PathGrid: a service-orientated architecture for microscopy image analysis

Walton, N. A.; Brenton, James D.; Caldas, Carlos; Irwin, M. J.; Akram, Asif; González-Solares, E.; Lewis, Jim; Maccallum, Peter H; Morris, Lorna; Rixon, G.

doi:10.1098/rsta.2010.0158

Cited by 6 publications

(7 citation statements)

References 24 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find that automated scores show excellent correlation with scores based on visual inspection and can effectively divide the population into ‘positive' and ‘negative' groups significantly associated with outcome in an unsupervised manner. These methods constitute a high-throughput pipeline for the generation of objective, reproducible and continuous IHC data (Walton et al , 2010). This study takes advantage of a unique digital pathology resource by bringing together the expertise of researchers from diverse disciplines in order to develop a true systems pathology approach to cancer medicine.…”

Section: Resultsmentioning

confidence: 99%

“…Driven by the large volume of data, image analysis in the field of astronomy has matured into a sophisticated, robust discipline. We therefore investigated the adaptation of algorithms used in astronomy to immunostained microscopic images of breast cancer in order to produce comparable measures of protein expression (Walton et al , 2010). We describe three algorithms developed for oestrogen receptor (ER), B-cell lymphoma protein 2 (BCL2) and human epidermal growth factor receptor 2 (HER2) representing examples of nuclear, cytoplasmic and membranous staining patterns, respectively.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Astronomical algorithms for automated analysis of tissue protein expression in breast cancer

Irwin

Morris

et al. 2013

Br J Cancer

View full text Add to dashboard Cite

Background:High-throughput evaluation of tissue biomarkers in oncology has been greatly accelerated by the widespread use of tissue microarrays (TMAs) and immunohistochemistry. Although TMAs have the potential to facilitate protein expression profiling on a scale to rival experiments of tumour transcriptomes, the bottleneck and imprecision of manually scoring TMAs has impeded progress.Methods:We report image analysis algorithms adapted from astronomy for the precise automated analysis of IHC in all subcellular compartments. The power of this technique is demonstrated using over 2000 breast tumours and comparing quantitative automated scores against manual assessment by pathologists.Results:All continuous automated scores showed good correlation with their corresponding ordinal manual scores. For oestrogen receptor (ER), the correlation was 0.82, P<0.0001, for BCL2 0.72, P<0.0001 and for HER2 0.62, P<0.0001. Automated scores showed excellent concordance with manual scores for the unsupervised assignment of cases to ‘positive' or ‘negative' categories with agreement rates of up to 96%.Conclusion:The adaptation of astronomical algorithms coupled with their application to large annotated study cohorts, constitutes a powerful tool for the realisation of the enormous potential of digital pathology.

show abstract

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

Astronomical algorithms for automated analysis of tissue protein expression in breast cancer

Irwin

Morris

et al. 2013

Br J Cancer

View full text Add to dashboard Cite

show abstract

“…Automated image analysis of TMAs using many different systems has been shown to perform well for multiple markers . However, most studies have been based on relatively small comparisons of TMAs from one or few centres.…”

Section: Discussionmentioning

confidence: 99%

“…Automated analysis of pathology images has been in use for more than 20 years and has been applied extensively in recent years in the study of breast cancer with increasingly complex algorithms and improved concordance with visual scores . However, most comparisons are based on TMAs of a few hundred to a few thousand tumours constructed and stained in a single pathology laboratory.…”

Section: Introductionmentioning

confidence: 99%

Performance of automated scoring of ER, PR, HER2, CK5/6 and EGFR in breast cancer tissue microarrays in the Breast Cancer Association Consortium

Howat

Blows

Provenzano

et al. 2014

The Journal of Pathology CR

View full text Add to dashboard Cite

Breast cancer risk factors and clinical outcomes vary by tumour marker expression. However, individual studies often lack the power required to assess these relationships, and large‐scale analyses are limited by the need for high throughput, standardized scoring methods. To address these limitations, we assessed whether automated image analysis of immunohistochemically stained tissue microarrays can permit rapid, standardized scoring of tumour markers from multiple studies. Tissue microarray sections prepared in nine studies containing 20 263 cores from 8267 breast cancers stained for two nuclear (oestrogen receptor, progesterone receptor), two membranous (human epidermal growth factor receptor 2 and epidermal growth factor receptor) and one cytoplasmic (cytokeratin 5/6) marker were scanned as digital images. Automated algorithms were used to score markers in tumour cells using the Ariol system. We compared automated scores against visual reads, and their associations with breast cancer survival. Approximately 65–70% of tissue microarray cores were satisfactory for scoring. Among satisfactory cores, agreement between dichotomous automated and visual scores was highest for oestrogen receptor (Kappa = 0.76), followed by human epidermal growth factor receptor 2 (Kappa = 0.69) and progesterone receptor (Kappa = 0.67). Automated quantitative scores for these markers were associated with hazard ratios for breast cancer mortality in a dose‐response manner. Considering visual scores of epidermal growth factor receptor or cytokeratin 5/6 as the reference, automated scoring achieved excellent negative predictive value (96–98%), but yielded many false positives (positive predictive value = 30–32%). For all markers, we observed substantial heterogeneity in automated scoring performance across tissue microarrays. Automated analysis is a potentially useful tool for large‐scale, quantitative scoring of immunohistochemically stained tissue microarrays available in consortia. However, continued optimization, rigorous marker‐specific quality control measures and standardization of tissue microarray designs, staining and scoring protocols is needed to enhance results.

show abstract

“…Chaining a number of analysis tools together to form domain-specific analysis pipelines or workflows is essential in many scientific disciplines [1-3]. For some scientists access to a command line login is all that is required for them to write custom scripts and programs to link these tasks.…”

Section: Introductionmentioning

confidence: 99%

Yabi: An online research environment for grid, high performance and cloud computing

Hunter¹,

Macgregor²,

Szabó³

et al. 2012

Source Code Biol Med

110

View full text Add to dashboard Cite

BackgroundThere is a significant demand for creating pipelines or workflows in the life science discipline that chain a number of discrete compute and data intensive analysis tasks into sophisticated analysis procedures. This need has led to the development of general as well as domain-specific workflow environments that are either complex desktop applications or Internet-based applications. Complexities can arise when configuring these applications in heterogeneous compute and storage environments if the execution and data access models are not designed appropriately. These complexities manifest themselves through limited access to available HPC resources, significant overhead required to configure tools and inability for users to simply manage files across heterogenous HPC storage infrastructure.ResultsIn this paper, we describe the architecture of a software system that is adaptable to a range of both pluggable execution and data backends in an open source implementation called Yabi. Enabling seamless and transparent access to heterogenous HPC environments at its core, Yabi then provides an analysis workflow environment that can create and reuse workflows as well as manage large amounts of both raw and processed data in a secure and flexible way across geographically distributed compute resources. Yabi can be used via a web-based environment to drag-and-drop tools to create sophisticated workflows. Yabi can also be accessed through the Yabi command line which is designed for users that are more comfortable with writing scripts or for enabling external workflow environments to leverage the features in Yabi. Configuring tools can be a significant overhead in workflow environments. Yabi greatly simplifies this task by enabling system administrators to configure as well as manage running tools via a web-based environment and without the need to write or edit software programs or scripts. In this paper, we highlight Yabi's capabilities through a range of bioinformatics use cases that arise from large-scale biomedical data analysis.ConclusionThe Yabi system encapsulates considered design of both execution and data models, while abstracting technical details away from users who are not skilled in HPC and providing an intuitive drag-and-drop scalable web-based workflow environment where the same tools can also be accessed via a command line. Yabi is currently in use and deployed at multiple institutions and is available at http://ccg.murdoch.edu.au/yabi.

show abstract

PathGrid: a service-orientated architecture for microscopy image analysis

Cited by 6 publications

References 24 publications

Astronomical algorithms for automated analysis of tissue protein expression in breast cancer

Astronomical algorithms for automated analysis of tissue protein expression in breast cancer

Performance of automated scoring of ER, PR, HER2, CK5/6 and EGFR in breast cancer tissue microarrays in the Breast Cancer Association Consortium

Yabi: An online research environment for grid, high performance and cloud computing

Contact Info

Product

Resources

About