Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates

TL;DR

The paper introduces Trident Segmentation CNN, a novel spatiotemporal deep learning model that improves the accuracy and efficiency of segmenting punctate white matter lesions in neonatal MR images, with a new loss function enhancing training.

Contribution

It proposes a new spatiotemporal transformation CNN and an improved loss function for better PWML segmentation in preterm neonates.

Findings

Achieves median DSC of 0.6355, sensitivity of 0.7126

Outperforms existing state-of-the-art algorithms

Reduces computational resource consumption

Abstract

Accurate segmentation of punctate white matter lesions (PWML) in preterm neonates by an automatic algorithm can better assist doctors in diagnosis. However, the existing algorithms have many limitations, such as low detection accuracy and large resource consumption. In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images. It can convert spatial information into temporal information, which reduces the consumption of computing resources. Furthermore, a new improved training loss called Self-balancing Focal Loss (SBFL) is proposed to balance the loss during the training process. The whole model is evaluated on a dataset of 704 MR images. Overall the method achieves median DSC, sensitivity, specificity, and Hausdorff distance of 0.6355, 0.7126, 0.9998, and 24.5836 mm which outperforms the state-of-the-art algorithm. (The code is now available on https://github.com/YalongLiu/Trident-Segmentation-CNN)