Artificial Intelligence in Pathology: From Prototype to Product

Modern image analysis techniques based on artificial intelligence (AI) have great potential to improve the quality and efficiency of diagnostic procedures in pathology and to detect novel biomarkers. Despite thousands of published research papers on applications of AI in pathology, hardly any research implementations have matured into commercial products for routine use. Bringing an AI solution for pathology to market poses significant technological, business, and regulatory challenges. In this paper, we provide a comprehensive overview and advice on how to meet these challenges. We outline how research prototypes can be turned into a product-ready state and integrated into the IT infrastructure of clinical laboratories. We also discuss business models for profitable AI solutions and reimbursement options for computer assistance in pathology. Moreover, we explain how to obtain regulatory approval so that AI solutions can be launched as in vitro diagnostic medical devices. Thus, this paper offers computer scientists, software companies, and pathologists a road map for transforming prototypes of AI solutions into commercial products.

[1]  Ahmed Hosny,et al.  Artificial intelligence in radiology , 2018, Nature Reviews Cancer.

[2]  Phedias Diamandis,et al.  Physician perspectives on integration of artificial intelligence into diagnostic pathology , 2019, npj Digital Medicine.

[3]  Liron Pantanowitz,et al.  Digital pathology and anatomic pathology laboratory information system integration to support digital pathology sign-out , 2016, Journal of pathology informatics.

[4]  J. Denny,et al.  Artificial intelligence, bias and clinical safety , 2019, BMJ Quality & Safety.

[5]  Slinger Jansen,et al.  Defining App Stores: The Role of Curated Marketplaces in Software Ecosystems , 2013, ICSOB.

[6]  Predrag Radivojac,et al.  Ten Simple Rules for a Community Computational Challenge , 2015, PLoS Comput. Biol..

[7]  Rajarsi R. Gupta,et al.  Overview of established and emerging immunohistochemical biomarkers and their role in correlative studies in MRI , 2020, Journal of magnetic resonance imaging : JMRI.

[8]  Michael Gadermayr,et al.  Generative Adversarial Networks in Digital Pathology: A Survey on Trends and Future Potential , 2020, Patterns.

[9]  Peter Bankhead,et al.  QuPath: Open source software for digital pathology image analysis , 2017, Scientific Reports.

[10]  Andrew H. Beck,et al.  Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association , 2019, The Journal of pathology.

[11]  Ann Benson,et al.  Business Model Canvas , 2003, Strategic Decisions.

[12]  J. M. Crawford,et al.  Pathologist workforce in the United States: I. Development of a predictive model to examine factors influencing supply. , 2013, Archives of pathology & laboratory medicine.

[13]  Larry J. Brindza,et al.  What is a premarket notification 510(k) , 1980 .

[14]  J. Samet,et al.  Food and Drug Administration , 2007, BMJ : British Medical Journal.

[15]  M. Gurcan,et al.  Digital pathology and artificial intelligence. , 2019, The Lancet. Oncology.

[16]  Tobias Bachmeier,et al.  Business Model Generation A Handbook For Visionaries Game Changers And Challengers , 2016 .

[17]  Susan Lamph,et al.  Regulation of medical devices outside the European Union , 2012, Journal of the Royal Society of Medicine.

[18]  Michael D Abramoff,et al.  Lessons learnt about Autonomous AI: Finding a safe, efficacious and ethical path through the development process. , 2020, American journal of ophthalmology.

[19]  Geert J. S. Litjens,et al.  Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology , 2019, Medical Image Anal..

[20]  Andrea L. Kalfoglou,et al.  Medicare Laboratory Payment Policy: Now and in the Future , 2000 .

[21]  Jie Xu,et al.  The practical implementation of artificial intelligence technologies in medicine , 2019, Nature Medicine.

[22]  M. Rantalainen,et al.  Artificial intelligence as the next step towards precision pathology , 2020, Journal of internal medicine.

[23]  Helen Pitman,et al.  Artificial intelligence in digital pathology: a roadmap to routine use in clinical practice , 2019, The Journal of pathology.

[24]  Ashish Sharma,et al.  A Regulatory Science Initiative to Harmonize and Standardize Digital Pathology and Machine Learning Processes to Speed up Clinical Innovation to Patients , 2020, Journal of pathology informatics.

[25]  Nikolas Stathonikos,et al.  Being fully digital: perspective of a Dutch academic pathology laboratory , 2019, Histopathology.

[26]  A. Parwani.  Next generation diagnostic pathology: use of digital pathology and artificial intelligence tools to augment a pathological diagnosis , 2019, Diagnostic Pathology.

[27]  Liron Pantanowitz,et al.  Artificial Intelligence and Digital Pathology: Challenges and Opportunities , 2018, Journal of pathology informatics.

[28]  Rainer Hasenauer,et al.  Assessing Technology Readiness for Artificial Intelligence and Machine Learning based Innovations , 2019, DATA.

[29]  Daniel Forsberg,et al.  Implementation and Benefits of a Vendor-Neutral Archive and Enterprise-Imaging Management System in an Integrated Delivery Network , 2018, Journal of Digital Imaging.

[30]  S. Klug,et al.  A randomized trial comparing conventional cytology to liquid‐based cytology and computer assistance , 2013, International journal of cancer.

[31]  Hammad Qureshi,et al.  Translational AI and Deep Learning in Diagnostic Pathology , 2019, Front. Med..

[32]  Mustafa Suleyman,et al.  Key challenges for delivering clinical impact with artificial intelligence , 2019, BMC Medicine.

[33]  M. Salto‐Tellez,et al.  Digital pathology and image analysis in tissue biomarker research. , 2014, Methods.

[34]  Yiping Wang,et al.  Synthesis of diagnostic quality cancer pathology images by generative adversarial networks , 2020, The Journal of pathology.

[35]  Ron Kikinis,et al.  Implementing the DICOM Standard for Digital Pathology , 2018, Journal of pathology informatics.

[36]  Sandeep Kumar Gupta,et al.  Medical Device Regulations: A Current Perspective , 2016 .

[37]  Marcial García-Rojo,et al.  New European Union Regulations Related to Whole Slide Image Scanners and Image Analysis Software , 2019, Journal of pathology informatics.

[38]  A. Madabhushi,et al.  Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology , 2019, Nature Reviews Clinical Oncology.

[39]  John D. Olson,et al.  College of American Pathologists , 2020, Definitions.

[40]  Glenford J. Myers,et al.  Art of Software Testing , 1979 .

[41]  Antonio Coronato,et al.  ISO 13485: medical devices - quality management systems - requirements for regulatory purposes , 2018 .

[42]  Alexandar Tzankov,et al.  Hands-On Experience: Accreditation of Pathology Laboratories according to ISO 15189 , 2016, Pathobiology.

[43]  Liron Pantanowitz,et al.  Anatomic Pathology Laboratory Information Systems: A Review , 2012, Advances in anatomic pathology.

[44]  Brijesh Singh,et al.  The Lean Startup:How Today's Entrepreneurs Use Continuous Innovation to Create Radically Successful Businesses , 2016 .

[45]  Robert C. Martin.  Clean Code - a Handbook of Agile Software Craftsmanship , 2008 .

[46]  Ronnachai Jaroensri,et al.  Artificial intelligence in digital breast pathology: Techniques and applications , 2019, Breast.

[47]  Todd H. Stokes,et al.  Pathology imaging informatics for quantitative analysis of whole-slide images , 2013, Journal of the American Medical Informatics Association : JAMIA.

[48]  Douglas Bowman,et al.  Introduction to Digital Image Analysis in Whole-slide Imaging: A White Paper from the Digital Pathology Association , 2019, Journal of pathology informatics.

[49]  Jens Rittscher,et al.  Precision immunoprofiling by image analysis and artificial intelligence , 2018, Virchows Archiv.

[50]  Xu Qian-qian,et al.  Study on Implementation Approach for Standard YY/T 0316(ISO 14971) "Medical Devices-Application of Risk Management to Medical Devices" , 2012 .

[51]  Jeff Schreier,et al.  Diagnostics Reform and Harmonization of Clinical Laboratory Testing. , 2019, The Journal of molecular diagnostics : JMD.

[52]  Jingzhi An,et al.  Imaging Intelligence: AI Is Transforming Medical Imaging Across the Imaging Spectrum , 2018, IEEE Pulse.

[53]  David Samson,et al.  Chapter 2: Medical Tests Guidance (2) Developing the Topic and Structuring Systematic Reviews of Medical Tests: Utility of PICOTS, Analytic Frameworks, Decision Trees, and Other Frameworks , 2012, Journal of general internal medicine.

[54]  Jesper Molin,et al.  Diagnostic Review with Digital Pathology: Design of digitals tools for routine diagnostic use , 2016 .

[55]  Tim Benson,et al.  Principles of Health Interoperability: SNOMED CT, HL7 and FHIR , 2016 .

[56]  Mitko Veta,et al.  Learning Domain-Invariant Representations of Histological Images , 2019, Front. Med..

[57]  E. Kinney,et al.  Health Insurance Coverage in the United States , 2002 .

[58]  Zhiyong Lu,et al.  Community challenges in biomedical text mining over 10 years: success, failure and the future , 2016, Briefings Bioinform..

[59]  James R. Armstrong.  6.4.2 Applying Technical Readiness Levels to Software: New Thoughts and Examples , 2010 .

[60]  Antonio Coronato,et al.  IEC 62304: medical device software - software life-cycle processes , 2018 .

[61]  Narayan Ramasubbu,et al.  Managing Technical Debt in Enterprise Software Packages , 2014, IEEE Transactions on Software Engineering.

[62]  R. Schindler.  Pricing Strategies: A Marketing Approach , 2011 .

[63]  K. Dreyer,et al.  When Machines Think: Radiology's Next Frontier. , 2017, Radiology.

[64]  Barbara Prainsack,et al.  Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations , 2020, European Radiology.

[65]  Kamran Sartipi,et al.  HL7 FHIR: An Agile and RESTful approach to healthcare information exchange , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

[66]  Gilles Louppe,et al.  Collaborative analysis of multi-gigapixel imaging data using Cytomine , 2016, Bioinform..

[67]  Hoon Seok Choi,et al.  Effects of Freemium Strategy in the Mobile App Market: An Empirical Study of Google Play , 2014, J. Manag. Inf. Syst..

[68]  Thomas Wiegand,et al.  WHO and ITU establish benchmarking process for artificial intelligence in health , 2019, The Lancet.

[69]  Andreas Magnusson.  Regulations for the development of medical device software , 2012 .

[70]  Laurie A. Williams,et al.  Test-driven development as a defect-reduction practice , 2003, 14th International Symposium on Software Reliability Engineering, 2003. ISSRE 2003..

[71]  Tahsin Kurc,et al.  Twenty Years of Digital Pathology: An Overview of the Road Travelled, What is on the Horizon, and the Emergence of Vendor-Neutral Archives , 2018, Journal of pathology informatics.

[72]  V. Sabatier,et al.  The role of costs in business model design for early-stage technology startups , 2020 .