The State of Image Analysis in Digital Pathology

by Aleksandra Zuraw, DVM, PhD, Dipl. ACVP; Charles River Laboratories

Image analysis (IA) as part of digital pathology has already been around for quite some time. In fact, the first systems for remote pathologic diagnosis were initially demonstrated in the USA in 1968. Enormous advancements in technology have been made since then, but the penetration of digital pathology applications in the clinical space remains limited.

There are various reasons for this, but one that’s very important has been compliance with regulatory requirements. The pathology IA space for research is pretty dynamic, and there are several companies competing with each other in providing research use only solutions. Many pharmaceutical companies have their own computational pathology divisions which support their drug development.

How many of these offered solutions and developed IA algorithms meet regulatory standards? Of the ones that don’t, how many will make it into the clinic to actually improve healthcare? Is this even the intention behind IA advancements?

It all started with cytology

The Papanicolau test is the most widely used screening method for uterine cervical cancer in women worldwide. It is indicated to be performed in women 21-65 years of age every 3- 5 years if the results of the tests are normal.

This gives a patient population of ca. 2 billion worldwide.

With such a large number of patients to screen, doctors and scientists started to search for a more efficient method of evaluation, than visual assessment.

The work on automating the Pap test started in the 1950s, but only in the 1990s did the first commercial computer-assisted pathology solutions based on IA algorithms received FDA approval. 

The approved devices were first approved for quality control purposes only – rescreening of smears previously visually classified as negative. Later one of the devices was approved as a primary screening device for a limited number of slides (up to 25% of the total workload).

The next big thing: tissue-based biomarker quantification

The area of drug development currently mostly invested in is oncology. Some cancer drugs rely on tissue biomarkers quantified by immunohistochemistry (IHC) for patient stratification. This is a qualitative method, for which, semi-quantitative pathology scores relying on visual estimation have been developed.

One would think, that to avoid adding up the variability of pathologist’s interpretation of the process, consisting of tissue processing, IHC assay and interpretation, this would be a perfect field for applying IA, and make the quantification objective and reproducible. However, so far out of the following five predictive IHC biomarker tests approved by the FDA as companion diagnostics:

  • Programmed Death Ligand 1 (PDL1) in non-small cell lung cancer, gastric or gastroesophageal junction adenocarcinoma, cervical cancer, urothelial carcinoma;
  • Anaplastic Lymphoma Kinase (ALK) in non-small cell lung cancer,
  • Epithelial Growth Factor Receptor (EGFR) in colorectal cancer,
  • c-kit receptor (CD 117) in gastrointestinal stromal tumor and
  • human epidermal growth factor receptor 2 (Her2) in breast cancer, gastric cancer

For only one – Her2 – have IA quantification algorithms been FDA cleared.

The lack of approved quantification algorithms is surprising, given that the task of estimating the amount of positive stain in an image simply is not a strength of the human brain. We are very good in recognizing different patterns and structures, but miserable at quantifying them, especially around the cut-off values, where interobserver variability is extremely high and may lead to misclassification of as many as 50% of the patients.

Apart from the predictive biomarkers which are part of companion diagnostic tests, there are a few other biomarkers used in the clinical practice, which interpretation benefits from the use of an IA algorithm.

The ones currently FDA cleared and routinely used in breast cancer diagnostics and treatment are:

  • Estrogen Receptor (ER),
  • Progesterone Receptor (PR), both used for qualifying patients for hormone therapy
  • p53 protein, responsible for activating apoptosis,
  • Ki67, indicating tumor proliferation index – both used as prognostic markers.

A comprehensive list of FDA 510 (k) clearances for IA algorithms can be found here.

Is there another way to use IA in IHC quantification? – Laboratory Developed Tests (LDTs)

One reason for the limited number of quantifiable IHC biomarkers is the biology itself, another is the state of discovery. There may just not be a large number of relevant biomarkers detectable by IHC, or they may have not yet been discovered.

On top of that, even though IHC is a widely available method, standardizing it for IA is a complex process that is not always possible. Both the preanalytical and analytical phases of IHC include multiple steps, each of which may contribute to the variability in results and differences in interpretation. This makes it difficult to keep the assays consistent across laboratories and scale up the availability of the test. IA algorithms are just the final, quantifying part of the process, usually optimized to a particular appearance (certain staining pattern and intensity, certain slide thickness etc.). If any of these aspects changes, the algorithm will no longer provide correct results. Therefore, the whole process needs to be strictly standardized, which is not always possible when working across laboratories.

A way of overcoming this is to keep the process restricted to one laboratory and to control as many steps of the process as possible. This is how Laboratory Developed Tests (LDTs) are created. The samples are usually sent to a particular lab for analysis, and most of the steps from tissue processing, through sectioning and staining, all the way to the IA take place there. In this scenario, it is possible to control most of the process and thus provide the most consistent results. There are several LDT’s on the market, which incorporate an IA component for both bright field and fluorescence microscopy. These tests are under the oversight of Clinical Laboratory Improvement Amendments (CLIA) enforced by the Centers for Medicare & Medicaid Services (CMS).

What about research? – Research Use Only (RUO)

Many of the pathology-supporting algorithms will never enter the regulated environment, meaning they will never comply with the strict regulations. They will remain for research use only. This is not necessarily bad, as there is not always a need to go this route. This, however, doesn’t mean that there should be total freedom in their design and their interpretation. As any other scientific method supporting bio-technological discoveries, IA for IHC quantification should always be tested for its specificity, sensitivity, and accuracy before data is generated.

Summary:

Even though the work on including IA algorithms in pathological evaluation already started in the 1960s, relatively few of them received an approval from regulatory bodies.

The first FDA-approved algorithms were used in cytology for automated evaluation of Pap smears.

Another important application of IA solutions is the quantification of IHC biomarkers. The following markers received FDA clearance for digital quantification:

  • Human Epidermal Growth Factor Receptor 2 (Her2) in breast cancer, gastric cancer
  • Estrogen Receptor (ER),
  • Progesterone Receptor (PR), both used for qualifying patients for hormone therapy
  • p53 protein, responsible for activating apoptosis,
  • Ki67, indicating tumor proliferation index – both used as prognostic markers.

Another way of introducing IA into the regulated environment is its incorporation in LDT’s.

Even though the number of regulated IA powered pathology tests is limited, the number of RUO applications is growing. A thorough internal validation of these tests and tools should be performed before data for research support is generated.

Disclaimer: In seeking to foster discourse on a wide array of ideas, the Digital Pathology Association believes that it is important to share a range of prominent industry viewpoints. This article does not necessarily express the viewpoints of the DPA, however we view this as a valuable point with which to facilitate discussion.

3 comments on “The State of Image Analysis in Digital Pathology

Leave a Reply

Your email address will not be published. Required fields are marked *

18 + 9 =