Deep Learning Enables Fast and Accurate Quantification of MRI-Guided Near-Infrared Spectral Tomography for Breast Cancer Diagnosis.

Abstract

The utilization of magnetic resonance (MR) imaging to guide near-infrared spectral tomography (NIRST) shows significant potential for improving the specificity and sensitivity of breast cancer diagnosis. However, the efficiency and accuracy of NIRST image reconstruction have been limited by the complexities of light propagation modeling and MRI image segmentation. To address these challenges, we developed and evaluated a deep learning-based approach for MR-guided 3D NIRST image reconstruction (DL-MRg-NIRST). Using a network trained on synthetic data, the DL-MRg-NIRST system reconstructed images from data acquired during 38 clinical imaging exams of patients with breast abnormalities. Statistical analysis of the results demonstrated a sensitivity of 87.5%, a specificity of 92.9%, and a diagnostic accuracy of 89.5% in distinguishing pathologically defined benign from malignant lesions. Additionally, the combined use of MRI and DL-MRg-NIRST diagnoses achieved an area under the receiver operating characteristic (ROC) curve of 0.98. Remarkably, the DL-MRg-NIRST image reconstruction process required only 1.4 seconds, significantly faster than state-of-the-art MR-guided NIRST methods.