目的:深度学习(DL)已应用于生物医学成像的概念证明中,包括跨模式和医学专业。标签数据对于训练和测试DL模型至关重要,但是人类专家标签是有限的。此外,DL传统上需要大量的训练数据,这在计算上是昂贵的处理和迭代。因此,优先使用那些最有可能提高模型性能的图像是很有用的,一种称为实例选择的做法。挑战是确定如何最好地确定优先级。喜欢直截了当是很自然的,健壮,定量指标作为实例选择优先级的基础。然而,在目前的实践中,这样的指标不是针对的,几乎从未使用过,图像数据集。
方法:为了解决这个问题,我们引入了ENRICH-消除成像挑战的噪声和冗余-一种可定制的方法,该方法根据每个图像在训练集中增加的多样性来确定图像的优先级。
结果:首先,我们表明,医学数据集的特殊之处在于,通常每个图像比非医学数据集增加更少的多样性。接下来,我们证明,ENRICH在几个医学图像数据集上的分类和分割任务上实现了几乎最大的性能,仅使用一小部分可用图像,而无需前期数据标记。ENRICH优于随机图像选择,阴性对照。最后,我们证明了ENRICH还可以用于识别成像数据集中的错误和异常值。
结论:ENRICH是一个简单的,计算有效的方法,用于对图像进行优先级排序,以便在DL中进行专家标记和使用。
Deep learning (DL) has been applied in proofs of concept across biomedical imaging, including across modalities and medical specialties. Labeled data are critical to training and testing DL models, but human expert labelers are limited. In addition, DL traditionally requires copious training data, which is computationally expensive to process and iterate over. Consequently, it is useful to prioritize using those images that are most likely to improve a model\'s performance, a practice known as instance selection. The challenge is determining how best to prioritize. It is natural to prefer straightforward, robust, quantitative metrics as the basis for prioritization for instance selection. However, in current practice, such metrics are not tailored to, and almost never used for, image datasets.
To address this problem, we introduce ENRICH-Eliminate Noise and Redundancy for Imaging Challenges-a customizable method that prioritizes images based on how much diversity each image adds to the training set.
First, we show that medical datasets are special in that in general each image adds less diversity than in nonmedical datasets. Next, we demonstrate that ENRICH achieves nearly maximal performance on classification and segmentation tasks on several medical image datasets using only a fraction of the available images and without up-front data labeling. ENRICH outperforms random image selection, the negative control. Finally, we show that ENRICH can also be used to identify errors and outliers in imaging datasets.
ENRICH is a simple, computationally efficient method for prioritizing images for expert labeling and use in DL.