Effect of the regularization hyperparameter on deep learning-based segmentation in LGE-MRI

TL;DR

This study investigates how the choice of L2 regularization hyperparameter influences the performance of deep learning models, specifically U-net, in segmenting LGE-MRI images, highlighting the importance of hyperparameter tuning.

Contribution

It demonstrates the impact of L2 regularization hyperparameter selection on segmentation accuracy in deep learning models for LGE-MRI, emphasizing the need for careful tuning.

Findings

Hyperparameter choice significantly affects segmentation results

Manual tuning is recommended when validation accuracy stalls

Objective and subjective evaluations confirm the hyperparameter impact

Abstract

The extent to which the arbitrarily selected L2 regularization hyperparameter value affects the outcome of semantic segmentation with deep learning is demonstrated. Demonstrations rely on training U-net on small LGE-MRI datasets using the arbitrarily selected L2 regularization values. The remaining hyperparameters are to be manually adjusted or tuned only when 10 % of all epochs are reached before the training validation accuracy reaches 90%. Semantic segmentation with deep learning outcomes are objectively and subjectively evaluated against the manual ground truth segmentation.