Abstract
BackgroundEndocytosis is regarded as a mechanism of attenuating the epidermal growth factor receptor (EGFR) signaling and of receptor degradation. There is increasing evidence becoming available showing that breast cancer progression is associated with a defect in EGFR endocytosis. In order to find related Ribonucleic acid (RNA) regulators in this process, high-throughput imaging with fluorescent markers is used to visualize the complex EGFR endocytosis process. Subsequently a dedicated automatic image and data analysis system is developed and applied to extract the phenotype measurement and distinguish different developmental episodes from a huge amount of images acquired through high-throughput imaging. For the image analysis, a phenotype measurement quantifies the important image information into distinct features or measurements. Therefore, the manner in which prominent measurements are chosen to represent the dynamics of the EGFR process becomes a crucial step for the identification of the phenotype. In the subsequent data analysis, classification is used to categorize each observation by making use of all prominent measurements obtained from image analysis. Therefore, a better construction for a classification strategy will support to raise the performance level in our image and data analysis system.ResultsIn this paper, we illustrate an integrated analysis method for EGFR signalling through image analysis of microscopy images. Sophisticated wavelet-based texture measurements are used to obtain a good description of the characteristic stages in the EGFR signalling. A hierarchical classification strategy is designed to improve the recognition of phenotypic episodes of EGFR during endocytosis. Different strategies for normalization, feature selection and classification are evaluated.ConclusionsThe results of performance assessment clearly demonstrate that our hierarchical classification scheme combined with a selected set of features provides a notable improvement in the temporal analysis of EGFR endocytosis. Moreover, it is shown that the addition of the wavelet-based texture features contributes to this improvement. Our workflow can be applied to drug discovery to analyze defected EGFR endocytosis processes.
Highlights
Endocytosis is regarded as a mechanism of attenuating the epidermal growth factor receptor (EGFR) signaling and of receptor degradation
Its signaling is regulated via endocytosis, a process that results in receptor degradation and thereby attenuation of the EGFR signaling
Along the same lines, for the second step classification, we have chosen the combination of branch and bound feature selection with the support vector machine classifier using the variance normalization scheme
Summary
Endocytosis is regarded as a mechanism of attenuating the epidermal growth factor receptor (EGFR) signaling and of receptor degradation. The endocytosis pathway is often defected, resulting in an uncontrolled EGFR signaling This uncontrolled EGFR signaling triggers breast cancer cells to escape from a primary tumor and spread to the lung, resulting in a poor prognosis for the disease progression. In addition to this route, EGFR can be partly transported back to the plasma-membrane sites This dynamic model is used as the major guideline for the analysis of the EGFR-regulation-related genetic pathway using microscopy images as a readout. In this manner the analysis is linked to the analysis of the characteristic episodes in EGFR endocytosis. We will focus our analysis on the aforementioned dynamic model, for the analysis we will only use the first three characteristic episodes, as shown in Fig. 1; the final episode of the EGFR signaling can not be visualized through markers in microscopy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
