Two-stage classification strategy for breast cancer diagnosis using ultrasound-guided diffuse optical tomography and deep learning

Abstract

Significance: Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated great potential for breast cancer diagnosis in which real-time or near realtime diagnosis with high accuracy is desired. Aim:We aim to use US-guided DOT to achieve an automated, fast, and accurate classification of breast lesions.Approach: We propose a two-stage classification strategy with deep learning. In the first stage, US images and histograms created from DOT perturbation measurements are combined to predict benign lesions. Then the non-benign suspicious lesions are passed through to the second stage, which combine US image features, DOT histogram features, and 3D DOT reconstructed images for final diagnosis. Results:The first stage alone identified 73.0% of benign cases without image reconstruction. In distinguishing between benign and malignant breast lesions in patient data, the two-stage classification approach achieved an area under the receiver operating characteristic curve of 0.946, outperforming the diagnoses of all single-modality models and of a single-stage classification model that combines all US images, DOT histogram, and imaging features. Conclusions:The proposed two-stage classification strategy achieves better classification accuracy than single-modality-only models and a single-stage classification model that combines all features. It can potentially distinguish breast cancers from benign lesions in near real-time.

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

“…More importantly, this new approach eliminates the need for image reconstruction and therefore avoids any potential image artifacts. DOT image reconstruction was a crucial step in our earlier breast lesion classification approaches [10,13,14]. This advancement not only streamlines the process but also increases the applicability of DOT in clinical settings.…”

“…The CNN architecture used for classifying DOT histograms was previously described in Ref. [14]. Briefly, the input data, which is the 2D DOT histogram with a size of 1 × 32 × 32, undergoes three convolutional layers with batch normalization and maxpooling, a flattening layer, and two fully connected layers.…”

“…However, the slow data preprocessing and image reconstruction speed of DOT has still hindered real-time diagnosis. To tackle this challenge, our group has developed a two-stage strategy [10,14]. In the first stage, we identify a portion of benign lesions without requiring image reconstruction, and in the second stage, we utilize reconstructed images to classify the remaining suspicious lesions.…”