Optimized Synthetic Correlated Diffusion Imaging for Improving Breast Cancer Tumor Delineation

Area of Science:

• Medical Imaging
• Oncology
• Radiology

Background:

• Breast cancer remains a leading cause of cancer death in women worldwide.
• Accurate tumor identification is crucial for effective breast cancer diagnosis, treatment, and monitoring.
• Advanced imaging technologies are vital for detailed visualization of tumor characteristics.

Purpose of the Study:

• To optimize the correlated diffusion imaging (CDI) protocol for breast cancer tumor delineation.
• To tailor the synthetic correlated diffusion imaging (CDI^s) protocol for improved breast cancer imaging.
• To enhance the diagnostic performance of CDI^s in breast cancer detection.

Main Methods:

• Optimized coefficients of the calibrated signal mixing function in the CDI^s protocol.
• Adjusted gradient pulse strengths and timings for CDI^s.
• Maximized the area under the receiver operating characteristic curve (AUC) across a breast cancer patient cohort.

Main Results:

• Optimized CDI^s increased breast cancer tumor delineation by over 0.03 compared to the unoptimized form.
• The optimized CDI^s protocol achieved the highest AUC among tested modalities.
• Significant improvement in diagnostic imaging performance for breast cancer was observed.

Conclusions:

• Optimizing the CDI^s imaging protocol is essential for specific cancer applications like breast cancer.
• Tailored CDI^s protocols yield superior diagnostic imaging performance.
• This study demonstrates the potential of optimized CDI^s for enhanced breast cancer detection and management.