Texture Analysis For Differentiation Research Articles

Machine learning-based texture analysis for differentiation of radiologically indeterminate small adrenal tumors on adrenal protocol CT scans.

To evaluate the ability of radiomic feature extraction and a machine learning algorithm to differentiate between benign and malignant indeterminate adrenal lesions on contrast-enhanced computed tomography (CT) studies. Adrenal "incidentalomas" are adrenal lesions that are accidentally discovered during workup not related to the adrenal glands; they have an incidence as high as 5%. Small adrenal incidentalomas (< 4cm) with high attenuation values on pre-contrast CT(> 10 HU) need further evaluation to calculate the absolute percentage of washout (APW). If the APW is < 60%, these lesions are considered non-adenomas and commonly classified as indeterminate adrenal lesions. Further workup for indeterminate lesions includes more complicated and expensive radiological studies or invasive procedures like biopsy or surgical resection. We searched our institutional database for indeterminate adrenal lesions with the following characteristics: < 4cm, pre-attenuation value > 10 HU, and APW < 60%. Exclusion criteria included pheochromocytoma and no histopathological examination. CT images were converted to Nifti format, and adrenal tumors were segmented using Amira software. Radiomic features from the adrenal mask were extracted using PyRadiomics software after removing redundant features (highly pairwise correlated features and low-variance features) using recursive feature extraction to select the final discriminative set of features. Lastly, the final features were used to build a binary classification model using a random forest algorithm, which was validated and tested using leave-one-out cross-validation, confusion matrix, and receiver operating characteristic curve. We found 40 indeterminate adrenal lesions (21 benign and 19 malignant). Feature extraction resulted in 3947 features, which reduced down to 62 features after removing redundancies. Recursive feature elimination resulted in the following top 4 discriminative features: gray-level size zone matrix-derived size zone non-uniformity from pre-contrast and delayed phases, gray-level dependency matrix-derived large dependence high gray-level emphasis from venous-phase, and gray-level co-occurrence matrix-derived cluster shade from delayed-phase. A binary classification model with leave-one-out cross-validation showed AUC = 0.85, sensitivity = 84.2%, and specificity = 71.4%. Machine learning and radiomic features extraction can differentiate between benign and malignant indeterminate adrenal tumors and can be used to direct further workup with high sensitivity and specificity.

Complementary Role of Computed Tomography Texture Analysis for Differentiation of Hepatocellular Carcinoma from Intrahepatic Peripheral Cholangiocellular Carcinoma on Single Portal-Venous Phase Computed Tomography

Hepatocellular carcinoma (HCC) and cholangiocellular carcinoma (CCC) are the most frequent primary hepatic malignancies...

Texture Analysis as a Radiomic Marker for Differentiating Benign From Malignant Adrenal Tumors.

The aim of this study was to evaluate the use of texture analysis for differentiation between benign from malignant adrenal lesions on contrast-enhanced abdominal computed tomography (CT). After institutional review board approval, a retrospective analysis was performed, including an electronic search of pathology records for all biopsied adrenal lesions. Patients were included if they also had a contrast-enhanced abdominal CT in the portal venous phase. Computed tomographic images were manually segmented, and texture analysis of the segmented tumors was performed. Texture analysis results of benign and malignant tumors were compared, and areas under the curve (AUCs) were calculated. One hundred twenty-five patients were included in the analysis. Excellent discriminators of benign from malignant lesions were identified, including entropy and standard deviation. These texture features demonstrated lower values for benign lesions compared with malignant lesions. Entropy values of benign lesions averaged 3.95 using a spatial scaling factor of 4 compared with an average of 5.08 for malignant lesions (P < .0001). Standard deviation values of benign lesions averaged 19.94 on the unfiltered image compared with an average of 34.32 for malignant lesions (P < .0001). Entropy demonstrated AUCs ranging from 0.95 to 0.97 for discriminating tumors, with sensitivities and specificities ranging from 81% to 95% and 88% to 100%, respectively. Standard deviation demonstrated AUCs ranging from 0.91 to 0.94 for discriminating tumors, with sensitivities and specificities ranging from 73% to 93% and 86% to 95%, respectively. Texture analysis offers a noninvasive tool for differentiating benign from malignant adrenal tumors on contrast-enhanced CT images. These results support the further development of texture analysis as a quantitative biomarker for characterizing adrenal tumors.

MRI-based texture analysis for differentiating pediatric craniofacial rhabdomyosarcoma from infantile hemangioma

To evaluate the diagnostic performance of MRI texture analysis (TA) for differentiation of pediatric craniofacial rhabdomyosarcoma (RMS) from infantile hemangioma (IH). This study included 15 patients with RMS and 42 patients with IH who underwent MRI before an invasive procedure. All patients had a solitary lesion. T2-weighted and fat-suppressed contrast-enhanced T1-weighted axial images were used for TA. Two readers delineated the tumor borders for TA independently and evaluated the qualitative MRI characteristics in consensus. The differences of the texture features' values between the groups were assessed and ROC curves were calculated. Logistic regression analysis was used to analyze the value of TA with and without the combination of the qualitative MRI characteristics. A p value < 0.05 was considered statistically significant. Thirty-eight texture features were calculated for each tumor. Eighteen features on T2-weighted images and 25 features on contrast-enhanced T1-weighted images were significantly different between the RMSs and IHs. On contrast-enhanced T1-weighted images, the short-zone emphasis (SZE), which was a gray-level zone length matrix (GLZLM) parameter, had the largest area under the curve: 0.899 (sensitivity 93%, specificity 87%). The independent predictor for the RMS among the qualitative MRI characteristics was heterogeneous contrast enhancement (p < 0.001). Using only a GLZLM_SZE value of lower than 0.72 was found to be the best diagnostic parameter in predicting RMS (p < 0.001; 95% CI, 8.770-992.4). MRI-based TA may contribute to differentiate RMS from IH without invasive procedures. • Texture analysis may help to distinguish between rhabdomyosarcoma and infantile hemangioma without invasive procedures. • The gray-level zone length matrix parameters, especially the short-zone emphasis, may be a potential predictor for rhabdomyosarcoma. • Using contrast-enhanced T1-weighted images may be superior to T2-weighted images to differentiate rhabdomyosarcoma from infantile hemangioma in texture analysis.

Complementary role of computed tomography texture analysis for differentiation of pancreatic ductal adenocarcinoma from pancreatic neuroendocrine tumors in the portal-venous enhancement phase

PurposeTo assess the role of CT-texture analysis (CTTA) for differentiation of pancreatic ductal adenocarcinoma (PDAC) from pancreatic neuroendocrine neoplasm (PNEN) in the portal-venous phase as compared with visual assessment and tumor-to-pancreas attenuation ratios.Methods53 patients (66.1 ± 8.6y) with PDAC and 42 patients (65.5 ± 12.2y) with PNEN who underwent contrast-enhanced CT for primary staging were evaluated. Volumes of interests (VOIs) were set in the tumor tissue at the portal-venous phase excluding adjacent structures. Based on pyradiomics library, 92 textural features were extracted including 1st, 2nd, and higher order features, and then compared between PNEN and PDAC. The visual assessment classified tumors into hypo-, iso-, or hyperdense to pancreas parenchyma or into homogeneous/heterogeneous. Additionally, attenuation ratios between the tumors and the non-involved pancreas were calculated.Results8/92 (8.6%) highly significant (p < 0.005) discriminatory textural features between PDAC and PNEN were identified including the 1st order features “median,” “total energy,” “energy,” “10th percentile,” “90th percentile,” “minimum,” “maximum,” and the 2nd order feature “Gray-Level co-occurrence Matrix (GLCM) Informational Measure of Correlation (Imc2).” In PNEN, the higher order feature “GLSZM Small Area High Gray-Level Emphasis” proved significantly higher in G1 compared to G2/3 tumors (p < 0.05). The tumor/parenchyma ratios as well as the visual assessment into hypo-/iso-/hyperdense or homogeneous/heterogeneous did not significantly differ between PDAC and PNEN.ConclusionsOur data indicate that CTTA is a feasible tool for differentiation of PNEN from PDAC and also of G1 from G2/3 PNEN in the portal-venous phase. Visual assessment and tumor-to-parenchyma ratios were not useful for discrimination.

Machine learning-based texture analysis for differentiation of large adrenal cortical tumours on CT

To compare the efficacy of computed tomography (CT) texture analysis and conventional evaluation by radiologists for differentiation between large adrenal adenomas and carcinomas. Quantitative CT texture analysis was used to evaluate 54 histopathologically proven adrenal masses (mean size=5.9 cm; range=4.1-10 cm) from 54 patients referred to Anderson Cancer Center from January 2002 through April 2014. The patient group included 32 women (mean age at mass evaluation=59 years) and 22 men (mean age at mass evaluation=61 years). Adrenal lesions seen on precontrast and venous-phase CT images were labelled by three different readers, and the labels were used to generate intensity- and geometry-based textural features. The textural features and the attenuation values were considered as input values for a random forest-based classifier. Similarly, the adrenal lesions were classified by two different radiologists based on morphological criteria. Prediction accuracy and interobserver agreement were compared. The textural predictive model achieved a mean accuracy of 82%, whereas the mean accuracy for the radiologists was 68.5% (p<0.0001). The interobserver agreements between the predictive model and radiologists 1 and 2 were 0.44 (p<0.0005; 95% confidence interval [CI]: 0.25-0.62) and 0.47 (p<0.0005; 95% CI: 0.28-0.66), respectively. The Dice similarity coefficient between the readers' image labels was 0.875±0.04. CT texture analysis of large adrenal adenomas and carcinomas is likely to improve CT evaluation of adrenal cortical tumours.

MRI texture analysis for differentiation of malignant and benign hepatocellular tumors in the non-cirrhotic liver

PurposeTo find potentially diagnostic texture analysis (TA) features and to evaluate the diagnostic accuracy of two-dimensional (2D) magnetic resonance (MR) TA for differentiation between hepatocellular carcinoma (HCC) and benign hepatocellular tumors in the non-cirrhotic liver in an exploratory MR-study. Materials and methods108 non-cirrhotic patients (62 female; 41.5 ± 18.3 years) undergoing preoperative contrast-enhanced MRI were retrospectively included in this multi-center-study. TA including gray-level histogram, co-occurrence and run-length matrix features (total 19 features) was performed by two independent readers. Native fat-saturated-T1w and T2w as well as arterial and portal-venous post contrast-enhanced 2D-image-slices were assessed. Conventional reading was performed by two separate independent readers. Differences in TA features between HCC and benign lesions were investigated using independent sample t-tests. Logistic regression analysis was performed to obtain the optimal number/combination of TA-features and diagnostic accuracy of TA analysis. Sensitivity and specificity of the better performing radiologist were compared to TA analysis. ResultsThe highest number of significantly differing TA-features (n = 5) was found using the arterial-phase images including one gray-level histogram (skewness, p = 0.018) and four run-length matrix features (all, p < 0.02). The optimal binary logistic regression model for TA-features of the arterial-phase images contained 13 parameters with an accuracy of 84.5% (sensitivity 84.1%, specificity 84.9%) and area-under-the-curve of 0.92 (95%-confidence-interval 0.85–0.98) for diagnosis of HCC. Conventional reading yielded a significantly lower sensitivity (63.6%, p = 0.027) and no significant difference in specificity (94.6%, p = 0.289) at best. Conclusion2D-TA of MR images is a feasible objective method that may help to distinguish HCC from benign hepatocellular tumors in the non-cirrhotic liver. Most promising results were found in TA features in the arterial phase images.

Evaluation of texture analysis for the differential diagnosis of focal nodular hyperplasia from hepatocellular adenoma on contrast-enhanced CT images.

To explore the value of CT texture analysis (CTTA) for differentiation of focal nodular hyperplasia (FNH) from hepatocellular adenoma (HCA) on contrast-enhanced CT (CECT). This is a retrospective, IRB-approved study conducted in a single institution. A search of the medical records between 2008 and 2017 revealed 48 patients with 70 HCA and 50 patients with 62 FNH. All lesions were histologically proven and with available pre-operative CECT imaging. Hepatic arterial phase (HAP) and portal venous phase (PVP) were used for CTTA. Textural features were extracted using a commercially available research software (TexRAD). The differences between textural parameters of FNH and HCA were assessed using the Mann-Whitney U test and the AUROC were calculated. CTTA parameters showing significant difference in rank sum test were used for binary logistic regression analysis. A p value < 0.05 was considered statistically significant. On HAP images, mean, mpp, and skewness were significantly higher in FNH than in HCA on unfiltered images (p ≤ 0.007); SD, entropy, and mpp on filtered analysis (p ≤ 0.006). On PVP, mean, mpp, and skewness in FNH were significantly different from HCA (p ≤ 0.001) on unfiltered images, while entropy and kurtosis were significantly higher in FNH on filtered images (p ≤ 0.018). The multivariate logistic regression analysis indicated that the mean, mpp, and entropy of medium-level and coarse-level filtered images on HAP were independent predictors for the diagnosis of HCA and a model based on all these parameters showed the largest AUROC (0.824). Multiple explored CTTA parameters are significantly different between FNH and HCA on CECT.

Whole-Tumor Quantitative Apparent Diffusion Coefficient Histogram and Texture Analysis to Differentiation of Minimal Fat Angiomyolipoma from Clear Cell Renal Cell Carcinoma

To evaluate the diagnostic value of whole-tumor quantitative apparent diffusion coefficient (ADC) histogram and texture analysis for differentiation of minimal fat angiomyolipoma (MFAML) from clear cell renal cell carcinoma (ccRCC). We retrospectively reviewed 27 patients with MFAML and 113 patients with ccRCC pathologically proven. All patients performed magnetic resonance imaging (MRI) including diffusion-weighted imaging (b = 0, 800s/mm2). Whole-tumor regions of interest were drawn on all slices of diffusion-weighted imaging to obtain histogram and texture parameters, including the mean ADC, median ADC, 10th, 25th, 75th, 90th percentiles ADC, standard deviation, skewness, kurtosis, and entropy. The Student's t test was used to compare the parameters between MFAML and ccRCC. Receiver operating characteristic curves analysis was used to compare the diagnostic value of each significant parameter. MFAML had significantly lower mean ADC, median ADC, 10th, 25th, 75th, 90th percentiles ADC than ccRCC (p < 0.001, p < 0.001, p < 0.001, p < 0.001, p < 0.001, p < 0.001, respectively). Skewness of MFAML was significantly higher than that of ccRCC (p = 0.016). However, standard deviation, kurtosis, and entropy were not significantly different (p = 0.409, p = 0.085, p = 0.206, respectively). The 90th percentile ADC generated the highest AUC (AUC, 0.854; Sensitivity, 78.8%; Specificity, 81.5%) for differentiating MFAML from ccRCC. Whole-tumor ADC histogram and texture analysis could be considered a useful and noninvasive method to help differentiate MFAML of ccRCC with higher accuracy.

SU‐E‐E‐16: The Application of Texture Analysis for Differentiation of Central Cancer From Atelectasis

Purpose:Prospectively assess the potential utility of texture analysis for differentiation of central cancer from atelectasis.Methods:0 consecutive central lung cancer patients who were referred for CT imaging and PET‐CT were enrolled. Radiotherapy doctor delineate the tumor and atelectasis according to the fusion imaging based on CT image and PET‐CT image. The texture parameters (such as energy, correlation, sum average, difference average, difference entropy), were obtained respectively to quantitatively discriminate tumor and atelectasis based on gray level co‐occurrence matrix (GLCM)Results:The texture analysis results showed that the parameters of correlation and sum average had an obviously statistical significance(P&lt;0.05).Conclusion:the results of this study indicate that texture analysis may be useful for the differentiation of central lung cancer and atelectasis.

Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas.

To retrospectively investigate the value of computerized three-dimensional texture analysis for differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas (IPAs) that manifest as part-solid ground-glass nodules (GGNs). The institutional review board approved this retrospective study with a waiver of patients' informed consent. The study consisted of 86 patients with 86 pathologic analysis-confirmed part-solid GGNs (mean size, 16 mm ± 5.4 [standard deviation]) who had undergone computed tomographic (CT) imaging between January 2005 and October 2011. Each part-solid GGN was manually segmented and its computerized texture features were quantitatively extracted by using an in-house software program. Multivariate logistic regression analysis was performed to investigate the differentiating factors of preinvasive lesions from IPAs. Three-layered artificial neural networks (ANNs) with a back-propagation algorithm and receiver operating characteristic curve analysis were used to build a discriminating model with texture features and to evaluate its discriminating performance. Pathologic analysis confirmed 58 IPAs (seven minimally invasive adenocarcinomas and 51 invasive adenocarcinomas) and 28 preinvasive lesions (four atypical adenomatous hyperplasias and 24 adenocarcinomas in situ). IPAs and preinvasive lesions exhibited significant differences in various histograms and volumetric parameters (P < .05). Multivariate analysis revealed that smaller mass (adjusted odds ratio, 0.092) and higher kurtosis (adjusted odds ratio, 3.319) are significant differentiators of preinvasive lesions from IPAs (P < .05). With mean attenuation, standard deviation of attenuation, mass, kurtosis, and entropy, the ANNs model showed excellent accuracy in differentiation of preinvasive lesions from IPAs (area under the curve, 0.981). In part-solid GGNs, higher kurtosis and smaller mass are significant differentiators of preinvasive lesions from IPAs, and preinvasive lesions can be accurately differentiated from IPAs by using computerized texture analysis. Online supplemental material is available for this article.

CHRISTINE Code for High ResolutIon Satellite mapping of optical ThIckness and Ångstrom Exponent. Part II

Previously developed DTA (Differential Textural Analysis) and SMA (Satellite Mapping of Aerosols) image processing codes address aerosol optical thickness (AOT) retrieval and mapping over urban are...

CHRISTINE Code for High ResolutIon Satellite mapping of optical ThIckness and ÅNgstrom Exponent. Part I: Algorithm and code

Previously developed DTA (Differential Textural Analysis) and SMA (Satellite Mapping of Aerosols) image processing codes address aerosol optical thickness (AOT) retrieval and mapping over urban areas by applying the contrast reduction principle to single spectral bands of high resolution satellite data. Two satellite images are required to apply this principle: one “reference”, with minimum aerosol content, and one “polluted” with AOT values to be assessed. Surface reflectance is assumed invariant between the two images thus AOT values are relative to the reference image. AOT values may be therefore miscalculated if surface changes, and consequent reflectance variations, have occurred in the time between the acquisitions of the two images. A new code abbreviated CHRISTINE (Code for High ResolutIon Satellite mapping of optical ThIckness and aNgstrom Exponent) has been developed to effectively reduce this kind of AOT miscalculation. The new code is not based on look-up tables and takes into consideration contrast reduction in more than one spectral band using the Ångstrom's power law to decouple reflectance variations due to surface changes, on the one hand, from reflectance variations due to atmospheric changes associated to the aerosol content, on the other. A second novelty of this code, emerging from the Ångstrom coefficient approximation, is its potential to provide information on aerosol size distribution. The application of CHRISTINE could supplement sparse urban monitoring networks and optimize the deployment of existing stations.

Comparison of contrast reduction based MODIS AOT estimates with AERONET measurements

Current satellite aerosol retrieval products could be complemented by contrast reduction methods to overcome limitations regarding highly reflective or heterogeneous surfaces such as urban, desert or snow covered areas. Algorithms based on the contrast reduction principle, define contrast loss in an image, inside a pre-determined window size, as an exponential function of the Aerosol Optical Thickness (AOT) difference between two images (a reference and a polluted) acquired under similar observation geometry conditions. This paper presents a contrast reduction algorithm designed for the MODIS sensor, based on the Differential Texture Analysis (DTA) approach. It focuses on algorithm optimization by: a) determining an optimal AOT spatial resolution; b) constraining the relative observation geometry differences between polluted and reference images; and c) assessing the influence of several land cover classes on the accuracy of the retrievals. A comparison of the results obtained for 192 images acquired for the year 2005 with data from five European AERONET stations is performed to assess overall algorithm accuracy as well as the impact of the proposed improvements. Comparative analysis of the results for the various sites showed an optimal algorithm performance for MODIS images using a 39pixel distance window, composed of only forest and urban pixels. Comparison with AERONET AOT data showed a good agreement with a correlation coefficient of 0.78. A similar correlation is found when comparing AERONET measurements and MODIS aerosol standard product. This research supports the establishment of contrast reduction methods as a potential complement to other aerosol retrieval methodologies. Future work will aim at removing the residual aerosol influence from reference images, including BRDFs to better reproduce surface heterogeneity and observation geometry influences and expanding the scope of this study to other AERONET sites so as to further test the algorithm at a global scale.

Aerosol Monitoring over Athens Using Satellite and Ground‐Based Measurements

Satellite data of moderate spatial resolution (MODIS and MERIS) were used to retrieve the aerosol optical depth (AOD) over the urban area of Athens. MODIS products were obtained at a horizontal resolution of 10 by 10 km2 centered over Athens, while the differential textural analysis (DTA) code was applied to MERIS images to retrieve relative‐to‐reference AOD with a resolution of 260 m by 290 m. The possibility of exploiting the full resolution of MERIS data in retrieving AOD over a grid of a few hundreds metres was thereby investigated for the first time. MERIS‐based AOD, centred at 560 nm, showed strong positive correlation to ground‐based PM10 data (R2 = 0.85), while MODIS AOD products were in agreement with both MERIS and PM10. Back trajectories were used to study the impact of atmospheric conditions prevailing during the examined days. Days associated with Saharan air masses corresponded to enhanced AOD and predominance of coarse‐mode particles. The results suggest that, at least for the case of Athens, AOD retrieved by MERIS images using the DTA code over cloud‐free areas can be related to PM10. The accuracy of retrieval mainly depends on the successful selection of the reference satellite data, namely, an image being least contaminated by tropospheric aerosols.

Urban aerosol mapping over Athens using the differential textural analysis (DTA) algorithm on MERIS-ENVISAT data

Low and moderate spatial resolution satellite sensors (such as TOMS, AVHRR, SeaWiFS) have already shown their capability in tracking aerosols at a global scale. Sensors with moderate to high spatial resolution (such as MODIS and MERIS) seem also to be appropriate for aerosol retrieval at a regional scale. We investigated in this study the potential of MERIS-ENVISAT data to resolve the horizontal spatial distribution of aerosols over urban areas, such as the Athens metropolitan area, by using the differential textural analysis (DTA) code. The code was applied to a set of geo-corrected images to retrieve and map aerosol optical thickness (AOT) values relative to a reference image assumed to be clean of pollution with a homogeneous atmosphere. The comparison of satellite retrieved AOT against PM10 data measured at ground level showed a high positive correlation particularly for the AOT values calculated using the 5th MERIS’ spectral band (R2=0.83). These first results suggest that the application of the DTA code on cloud free areas of MERIS images can be used to provide AOT related to air quality in this urban region. The accuracy of retrieved AOT mainly depends on the overall quality, the pollution cleanness and the atmospheric homogeneity of the reference image.

Estimation and Mapping of Aerosol Optical Thickness over the City of Brescia ‐ Italy Using Diachronic and Multiangle SPOT-1, SPOT-2 and SPOT-4 Imagery

In this paper we process diachronic SPOT satellite images acquired with different viewing angles in order to assess the aerosol optical thickness (AOT) spatial distribution over Brescia. This urban area, located in Northern Italy, is subject to frequent visibility‐reducing smog episodes. AOT was calculated by using the Differential Textural Analysis (DTA) code on a satellite data series consisting by one pollution‐free and various pollution‐loaded SPOT images. The resulting maps showed the horizontal distribution of AOT with a resolution of 500 metres. These maps can be readily integrated with the results obtained by mesoscale modelling, ground measurements, and respond to local scale application requirements. Satellite AOT retrieval compared successfully with available AOT ground‐based measurements and with pollution measurements in the ambient air. In this study the use of diachronic multiangle SPOT imagery allowed us to analyse the effect of the viewing angle variation on AOT retrieval accuracy based on the contrast reduction method.

Wavelet-packet-based texture analysis for differentiation between benign and malignant liver tumours in ultrasound images

The purpose of this study was to apply a novel method of multiscale echo texture analysis for distinguishing benign (hemangiomas) from malignant (hepatocellular carcinomas (HCCs) and metastases) focal liver lesions in B-mode ultrasound images. In this method, regions of interest (ROIs) extracted from within the lesions were decomposed into subimages by wavelet packets. Multiscale texture features that quantify homogeneity of the echogenicity were calculated from these subimages and were combined by an artificial neural network (ANN). A subset of the multiscale features was selected that yielded the highest performance in the classification of lesions measured by the area under the receiver operating characteristic curve (Az). In an analysis of 193 ROIs consisting of 50 hemangiomas, 87 hepatocellular carcinomas and 56 metastases, the multiscale features yielded a high Az value of 0.92 in distinguishing benign from malignant lesions, 0.93 in distinguishing hemangiomas from HCCs and 0.94 in distinguishing hemangiomas from metastases. Our new multiscale texture analysis method can effectively differentiate malignant from benign lesions, and thus has the potential to increase the accuracy of diagnosis of focal liver lesions in ultrasound images.

Improvement of satellite derived pollution maps with the use of a geostatistical interpolation method

The small number of ground stations for the assessment of the spatial distribution of air pollutants motivates the search for methods that make use of satellite images. One such method, known as Differential Texture Analysis (DTA), is used to measure the Aerosol Optical Thickness in the Visible (AOTV), which correlates highly with air quality. With this method, the presence of clouds and/or land cover changes produce patches of missing values. In this paper we demonstrate that universal kriging can be used to obtain reasonable estimates for these missing values. The methodology was applied to a satellite derived AOTV map of the city of Brescia (Italy).