Phase contrast cell detection using multilevel classification

Abstract

In this paper, we propose a fully automated learning-based approach for detecting cells in time-lapse phase contrast images. The proposed system combines 2 machine learning approaches to achieve bottom-up image segmentation. We apply pixel-wise classification using random forests (RF) classifiers to determine the potential location of the cells. Each pixel is classified into 4 categories (cell, mitotic cell, halo effect, and background noise). Various image features are extracted at different scales to train the RF classifier. The resulting probability map is partitioned using the k-means algorithm to form potential cell regions. These regions are expanded into the neighboring areas to recover some missing or broken cell regions. To validate the cell regions, another machine learning method based on the bag-of-features and spatial pyramid encoding is proposed. The result of the second classifier can be a validated cell, a merged cell, or a noncell. In the case that the cell region is classified as a merged cell, it is split by using the seeded watershed method. The proposed method is demonstrated on several phase contrast image datasets, ie, U2OS, HeLa, and NIH 3T3. In comparison to state-of-the-art cell detection techniques, the proposed method shows improved performance, particularly in dealing with noise interference and drastic shape variations.

Image-based phenotyping of disaggregated cells using deep learning

“…However, trypsin digestion also provides an important practical advantage, because disaggregated cells can be more evenly dispersed in a microscopy well-plate, which improves the robustness of the segmentation process. Previous studies to discriminate cells based on imaging required seeding cells on a surface, where segmentation is more complex and cell-surface interactions can influence cell morphology [26][27][28] or by looking directly at histopathology tissue slides 29 . Sirinukunwattana et al 29 applied a deep-learning approach to classifying cells in histopathology tissue slides and was able to achieve an average F1-score, across 4 classes, of 78.4%.…”

Image-based Cell Phenotyping Using Deep Learning

“…However, trypsin digestion also provide important practical advantages because disaggregated cells can be more evenly dispersed in a microscopy well-plate, which improves the robustness of the segmentation process. Previous studies to discriminate cells based on imaging required seeding cells on a surface, where segmentation is more complex and cell-surface interactions can influence cell morphology [26][27][28] . Disaggregated cell samples provide a simpler, more rapid, and more uniform imaging condition.…”

Label-free classification of cells based on supervised machine learning of subcellular structures

“…In such diagnosis, the texture of labeled or stained tissue slices and cells are automatically recognized and classified as normal or abnormal by computer vision trained by machine learning. On the other hand, label-free automated detection [5–8] and classification [9–13] of single cells (not in tissue) have been developed over the last decade or so. For instance, cells have been classified via imaging-flow cytometry in a manner of bright-field microcopy except quantitative-phase microscopy (QPM), dark-field microscopy, and machine learning of subcellular morphology [14].…”