Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
This work addresses automated segmentation for timely diagnosis of developmental disorders in preterm infants, representing a domain-specific incremental improvement.
The paper tackled the problem of accurately segmenting punctate white matter lesions (PWMLs) in preterm infants from brain MR images, which is challenging due to small, low-contrast lesions with variable counts, and proposed DeepPWML, a deep-learning framework using counterfactual reasoning and tissue segmentation to achieve state-of-the-art performance on a real-clinical dataset.
Accurate segmentation of punctate white matter lesions (PWMLs) are fundamental for the timely diagnosis and treatment of related developmental disorders. Automated PWMLs segmentation from infant brain MR images is challenging, considering that the lesions are typically small and low-contrast, and the number of lesions may dramatically change across subjects. Existing learning-based methods directly apply general network architectures to this challenging task, which may fail to capture detailed positional information of PWMLs, potentially leading to severe under-segmentations. In this paper, we propose to leverage the idea of counterfactual reasoning coupled with the auxiliary task of brain tissue segmentation to learn fine-grained positional and morphological representations of PWMLs for accurate localization and segmentation. A simple and easy-to-implement deep-learning framework (i.e., DeepPWML) is accordingly designed. It combines the lesion counterfactual map with the tissue probability map to train a lightweight PWML segmentation network, demonstrating state-of-the-art performance on a real-clinical dataset of infant T1w MR images. The code is available at \href{https://github.com/ladderlab-xjtu/DeepPWML}{https://github.com/ladderlab-xjtu/DeepPWML}.