Bioinformatics and pathology are obvious scientific partners. Bioinformatics often takes places at the most basic (almost chemical, or even physical) level of life, but much of its procedures to obtain data are destructive. Pathology on the other hand takes place at a much more coarse level of data acquisition (usually where the physical properties of visible light end), but has the advantage of being rooted in the tradition of medicine. The traditional paradigm of pathology is "tissue is the issue". Morphology (exactly the component that often gets overlooked in bioinformatics) plays a large role and helps millions of patients each year around the world. Pathology is proven technology, bioinformatics is limited to niche applications.
With the development of whole slide imaging technology some twenty years ago, digital pathology became possible. Observations that used to be for the eyes of the pathologist only, could now be captured and translated into high-resolution pixels, and studied by and communicated to many. Many began to dream of automated tissue evaluation systems and AI-pathology, some even going as far as to suggest the replacement of the pathologist by intelligent computer systems.
Meanwhile in several areas of bioinformatics, new limits are being hit. Yes, we can do high-throughput experiments, but noisy datasets are often the results, (inter- and even intra-observer) replicability is difficult, and statistics only offer limited relief.
The goal of this introductory lecture is to highlight the problems as well as opportunities for both fields of study, and how exchange of experiences, and (in a later stadium) integration of techniques close the scientific gap that still exists in a great many areas.
There is no lack of pathology-centric workshops that offer insights into the world of algorithms. With the CPW event however, we take another approach. We want to bring together the most advanced groups in digital pathology, with the bioinformatics community, to explore the opportunities that exist on both sides of the fence.
We start by explaining the basic data types that are introduced by digital pathology. We also explain where they come from, and why this presents unique challenges when it comes to data mining and image analysis. Finally, we introduce PMA.start, a free software environment that can be used to universally gain access to digital pathology (imaging) data.
Bioinformatics groups can help quantify, model, and reduce morphological whole tissue data. Pathologists can help interpret and explain heterogeneous high-throughput datasets. And the first seeds of such collaboration can be planted right here, in Athens.
5. Let’s go WAAAAAY back
a) Nebelthau's Sliding Microscope as described in Zeitschrift für wissenschaftliche Mikroskopie, XIII, 1896
b) “Photo-micrographic apparatus, for use in horizontal and vertical position”.
6. My educational
background
• BS. Computer science
• MS. Biological sciences
• Replication between transcription termination and
replication initiation through in vivo and in silico
study of Autonomous Replication Sequences
• 2003: Keynote by Manolis Kellis at YGMB Göteborg
• PhD. Bioinformatics
• Network biology with plant modeling systems
• In silico pathway integration of heterogeneous
datasets: TAIR, AraCyc, atPID
7. After graduation
Joined an unknown CRO in Belgium: HistoGeneX
2010: About 30 people in Antwerp
Today: 110+ people in Belgium, US, planning a third site in China
The challenge: develop complementary bioinformatics
activities to a mostly wet-lab based product portfolio
Veerle was there when I was hired
16. Bioinformatics + digital
pathology =
computational
pathology
• The term was coined first by Dr.
Thomas Fuchs
• Other terms used: augmented
pathology, integrated /
integrative pathology,
histonomics, …
• Many workshops now on the
subject, at API, DPA, Global
Engage…
• CPW is the only event organized
at the bioinformatics community
level!
27. Are we there yet?
• Anno 2018, big divides remain, adaptation is slower than
expected, and bridging communities is more necessary than ever
• Beacons of hope: “students don’t begin from scratch but enjoy a
wealth of tools and code written before them. Most of our
students likely don’t even realize that they’re using openslide or
matlab as a backend because we’ve already written appropriate
wrappers for our common tasks. In that context as well, us with
our collaborators have established working protocols (e.g., file
formats, scanners, etc) which our code is based around.”
• But (much) more work is definitely needed!
30. 1) Don’t build software for a single scanner
• It’s (still) about the file formats
• Build your software on a digital pathology abstraction layer
• PMA.start, OpenSlide, OMERO,…
32. 2) Don’t reinvent the wheel
• But you can still improve the cars!
• Network analysis:
• Cytoscape plugins for digital pathology?
• Expand AI environments so they become friendlier for image analysis:
• AzureML Studio
• Contribute content, tutorials, presentations:
• a DataCamp or Coursea MOOC on digital pathology?
• Talk to Pavel Pevzner for a new section in the UCSD Bioinformatics
curriculum?
34. 3) Usability and replicability are not the same
• Test your software / protocols / algorithms
on data from others
• People in your own lab (or even building) don’t
count
• This is not just about user-friendliness, it’s
about getting similar results on data
generated on different imaging platforms
• Your segmentation algorithm may only work
for you; what about others?