通过探索性训练解决通用病灶检测任务中的不完整标注问题
Tackling the Incomplete Annotation Issue in Universal Lesion Detection Task By Exploratory Training
AI总结：
针对通用病灶检测中的不完整标注问题，本文提出探索性师生训练与预测库，通过跨迭代一致性筛选可靠伪标签，并在两个医学图像数据集上超过现有方法。
摘要：
通用病灶检测旨在检测医学图像中多个器官上的各类病灶，因此对临床实践具有重要价值。深度学习方法已展现出良好效果，但需要大量标注数据用于训练。然而，标注医学图像成本高昂，且需要专业知识。医学图像中目标形态和对比度的多样性使完整标注更具挑战性，从而导致不完整标注。在此类数据集上直接训练ULD检测器会产生次优结果。基于伪标签的方法会检查训练数据并挖掘未标注目标以进行再训练，已被证明可有效解决该问题。目前，性能最佳的方法依赖于在小批量层面运行的动态标签挖掘机制。然而，模型在不同迭代中的性能存在差异，导致挖掘标签的质量不一致，并限制了其性能提升。受深度模型按复杂度递增方式学习概念这一观察启发，我们提出一种创新的探索性训练，用于随时间评估所挖掘病灶的可靠性。具体而言，我们引入师生检测模型作为基础，其中教师的预测与不完整标注相结合以训练学生。此外，我们设计了一个预测库来记录高置信度预测。每个样本会被训练多次，使我们能够获得每个样本的一系列记录。如果某个预测始终出现在记录序列中，它很可能是真实目标，否则可能只是噪声。这构成了为再训练选择可靠挖掘病灶的关键标准。实验结果证实，所提出框架在两个医学图像数据集上超越了最先进方法，展示了其优越性能。
英文摘要：
Universal lesion detection has great value for clinical practice as it aims to detect various types of lesions in multiple organs on medical images. Deep learning methods have shown promising results, but demanding large volumes of annotated data for training. However, annotating medical images is costly and requires specialized knowledge. The diverse forms and contrasts of objects in medical images make fully annotation even more challenging, resulting in incomplete annotations. Directly training ULD detectors on such datasets can yield suboptimal results. Pseudo-label-based methods examine the training data and mine unlabelled objects for retraining, which have shown to be effective to tackle this issue. Presently, top-performing methods rely on a dynamic label-mining mechanism, operating at the mini-batch level. However, the model's performance varies at different iterations, leading to inconsistencies in the quality of the mined labels and limits their performance enhancement. Inspired by the observation that deep models learn concepts with increasing complexity, we introduce an innovative exploratory training to assess the reliability of mined lesions over time. Specifically, we introduce a teacher-student detection model as basis, where the teacher's predictions are combined with incomplete annotations to train the student. Additionally, we design a prediction bank to record high-confidence predictions. Each sample is trained several times, allowing us to get a sequence of records for each sample. If a prediction consistently appears in the record sequence, it is likely to be a true object, otherwise it may just a noise. This serves as a crucial criterion for selecting reliable mined lesions for retraining. Our experimental results substantiate that the proposed framework surpasses state-of-the-art methods on two medical image datasets, demonstrating its superior performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
