First step to facilitate long-term and multi-centre studies of shear wave elastography in solid breast lesions using a computer-assisted algorithm

Evaluating different combination methods to analyse ultrasound and shear wave elastography images automatically through discriminative convolutional neural network in breast cancer imaging

Purpose

Ultrasound (US) and Shear Wave Elastography (SWE) imaging are non-invasive methods used for breast lesion characterization. While US and SWE images provide both morphological information, SWE visualizes in addition the elasticity of tissue. In this study a Discriminative Convolutional Neural Network (DCNN) model is applied to US and SWE images and their combination to classify the breast lesions into malignant or benign cases. Furthermore, it is identified whether analysing only the region of the elastogram or including the surrounding B-mode image gives a superior performance.

Methods

The dataset used in this study consists of 746 images obtained from 207 patients comprising 486 malignant and 260 benign breast lesions. From each image the US and SWE image was extracted, once including only the region of the elastogram and once including also the surrounding B-mode image. These four datasets were applied individually to a DCNN to determine their predictive capability. Each the best US and SWE dataset were used to examine different combination methods with DCNN. The results were compared to the manual assessment by an expert radiologist.

Results

The combination of US and SWE images with the surrounding B-mode image using two ensembled DCNN models achieved best results with an accuracy of 93.53 %, sensitivity of 94.42 %, specificity of 90.75 % and area under the curve (AUC) of 96.55 %.

Conclusion

This study showed that using the whole US and SWE images through DCNN was superior to methods, in which only the region of elastogram was used. Combining breast cancer US and SWE images with two ensembled DCNN models in parallel improved the results. The accuracy, sensitivity and AUC of the best combination method were significantly superior to the results of using a single dataset through DCNN and to the results of the expert radiologist.

Shear wave imaging and classification using extended Kalman filter and decision tree algorithm

Shear wave ultrasound elastography is a quantitative imaging approach in soft tissues based on viscosity-elastic properties. Complex shear modulus (CSM) estimation is an effective solution to analyze tissues' physical properties for elasticity and viscosity based on the wavenumber and attenuation coefficient. CSM offers a way to detect and classify some types of soft tissues. However, CSM-based elastography inherits some obstacles, such as estimation precision and calculation complexity. This work proposes an approach for two-dimensional CSM estimation and soft tissue classification using the Extended Kalman Filter (EKF) and Decision Tree (DT) algorithm, named the EKF-DT approach. CSM estimation is obtained by applying EKF to exploit shear wave propagation at each spatial point. Afterward, the classification of tissues is done by a direct and efficient decision tree algorithm categorizing three types of normal, cirrhosis, and fibrosis liver tissues. Numerical simulation scenarios have been employed to illustrate the recovered quality and practicality of the proposed method's liver tissue classification. With the EKF, the estimated wave number and attenuation coefficient are close to the ideal values, especially the estimated wave number. The states of three liver tissue types were automatically classified by applying the DT coupled with two proposed thresholds of elasticity and viscosity: (2.310 kPa, 1.885 Pa.s) and (3.620 kPa 3.146 Pa.s), respectively. The proposed method shows the feasibility of CSM estimation based on the wavenumber and attenuation coefficient by applying the EKF. Moreover, the DT can automate the classification of liver tissue conditions by proposing two thresholds. The proposed EKF-DT method can be developed by 3D image reconstruction and empirical data before applying it in medical practice.

Breast tumor classification using different features of quantitative ultrasound parametric images

RATIONALE AND OBJECTIVES

The ultrasound B-mode-based morphological and texture analysis and Nakagami parametric imaging have been proposed to characterize breast tumors. Since these three feature categories of ultrasonic tissue characterization supply information on different physical characteristics of breast tumors, by combining the above methods is expected to provide more clues for classifying breast tumors.

MATERIALS AND METHODS

To verify the validity of the concept, raw data were obtained from 160 clinical cases. Six different types of morphological-feature parameters, four texture features, and the Nakagami parameter of benignancy and malignancy were extracted for evaluation. The Pearson's correlation matrix was used to calculate the correlation between different feature parameters. The fuzzy c-means clustering and stepwise regression techniques were utilized to determine the optimal feature set, respectively. The logistic regression, receiver operating characteristic curve, and support vector machine were used to estimate the diagnostic ability.

RESULTS

The best performance was obtained by combining morphological-feature parameter (e.g., standard deviation of the shortest distance), texture feature (e.g., variance), and the Nakagami parameter, with an accuracy of 89.4%, a specificity of 86.3%, a sensitivity of 92.5%, and an area under receiver operating characteristic curve of 0.96. There was no significant difference between using fuzzy c-means clustering, logistic regression, and support vector machine based on the optimal feature set for breast tumors classification.

CONCLUSION

Therefore, we verified that different physical ultrasonic features are functionally complementary and thus improve the performance in diagnosing breast tumors. Moreover, the optimal feature set had the maximum discriminating performance should be irrelative to the power of classifiers.