Assessment and Prediction of Response to Neoadjuvant Chemotherapy in Breast Cancer: A Comparison of Imaging Modalities and Future Perspectives

Abstract

Neoadjuvant chemotherapy (NAC) is becoming the standard of care for locally advanced breast cancer, aiming to reduce tumor size before surgery. Unfortunately, less than 30% of patients generally achieve a pathological complete response and approximately 5% of patients show disease progression while receiving NAC. Accurate assessment of the response to NAC is crucial for subsequent surgical planning. Furthermore, early prediction of tumor response could avoid patients being overtreated with useless chemotherapy sections, which are not free from side effects and psychological implications. In this review, we first analyze and compare the accuracy of conventional and advanced imaging techniques as well as discuss the application of artificial intelligence tools in the assessment of tumor response after NAC. Thereafter, the role of advanced imaging techniques, such as MRI, nuclear medicine, and new hybrid PET/MRI imaging in the prediction of the response to NAC is described in the second part of the review. Finally, future perspectives in NAC response prediction, represented by AI applications, are discussed.

Keywords: artificial intelligence; breast cancer; imaging; machine learning; neoadjuvant chemotherapy; nuclear medicine; radiomics.

Figure 1

A 36-year-old patient with G3, Luminal B, HER2+ left breast cancer undergoing NAC. An irregular, hyperdense opacity with inner microcalcifications, determining distortion of the surrounding parenchyma, is depicted on both MLO (arrow in (A)) and CC (arrow in (C)) views. After NAC, the irregular opacity is no longer appreciable on both MLO (arrow in (B)) and CC, while some microcalcifications are still detectable as expression of in situ carcinoma (arrow in (D)) as revealed by histological specimen (pCR).

Figure 2

Diffusion weighed imaging. In (A), free diffusion of water molecules (circles with arrows) in the extracellular space, due to limited number of cells, is shown. In (B), an example of restricted diffusion of water molecules due to higher cellularity is shown.

Figure 3

Dynamic contrast-enhanced MRI—significance of quantitative parameters according to the compartmental model. Quantitative parameters reflect exchanges of contrast agent concentration (yellow circles) between the plasma and extracellular extravascular space (EES) (Ktrans) and between EES and plasma (Kep). Ve represents the volume of EES.

Figure 4

Example of early assessment of the response to NAC using diffusion weighted imaging (DWI). (A–C) = pre-NAC examinations; (D–F) = early assessment examination after two cycles of cytotoxic NAC. (A,D) = dynamic post-contrast images; (B,E) = DWI images; (C,F) = ADC maps. A 37-year-old patient with a G3, triple negative invasive ductal carcinoma of the right breast (white and black arrows). Early assessment showed a reduction of tumor size along with increase of signal intensity on ADC maps (C) compared to the pre-treatment examination (F). Pathology after surgical resection revealed pathological complete response (pCR).

Figure 5

Example of early assessment of the response to NAC using dynamic contrast-enhanced imaging (DCE-MRI) in a 37-year-old patient with a G3, triple negative invasive ductal carcinoma of the right breast (arrows, same case shown in Figure 4). (A–C) = pre-NAC examinations; (D–F) = early assessment examination after two cycles of cytotoxic NAC. Ktrans (A,D), Kep (B,E) and Ve (C,F) maps. Early assessment showed a reduction of Ktrans (286 vs. 83.9 min⁻¹) and kep (91.49 vs. 20.14 min⁻¹ × 100) with a slight increase of Ve (275.34 vs. 308.08 × 1000) signal intensity on ADC maps (C) compared to the pre-treatment examination (F). Pathological complete response (pCR) was proved at pathology examination after surgical resection.

Figure 6

A 36-year-old patient with left breast cancer undergoing NAC (same patient shown in Figure 1). Fused PET/MRI images acquired before (A), during (B), and after (C) NAC are shown. While a slight reduction of the tumor and its satellite nodule (white arrows in B) is appreciable, ¹⁸F-FDG uptake is significantly reduced after the second cycle of chemotherapy (B) as compared to the pre-treatment evaluation (A). The tumor was not detectable at the post-treatment evaluation (C). Pathology after surgery demonstrated a complete response (pCR).