LOCALIZING IMAGE-BASED BIOMARKER REGRESSION WITHOUT TRAINING MASKS: A NEW APPROACH TO BIOMARKER DISCOVERY.
LOCALIZING IMAGE-BASED BIOMARKER REGRESSION WITHOUT TRAINING MASKS: A NEW APPROACH TO BIOMARKER DISCOVERY.
复制标题
无需训练掩模即可定位基于图像的生物标志物回归：生物标志物发现的新方法。
DOI：
10.1109/isbi.2019.8759474
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Estépar,RaúlSanJosé
中科院分区：
文献类型：
--
作者：
Cano-Espinosa,Carlos;González,Germán;Washko,GeorgeR;Cazorla,Miguel;Estépar,RaúlSanJosé
从生物医学图像中提取生物标志物是医学图像分析的主要任务之一。标准技术遵循分割和测量策略，其中首先对结构进行分割，然后执行测量。最近的工作表明，这种策略可以通过使用回归网络中的生物标志物值的直接回归来代替。虽然实现了高相关系数，但这些技术作为“黑盒”操作，不提供质量控制图像。我们提出了一种方法，从图像回归的生物标志物，同时计算质量控制图像。我们提出的方法不需要用于训练的分割掩模，而是直接从用于计算生物标志物值的像素推断分割。提出的网络由两个步骤组成：一个未知参考的分割方法和生物标志物估计的求和方法。该网络使用双重损失函数进行优化，L2用于生物标志物，L1用于增强稀疏性。我们展示了我们的方法，在胸肌面积（PMA）和皮下脂肪面积（SFA）的推理问题，在一个单一的切片从胸部CT图像。我们使用7000个病例的数据库，其中只有生物标志物的值是已知的，用于训练和3000个病例的测试集，生物标志物和分割。相对于参比标准品，PMA和SFA的相关系数分别为0.97和0.98。平均DICE系数为0.88（PMA）和0.89（SFA）。与标准的分割和测量技术相比，我们实现了相同的相关性的生物标志物，但较小的DICE系数分割。这并不奇怪，因为分割网络是可实现的性能上限，并且我们没有使用分割掩码进行训练。我们可以得出结论，可以从生物标志物回归网络中推断分割掩码。
Biomarker inference from biomedical images is one of the main tasks of medical image analysis. Standard techniques follow a segmentation-and-measure strategy, where the structure is first segmented and then the measurement is performed. Recent work has shown that such strategy could be replaced by a direct regression of the biomarker value in using regression networks. While achieving high correlation coefficients, such techniques operate as a 'black-box', not offering quality-control images. We present a methodology to regress the biomarker from the image while simultaneously computing the quality control image. Our proposed methodology does not require segmentation masks for training, but infers the segmentations directly from the pixels that used to compute the biomarker value. The network proposed consists of two steps: a segmentation method to an unknown reference and a summation method for the biomarker estimation. The network is optimized using a dual loss function, L2 for the biomarkers and an L1 to enforce sparsity. We showcase our methodology in the problem of pectoralis muscle area (PMA) and subcutaneous fat area (SFA) inference in a single slice from chest-CT images. We use a database of 7000 cases to which only the value of the biomarker is known for training and a test set of 3000 cases with both, biomarkers and segmentations. We achieve a correlation coefficient of 0.97 for PMA and 0.98 for SFA with respect to the reference standard. The average DICE coefficient is of 0.88 (PMA) and 0.89 (SFA). Comparing with standard segment-and-measure techniques, we achieve the same correlation for the biomarkers but smaller DICE coefficients in segmentation. Such is of little surprise, since segmentation networks are the upper limit of performance achievable, and we are not using segmentation masks for training. We can conclude that it is possible to infer segmentation masks from biomarker regression networks.