Correlation between image quality metrics of magnetic resonance images and the neural network segmentation accuracy

TL;DR

This paper investigates how the quality of magnetic resonance images, measured by image quality metrics, correlates with the accuracy of neural network segmentation, aiming to improve training data selection and segmentation outcomes.

Contribution

It introduces a method to select training data based on image quality metrics to enhance neural network segmentation accuracy in MRI images.

Findings

Higher image quality metrics correlate with better segmentation accuracy

IQM-based training data selection improves neural network performance

Using IQM to tune training data enhances learning efficiency

Abstract

Deep neural networks with multilevel connections process input data in complex ways to learn the information.A networks learning efficiency depends not only on the complex neural network architecture but also on the input training images.Medical image segmentation with deep neural networks for skull stripping or tumor segmentation from magnetic resonance images enables learning both global and local features of the images.Though medical images are collected in a controlled environment,there may be artifacts or equipment based variance that cause inherent bias in the input set.In this study, we investigated the correlation between the image quality metrics of MR images with the neural network segmentation accuracy.For that we have used the 3D DenseNet architecture and let the network trained on the same input but applying different methodologies to select the training data set based on the IQM values.The difference in the segmentation accuracy between models based on the random training inputs with IQM based training inputs shed light on the role of image quality metrics on segmentation accuracy.By running the image quality metrics to choose the training inputs,further we may tune the learning efficiency of the network and the segmentation accuracy.