Liu Xiaofeng, Shih Helen A, Xing Fangxu, Santarnecchi Emiliano, El Fakhri Georges, Woo Jonghye
Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, 02114.
Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, 02114.
Med Image Comput Comput Assist Interv. 2023 Oct;14221:46-56. doi: 10.1007/978-3-031-43895-0_5. Epub 2023 Oct 1.
Deep learning (DL) models for segmenting various anatomical structures have achieved great success via a static DL model that is trained in a single source domain. Yet, the static DL model is likely to perform poorly in a continually evolving environment, requiring appropriate model updates. In an incremental learning setting, we would expect that well-trained static models are updated, following continually evolving target domain data-e.g., additional lesions or structures of interest-collected from different sites, without catastrophic forgetting. This, however, poses challenges, due to distribution shifts, additional structures not seen during the initial model training, and the absence of training data in a source domain. To address these challenges, in this work, we seek to progressively evolve an "off-the-shelf" trained segmentation model to diverse datasets with additional anatomical categories in a unified manner. Specifically, we first propose a divergence-aware dual-flow module with balanced rigidity and plasticity branches to decouple old and new tasks, which is guided by continuous batch renormalization. Then, a complementary pseudo-label training scheme with self-entropy regularized momentum MixUp decay is developed for adaptive network optimization. We evaluated our framework on a brain tumor segmentation task with continually changing target domains-i.e., new MRI scanners/modalities with incremental structures. Our framework was able to well retain the discriminability of previously learned structures, hence enabling the realistic life-long segmentation model extension along with the widespread accumulation of big medical data.
用于分割各种解剖结构的深度学习（DL）模型通过在单个源域中训练的静态DL模型取得了巨大成功。然而，静态DL模型在不断变化的环境中可能表现不佳，需要进行适当的模型更新。在增量学习设置中，我们期望经过良好训练的静态模型能够随着不断变化的目标域数据（例如，从不同站点收集的额外病变或感兴趣的结构）进行更新，而不会出现灾难性遗忘。然而，由于分布变化、初始模型训练期间未见过的额外结构以及源域中缺乏训练数据，这带来了挑战。为了应对这些挑战，在这项工作中，我们试图以统一的方式将一个“现成”训练的分割模型逐步演进到具有额外解剖类别的不同数据集。具体而言，我们首先提出了一个具有平衡刚性和可塑性分支的差异感知双流模块，以解耦新旧任务，该模块由连续批量归一化引导。然后，开发了一种具有自熵正则化动量MixUp衰减的互补伪标签训练方案，用于自适应网络优化。我们在一个脑肿瘤分割任务上评估了我们的框架，该任务的目标域不断变化，即具有增量结构的新MRI扫描仪/模态。我们的框架能够很好地保留先前学习结构的可辨别性，从而能够随着大量医学数据的广泛积累，实现现实的终身分割模型扩展。
