBetween 2013 and 2020, 100 patients were retrospectively analyzed for the radiomics study. Immunohistochemistry of the pathological specimen was used to initially identify patients for the IDH mutant/wild phenotype and was then confirmed by Sanger’s sequencing. Image texture analysis was performed on contrast-enhanced T1 (T1C) and T2 weighted (T2W) MR images. Manual segmentation was performed on MR image slices followed by single-slice multiple sampling image augmentation. Both whole tumor multislice segmentation and single-slice multiple sampling approaches were used to arrive at the best model. Radiomic features were extracted, which included first-order features, second-order (GLCM—Grey level co-occurrence matrix), and shape features. Feature enrichment was done using LASSO (Least Absolute Shrinkage and Selection Operator) regression, followed by radiomic classification using Support Vector Machine (SVM) and a 10-fold cross-validation strategy for model development. The area under the Receiver Operator Characteristic (ROC) curve and predictive accuracy were used as diagnostic metrics to evaluate the model to classify IDH mutant and wild-type subgroups.ResultsMultislice analysis resulted in a better model compared to the single-slice multiple-sampling approach. A total of 164 MR-based texture features were extracted, out of which LASSO regression identified 14 distinctive GLCM features for the endpoint, which were used for further model development. The best model was achieved by using combined T1C and T2W MR images using a Quadratic Support Vector Machine Classifier and a 10-fold internal cross-validation approach, which demonstrated a predictive accuracy of 89% with an AUC of 0.89 for each IDH mutant and IDH wild subgroup.ConclusionA machine learning classifier of radiomic features extracted from multiparametric MRI images (T1C and T2w) provides important diagnostic information for the non-invasive prediction of the IDH mutant or wild-type phenotype of high-grade gliomas and may have potential use in either escalating or de-escalating adjuvant therapy for gliomas or for using targeted agents in the future.