Comparison of methods for texture analysis of QUS parametric images in the characterization of breast lesions

Abstract

Purpose Accurate and timely diagnosis of breast carcinoma is very crucial because of its high incidence and high morbidity. Screening can improve overall prognosis by detecting the disease early. Biopsy remains as the gold standard for pathological confirmation of malignancy and tumour grading. The development of diagnostic imaging techniques as an alternative for the rapid and accurate characterization of breast masses is necessitated. Quantitative ultrasound (QUS) spectroscopy is a modality well suited for this purpose. This study was carried out to evaluate different texture analysis methods applied on QUS spectral parametric images for the characterization of breast lesions. Methods Parametric images of mid-band-fit (MBF), spectral-slope (SS), spectral-intercept (SI), average scatterer diameter (ASD), and average acoustic concentration (AAC) were determined using QUS spectroscopy from 193 patients with breast lesions. Texture methods were used to quantify heterogeneities of the parametric images. Three statistical-based approaches for texture analysis that include Gray Level Co-occurrence Matrix (GLCM), Gray Level Run-length Matrix (GRLM), and Gray Level Size Zone Matrix (GLSZM) methods were evaluated. QUS and texture-parameters were determined from both tumour core and a 5-mm tumour margin and were used in comparison to histopathological analysis in order to classify breast lesions as either benign or malignant. We developed a diagnostic model using different classification algorithms including linear discriminant analysis (LDA), k-nearest neighbours (KNN), support vector machine with radial basis function kernel (SVM-RBF), and an artificial neural network (ANN). Model performance was evaluated using leave-one-out cross-validation (LOOCV) and hold-out validation. Results Classifier performances ranged from 73% to 91% in terms of accuracy dependent on tumour margin inclusion and classifier methodology. Utilizing information from tumour core alone, the ANN achieved the best classification performance of 93% sensitivity, 88% specificity, 91% accuracy, 0.95 AUC using QUS parameters and their GLSZM texture features. Conclusions A QUS-based framework and texture analysis methods enabled classification of breast lesions with >90% accuracy. The results suggest that optimizing method for extracting discriminative textural features from QUS spectral parametric images can improve classification performance. Evaluation of the proposed technique on a larger cohort of patients with proper validation technique demonstrated the robustness and generalization of the approach.

A priori prediction of response in multicentre locally advanced breast cancer (LABC) patients using quantitative ultrasound and derivative texture methods

“…This can be attributed to the fact that a linear classification algorithm works best only for linearly separable data. Nonlinear classification algorithms in the SVM-RBF methodology outperformed the other two classification algorithms as has been demonstrated previously in various contexts [25,26,29].…”

“…Margin analysis akin to that in this study has been demonstrated earlier to have sufficient discriminative power to differentiate responders from non-responders [30]. In addition, margin analysis has also been explored in the characterization of breast lesions [25,26]. Tumour responses to NAC are thought to be different between responders and non-responders.…”

“…Quantitative ultrasound (QUS) spectroscopy has been used for characterizing different types of tissue [17][18][19][20][21][22][23], classifying tissue abnormalities, differentiating benign from malignant tumours [24][25][26], and assessing tumour responses to treatment [27][28][29][30][31][32]. In pre-clinical studies, QUS spectroscopy has been used to differentiate benign versus malignant breast tumours and to differentiate types of mammary cancers [33,34].…”

“…In addition, the model was developed using ultrasound RF data collected from multi-centric cancer centers. This work is a part of ongoing efforts in the inclusion of artificial intelligence tools in diagnostic and predictive models for cancer therapies [25][26][27][28][29][30][31][32]. A necessary step in the use of artificial intelligence tools in diagnostic and prediction is to generalize the model [50].…”

Comparative Analysis of Classification Algorithms in the Analysis of Medical Images From Speckle Tracking Echocardiography Video Data

“…Тому, щоб отримати найбільш інформативні характеристики та високу якість діагностичних моделей, в усіх випадках було використано дані текстурного аналізу, який ми успішно застосували в роботах [3][4][5][6]. Для отримання вхідних даних, необхідних для класифікації зображення, було прийнято рішення використати текстурний аналіз [10][11][12]. Ми застосовували різні підходи для отримання ознак текстурного аналізу через використання матриці відтінків сірого зображення (GM), матриці суміжності відтінків сірого (GLCM) [13] та матриці довжин пробігу відтінків сірого (GLRLM) [14].…”