Ensembling Low Precision Models for Binary Biomedical Image Segmentation
Ensembling Low Precision Models for Binary Biomedical Image Segmentation
复制标题
DOI：
10.1109/wacv48630.2021.00037
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Tianyu Ma;Hang Zhang;Hanley Ong;Amar Vora;Thanh D. Nguyen;Ajay Gupta;Yi Wang;M. Sabuncu
中科院分区：
文献类型：
--
作者：
Tianyu Ma;Hang Zhang;Hanley Ong;Amar Vora;Thanh D. Nguyen;Ajay Gupta;Yi Wang;M. Sabuncu
医学图像中感兴趣的解剖区域（如血管或小病变）的分割仍然是一个难题，通常由专家手工输入来解决。该任务的主要挑战之一是前景（正）区域的外观可能与背景（负）区域相似。因此，许多自动分割算法往往会出现不对称错误，通常会产生更多的假阳性而不是假阴性。在本文中，我们的目标是利用这种不对称性并训练具有非常高召回率的多样化模型集合，同时牺牲它们的精度。我们的核心思想很简单：低精度和高召回率模型的不同集合可能会产生不同的假阳性错误（将图像的不同部分的背景分类为前景），但真阳性将趋于一致。因此，总的来说，假阳性误差将被抵消，从而为集成带来高性能。我们的策略是通用的，可以应用于任何分割模型。在三种不同的应用中（颈部CT血管造影中的颈动脉分割，心血管MRI中的心肌分割和脑MRI中的多发性硬化症病变分割），我们展示了该方法如何显著提高基线分割方法的性能。
Segmentation of anatomical regions of interest such as vessels or small lesions in medical images is still a difficult problem that is often tackled with manual input by an ex-pert. One of the major challenges for this task is that the appearance of foreground (positive) regions can be similar to background (negative) regions. As a result, many automatic segmentation algorithms tend to exhibit asymmetric errors, typically producing more false positives than false negatives. In this paper, we aim to leverage this asymmetry and train a diverse ensemble of models with very high recall, while sacrificing their precision. Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent. Thus, in aggregate the false positive errors will cancel out, yielding high performance for the ensemble. Our strategy is general and can be applied with any segmentation model. In three different applications (carotid artery segmentation in a neck CT angiography, myocardium segmentation in a cardiovascular MRI and multiple sclerosis lesion segmentation in a brain MRI), we show how the proposed approach can significantly boost the performance of a baseline segmentation method.