Since the inception of the microscope, researchers and clinicians have characterized tissues qualitatively through the process of embedding, sectioning, staining and evaluation with a microscope. While this practice has been the gold standard for diagnosis and addressing many research questions, this human-driven approach is highly limited in throughput, qualitative, and subjective. Many studies have shown significant inter- and intra-pathologist variability using a subjective characterization approach.
To help address the limitations of human-based slide characterization, the field of digital pathology has evolved wherein histology slides are analyzed by algorithms that can quantitatively assess staining, morphological features, and cell counts. This computational approach provides high throughput, excellent reproducibility, and quantitative metrics (e.g. total cell counts) for evaluation of histological sections. Furthermore, utilizing machine learning techniques, histological sections can be classified based on morphological or staining characteristics, with the use of training data (supervised machine learning) or by unsupervised machine learning to classify tissue sections into categories based on similarities and differences.
Our approach to digital pathology
We offer our Clients a full suite of digital pathology services from slide scanning and quantitative slide analysis, custom development of image analysis algorithms, and the complete build out and validation of 21 CFR part 11 compliant digital pathology software for use in clinical applications. We have developed a suite of image analysis and digital pathology tools that we call 3Screen™. This custom-built toolbox allows us to quantitatively analyze image data obtained from histological sections to assess tumor area, quantify nuclear morphology, and utilize machine learning techniques for slide classification. We work closely with our Clients to determine the best digital pathology approach for their specific research question and will develop a customized solution if required.
How Clients work with us
For digital pathology projects, typically clients will send us a image data, supplied by flash drive or via the cloud, or send us fixed tissues for embedding, sectioning, and staining, or send glass microscope slides for scanning and analysis. We have expertise in conducting immunohistochemistry, and can utilize special stains as well. Our typical digital pathology projects require 2-3 weeks to complete, although for routine work (e.g. cell counting, tumor area quantification), turnaround can be as quick as next-day.