Deep Quantized Representation for Enhanced Reconstruction

TL;DR

This paper introduces a deep quantized latent representation method to enhance the quality of biomedical images, specifically for Arabidopsis thaliana's shoot apical meristem, improving reconstruction from low-quality z-stack slices.

Contribution

The paper presents a novel deep quantized latent space approach for reconstructing high-quality images from low-quality biomedical data, addressing challenges in imaging the SAM of Arabidopsis thaliana.

Findings

Effective image sharpening demonstrated on publicly available dataset.

Improved reconstruction quality from degraded z-stack slices.

Potential to reduce manual effort in biomedical image collection.

Abstract

While machine learning approaches have shown remarkable performance in biomedical image analysis, most of these methods rely on high-quality and accurate imaging data. However, collecting such data requires intensive and careful manual effort. One of the major challenges in imaging the Shoot Apical Meristem (SAM) of Arabidopsis thaliana, is that the deeper slices in the z-stack suffer from different perpetual quality-related problems like poor contrast and blurring. These quality-related issues often lead to the disposal of the painstakingly collected data with little to no control on quality while collecting the data. Therefore, it becomes necessary to employ and design techniques that can enhance the images to make them more suitable for further analysis. In this paper, we propose a data-driven Deep Quantized Latent Representation (DQLR) methodology for high-quality image reconstruction in the Shoot Apical Meristem (SAM) of Arabidopsis thaliana. Our proposed framework utilizes multiple consecutive slices in the z-stack to learn a low dimensional latent space, quantize it and subsequently perform reconstruction using the quantized representation to obtain sharper images. Experiments on a publicly available dataset validate our methodology showing promising results.