发表机构
Duke University; Pratt School of Engineering（杜克大学; 普拉特工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究长尾分布下医学图像分类困难，通过深度学习模型及增强等技术最小化误差，用多种指标评估不同模型，得出最佳模型有良好结果及医疗领域潜在应用。
AI 中文摘要
在本文中，我们研究了由于长尾分布（其中罕见病症样本极少）导致使用标准技术进行医学图像分类时存在困难，这会使诊断偏向常见疾病而远离罕见疾病。接着我们讨论并实现了深度学习模型，采用如增强等技术来最小化误差，特别是来自罕见疾病的误差。我们用平均精度、F1分数、曲线下面积和损失（均在验证集上）评估了各种不同模型。最后我们得出了最佳模型的良好结果以及在医疗领域的潜在应用。
英文摘要
In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer conditions have very few samples) resulting in bias towards diagnosing common diseases and away from rarer diseases. We then discuss and implement deep learning models with techniques such as augmentation to minimize error, especially from rarer diseases. We evaluate various different models with AP, F1 score, AUROC, and loss (all on the validation set). We conclude with the promising results from our best model, and potential applications in the healthcare space.
