Gray-level Co-occurrence Matrix Texture Features Research Articles

Real-time Burn Classification using Ultrasound Imaging

This article presents a real-time approach for classification of burn depth based on B-mode ultrasound imaging. A grey-level co-occurrence matrix (GLCM) computed from the ultrasound images of the tissue is employed to construct the textural feature set and the classification is performed using nonlinear support vector machine and kernel Fisher discriminant analysis. A leave-one-out cross-validation is used for the independent assessment of the classifiers. The model is tested for pair-wise binary classification of four burn conditions in ex vivo porcine skin tissue: (i) 200 °F for 10 s, (ii) 200 °F for 30 s, (iii) 450 °F for 10 s, and (iv) 450 °F for 30 s. The average classification accuracy for pairwise separation is 99% with just over 30 samples in each burn group and the average multiclass classification accuracy is 93%. The results highlight that the ultrasound imaging-based burn classification approach in conjunction with the GLCM texture features provide an accurate assessment of altered tissue characteristics with relatively moderate sample sizes, which is often the case with experimental and clinical datasets. The proposed method is shown to have the potential to assist with the real-time clinical assessment of burn degrees, particularly for discriminating between superficial and deep second degree burns, which is challenging in clinical practice.

Identification of Madura Tobacco Leaf Disease Using Gray- Level Co-Occurrence Matrix, Color Moments and Naïve Bayes

Indonesia is one of the world’s biggest tobacco crop producers. By tobacco farmer, this plant is often even dubbed “green gold”. Madura Island is one of the best tobacco-producing areas in Indonesia. Tobacco is a significant trading crop in the eastern part of Madura Island, specifically in Pamekasan and Sumenep. The decline in tobacco yields is usually caused by pests and diseases that attack tobacco plants. Experts can easily detect conditions in plants (including tobacco) with their eyes, but this is very suitable and requires expensive operational costs when the size of the planting area is vast, and the distance of the planting area is far from the location of the expert. So that digital image processing techniques need to be applied to detect tobacco plant diseases earlier. By using data in the form of photographs of tobacco plant leaves, the condition will be identified. The method used in this research is GLCM (Gray Level Co-Occurrence Matrix) texture feature extraction, while CM (Color Moment) colour feature extraction and Naïve Bayes method are used for classification. The results of testing tobacco identification obtained the best accuracy of 82.2% for Pamekasan tobacco and 84.4% for Sumenep tobacco. The best results are obtained by using the colour feature extraction.

Effect of MR Field Strength on the Texture Features of Cerebral T2-FLAIR Images: A Pilot Study

Objective To investigate effect of MR field strength on texture features of cerebral T2 fluid attenuated inversion recovery (T2-FLAIR) images. Methods We acquired cerebral 3D T2-FLAIR images of thirty patients who were diagnosed with ischemic white matter lesion (WML) with MR-1.5T and MR-3.0T scanners. Histogram texture features which included mean signal intensity (Mean), Skewness and Kurtosis, and gray level co-occurrence matrix (GLCM) texture features which included angular second moment (ASM), Contrast, Correlation, Inverse difference moment (IDM) and Entropy, of regions of interest located in the area of WML and normal white matter (NWM) were measured by ImageJ software. The texture parameters acquired with MR-1.5T scanning were compared with MR-3.0T scanning. Results The Mean of both WML and NWM obtained with MR-1.5T scanning was significantly lower than that acquired with MR-3.0T (P<0.001), while Skewness and Kurtosis between MR-1.5T and MR-3.0T scanning showed no significant difference (P>0.05). ASM, Correlation and IDM of both WML and NWM acquired with MR-1.5T revealed significantly lower values than those with MR-3.0T (P<0.001), while Contrast and Entropy acquired with MR-1.5T showed significantly higher values than those with MR-3.0T (P<0.001). Conclusion MR field strength showed no significant effect on histogram textures, while had significant effect on GLCM texture features of cerebral T2-FLAIR images, which indicated that it should be cautious to explain the texture results acquired based on the different MR field strength.

Multi-class discrimination of lymphadenopathy by using dual-modal ultrasound radiomics with elastography and B-mode ultrasound

The purpose of our study is to evaluate the diagnostic performance of radiomics in multi-class discrimination of lymphadenopathy based on elastography and B-mode dual-modal ultrasound images. We retrospectively analyzed a total of 251 lymph nodes (89 benign lymph nodes, 70 lymphoma and 92 metastatic lymph nodes) from 248 patients, which were examined by both elastography and B-mode sonography. Firstly, radiomic features were extracted from multimodal ultrasound images, including shape features, intensity statistics features and gray-level co-occurrence matrix texture features. Secondly, three feature selection methods based on information theory were used on the radiomic features to select different subsets of radiomic features, consisting of conditional infomax feature extraction, conditional mutual information maximization, and double input symmetric relevance. Thirdly, the support vector machine classifier was performed for diagnosis of lymphadenopathy on each radiomic subsets. Finally, we fused the results from different modalities and different radiomic feature subsets with Adaboost to improve the performance of lymph node classification. The results showed that the accuracy and overall F1 score with five-fold cross-validation were 76.09%±1.41% and 75.88%±4.32%, respectively. Moreover, when considering on benign lymph nodes, lymphoma or metastatic lymph nodes respectively, the area under the receiver operating characteristic curve of multi-class classification were 0.77, 0.93 and 0.84, respectively. This study indicates that radiomic features derived from multimodal ultrasound images are benefit for diagnosis of lymphadenopathy. It is expected to be useful in clinical differentiation of lymph node diseases.

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features.

Microscopic biopsy images are coloured in nature because pathologists use the haematoxylin and eosin chemical colour dyes for biopsy examinations. In this study, biopsy images are used for histological grading and the analysis of benign and malignant prostate tissues. The following PCa grades are analysed in the present study: benign, grade 3, grade 4, and grade 5. Biopsy imaging has become increasingly important for the clinical assessment of PCa. In order to analyse and classify the histological grades of prostate carcinomas, pixel-based colour moment descriptor (PCMD) and gray-level co-occurrence matrix (GLCM) methods were used to extract the most significant features for multilayer perceptron (MLP) neural network classification. Haar wavelet transformation was carried out to extract GLCM texture features, and colour features were extracted from RGB (red/green/blue) colour images of prostate tissues. The MANOVA statistical test was performed to select significant features based on F-values and P-values using the R programming language. We obtained an average highest accuracy of 92.7% using level-1 wavelet texture and colour features. The MLP classifier performed well, and our study shows promising results based on multi-feature classification of histological sections of prostate carcinomas.

Feasibility of contrast-enhanced MRI derived textural features to predict overall survival in locally advanced breast cancer.

The prognosis for women with locally advanced breast cancer (LABC) is poor and there is a need for better treatment stratification. Gray-level co-occurrence matrix (GLCM) texture analysis of magnetic resonance (MR) images has been shown to predict pathological response and could become useful in stratifying patients to more targeted treatments. To evaluate the ability of GLCM textural features obtained before neoadjuvant chemotherapy to predict overall survival (OS) seven years after diagnosis of patients with LABC. This retrospective study includes data from 55 patients with LABC. GLCM textural features were extracted from segmented tumors in pre-treatment dynamic contrast-enhanced 3-T MR images. Prediction of OS by GLCM textural features was assessed and compared to predictions using traditional clinical variables. Linear mixed-effect models showed significant differences in five GLCM features (f1, f2, f5, f10, f11) between survivors and non-survivors. Using discriminant analysis for prediction of survival, GLCM features from 2 min post-contrast images achieved a classification accuracy of 73% (P < 0.001), whereas traditional prognostic factors resulted in a classification accuracy of 67% (P = 0.005). Using a combination of both yielded the highest classification accuracy (78%, P < 0.001). Median values for features f1, f2, f10, and f11 provided significantly different survival curves in Kaplan-Meier analysis. This study shows a clear association between textural features from post-contrast images obtained before neoadjuvant chemotherapy and OS seven years after diagnosis. Further studies in larger cohorts should be undertaken to investigate how this prognostic information can be used to benefit treatment stratification.

Evaluation of TP53/PIK3CA mutations using texture and morphology analysis on breast MRI

PurposeSomatic mutations in TP53 and PIK3CA genes, the two most frequent genetic alternations in breast cancer, are associated with prognosis and therapeutic response. This study predicted the presence of TP53 and PIK3CA mutations in breast cancer by using texture and morphology analyses on breast MRI. Materials and methodsA total of 107 breast cancers (dataset A) from The Cancer Imaging Archive (TCIA) consisting of 40 TP53 mutation cancer and 67 cancers without TP53 mutation; 35 PIK3CA mutations cancer and 72 without PIK3CA mutation. 122 breast cancer (dataset B) from Seoul National University Hospital containing 54 TP53 mutation cancer and 68 without mutations were used in this study. At first, the tumor area was segmented by a region growing method. Subsequently, gray level co-occurrence matrix (GLCM) texture features were extracted after ranklet transform, and a series of features including compactness, margin, and ellipsoid fitting model were used to describe the morphological characteristics of tumors. Lastly, a logistic regression was used to identify the presence of TP53 and PIK3CA mutations. The classification performances were evaluated by accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Taking into account the trade-offs of sensitivity and specificity, the overall performances were evaluated by using receiver operating characteristic (ROC) curve analysis. ResultsThe GLCM texture feature based on ranklet transform is more capable of recognizing TP53 and PIK3CA mutations than morphological feature, especially for the TP53 mutation that achieves statistically significant. The area under the ROC curve (AUC) for TP53 mutation dataset A and dataset B achieved 0.78 and 0.81 respectively. For PIK3CA mutation, the AUC of ranklet texture feature was 0.70. ConclusionTexture analysis of segmented tumor on breast MRI based on ranklet transform is potential in recognizing the presence of TP53 mutation and PIK3CA mutation.

Data and resolution requirements in mapping vegetation in spatially heterogeneous landscapes

It has been argued that even centimeter-level resolution is needed for mapping vegetation patterns in spatially heterogeneous landscapes such as northern peatlands. However, there are few systematic tests for determining what kind of spatial resolution and data combinations are needed and what the differences in mapping accuracy are when different datasets are omitted or included. We conducted 78 different object-based supervised random forest classifications on a patterned fen and its surroundings in Kaamanen, northern Finland, using remotely sensed optical imagery, topography, and vegetation height datasets from different platforms (unmanned aerial vehicle (UAV), aerial, satellite) with spatial resolution ranging from 5 cm to 3 m. We compared differences in classification performance when we altered (1) classification and segmentation input data and features calculated from the data, or (2) the segmentation scale. We constructed training data with the help of transect-based field sampling and UAV imagery and tested classification accuracy using 412 field-surveyed vegetation plots. The most accurate classifications (75.7% overall accuracy) were obtained when we segmented a 5 cm resolution UAV image with a small segmentation scale and calculated features from all datasets. Classification accuracy was 2.2 percentage points (pp) lower with the most accurate aerial image (50 cm resolution) based classification, and 7.6 pp and 11.9 pp lower with the most accurate WorldView-2 (2 m resolution) and PlanetScope (3 m resolution) satellite image based classifications respectively. Classification accuracies were low (46.7–56.0%) when we used only spectral data from one dataset. The inclusion of gray-level co-occurrence matrix textural features increased classification accuracy by 0.4–12.1 pp and inclusion of multiple datasets by 8.2–25.0 pp. Segmentation scale had a minor effect on classification accuracy (2.5–7.3 pp difference between the finest and coarsest segmentation scale); however, both too small and large segmentation scale might lead to suboptimal classification. The differences in land cover type areal coverage were relatively small between classifications with multiple datasets, but if classifications included features from only one dataset, the differences were larger. We conclude that multiple different optical, topographical, and vegetation height datasets should be used when mapping vegetation in spatially heterogeneous landscapes, and that sub-meter resolution data (e.g. UAV or aerial) are necessary for the most accurate maps. Although UAV data is not essentially needed for classification, it is useful for training dataset construction and especially helpful in areas lacking other sub-meter resolution data.

Tree Species Classification by Employing Multiple Features Acquired from Integrated Sensors

Explicit information of tree species composition provides valuable materials for the management of forests and urban greenness. In recent years, scholars have employed multiple features in tree species classification, so as to identify them from different perspectives. Most studies use different features to classify the target tree species in a specific growth environment and evaluate the classification results. However, the data matching problems have not been discussed; besides, the contributions of different features and the performance of different classifiers have not been systematically compared. Remote sensing technology of the integrated sensors helps to realize the purpose with high time efficiency and low cost. Benefiting from an integrated system which simultaneously acquired the hyperspectral images, LiDAR waveform, and point clouds, this study made a systematic research on different features and classifiers in pixel-wised tree species classification. We extracted the crown height model (CHM) from the airborne LiDAR device and multiple features from the hyperspectral images, including Gabor textural features, gray-level co-occurrence matrix (GLCM) textural features, and vegetation indices. Different experimental schemes were tested at two study areas with different numbers and configurations of tree species. The experimental results demonstrated the effectiveness of Gabor textural features in specific tree species classification in both homogeneous and heterogeneous growing environments. The GLCM textural features did not improve the classification accuracy of tree species when being combined with spectral features. The CHM feature made more contributions to discriminating tree species than vegetation indices. Different classifiers exhibited similar performances, and support vector machine (SVM) produced the highest overall accuracy among all the classifiers.

Hyperspectral images classification with convolutional neural network and textural feature using limited training samples

ABSTRACTIn this letter, a new deep learning framework, which integrates textural features of gray level co-occurrence matrix (GLCM) into convolutional neural networks (CNNs) is proposed for hyperspectral images (HSIs) classification using limited number of labeled samples. The proposed method can be implemented in three steps. Firstly, the GLCM textural features are extracted from the first principal component after the principal components analysis (PCA) transformation. Secondly, a CNN is built to extract the deep spectral features from the original HSIs, and the features are concatenated with the textural features obtained in the first step in a concat layer of CNN. Finally, softmax is employed to generate classification maps at the end of the framework. In this way, the CNN focuses on the learning of spectral features only, and the generated textural features are used directly as one set of features before softmax. These lead to the reduction of the requirements for the size of training samples and the improvement of computing efficiency. The experimental results are presented for three HSIs and compared with several advanced deep learning and spectral-spatial classification techniques. The competitive classification accuracy can be obtained, especially when only a limited number of training samples are available.

A Model for Yellow Tea Polyphenols Content Estimation Based on Multi-Feature Fusion

Polyphenols are one of the important ingredients determining the quality of tea, which play an important role in affecting tea quality standards and quality control. At present, NIR spectroscopy technology has been widely used in tea quality detection to achieve good results. However, due to the lack of spatial features, it is difficult to meet the accuracy requirements to comprehensively judge the quality of both inside and outside of tea. With the development of hyperspectral imaging system (HIS), although progress has been made in the estimation of tea texture based on gray level co-occurrence matrix (GLCM) extraction, there are still some obstacles in practical applications. When the resolution is low, the texture features of the image are not significantly different, and a small number of features cannot more fully represent the image features, resulting in lower model accuracy. When the resolution is higher, the increase in the dimension of the feature leads to a more complex model. Therefore, it is necessary to extract multi-scale features from the hyperspectral image while preserving the original information of the hyperspectral image. In this study, a multi-feature fusion method is proposed to improve the accuracy of tea polyphenols content estimation. The process includes multi-scale wavelet decomposition, and feature fusion based on wavelet coefficient features, GLCM texture features and wavelet texture features. Experiments were carried out on five kinds of yellow tea by comparing different models based on different features, including partial least squares regression (PLSR) and support vector regression (SVR). Results indicated that the model based on multi-feature fusion is more accurate than the individual indicators, and models based on SVR perform better than PLSR.

Technical report: An advanced algorithm for the description of mice oocyte cytoplasm and polar body

Abstract Objective To assess oocyte quality to improve assisted reproductive technologies and high quality embryo production using image processing methods. Design A cross-sectional study. Setting Pasteur Institute, Iran. Subject(s) 6 microscopic graphs (including 31 oocytes) of the NMRI mice oocytes that were recorded with a stereomicroscope (Olympus, CX21, Tokyo, Japan). Intervention(s) To apply image processing techniques for oocyte quality assessment. Main outcome measure(s) oocyte areas segmentation using Moore neighborhood contour tracking method and, oocytes clustering in terms of the number of particles in the cytoplasm with the gray-level co-occurrence matrix texture features. Result(s) The success rate of the proposed algorithm is 82/48% and 91/00% in segmentation and clustering stages, respectively. Conclusion(s) The results of the evaluation criteria also reflect the proper functioning of the proposed algorithm. The three obtained clusters provided the following classification of oocyte images. Oocytes with medium or high granularity and eventually some anomalies such as inclusions or vacuoles, oocytes with medium granularity, oocytes with low granularity are oocyte's clusters.

Non-destructive Evaluation of Bread Staling Using Gray Level Co-occurrence Matrices

The potential application of image texture processing for non-destructive evaluation of bread staling was investigated by monitoring the changes in gray level co-occurrence matrix (GLCM) features (energy, contrast, homogeneity, correlation, and entropy) of baguette bread over a 5-day storage period. Energy experienced a significant reduction after 2 days of storage and increased significantly afterwards. However, contrast tended to increase dramatically over the entire storage time. While homogeneity and correlation showed a decreasing trend during the storage period, no meaningful trend was observed for changes of entropy. The GLCM texture features contrast, homogeneity, and correlation showed high correlations with the instrumental texture parameters and physicochemical properties of the bread during storage; in fact, the breads with firmer and less springy crumbs and higher crust moisture contents (the stale breads) had noticeably higher contrast and lower homogeneity and correlation values compared to the freshly baked samples. The results suggested that the GLCM texture features are promising indices for non-destructively assessing bread staling progress.

Assessing Texture Features to Classify Coastal Wetland Vegetation from High Spatial Resolution Imagery Using Completed Local Binary Patterns (CLBP)

Coastal wetland vegetation is a vital component that plays an important role in environmental protection and the maintenance of the ecological balance. As such, the efficient classification of coastal wetland vegetation types is key to the preservation of wetlands. Based on its detailed spatial information, high spatial resolution imagery constitutes an important tool for extracting suitable texture features for improving the accuracy of classification. In this paper, a texture feature, Completed Local Binary Patterns (CLBP), which is highly suitable for face recognition, is presented and applied to vegetation classification using high spatial resolution Pléiades satellite imagery in the central zone of Yancheng National Natural Reservation (YNNR) in Jiangsu, China. To demonstrate the potential of CLBP texture features, Grey Level Co-occurrence Matrix (GLCM) texture features were used to compare the classification. Using spectral data alone and spectral data combined with texture features, the image was classified using a Support Vector Machine (SVM) based on vegetation types. The results show that CLBP and GLCM texture features yielded an accuracy 6.50% higher than that gained when using only spectral information for vegetation classification. However, CLBP showed greater improvement in terms of classification accuracy than GLCM for Spartina alterniflora. Furthermore, for the CLBP features, CLBP_magnitude (CLBP_m) was more effective than CLBP_sign (CLBP_s), CLBP_center (CLBP_c), and CLBP_s/m or CLBP_s/m/c. These findings suggest that the CLBP approach offers potential for vegetation classification in high spatial resolution images.

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

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

Sonoelastomics for Breast Tumor Classification: A Radiomics Approach with Clustering-Based Feature Selection on Sonoelastography

A radiomics approach to sonoelastography, called “sonoelastomics,” is proposed for classification of benign and malignant breast tumors. From sonoelastograms of breast tumors, a high-throughput 364-dimensional feature set was calculated consisting of shape features, intensity statistics, gray-level co-occurrence matrix texture features and contourlet texture features, which quantified the shape, hardness and hardness heterogeneity of a tumor. The high-throughput features were then selected for feature reduction using hierarchical clustering and three-feature selection metrics. For a data set containing 42 malignant and 75 benign tumors from 117 patients, seven selected sonoelastomic features achieved an area under the receiver operating characteristic curve of 0.917, an accuracy of 88.0%, a sensitivity of 85.7% and a specificity of 89.3% in a validation set via the leave-one-out cross-validation, revealing superiority over the principal component analysis, deep polynomial networks and manually selected features. The sonoelastomic features are valuable in breast tumor differentiation.

Using Reflectance and Gray-Level Texture for Water Content Prediction in Grape Vines

In this study, we used visible/near-infrared (Vis/NIR) hyperspectral imaging technology to measure the reflectance and gray-level texture features of grape leaf surfaces, and we predicted water content based on those features for more effective irrigation control. Grape vine specimens were potted in the actual field environment, and five levels of water treatment with two replicates were applied to create controlled water stresses. The reflectance and gray-level co-occurrence matrix (GLCM) texture features were used to develop partial least squares (PLS) models for water content prediction. The results showed that when using both reflectance and GLCM texture features, the results achieved a correlation coefficient (rp), root mean square error of prediction (RMSEP), bias, and residual predictive deviation (RPD) of 0.900, 0.826, -2.213e-04, and 2.084, respectively. The experimental results indicated that using a Vis/NIR hyperspectral imaging system could enable this combined method of reflectance and GLCM texture to predict water content of grape vines and be beneficial for grape vine management.

Diffusion-weighted imaging of the abdomen: Impact of b-values on texture analysis features.

The purpose of this work was to systematically assess the impact of the b-value on texture analysis in MR diffusion-weighted imaging (DWI) of the abdomen. In eight healthy male volunteers, echo-planar DWI sequences at 16 b-values ranging between 0 and 1000s/mm2 were acquired at 3T. Three different apparent diffusion coefficient (ADC) maps were computed (0, 750/100, 390, 750s/mm2 /all b-values). Texture analysis of rectangular regions of interest in the liver, kidney, spleen, pancreas, paraspinal muscle and subcutaneous fat was performed on DW images and the ADC maps, applying 19 features computed from the histogram, grey-level co-occurrence matrix (GLCM) and grey-level run-length matrix (GLRLM). Correlations between b-values and texture features were tested with a linear and an exponential model; the best fit was determined by the smallest sum of squared residuals. Differences between the ADC maps were assessed with an analysis of variance. A Bonferroni-corrected p-value less than 0.008 (=0.05/6) was considered statistically significant. Most GLCM and GLRLM-derived texture features (12-18 per organ) showed significant correlations with the b-value. Four texture features correlated significantly with changing b-values in all organs (p<0.008). Correlation coefficients varied between 0.7 and 1.0. The best fit varied across different structures, with fat exhibiting mostly exponential (17 features), muscle mostly linear (12 features) and the parenchymatous organs mixed feature alterations. Two GLCM features showed significant variability in the different ADC maps. Several texture features vary systematically in healthy tissues at different b-values, which needs to be taken into account if DWI data with different b-values are analyzed. Histogram and GLRLM-derived texture features are stable on ADC maps computed from different b-values.

Quantitative ultrasound for tumour characterization and a priorichemotherapy response prediction

Previous studies have demonstrated that quantitative ultrasound (QUS) is an effective tool for monitoring breast cancer patients undergoing neoadjuvant chemotherapy. Here, for the first time, we demonstrate the clinical utility of pre-treatment QUS texture features in predicting the response of breast cancer patients to NAC. Using a 6 MHz center frequency clinical ultrasound imaging system, radiofrequency breast ultrasound data were acquired from 92 locally advanced breast cancer patients prior to their NAC treatment. QUS spectral parameters including mid-band fit, spectral slope, and spectral intercept, and average acoustic concentration and average scatterer diameter were computed from regions of interest in the tumor core and its margin. Subsequently, gray-level co-occurrence matrix textural features were extracted from the parametric images as potential predictive indicators. Results were compared with the clinico-pathological response of each patient determined at their treatment end. A composite QUS...

Early prognosis of metastasis risk in inflammatory breast cancer by texture analysis of tumour microscopic images.

Inflammatory breast cancer (IBC) is a rare and aggressive type of locally advanced breast cancer. The purpose of this study was to determine the value of microscopic tumour histomorphology texture for prognosis of local and systemic recurrence at the time of initial IBC diagnosis. This retrospective study included a group of 52 patients selected on the basis of non-metastatic IBC diagnosis, stage IIIB. Gray-Level-Co-Occurrence-Matrix (GLCM) texture analysis was performed on digital images of primary tumour tissue sections stained with haematoxylin/eosin. Obtained values were categorized by use of both data- and outcome-based methods. All five acquired GLCM texture features significantly associated with metastasis outcome. By accuracies of 69-81% and AUCs of 0.71-0.81, prognostic performance of GLCM parameters exceeded that of standard major IBC clinical prognosticators such as tumour grade and response to induction chemotherapy. Furthermore, a composite score consisting of tumour grade, contrast and correlation as independent features resulted in further enhancement of prognostic performance by accuracy of 89%, discrimination efficiency by AUC of 0.93 and an outstanding hazard ratio of 71.6 (95%CI, 41.7-148.4). Internal validation was successfully performed by bootstrap and split-sample cross-validation, suggesting that the model is generalizable. This study indicates for the first time the potential use of primary breast tumour histology texture as a highly accurate, simple and cost-effective prognostic indicator of metastasis risk in IBC. Clinical relevance of the obtained results rests on the role of prognosis in decisions on induction chemotherapy and the resulting impact on quality of life and survival.