Imaging Biomarker Links Breast Tumor Heterogeneity to Targeted Therapy Response

This variability can expose some patients to treatments that provide limited benefit while still causing toxicity, particularly in high-risk, early-stage disease treated before surgery. To improve treatment selection, researchers have developed an imaging biomarker designed to identify patients more likely to respond to AKT inhibition.

Researchers at The Hong Kong Polytechnic University developed the Tumour Heterogeneity Index (THI) to noninvasively assess likely treatment response before therapy begins. THI uses data from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which is already widely used in breast cancer diagnosis and treatment planning. The method applies advanced radiomics to detect subtle imaging features that may not be apparent through conventional visual assessment.

The study evaluated patients with high-risk, early-stage breast cancer who received the investigational AKT inhibitor MK2206 in combination with neoadjuvant chemotherapy before surgery. The AKT/mTOR/PI3K signaling pathway plays an important role in tumor growth and survival and is a major target in cancer therapy. MK2206 had previously improved pathological complete response in the I-SPY2 clinical trial, although treatment response varied across aggressive subtypes including HER2-negative, hormone receptor-negative, and triple-negative breast cancer.

THI outperformed conventional immunohistochemistry-based receptor testing in identifying patients more likely to benefit from AKT inhibitor therapy. The index also provided information about the tumor microenvironment by assessing immune-cell characteristics and vascular features surrounding the tumor. Patients with high THI had an estimated pathological complete response rate of up to 56.1%, significantly higher than that observed in patients with low THI.

The findings were published in Breast Cancer Research. The team also developed DCE-MRI Vascularisation-based Response Tracking, or DCE-VASC-TRACK, for longitudinal monitoring of tumor vasculature during treatment. The model combines repeatable vascular texture features associated with pathological complete response at surgery with hormone receptor status, age, baseline functional tumor volume, and mid-treatment changes in functional tumor volume. The DCE-VASC-TRACK findings were published in Radiology: Artificial Intelligence.

“This challenge highlights the importance of accurately predicting treatment response before therapy begins. Our study presents an effective strategy for identifying patients who are most likely to benefit from treatment, with the potential to enhance the clinical value of drugs that may not have achieved the expected outcomes in large-scale clinical trials. THI is more than an imaging analysis tool. It quantifies the complexity of a tumor's internal structure, transforming assessment that has traditionally relied on experience into an objective, data-driven approach,” said Cai Jing, head of the Department of Health Technology and Informatics and chair professor of medical physics and intelligent oncology at PolyU.

Related Links
The Hong Kong Polytechnic University