Wu Yilei, Dong Zijian, Li Hongwei Bran, Chong Yao Feng, Ji Fang, Chong Joanna Su Xian, Tang Nathanael Ren Jie, Hilal Saima, Fu Huazhu, Chen Christopher Li-Hsian, Zhou Juan Helen
Centre for Sleep and Cognition & Centre for Translational Magnetic Resonance Research, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Human Potential Translational Research Program and Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Hum Brain Mapp. 2025 Apr 15;46(6):e70212. doi: 10.1002/hbm.70212.
White matter hyperintensities (WMH) are neuroimaging markers linked to an elevated risk of cognitive decline. WMH severity is typically assessed via visual rating scales and through volumetric segmentation. While visual rating scales are commonly used in clinical practice, they offer limited descriptive power. In contrast, supervised volumetric segmentation requires manually annotated masks, which are labor-intensive and challenging to scale for large studies. Therefore, our goal was to develop an automated deep-learning model that can provide accurate and holistic quantification of WMH severity with minimal supervision. We developed WMH-DualTasker, a deep learning model that simultaneously performs voxel-wise segmentation and visual rating score prediction. The model employs self-supervised learning with transformation-invariant consistency constraints, using WMH visual ratings (ARWMC scale, range 0-30) from clinical settings as the sole supervisory signal. Additionally, we assessed its clinical utility by applying it to identify individuals with mild cognitive impairment (MCI) and to predict dementia conversion. The volumetric quantification performance of WMH-DualTasker was either superior to or on par with existing supervised methods, as demonstrated on the MICCAI-WMH dataset (N = 60, Dice = 0.602) and the SINGER dataset (N = 64, Dice = 0.608). Furthermore, the model exhibited strong agreement with clinical visual rating scales on an external dataset (SINGER, MAE = 1.880, K = 0.77). Importantly, WMH severity metrics derived from WMH-DualTasker improved predictive performance beyond conventional clinical features for MCI classification (AUC = 0.718, p < 0.001) and MCI conversion prediction (AUC = 0.652, p < 0.001) using the ADNI dataset. WMH-DualTasker substantially reduces the reliance on labor-intensive manual annotations, facilitating more efficient and scalable quantification of WMH severity in large-scale population studies. This innovative approach has the potential to advance preventive and precision medicine by enhancing the assessment and management of vascular cognitive impairment associated with WMH.
白质高信号（WMH）是与认知能力下降风险升高相关的神经影像学标志物。WMH严重程度通常通过视觉评分量表和体积分割来评估。虽然视觉评分量表在临床实践中常用，但它们的描述能力有限。相比之下，监督式体积分割需要手动标注掩码，这既费力又难以在大型研究中进行扩展。因此，我们的目标是开发一种自动化深度学习模型，该模型能够在最少监督的情况下，对白质高信号严重程度进行准确且全面的量化。我们开发了WMH-DualTasker，这是一种深度学习模型，可同时进行逐体素分割和视觉评分预测。该模型采用具有变换不变一致性约束的自监督学习，将临床环境中的WMH视觉评分（ARWMC量表，范围0-30）作为唯一监督信号。此外，我们通过将其应用于识别轻度认知障碍（MCI）个体和预测痴呆症转化来评估其临床效用。如在MICCAI-WMH数据集（N = 60，Dice = 0.602）和SINGER数据集（N = 64，Dice = 0.608）上所示，WMH-DualTasker的体积量化性能优于或等同于现有的监督方法。此外，该模型在外部数据集（SINGER，平均绝对误差= 1.880，K = 0.77）上与临床视觉评分量表表现出高度一致性。重要的是，使用ADNI数据集，从WMH-DualTasker得出的WMH严重程度指标在MCI分类（AUC = 0.718，p < 0.001）和MCI转化预测（AUC = 0.652，p < 0.001）方面的预测性能优于传统临床特征。WMH-DualTasker大大减少了对劳动密集型手动标注的依赖，便于在大规模人群研究中更高效、可扩展地量化WMH严重程度。这种创新方法有可能通过加强与WMH相关的血管性认知障碍的评估和管理，推动预防医学和精准医学的发展。
