Spectral Decomposition in Deep Networks for Segmentation of Dynamic Medical Images

TL;DR

This paper introduces a spectral decomposition method to identify and remove redundant information in dynamic medical imaging data, improving training efficiency and segmentation performance while reducing data size by over 80%.

Contribution

It presents a novel spectral decomposition approach to enhance deep network training for dynamic medical image segmentation by effectively reducing data redundancy.

Findings

Over 80% data reduction preserves segmentation accuracy.

Spectral decomposition suppresses noise and irrelevant information.

Training and testing efficacy improved on heterogeneous datasets.

Abstract

Dynamic contrast-enhanced magnetic resonance imaging (DCE- MRI) is a widely used multi-phase technique routinely used in clinical practice. DCE and similar datasets of dynamic medical data tend to contain redundant information on the spatial and temporal components that may not be relevant for detection of the object of interest and result in unnecessarily complex computer models with long training times that may also under-perform at test time due to the abundance of noisy heterogeneous data. This work attempts to increase the training efficacy and performance of deep networks by determining redundant information in the spatial and spectral components and show that the performance of segmentation accuracy can be maintained and potentially improved. Reported experiments include the evaluation of training/testing efficacy on a heterogeneous dataset composed of abdominal images of pediatric DCE patients, showing that drastic data reduction (higher than 80%) can preserve the dynamic information and performance of the segmentation model, while effectively suppressing noise and unwanted portion of the images.