Phase contrast microscopy (PCM) is routinely used for the inspection of adherent cell cultures in all fields of biology and biomedicine. Key decisions for experimental protocols are often taken by an operator based on typically qualitative observations. However, automated processing and analysis of PCM images remain challenging due to the low contrast between foreground objects (cells) and background as well as various imaging artefacts. We propose a trainable pixel-wise segmentation approach whereby image structures and symmetries are encoded in the form of multi-scale Basic Image Features local histograms, and classification of them is learned by random decision trees. This approach was validated for segmentation of cell versus background, and discrimination between two different cell types. Performance close to that of state-of-the-art specialised algorithms was achieved despite the general nature of the method. The low processing time ( < 4 s per 1280 × 960 pixel images) is suitable for batch processing of experimental data as well as for interactive segmentation applications.
展开▼
机译：相衬显微镜（PCM）通常用于检查生物学和生物医学所有领域中的贴壁细胞培养。实验方案的关键决策通常由操作员根据典型的定性观察来做出。然而，由于前景物体（细胞）与背景之间的对比度低以及各种成像伪像，PCM图像的自动处理和分析仍然具有挑战性。我们提出了一种可训练的逐像素分割方法，其中图像结构和对称性以多尺度基本图像特征局部直方图的形式编码，并通过随机决策树学习它们的分类。验证此方法可用于区分细胞与背景，以及区分两种不同细胞类型。尽管该方法具有一般性，但其性能仍接近最新的专用算法。处理时间短（每1280 x 960像素图像<4秒）适用于实验数据的批处理以及交互式分割应用。
展开▼
