Convolutional Feature Noise Reduction for 2D Cardiac MR Image Segmentation

TL;DR

This paper introduces a novel Convolutional Feature Filter (CFF) that effectively reduces noise in convolutional features for 2D cardiac MR image segmentation, improving the quality of feature signals and potentially enhancing segmentation accuracy.

Contribution

The study proposes a simple low-amplitude pass filter for convolutional features, validated on multiple networks and datasets, addressing a neglected noise reduction step in segmentation models.

Findings

CFF reduces noise in feature signal matrices.

Experimental validation on cardiac MR datasets shows improved feature quality.

Entropy analysis confirms noise reduction effectiveness.

Abstract

Noise reduction constitutes a crucial operation within Digital Signal Processing. Regrettably, it frequently remains neglected when dealing with the processing of convolutional features in segmentation networks. This oversight could trigger the butterfly effect, impairing the subsequent outcomes within the entire feature system. To complete this void, we consider convolutional features following Gaussian distributions as feature signal matrices and then present a simple and effective feature filter in this study. The proposed filter is fundamentally a low-amplitude pass filter primarily aimed at minimizing noise in feature signal inputs and is named Convolutional Feature Filter (CFF). We conducted experiments on two established 2D segmentation networks and two public cardiac MR image datasets to validate the effectiveness of the CFF, and the experimental findings demonstrated a decrease in noise within the feature signal matrices. To enable a numerical observation and analysis of this reduction, we developed a binarization equation to calculate the information entropy of feature signals.