Duarte Kauê T N, Sidhu Abhijot S, Barros Murilo C, Gobbi David G, McCreary Cheryl R, Saad Feryal, Camicioli Richard, Smith Eric E, Bento Mariana P, Frayne Richard
Departments of Radiology and Clinical Neurosciences, Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada.
Calgary Image Processing and Analysis Centre, Foothills Medical Centre, Calgary, AB, Canada.
Front Comput Neurosci. 2024 Oct 22;18:1487877. doi: 10.3389/fncom.2024.1487877. eCollection 2024.
White matter hyperintensities (WMHs) are frequently observed on magnetic resonance (MR) images in older adults, commonly appearing as areas of high signal intensity on fluid-attenuated inversion recovery (FLAIR) MR scans. Elevated WMH volumes are associated with a greater risk of dementia and stroke, even after accounting for vascular risk factors. Manual segmentation, while considered the ground truth, is both labor-intensive and time-consuming, limiting the generation of annotated WMH datasets. Un-annotated data are relatively available; however, the requirement of annotated data poses a challenge for developing supervised machine learning models.
To address this challenge, we implemented a multi-stage semi-supervised learning (M3SL) approach that first uses un-annotated data segmented by traditional processing methods ("bronze" and "silver" quality data) and then uses a smaller number of "gold"-standard annotations for model refinement. The M3SL approach enabled fine-tuning of the model weights with the gold-standard annotations. This approach was integrated into the training of a U-Net model for WMH segmentation. We used data from three scanner vendors (over more than five scanners) and from both cognitively normal (CN) adult and patients cohorts [with mild cognitive impairment and Alzheimer's disease (AD)].
An analysis of WMH segmentation performance across both scanner and clinical stage (CN, MCI, AD) factors was conducted. We compared our results to both conventional and transfer-learning deep learning methods and observed better generalization with M3SL across different datasets. We evaluated several metrics (-measure, , and Hausdorff distance) and found significant improvements with our method compared to conventional ( < 0.001) and transfer-learning ( < 0.001).
These findings suggest that automated, non-machine learning, tools have a role in a multi-stage learning framework and can reduce the impact of limited annotated data and, thus, enhance model performance.
白质高信号（WMHs）在老年人的磁共振（MR）图像中经常可见，通常在液体衰减反转恢复（FLAIR）MR扫描中表现为高信号强度区域。即使在考虑血管危险因素之后，WMH体积升高也与痴呆和中风的风险增加相关。手动分割虽被视为金标准，但既耗费人力又耗时，限制了带注释的WMH数据集的生成。未注释的数据相对容易获取；然而，带注释数据的需求对开发监督式机器学习模型构成了挑战。
为应对这一挑战，我们实施了一种多阶段半监督学习（M3SL）方法，该方法首先使用通过传统处理方法分割的未注释数据（“青铜”和“银”质量数据），然后使用数量较少的“金”标准注释来优化模型。M3SL方法能够使用金标准注释对模型权重进行微调。该方法被整合到用于WMH分割的U-Net模型的训练中。我们使用了来自三个扫描仪供应商（超过五台扫描仪）以及认知正常（CN）成年人和患者队列[患有轻度认知障碍和阿尔茨海默病（AD）]的数据。
对跨扫描仪和临床阶段（CN、MCI、AD）因素的WMH分割性能进行了分析。我们将我们的结果与传统和迁移学习深度学习方法进行了比较，并观察到M3SL在不同数据集上具有更好的泛化能力。我们评估了几个指标（F1分数、准确率和豪斯多夫距离），发现与传统方法（P < 0.001）和迁移学习方法（P < 0.001）相比，我们的方法有显著改进。
这些发现表明，自动化的、非机器学习的工具在多阶段学习框架中发挥着作用，可以减少有限注释数据的影响，从而提高模型性能。
