Real-time breast lesion classification combining diffuse optical tomography frequency domain data and BI-RADS assessment

Abstract

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential for breast cancer diagnosis, in which real-time or near real-time diagnosis with high accuracy is desired. However, DOT's relatively slow data processing and image reconstruction speeds have hindered real-time diagnosis. Here, we propose a real-time classification scheme that combines US breast imaging reporting and data system (BI-RADS) readings and DOT frequency domain measurements. A convolutional neural network is trained to generate malignancy probability scores from DOT measurements. Subsequently, these scores are integrated with BI-RADS assessments using a support vector machine classifier, which then provides the final diagnostic output. An area under the receiver operating characteristic curve of 0.978 is achieved in distinguishing between benign and malignant breast lesions in patient data without image reconstruction.

Keywords: breast cancer diagnosis; diffuse optical tomography; frequency domain optical systems.

FIGURE 1.

Examples of DOT histograms for a malignant case (a) and (b), and a benign case (c) and (d). The perturbation values were averaged across all lesion files for each patient.

FIGURE 2.

Combined classification scheme

FIGURE 3.

Receiver operating characteristic (ROC) curves for testing data

FIGURE 4.

Predicted probability of being malignant for matched and mismatched scenarios