DAN: A Deformation-Aware Network for Consecutive Biomedical Image Interpolation

TL;DR

This paper introduces a deformation-aware neural network designed for biomedical image interpolation, effectively handling large deformations, noise, and blur differences to improve the synthesis of intermediate images.

Contribution

The paper proposes a novel deformation-aware layer and an adaptive style-balance loss to enhance biomedical image interpolation, addressing challenges like deformation and style differences.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively handles large deformations and noise in biomedical images.

Improves pixel synthesis quality through global domain adaptation.

Abstract

The continuity of biological tissue between consecutive biomedical images makes it possible for the video interpolation algorithm, to recover large area defects and tears that are common in biomedical images. However, noise and blur differences, large deformation, and drift between biomedical images, make the task challenging. To address the problem, this paper introduces a deformation-aware network to synthesize each pixel in accordance with the continuity of biological tissue. First, we develop a deformation-aware layer for consecutive biomedical images interpolation that implicitly adopting global perceptual deformation. Second, we present an adaptive style-balance loss to take the style differences of consecutive biomedical images such as blur and noise into consideration. Guided by the deformation-aware module, we synthesize each pixel from a global domain adaptively which further improves the performance of pixel synthesis. Quantitative and qualitative experiments on the benchmark dataset show that the proposed method is superior to the state-of-the-art approaches.