我们是否在使用合适的分割指标？识别CNN训练中超越滚动DICE系数的人类专家感知相关因素
Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient
AI总结：
该研究针对医学图像分割指标与人类专家感知契合度不明的问题，通过心理物理学实验发现现有标准指标与专家评估相关性中等，提出用经典统计构建复合损失函数以近似专家感知，质疑了现有分割实践并提供研究方向。
摘要：
复杂机器学习任务中优化的指标通常是以临时方式选择的，目前尚不清楚它们与人类专家感知的契合程度。我们探究了已确立的定量分割质量指标与经过专业训练的人类评分员的定性评估之间的相关性。为此，我们针对两个复杂的生物医学语义分割问题开展了心理物理学实验。我们发现，当前的标准指标和损失函数与专家的分割质量评估仅呈中等相关性。值得注意的是，这种效应在临床相关结构中尤为显著，例如脑部磁共振成像中胶质瘤的强化肿瘤区，以及超声成像中的灰质。在卷积神经网络（CNN）训练中，如何优化诸如人类专家感知这类抽象指标往往尚不明确。为应对这一挑战，我们提出了一种新策略，采用经典统计学技术构建互补的复合损失函数，以更好地近似人类专家感知。在所有评分实验中，人类专家始终认为计算机生成的分割结果优于人工标注的参考标签。因此，我们的研究结果对当前医学图像分割中的许多常用做法提出了强烈质疑，并为未来研究提供了有价值的线索。
英文摘要：
Metrics optimized in complex machine learning tasks are often selected in an ad-hoc manner. It is unknown how they align with human expert perception. We explore the correlations between established quantitative segmentation quality metrics and qualitative evaluations by professionally trained human raters. Therefore, we conduct psychophysical experiments for two complex biomedical semantic segmentation problems. We discover that current standard metrics and loss functions correlate only moderately with the segmentation quality assessment of experts. Importantly, this effect is particularly pronounced for clinically relevant structures, such as the enhancing tumor compartment of glioma in brain magnetic resonance and grey matter in ultrasound imaging. It is often unclear how to optimize abstract metrics, such as human expert perception, in convolutional neural network (CNN) training. To cope with this challenge, we propose a novel strategy employing techniques of classical statistics to create complementary compound loss functions to better approximate human expert perception. Across all rating experiments, human experts consistently scored computer-generated segmentations better than the human-curated reference labels. Our results, therefore, strongly question many current practices in medical image segmentation and provide meaningful cues for future research.
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。
