Applying Faster R-CNN for Object Detection on Malaria Images.
Applying Faster R-CNN for Object Detection on Malaria Images.
复制标题
DOI：
10.1109/cvprw.2017.112
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Carpenter AE
中科院分区：
文献类型：
--
作者：
Hung J;Lopes SCP;Nery OA;Nosten F;Ferreira MU;Duraisingh MT;Marti M;Ravel D;Rangel G;Malleret B;Lacerda MVG;Rénia L;Costa FTM;Carpenter AE
基于深度学习的模型在目标检测方面取得了巨大成功，但最先进的模型尚未广泛应用于生物图像数据。我们第一次应用了以前在自然图像上使用的对象检测模型，以识别细胞并在疟疾感染血液的明场显微镜图像中识别它们的阶段。许多微生物，如疟疾寄生虫，仍然通过专家手工检查和手工计数进行研究。由于细胞形状、密度和颜色的变化以及某些细胞类别的不确定性等因素，这种类型的目标检测任务具有挑战性。此外，用于训练的注释数据很少，并且由于未感染的红细胞占主导地位，类别分布固有地高度不平衡。我们使用更快的基于区域的卷积神经网络（Faster R-CNN），这是近年来性能最好的对象检测模型之一，在ImageNet上进行了预训练，但根据我们的数据进行了微调，并将其与基线进行比较，该基线基于传统方法，包括细胞分割、提取几个单细胞特征以及使用随机森林进行分类。为了进行我们的初步研究，我们收集并标记了一个由大约10万个单个细胞组成的1300个视场的数据集。我们证明了Faster R-CNN的性能优于我们的基线，并将结果置于人类表现的背景下。
Deep learning based models have had great success in object detection, but the state of the art models have not yet been widely applied to biological image data. We apply for the first time an object detection model previously used on natural images to identify cells and recognize their stages in brightfield microscopy images of malaria-infected blood. Many micro-organisms like malaria parasites are still studied by expert manual inspection and hand counting. This type of object detection task is challenging due to factors like variations in cell shape, density, and color, and uncertainty of some cell classes. In addition, annotated data useful for training is scarce, and the class distribution is inherently highly imbalanced due to the dominance of uninfected red blood cells. We use Faster Region-based Convolutional Neural Network (Faster R-CNN), one of the top performing object detection models in recent years, pre-trained on ImageNet but fine tuned with our data, and compare it to a baseline, which is based on a traditional approach consisting of cell segmentation, extraction of several single-cell features, and classification using random forests. To conduct our initial study, we collect and label a dataset of 1300 fields of view consisting of around 100,000 individual cells. We demonstrate that Faster R-CNN outperforms our baseline and put the results in context of human performance.