Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks

Abstract

Objective: The purpose of this study was to evaluate contrast-enhanced ultrasound and neural network data classification for determining the breast cancer response to bevacizumab therapy in a murine model.

Methods: An ultrasound scanner operating in the harmonic mode was used to measure ultrasound contrast agent (UCA) time-intensity curves in vivo. Twenty-five nude athymic mice with orthotopic breast cancers received a 30-microL tail vein bolus of a perflutren microsphere UCA, and baseline tumor imaging was performed using microbubble destruction-replenishment techniques. Subsequently, 15 animals received a 0.2-mg injection of bevacizumab, whereas 10 control animals received an equivalent dose of saline. Animals were reimaged on days 1, 2, 3, and 6 before euthanasia. Histologic assessment of excised tumor sections was performed. Time-intensity curve analysis for a given region of interest was conducted using customized software. Tumor perfusion metrics on days 1, 2, 3, and 6 were modeled using neural network data classification schemes (60% learning and 40% testing) to predict the breast cancer response to therapy.

Results: The breast cancer response to a single dose of bevacizumab in a murine model was immediate and transient. Permutations of input to the neural network data classification scheme revealed that tumor perfusion data within 3 days of bevacizumab dosing was sufficient to minimize the prediction error to 10%, whereas measurements of physical tumor size alone did not appear adequate to assess the therapeutic response.

Conclusions: Contrast-enhanced ultrasound may be a useful tool for determining the response to bevacizumab therapy and monitoring the subsequent restoration of blood flow to breast cancer.

Figure 1

Architecture of the MLFN for predicting the breast cancer response to bevacizumab therapy.

Figure 2

Representative ultrasound images (top) illustrating progression of breast cancer perfusion at times 0.1 (a), 2 (b), 10 (c), and 20 (d) seconds after UCA destruction from the image field. The bottom plot shows the average time-intensity curve derived from an ROI (0.75 cm diameter) centered and encompassing the tumor entirety.

Figure 3

Changes in normalized tumor size for control and bevacizumab- treated animal groups.

Figure 4

Microbubble-enhanced ultrasound tumor perfusion metrics, namely, AUC (a), I_PK (b), and T_PK (c), mapped as a function of time. Microbubble perfusion was derived from averaged time-intensity curves for the corresponding day.

Figure 5

Effect of bevacizumab on histologic characteristics of breast cancer xenografts. Top, Representative H&E-stained sections for control (left) and bevacizumab-treated (right) tumors. Focal areas of tumor necrosis are seen on both groups, as indicated by asterisks. Bottom, Representative CD31 immunohistologic sections for control (left) and bevacizumab-treated (right) tumors. Arrows indicate tumor microvessels.

Figure 6

Summary of immunohistologic results from control and therapy group tumors. Results are depicted for both MVD counts and percent intratumoral necrosis.