LNAI 12090 has just been published and is available online:
AI/ML students please read the paper “Expectations of Artificial Intelligence for Pathology” here:
Following the huge success of LNAI 9605 which has 93k downloads so far, we have collected papers on the hot and emerging topic of AI and Machine Learning for Digital Pathology for Springer Lecture Notes on Artificial Intellience (LNAI) Volume 12090.
Data driven Artificial Intelligence (AI) and Machine Learning (ML) in digital pathology (and radiology, dermatology, …) is very promising. In specific cases AI/ML approaches, particularly Deep Learning (DL), even exceed human performance (see for the difference of AI/ML/DL). However, in the context of AI in medicine it is important for a medical expert to verify the outcome, to re-trace and to re-enact on demand. Current AI models lack an explicit explanation component that allows a human expert to inerpret and understand the results and to bring in human conceptual knowledge. Consequently, there is an urgent need for transparency and re-traceability of state-of-the-art solutions to make them usable for ethical responsible medical decision support. The combined use of human intelligence and artificial intelligence for context understanding should bring important insights and new methodological solutions in this exciting emerging field.
Moreover, Machine Learning requires big data sets for training that well cover the spectrum of a variety of human diseases in different organ systems. Data sets have to meet top-end quality- and regulatory criteria and must be well annotated for machine learning at patient-, sample- and image-level. Here, biobanks play internationally a central and future role in providing large collections of high-quality well-annotated samples, data and meta data. The main challenges are finding biobanks containing ‘‘fit-for-purpose’’ samples, providing quality related meta-data, gaining access to standardized medical data and top-quality annotations, and mass scanning of whole slide images including efficient data management solutions (FAIR principle). A very important issue is information fusion, because it is more and more important to fuse together information from various data sources (images, text, *omics). Note, that we speak about information fusion, not just about data fusion and on information quality not just data quality (see also LNCS 7058).
INSTRUCTIONS FOR AUTHORS:
A) VOLUME SCOPE
Papers are sought cross-domain from Artificial Intelligence/Machine Learning for Digital Pathlogy (and related medical fields including radiology, dermatology, oncology, …), including but not limited to (alphabetically, not prioritized):
- Adversarial attacks on medical machine learning
- Biobank-sample and data quality
- Conditional random fields
- Data management of Gigapixel images
- Data preprocessing, Data mapping, Data fusion, Data integration, Data mapping
- Data provenance and data curation
- Deep Learning and alternative approaches
- Decision Support Systems
- Ethical, Social and Legal Aspects of AI
- Explainability, Causality and Causability
- Explainable AI (exAI), interpretable and transparent machine learning
- Human-AI interfaces for decision support
- Human-centered AI
- Identification of diagnostic, prognostic and theragnostic biomarkers
- Interactive Machine Learning
- Intelligent User Interfaces
- Multi-Classifier Systems
- Multiple Instance Learning
- Ontologies and Machine Learning
- Performance measures
- Privacy-Preserving Machine Learning
- Recommender systems
- Transfer Learning
- Weakly supervised learning
Each paper shall have a special structure (see below).
Papers which deal with fundamental research questions and theoretical aspects in machine learning/digital pathology are very welcome.
Quality needs time – and we want to ensure the highest possible quality, to provide a clear benefit to our potential readers; this needs careful reviewing and revision phases so we aim to complete this Volume in spring of 2020.
Please send your paper proposal directly to the editors. After invitation for submission prepare your paper following the Springer llncs2e style (llncs.cls, splncs.bst), the template can be found comfortably on Overleaf:
There is no definite page limit – but the ususal chapters are between 10 and 20 pages. However, in any case, please produce even pages to ensure smooth page breaks, e.g. 10, 12, 14, 16, 18, 20 pages.
NOTE: This State-of-the-art volume shall bring exclusive benefits for the readers and shall be of archival value on the desks and benches of both scientists, industrial practictioners, teachers and students (it is not necessary to produce rocket-science papers or Nobel-prize papers, which only a few people on this planet understand). Moreover, it shall be useful for fostering joint projects at national, European, and international level.
C) CHAPTER STRUCTURE
For this purpose each chapter is required to follow a specific structure:
- INTRODUCTION and MOTIVATION
A very short and concise introduction and motivation on why and how this chapter is important and for whom;
The used terms shall be defined at first, so that a common understanding is guaranteed;
This is the main part and may be divided into traditional subchapters accordingly;
- OPEN PROBLEMS
Here you should highlight potential known obstacles so that others can avoid to make these errors in advance;
- FUTURE OUTLOOK
This shall outline future research avenues, hot topics and research challenges of further interest;
You can refer to a successful sample Volume and look there for sample papers:
Holzinger, A. & Jurisica I. (2014). Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges, LNCS 8401, Berlin Heidelberg: Springer, 2014. https://rd.springer.com/book/10.1007%2F978-3-662-43968-5
Here you find the general Springer LNCS information page
D) CHAPTER SUBMISSION
Please submit your paper directly to one of the editors: firstname.lastname@example.org
E) REVIEW PHASE
Your paper will be assigned to at least two reviewers from our international advisory and review board, so that you will receive useful feedback on how to further improve your paper. You will get notified in due course to prepare the final version. For full transparency of the review process, you can find the review template here (scroll down to the middle of the page):
F) REVISION PHASE
To fully understand the intention of a state-of-the-art Volume you can read a draft editorial here:
Holzinger (2016) DRAFT-Editorial-Integrative-Machine-Learning-for-Health (pdf, 564kB)
Please revise your paper according to the reviewer requests and send the following three items
directly to the editors:
1) Your paper as pdf (please ensure even page numbers, e.g. … 14, 16, 18, 20, 22 … pages)
2) Your source files (LaTeX preferred – pack all source files in one single zip-folder)
3) The signed letter of consent as pdf scan –
please download the form here: LNCS-Springer-Letter-of-Consent-LNCS-SOTA-MLHealth (pdf, 68kB)
G) PRODUCTION PHASE
Your files will be carefully checked and send into production. Authors will be contacted for checking the page proofs directly by the Springer production team. The Volume is targeted to be finalized and printed end of the year 2019 – quality needs time. As a gratitude you will receive one copy of the printed volume fresh from the press.
International Scientific Advisory Board
(in alphabetic order)
Peter BANKHEAD, Centre for Genomic and Experimental Medicine, Division of Pathology, University of Edinburgh, United Kingdom
Jaesik CHOI, Statistical Explainable Artificial Intelligence Center, Statistical Artificial Intlelligence Lab, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea and affiliated with the Lawrence Berkeley National Laboratory.
Toby CORNISH, Department of Pathology, School of Medicine, Anschutz Medical Campus, University of Colorado, Aurora (CO), United States of America
Thomas J. FUCHS, Fuchs Lab, Memorial Sloan Kettering Cancer Center, New York (NY), United States of America
David Andrew GUTMAN, Gutman Lab, Department of Biomedical Informatics, Emory University School of Medicine, Atlanta (GA), United States of America
Randy GOEBEL, explainable AI Lab, Alberta Machine Intelligence Insitute (amii), University of Alberta, Canada
Anant MADABHUSHI, Center for Computational Imaging & Personalized Diagnostics, Department of Biomedical Engineering, Case Western Reserve University, Cleveland (OH), United States of America
Craig MERMEL, Digital Pathology, Google Brain (AI), Mountain View, Santa Clara (CA), United States of America
Liron PANTANOWITZ, Department of Pathology, University of Pittsburgh Schools of Health Sciences (UPMC), Pittsburgh, United States of America
Christin SEIFERT, Data Science group, University of Twente, Enschede, The Netherlands
Klaus-Robert MÜLLER, Machine Learning Group, TU Berlin, Germany and Korea University, Seoul, South Korea
Nasir M. RAJPOOT, Tissue Image Analytics (TIA) Lab, Department of Computer Science, University of Warwick, UK
Kurt ZATLOUKAL, Diagnostic and Research Center for Molecular BioMedicine, Medical University Graz, Austria
Jianlong ZHOU, Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia
We thank all the additional reviewers from the international research community!