Variable Augmented Network for Invertible Modality Synthesis-Fusion

TL;DR

The paper introduces an invertible and variable augmented network (iVAN) for medical image synthesis and fusion, enhancing data relevance and enabling bidirectional inference, with superior performance demonstrated in experiments.

Contribution

The novel iVAN architecture allows flexible multi-input and multi-output mappings in medical image synthesis and fusion using invertible and variable augmentation techniques.

Findings

Achieved competitive or superior performance compared to existing methods.

Enabled bidirectional inference processes in medical image synthesis and fusion.

Demonstrated versatility in multi-input to multi-output mappings.

Abstract

As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning. In this paper, an invertible and variable augmented network (iVAN) is proposed for medical image synthesis and fusion. In iVAN, the channel number of the network input and output is the same through variable augmentation technology, and data relevance is enhanced, which is conducive to the generation of characterization information. Meanwhile, the invertible network is used to achieve the bidirectional inference processes. Due to the invertible and variable augmentation schemes, iVAN can not only be applied to the mappings of multi-input to one-output and multi-input to multi-output, but also be applied to one-input to multi-output. Experimental results demonstrated that the proposed method can obtain competitive or superior performance in comparison to representative medical image synthesis and fusion methods.