Scalable analysis of Big pathology image data cohorts using efficient methods and high-performance computing strategies

Abstract

BackgroundWe describe a suite of tools and methods that form a core set of capabilities for researchers and clinical investigators to evaluate multiple analytical pipelines and quantify sensitivity and variability of the results while conducting large-scale studies in investigative pathology and oncology. The overarching objective of the current investigation is to address the challenges of large data sizes and high computational demands.ResultsThe proposed tools and methods take advantage of state-of-the-art parallel machines and efficient content-based image searching strategies. The content based image retrieval (CBIR) algorithms can quickly detect and retrieve image patches similar to a query patch using a hierarchical analysis approach. The analysis component based on high performance computing can carry out consensus clustering on 500,000 data points using a large shared memory system.ConclusionsOur work demonstrates efficient CBIR algorithms and high performance computing can be leveraged for efficient analysis of large microscopy images to meet the challenges of clinically salient applications in pathology. These technologies enable researchers and clinical investigators to make more effective use of the rich informational content contained within digitized microscopy specimens.

Automated grading of breast cancer histopathology using cascaded ensemble with combination of multi-level image features

“…Histological grading of breast cancer is a challenging task and can be ambiguous for some cases exhibiting characteristics within the various stages of progression ranging from low grade to high grade [32]. In this study, we presented a computer-aided grading method based on multi-level features and cascaded SVM classification to automatically distinguish histopathological breast cancer images with low, intermediate, and high grade.…”

“…Multiple image patches were processed concurrently on multiple CPU cores. This parallelization strategy has been utilized to conduct large-scale image retrieval in histopathology and proved to be effective in reducing memory cost and increasing computational efficiency [32]. Further, the cascaded classification containing multiple SVM classifiers for hierarchically discriminating cancer grade categories was partitioned across CPU-cores to effectively minimize the computation time.…”

“…Final cancer grade is determined by fusing the scores produced by the individual SVM classifiers. The segmentation and feature computation are efficiently performed on a multi-core CPU in which each operation is parallelized to run on multiple CPU cores via a high throughput parallelization strategy to speed up processing of large numbers of histopathological images [32]. The cascaded ensemble allows us to effectively reduce the computational cost by hierarchically classifying the images in step-wise fashion while maintaining a high level of discriminatory performance through the combination of multi-level features.…”

Parallel and Efficient Sensitivity Analysis of Microscopy Image Segmentation Workflows in Hybrid Systems

“…All operations on our three most compute intensive stages have been implemented for CPU and Intel Phi. More details on the internal operations of each application stage may be found in our previous work [7], [8]. …”

Automated mitosis detection in histopathology based on non-gaussian modeling of complex wavelet coefficients

“…Multiple images were processed concurrently on multiple CPU cores. This parallelization strategy has been utilized to conduct cancer grading [9] and large-scale image retrieval in histopathology [68].…”