What is computational
Computational Pathology uses the power of deep machine learning, image analytics and big data integration to enhance diagnostic precision and transform the next generation of pathologists.
Philips is leading the way in computational pathology research, delivering novel technologies for image analytics, which are fully embedded within their digital pathology scanning, storage and display solution.
Need for Computational pathology 2.1
We are moving rapidly into an era where next-generation pathology is becoming a reality with the advent of digital pathology. Paradigm shifts are being witnessed in cancer care with precision medicine and personalized treatments increasing by the day. Pathologists are absolutely central to this dream of personalized medicine. It is at the desk of the pathologist that first clinical decisions regarding the patient are made and that will continue to be the case.
Increasing workload 3.1
- Cancer projections are growing
- Number of tests applied are increasing
- 20% of pathologists work overtime weekly or have to outsource services
Shortage of pathologist 1.1
- 10.4% decrease in active physicians pathology in 2008 – 2013
- 60.7% of active physicians in pathology are age 55 or older
A transformation in computational pathology 4.1
The evolution of deep learning and the improvement in accuracy for image pattern recognition has been staggering in the last few years. Everything from bio-metric and security, voice recognition and intelligent advertising, to driver-less cars is powered by deep learning technologies.
Next up is pathology. We believe that digital pathology and machine learning combined, could empower pathologists with new tools, and help drive improvements in workflow and diagnostic precision in both discovery and diagnosis.
Recent convergence of technologies, together with Philips innovation in computational pathology will help us to transform pathology together.
Philips computational pathology
Clinical Algorithms 1
We have an extensive roadmap for the delivery of CE-IVD approved algorithms to support clinical decision making in multiple tissues. Initially we are providing digital image analysis applications in support of the pathologist for ER, PR, HER2 and Ki-67 clinical assessments.
Guiding molecular pathology with TissueMark 2, 3
Using machine learning we can analyze tumor tissue samples fast, measure tumor purity and enhance the quality and reliability of macro-dissection, nucleic acid extraction and molecular profiling in solid tumors.
Research and discovery with Xplore 4, 5
A powerful and comprehensive image and data management platform to store and interrogate digital pathology research data, driving bio-marker discovery and tissue-based research.
- For Research Use only in USA. Not for use in diagnostic procedures. Legal manufacturer of the product is Visiopharm A/S.
- TissueMark is a research application. Not intended for diagnostic use.
- PathXL is the legal manufacturer of TissueMark and is a Philips company.
- Xplore is a research application. Not intended for diagnostic use.
- PathXL is the legal manufacturer of Xplore and is a Philips company.
1.1 – Sara Bainbridge et al.. (2016). TESTING TIMES TO COME?. Available: http://www.cancerresearchuk.org/sites/default/files/testing_times_to_come_nov_16_cruk.pdf.
2.1 – Louis DN et al, Computational pathology: an emerging definition, Arch Pathol Lab Med, Volume 138, Issue 9, 2014
3.1 – Cancer Facts & Figures – US figures – AAMC 2014
4.1 – Louis DN et al, Computational Pathology. A Path Ahead, Arch Pathol Lab Med, Vol 140, 2016