Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Using Multiparametric MRI with Optimized Synthetic Correlated Diffusion Imaging to Enhance Breast Cancer Pathologic Complete Response Prediction

Chi-en Amy Tai, Alexander Wong

TL;DR

This work targets noninvasive, MRI-based prediction of pathologic complete response (pCR) to guide neoadjuvant chemotherapy in breast cancer, addressing the subjectivity and uncertainty of manual assessments. It introduces an optimized synthetic correlated diffusion imaging signal ($CDI^{s}$) fused with diffusion-weighted imaging (DWI) within a multiparametric MRI framework, with Nelder-Mead optimization to maximize $AUC$ for tumor delineation and deep radiomic feature extraction via a MONAI-based 34-layer CNN. On the pre-treatment cohort from ACRIN 6698/I-SPY2, the approach achieves a LOOCV accuracy of $93.28\%$, surpassing the unoptimized CDI$_{s}$ by $5.53$ percentage points and delivering high sensitivity ($95.12\%$), specificity ($92.40\%$), and $F1$ ($90.17\%$). This demonstrates the value of domain-specific CDI tuning to improve noninvasive pCR prediction using routinely acquired MRI, potentially enabling more accurate and less risky neoadjuvant therapy decisions.

Abstract

In 2020, 685,000 deaths across the world were attributed to breast cancer, underscoring the critical need for innovative and effective breast cancer treatment. Neoadjuvant chemotherapy has recently gained popularity as a promising treatment strategy for breast cancer, attributed to its efficacy in shrinking large tumors and leading to pathologic complete response. However, the current process to recommend neoadjuvant chemotherapy relies on the subjective evaluation of medical experts which contain inherent biases and significant uncertainty. A recent study, utilizing volumetric deep radiomic features extracted from synthetic correlated diffusion imaging (CDI$^s$), demonstrated significant potential in noninvasive breast cancer pathologic complete response prediction. Inspired by the positive outcomes of optimizing CDI$^s$ for prostate cancer delineation, this research investigates the application of optimized CDI$^s$ to enhance breast cancer pathologic complete response prediction. Using multiparametric MRI that fuses optimized CDI$^s$ with diffusion-weighted imaging (DWI), we obtain a leave-one-out cross-validation accuracy of 93.28%, over 5.5% higher than that previously reported.

Using Multiparametric MRI with Optimized Synthetic Correlated Diffusion Imaging to Enhance Breast Cancer Pathologic Complete Response Prediction

TL;DR

This work targets noninvasive, MRI-based prediction of pathologic complete response (pCR) to guide neoadjuvant chemotherapy in breast cancer, addressing the subjectivity and uncertainty of manual assessments. It introduces an optimized synthetic correlated diffusion imaging signal () fused with diffusion-weighted imaging (DWI) within a multiparametric MRI framework, with Nelder-Mead optimization to maximize for tumor delineation and deep radiomic feature extraction via a MONAI-based 34-layer CNN. On the pre-treatment cohort from ACRIN 6698/I-SPY2, the approach achieves a LOOCV accuracy of , surpassing the unoptimized CDI by percentage points and delivering high sensitivity (), specificity (), and (). This demonstrates the value of domain-specific CDI tuning to improve noninvasive pCR prediction using routinely acquired MRI, potentially enabling more accurate and less risky neoadjuvant therapy decisions.

Abstract

In 2020, 685,000 deaths across the world were attributed to breast cancer, underscoring the critical need for innovative and effective breast cancer treatment. Neoadjuvant chemotherapy has recently gained popularity as a promising treatment strategy for breast cancer, attributed to its efficacy in shrinking large tumors and leading to pathologic complete response. However, the current process to recommend neoadjuvant chemotherapy relies on the subjective evaluation of medical experts which contain inherent biases and significant uncertainty. A recent study, utilizing volumetric deep radiomic features extracted from synthetic correlated diffusion imaging (CDI), demonstrated significant potential in noninvasive breast cancer pathologic complete response prediction. Inspired by the positive outcomes of optimizing CDI for prostate cancer delineation, this research investigates the application of optimized CDI to enhance breast cancer pathologic complete response prediction. Using multiparametric MRI that fuses optimized CDI with diffusion-weighted imaging (DWI), we obtain a leave-one-out cross-validation accuracy of 93.28%, over 5.5% higher than that previously reported.
Paper Structure (3 sections, 2 figures, 1 table)

This paper contains 3 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Results

Figures (2)

  • Figure 1: Clinical support workflow copied from tai2023enhancing that is used in this study.
  • Figure 2: An example slice illustrating visual differences between (a) Unoptimized CDIs, (b) Optimized CDIs, (c) the associated DWI image, and (d) the associated tumour mask at pre-treatment for a patient who obtained pCR. For this patient, the pCR prediction was correct using the Optimized CDIs signal fused with DWI.