论文标题
使用计算机视觉预测胸部X射线的射血分数，以诊断心力衰竭
Predicting Ejection Fraction from Chest X-rays Using Computer Vision for Diagnosing Heart Failure
论文作者
论文摘要
由于成本不断增长，心力衰竭仍然是一个重大的公共卫生挑战。射血分数（EF）是用于诊断和管理心力衰竭的关键指标，但是使用超声心动图对EF进行估算对于医疗系统而言仍然昂贵，并且受内部/间操作员的可变性约为。虽然胸部X射线（CXR）快速，便宜，并且需要更少的专业知识，但它们没有为人类的眼睛提供足够的信息来估算EF。这项工作探讨了计算机视觉技术的疗效，仅预测仅CXR的EF降低。我们从MIMIC CXR-JPG（MCR）数据集研究了一个3488 CXR的数据集。我们的工作使用多个最先进的卷积神经网络体系结构建立了基准。随后的分析显示，在不适合数据集的情况下，将模型尺寸从8M到23M参数提高了分类性能。我们进一步展示了CXR旋转和随机种植等数据增强技术如何进一步提高模型性能又大约5％。最后，我们使用显着图和毕业-CAM进行错误分析，以更好地了解该任务上卷积模型的故障模式。
Heart failure remains a major public health challenge with growing costs. Ejection fraction (EF) is a key metric for the diagnosis and management of heart failure however estimation of EF using echocardiography remains expensive for the healthcare system and subject to intra/inter operator variability. While chest x-rays (CXR) are quick, inexpensive, and require less expertise, they do not provide sufficient information to the human eye to estimate EF. This work explores the efficacy of computer vision techniques to predict reduced EF solely from CXRs. We studied a dataset of 3488 CXRs from the MIMIC CXR-jpg (MCR) dataset. Our work establishes benchmarks using multiple state-of-the-art convolutional neural network architectures. The subsequent analysis shows increasing model sizes from 8M to 23M parameters improved classification performance without overfitting the dataset. We further show how data augmentation techniques such as CXR rotation and random cropping further improves model performance another ~5%. Finally, we conduct an error analysis using saliency maps and Grad-CAMs to better understand the failure modes of convolutional models on this task.
