A semi-automated machine learning-aided approach to quantitative analysis of centrosomes and microtubule organization.

Microtubules (MTs) promote important cellular functions including migration, intracellular trafficking, and chromosome segregation. The centrosome, comprised of two centrioles surrounded by the pericentriolar material (PCM), is the cell's central MT-organizing center. Centrosomes in cancer cells are commonly numerically amplified. However, the question of how the amplification of centrosomes alters MT organization capacity is not well studied. We developed a quantitative image-processing and machine learning-aided approach for the semi-automated analysis of MT organization. We designed a convolutional neural network-based approach for detecting centrosomes, and an automated pipeline for analyzing MT organization around centrosomes, encapsulated in a semi-automatic graphical tool. Using this tool, we find that breast cancer cells with supernumerary centrosomes not only have more PCM protein per centrosome, which gradually increases with increasing centriole numbers, but also exhibit expansion in PCM size. Furthermore, cells with amplified centrosomes have more growing MT ends, higher MT density and altered spatial distribution of MTs around amplified centrosomes. Thus, the semi-automated approach developed here enables rapid and quantitative analyses revealing important facets of centrosomal aberrations.

Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns.

Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation, where we improve state-of-the-art from 49.7 mean APr to 62.4, keypoint localization, where we get a 3.3 point boost over a strong regression baseline using CNN features, and part labeling, where we show a 6.6 point gain over a strong baseline.