Shenzhen University, 3688 Nanhai Ave., Shenzhen, 518060, Guangdong, China.
Shenzhen University, 3688 Nanhai Ave., Shenzhen, 518060, Guangdong, China.
Comput Biol Med. 2024 Mar;170:108088. doi: 10.1016/j.compbiomed.2024.108088. Epub 2024 Feb 3.
The Internet of Medical Things (IoMT) is being incorporated into current healthcare systems. This technology intends to connect patients, IoMT devices, and hospitals over mobile networks, allowing for more secure, quick, and convenient health monitoring and intelligent healthcare services. However, existing intelligent healthcare applications typically rely on large-scale AI models, and standard IoMT devices have significant resource constraints. To alleviate this paradox, in this paper, we propose a Knowledge Distillation (KD)-based IoMT end-edge-cloud orchestrated architecture for medical image segmentation tasks, called Light-M, aiming to deploy a lightweight medical model in resource-constrained IoMT devices. Specifically, Light-M trains a large teacher model in the cloud server and employs computation in local nodes through imitation of the performance of the teacher model using knowledge distillation. Light-M contains two KD strategies: (1) active exploration and passive transfer (AEPT) and (2) self-attention-based inter-class feature variation (AIFV) distillation for the medical image segmentation task. The AEPT encourages the student model to learn undiscovered knowledge/features of the teacher model without additional feature layers, aiming to explore new features and outperform the teacher. To improve the distinguishability of the student for different classes, the student learns the self-attention-based feature variation (AIFV) between classes. Since the proposed AEPT and AIFV only appear in the training process, our framework does not involve any additional computation burden for a student model during the segmentation task deployment. Extensive experiments on cardiac images and public real-scene datasets demonstrate that our approach improves student model learning representations and outperforms state-of-the-art methods by combining two knowledge distillation strategies. Moreover, when deployed on the IoT device, the distilled student model takes only 29.6 ms for one sample at the inference step.
物联网医疗（IoMT）正被整合到当前的医疗保健系统中。这项技术旨在通过移动网络将患者、IoMT 设备和医院连接起来，从而实现更安全、更快速和更便捷的健康监测和智能医疗服务。然而，现有的智能医疗应用程序通常依赖于大规模 AI 模型，而标准的 IoMT 设备资源有限。为了解决这个矛盾，本文提出了一种基于知识蒸馏（KD）的 IoMT 端边云协同架构，用于医学图像分割任务，称为 Light-M，旨在将轻量级医疗模型部署到资源受限的 IoMT 设备中。具体来说，Light-M 在云服务器中训练一个大型教师模型，并通过知识蒸馏模仿教师模型的性能在本地节点中进行计算。Light-M 包含两种 KD 策略：（1）主动探索和被动转移（AEPT）和（2）基于自注意力的类间特征变化（AIFV）蒸馏，用于医学图像分割任务。AEPT 鼓励学生模型在不增加额外特征层的情况下学习教师模型的未发现知识/特征，旨在探索新的特征并超越教师。为了提高学生对不同类别的可区分性，学生学习类间基于自注意力的特征变化（AIFV）。由于所提出的 AEPT 和 AIFV 仅出现在训练过程中，因此我们的框架在分割任务部署期间不会给学生模型增加任何额外的计算负担。在心脏图像和公共真实场景数据集上的广泛实验表明，我们的方法通过结合两种知识蒸馏策略来提高学生模型的学习表示能力，并优于最先进的方法。此外，当部署在物联网设备上时，蒸馏后的学生模型在推理步骤中每个样本只需 29.6 毫秒。
