An Active Learning Approach for Rapid Characterization of Endothelial Cells in Human Tumors

Abstract

Currently, no available pathological or molecular measures of tumor angiogenesis predict response to antiangiogenic therapies used in clinical practice. Recognizing that tumor endothelial cells (EC) and EC activation and survival signaling are the direct targets of these therapies, we sought to develop an automated platform for quantifying activity of critical signaling pathways and other biological events in EC of patient tumors by histopathology. Computer image analysis of EC in highly heterogeneous human tumors by a statistical classifier trained using examples selected by human experts performed poorly due to subjectivity and selection bias. We hypothesized that the analysis can be optimized by a more active process to aid experts in identifying informative training examples. To test this hypothesis, we incorporated a novel active learning (AL) algorithm into FARSIGHT image analysis software that aids the expert by seeking out informative examples for the operator to label. The resulting FARSIGHT-AL system identified EC with specificity and sensitivity consistently greater than 0.9 and outperformed traditional supervised classification algorithms. The system modeled individual operator preferences and generated reproducible results. Using the results of EC classification, we also quantified proliferation (Ki67) and activity in important signal transduction pathways (MAP kinase, STAT3) in immunostained human clear cell renal cell carcinoma and other tumors. FARSIGHT-AL enables characterization of EC in conventionally preserved human tumors in a more automated process suitable for testing and validating in clinical trials. The results of our study support a unique opportunity for quantifying angiogenesis in a manner that can now be tested for its ability to identify novel predictive and response biomarkers.

Quantitative 3-D analysis of GFAP labeled astrocytes from fluorescence confocal images

“…The next step is to detect and delineate all cell nuclei from the DAPI channel using a previously published method (Al-Kofahi et al, 2010). The next step is to isolate the sub-population of astrocyte nuclei using a statistical classifier that can be trained efficiently from examples (Padmanabhan et al, 2014). At a minimum, the method requires a two-channel image consisting of GFAP, and a nuclear label.…”

“…For each GFAP+ interest point, we compute its local spatial scale, fiber orientation diversity, GFAP intensity statistics, local shape, and spatial associations with other available imaging channels, as described further below. A machine learning algorithm is then used to identify the root points from these measurements (Padmanabhan et al, 2014).…”

“…In addition, when analyzing large datasets with thousands of samples, choosing the appropriate training samples to train an algorithm to classify cells is a skill-intensive task. With the intent of making our method widely usable, we adopted a recently reported active learning based classifier algorithm that is designed to maximize automation, and minimize parameter tuning and training effort (Padmanabhan et al, 2014). The active learning algorithm analyzes the set of multivariate data points representing the features of the GFAP+ interest points, and selects a parsimonious subset of five data points that are presented to the user for visual labeling into two categories: interest points that belong to the basal "root" regions, and other interest points.…”

“…This sequential procedure converges rapidly, and stops when the information gain across successive iterations reaches a plateau indicating that classification boundaries can be identified to within a specified confidence level. This active learning algorithm is based on the D-optimal experimental design criterion (Padmanabhan et al, 2014), and it learns a multi-class logistic classifier with L 1 -norm based regularization. It not only leads to efficient learning of the decision boundary, but also helps in selecting an optimal subset of the relevant features.…”

An interactive learning framework for scalable classification of pathology images

“…The FARSIGHT toolkit is a comprehensive software platform for managing and analyzing microscopy images [6, 7]. It provides extensive functionality for the segmentation and classification of microscopy image data, including some active learning capabilities, but is intended for traditional microscopy modalities with limited fields and does not scale to support WSI images.…”