The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China.
The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China; Xi'an Hospital of Traditional Chinese Medicine, Xi'an 710021, PR China.
Comput Med Imaging Graph. 2023 Oct;109:102290. doi: 10.1016/j.compmedimag.2023.102290. Epub 2023 Aug 20.
Despite the fact that traditional deep learning (DL) approaches provide promising accuracy and efficiency in medical ultrasound image analysis, they cannot replace the physician in making a diagnosis since the DL model is only appropriate in static application scenarios. Currently, most DL-based models are incapable of learning new tasks in the dynamic clinical environments due to the catastrophic forgetting of old tasks. To address the above problem, we propose an incremental classifier that is sequentially trained on evolving tasks for medical ultrasound images by counterfactual thinking. Specifically, the proposed model consists of a feature extractor and a classifier that can add new classes at any time during training. Toward a more discriminative model in the continual learning setting, a contrastive strategy is designed to leverage fine-grained information by generating a series of counterfactual regions. For model optimization, we design a multi-task loss made up of a knowledge distillation loss, a cross-entropy loss, and a contrasting loss. This objective jointly enjoys the merits of less forgetting, better accuracy, and fine-grained information utilization. A newly collected dataset with 52 medical ultrasound classification tasks is used to demonstrate the effectiveness of our method. The proposed approach achieves 76.59%, 11.67%, and 7.93% in terms of the average incremental accuracy, forgetting rate, and feature retention, respectively.
尽管传统的深度学习（DL）方法在医学超声图像分析中提供了有希望的准确性和效率，但它们不能替代医生进行诊断，因为 DL 模型仅适用于静态应用场景。目前，由于灾难性遗忘旧任务，大多数基于 DL 的模型无法在动态临床环境中学习新任务。为了解决上述问题，我们提出了一种增量分类器，通过反事实思维，对医学超声图像的不断发展的任务进行顺序训练。具体来说，所提出的模型由特征提取器和分类器组成，它们可以在训练过程中的任何时候添加新的类别。为了在连续学习设置中获得更具辨别力的模型，我们设计了一种对比策略，通过生成一系列反事实区域来利用细粒度信息。为了进行模型优化，我们设计了一个由知识蒸馏损失、交叉熵损失和对比损失组成的多任务损失。该目标共同享有遗忘较少、准确性更高和细粒度信息利用更好的优点。我们使用一个新收集的包含 52 个医学超声分类任务的数据集来证明我们方法的有效性。所提出的方法在平均增量准确性、遗忘率和特征保留方面分别达到了 76.59%、11.67%和 7.93%。
