A Time-Intensity Aware Pipeline for Generating Late-Stage Breast DCE-MRI using Generative Adversarial Models

• Main Authors: Fonnegra, Ruben D, Hernández, Maria Liliana, Caicedo, Juan C, Díaz, Gloria M
• Format: Journal Article
• Language: English
• Published: 03-09-2024
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.2409.01596

Contrast-enhancement pattern analysis is critical in breast magnetic
resonance imaging (MRI) to distinguish benign from probably malignant tumors.
However, contrast-enhanced image acquisitions are time-consuming and very
expensive. As an alternative to physical acquisition, this paper proposes a
comprehensive pipeline for the generation of accurate long-term (late)
contrast-enhanced breast MRI from the early counterpart. The proposed strategy
focuses on preserving the contrast agent pattern in the enhanced regions while
maintaining visual properties in the entire synthesized images. To that end, a
novel loss function that leverages the biological behavior of contrast agent
(CA) in tissue, given by the Time-Intensity (TI) enhancement curve, is proposed
to optimize a pixel-attention based generative model. In addition, unlike
traditional normalization and standardization methods, we developed a new
normalization strategy that maintains the contrast enhancement pattern across
the image sequences at multiple timestamps. This ensures the prevalence of the
CA pattern after image preprocessing, unlike conventional approaches.
Furthermore, in order to objectively evaluate the clinical quality of the
synthesized images, two metrics are also introduced to measure the differences
between the TI curves of enhanced regions of the acquired and synthesized
images. The experimental results showed that the proposed strategy generates
images that significantly outperform diagnostic quality in contrast-enhanced
regions while maintaining the spatial features of the entire image. This
results suggest a potential use of synthetic late enhanced images generated via
deep learning in clinical scenarios.