Computer-aided tumor diagnosis using shear wave breast elastography.

Area of Science:

• Medical Imaging
• Biomedical Engineering
• Oncology

Background:

• Shear wave elastography (SWE) measures tissue stiffness using acoustic radiation force, offering reduced operator dependency in data acquisition compared to strain elastography.
• Despite advancements, the reproducibility of SWE results remains interpreter-dependent, necessitating objective diagnostic tools.
• Accurate differentiation between benign and malignant breast tumors is crucial for effective patient management and treatment planning.

Purpose of the Study:

• To develop and evaluate a computer-aided diagnosis (CAD) system for differentiating benign from malignant breast tumors using SWE imaging.
• To assess the diagnostic performance of SWE-derived features compared to traditional B-mode ultrasound features.
• To investigate the combined diagnostic utility of SWE and B-mode ultrasound features for breast tumor classification.

Main Methods:

• Development of a CAD method involving automatic tumor segmentation using the level set method and hue-saturation-value color transformation.
• Calculation of SWE features: average tissue elasticity, sectional stiffness ratio, and normalized minimum distance for stiffer pixels.
• Comparison of CAD performance using SWE features, B-mode ultrasound features (morphologic and textural), and a combination of both feature sets in 109 biopsy-proven breast tumors.

Main Results:

• The CAD system achieved a sensitivity, specificity, accuracy, and area under the ROC curve (Az) of 86.5%, 93.0%, 89.9%, and 0.905 for SWE features alone.
• B-mode ultrasound features yielded a sensitivity, specificity, accuracy, and Az of 86.5%, 80.7%, 83.5%, and 0.893.
• The combined feature set demonstrated superior performance with sensitivity, specificity, accuracy, and Az values of 90.4%, 94.7%, 92.3%, and 0.961, respectively, with statistically significant improvements over individual feature sets (p<0.05).

Conclusions:

• The developed CAD system utilizing SWE features shows promise in enhancing the classification of breast tumors.
• Combining SWE and B-mode ultrasound features significantly improves diagnostic performance, outperforming either modality alone.
• This integrated approach offers a potential advancement in non-invasive breast tumor characterization, aiding in clinical decision-making.