BrainVoxGen: Deep learning framework for synthesis of Ultrasound to MRI

TL;DR

This paper introduces BrainVoxGen, a deep learning framework that synthesizes 3D MRI images from ultrasound scans using a modified GAN, aiming to enhance neuroimaging diagnostics despite current limitations.

Contribution

The study presents a novel GAN-based method for ultrasound-to-MRI synthesis, addressing modality disparity and establishing a foundational benchmark in neuroimaging.

Findings

Achieved a measurable similarity between synthesized and real MRI volumes.

Demonstrated the potential of deep learning for modality translation in neuroimaging.

Identified dataset size and computational resources as current limitations.

Abstract

The work proposes a novel deep-learning framework for the synthesis of three-dimensional MRI volumes from corresponding 3D ultrasound images of the brain, leveraging a modified iteration of the Pix2Pix Generative Adversarial Network (GAN) model. Addressing the formidable challenge of bridging the modality disparity between ultrasound and MRI, this research holds promise for transformative applications in medical diagnostics and treatment planning within the neuroimaging domain. While the findings reveal a discernible degree of similarity between the synthesized MRI volumes and anticipated outcomes, they fall short of practical deployment standards, primarily due to constraints associated with dataset scale and computational resources. The methodology yields MRI volumes with a satisfactory similarity score, establishing a foundational benchmark for subsequent investigations.