Title Artificial intelligence and machine learning for digital pathology : state-of-the-art and future challenges / Andreas Holzinger, Randy Goebel, Michael Mengel, Heimo Müller (eds.)

Published Cham, switzerlandr : Springer Nature ; Springer, [2020]

Click on the following:
Springer eBooks
Springer Computer Science eBooks

Copies

Description 1 online resource Series Lecture notes in artificial intelligence Lecture notes in computer science ; 12090 LNCS Sublibrary: SL 7, Artificial Intelligence Lecture notes in computer science. Lecture notes in artificial intelligence. Lecture notes in computer science ; 12090. LNCS sublibrary. SL 7, Artificial intelligence. Contents Intro -- Preface -- Organization -- Contents -- About the Editors -- Expectations of Artificial Intelligence for Pathology -- 1 Introduction and Motivation -- 1.1 What Is the Difference Between Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL)? -- 1.2 Is Pathology an Uncomplicated Medical Speciality? -- 2 Glossary -- 3 State-of-the-Art -- 3.1 The Position of AI in Pathology Today? -- 3.2 Where Could Pathologists Need Support by AI? -- 4 Open Problems -- 5 Future Outlook -- References Interpretable Deep Neural Network to Predict Estrogen Receptor Status from Haematoxylin-Eosin Images -- 1 Introduction and Motivation -- 2 Glossary -- 3 State of the Art -- 3.1 Prediction of er Status Using nn -- 3.2 Post-hoc Model Explanation -- 4 Methods -- 4.1 Data and Preprocessing -- 4.2 Training and Evaluation -- 4.3 Visual Explanation of er Status Predictions -- 5 Experiments -- 5.1 Hyperparameter Tuning and Performance Evaluation -- 5.2 Comparison to a State-of-the-Art Method -- 5.3 Variance over the Splits -- 5.4 Rejection Option -- 5.5 Visual Explanation -- 6 Discussion -- 7 Conclusion 8 Open Challenges and Future Work -- References -- Supporting the Donation of Health Records to Biobanks for Medical Research -- 1 Introduction -- 2 A Motivating Scenario -- 3 ELGA -- A Prototypical Mediator of Health Records -- 4 Stakeholders -- 4.1 Donors -- 4.2 Researchers -- 4.3 General Public -- 4.4 Health Care Providers -- 4.5 Mediators -- 5 Laws and Regulations -- 5.1 European General Data Protection Regulation -- 5.2 Laws Governing Health Data Mediators -- 6 Interoperability Requirements -- 6.1 ELGA Infrastructure -- 6.2 ELGA Documents -- 7 Incentivizing Data Donation by Building Trust 7.1 Security and Privacy -- 7.2 Access Control and Monitoring -- 7.3 Information -- 7.4 Ethical Principles -- 7.5 Informed Consents -- 8 Electronic Informed Consent with Disclosure Filters -- 8.1 Example -- 8.2 Electronic Informed Consent (eIC) -- 8.3 Disclosure Filter Specification -- 9 Discussion and Conclusions -- References -- Survey of XAI in Digital Pathology -- 1 Introduction and Motivation -- 1.1 Background -- 1.2 AI in Pathology -- 1.3 Needs of XAI in Digital Pathology -- 2 Glossary -- 3 State-of-the-Art -- 3.1 Explanation Target -- 3.2 Result Representation -- 3.3 Technical Approach 3.4 XAI Methods in Medical Imaging -- 4 Open Problems -- 5 Future Outlook -- A Reviewed Methods -- References -- Sample Quality as Basic Prerequisite for Data Quality: A Quality Management System for Biobanks -- 1 Introduction and Motivation -- 2 Glossary -- 3 State-of-the-Art -- 3.1 The Quality Management Concept of GBN -- 3.2 QM Manual -- 3.3 Software Solution -- 3.4 Friendly Audits -- 3.5 Ring Trials -- 3.6 Satisfaction Survey for Biobank Users -- 4 Challenges and Opportunities -- 5 Outlook -- References Summary Data driven Artificial Intelligence (AI) and Machine Learning (ML) in digital pathology, radiology, and dermatology is very promising. In specific cases, for example, Deep Learning (DL), even exceeding human performance. However, in the context of medicine it is important for a human expert to verify the outcome. Consequently, there is a need for transparency and re-traceability of state-of-the-art solutions to make them usable for ethical responsible medical decision support. Moreover, big data is required for training, covering a wide spectrum of a variety of human diseases in different organ systems. These data sets must meet top-quality and regulatory criteria and must be well annotated for ML at patient-, sample-, and image-level. Here biobanks play a central and future role in providing large collections of high-quality, well-annotated samples and data. The main challenges are finding biobanks containing ''fit-for-purpose samples, providing quality related meta-data, gaining access to standardized medical data and annotations, and mass scanning of whole slides including efficient data management solutions Bibliography Includes bibliographical references and index Notes Online resource; title from digital title page (viewed on August 10, 2020) Subject Pathology -- Data processing Artificial intelligence -- Medical applications. Machine learning. Pathology -- methods5 Machine Learning Pathology -- Data processing Machine learning Artificial intelligence -- Medical applications Form Electronic book Author Holzinger, Andreas. Goebel, Randy. Mengel, Michael Müller, Heimo ISBN 3030504026 9783030504021

  Permalink