By Anirban Mukhopadhyay
AI-ready HealthcareSep 04, 2023
Dan Hashimoto: Making surgery AI-ready
Daniel Hashimoto is an assistant Professor of Surgery at the Hospital of the University of Pennsylvania, USA. Dan has developed multiple computer vision algorithms for the analysis of surgical video, led international consensus on defining ground truth for the annotation of surgical video, and worked to define metrics to assess performance of AI algorithms on surgical tasks. His work has been published in the New England Journal of Medicine, Nature Biotechnology, Annals of Surgery, and other journals. He is editor of the textbook Artificial Intelligence in Surgery: Understanding the Role of AI in Surgical Practice. He is also heavily involved in MICCAI society with a focused attention to CLINICCAI.
Stephen Gilbert: AIaMD regulations
Prof. Stephen Gilbert is a professor in Medical Device Regulatory Science at the Else Kröner Fresenius Center for Digital Health in TU Dresden, Germany. His research goal is to advance regulatory requirements, especially for software as a medical device and artificial intelligence in medical devices.
Papers we discussed: Large language model AI chatbots require approval as medical devices
Nitika Pai: Global Digital Health
Prof. Nitika Pai is an Associate Professor in the Department of Medicine at the McGill University, Canada. Her global implementation research program in Canada, India and South Africa is primarily focused on point-of-care diagnostics for HIV and associated co-infections. Her research informs domestic and global policy on point-of-care diagnostics.
Swapnil Rane: Indian Image BioBank
Prof. Swapnil Rane is a Pathologist by training, and currently a professor in Tata Memorial Center, Mumbai, India. He is instrumental in bringing forward the AI and digital pathology research from India, especially the ongoing project of Indian Image BioBank.
Ishita Barua: Gender gap in health data
Dr. Ishita Barua leads AI in healthcare at Deloitte, with a focus on improving equity and outcomes in digital health. She is a medical doctor and PhD by training with expertise in application and clinical validation of AI in Medicine. Ishita has won numerous awards including Top 50 women in tech and top 30 women in Norway shaping the field of artificial intelligence.
Raphael Sznitman: AI-powered Eye Surgery
Prof. Raphael Sznitman is the Director of the ARTORG center for Biomedical Engineering at the University of Bern (Switzerland). Raphael is interested in computational vision, probabilistic methods and statistical learning, applied to applications in medical imaging.
Instead of having a guest, Anirban and Henry just chit chats about the background stories, lessons learned, our ever-evolving thoughts etc. in the 50th episode of AI-ready Healthcare.
Nikos Paragios: AI-guided Precision Radiotherapy
Prof. Nikos Paragios is a senior researcher focusing on computer vision and medical imaging. Nikos is a professor of Computer Science and Applied mathematics at CentraleSupélec, an affiliated scientific leader at INRIA while serving as the editor in chief of the Computer Vision and Image Understanding Journal. Nikos is also the founder and CEO of TheraPanacea, provider of AI-powered software for more efficient radiotherapy workflow.
Lene Topp: Science4Policy
Lene Topp is passionate about designing and delivering training and other capacity building activities primarily for researchers looking to increase the impact of their research in policy sectors. Until February 2023, she worked in the European Union's Joint Research Center focusing on the "Science4Policy" gap. Among many other things, she led the development of Smart4Policy researchers tool to help researchers working in science-for-policy reflect on their level of competence. .
Stefanie Speidel: Simulation in Surgical Data Science
Prof. Stefanie Speidel is a full professor for “Translational Surgical Oncology” and director at the National Center for Tumor Diseases Dresden since 2017. She is an elected board member of the MICCAI society. She is well-know for her research on Surgical Data Science, data-driven surgical training and context-aware human-machine collaboration in the operating room.
Sotirios Tsaftaris: Causal Representation Learning
Prof. Sotirios Tsaftaris is the Chair in Machine Learning and Computer Vision at the University of Edinburgh, UK. He also holds the Canon Medical/Royal Academy of Engineering Research Chair in Healthcare AI. He is also a Turing Fellow with the Alan Turing Institute and an ELLIS Fellow.
Pascal Wettstein: FDA or MDR? Where should SMEs go for their AI SaMD
Pascal Wettstein is the owner of QDC GmbH. He is the self-proclaimed "SME safari guide in the regulatory jungle." I highly recommend his rather sarcastic LinkedIn posts on European Medical Device Regulations. Beyond Europe, he has extensive knowledge about the 510K regulations in FDA.
Sharib Ali: AI-powered Endoscopic Image Analysis
Sharib Ali is the lecturer at School of Computing in the University of Leeds, UK. He has a PhD from France and spent time as a PostDoc in Germany as well as in Oxford before starting as the PI in Leeds. He is well-known for his research on AI for analyzing Endoscopic images.
The two articles we discussed in this episode:
Jocelyne Troccaz: MICCAI impacting Prostrate Biopsy
Prof. Jocelyne Troccaz is a legendary figure in image-guided medical robotics, with a career spanning across four decades. She covered a broad spectrum of applications including urology, radiotherapy, cardiac surgery, orthopedics to name a few. She won numerous awards. Some highlights include MICCAI 2022 enduring impact award and the highest French decoration (Légion d’Honneur).
Monir El Azzouzi: Medical Device Regulation of AI SaMD
Monir El Azzouzi created the Easy Medical Device ecosystem, that includes blogs, podcasts, YouTube videos and regular updates in LinkedIn. His mission is to make the process of bringing Compliant Medical Device to the Market easier. He has a deep understanding of the Medical Device Regulations at European Union.
Easy Medical Device: https://easymedicaldevice.com/home/
Monika Sonu: Frugal digital health innovation
Dr. Monika Sonu is a physician by training and Digital Health Entrepreneur by passion. She is the CEO of Health Innovation Toolbox. Monika drives digitisation of the operating models, functions and workflows within hospitals. She is also interested in creating better patient experience. She is named as HIMSS Future50 Innovation Leader in 2021.
Purang Abolmaesumi: Telehealth = POCUS+AI
Professor Purang Abolmaesumi is a Professor in University of British Columbia. He is very well-known within the MICCAI community for his research on Ultrasound imaging. Purang won numerous awards and honors. Some highlights would include being the 2020 MICCAI fellow and winning the Killam faculty research prize.
Joseph Kvedar: Nurturing Digital Health through Nature
Prof. Joseph Kvedar is THE expert in terms of telehealth and digital health. He is leveraging information technology, such as cell phones, computers, networked devices and remote health monitoring tools to improve care delivery. He is a Professor of Dermatology at Harvard Medical School, and vice president of Partners healthcare. He is also the editor-in-chief of npj Digital Medicine.
Andrew Janowczyk: Quality Assurance in histopathology images
Andrew Janowczyk is an assistant professor at Emory University, USA. Andrew’s research focuses on applying computer vision and machine learning algorithms to digital pathology. His key area of expertise is in leveraging deep learning to build computational models for aiding pathologists in many common tasks, such as disease detection and cancer grading.
Robert MacDougall: Quantivly's digital twin of radiology operations
Daniel Rückert: Federated Disentanglement
Professor Rückert’s field of research is the area of Artificial Intelligence (AI) and Machine Learning and their application to medicine and healthcare. His research focuses on (1) the development of innovative algorithms for biomedical image acquisition, image analysis and image interpretation – especially in the areas of image reconstruction, registration, segmentation, tracking and modelling; (2) AI for extracting clinically useful information from biomedical images – especially for computer-assisted diagnosis and prognosis. Since 2020, Daniel Rückert is Alexander von Humboldt Professor for AI in Medicine and Healthcare at the Technical University of Munich. He is also a Professor at Imperial College London.
Jakob Nikolas Kather: Swarm intelligence for Oncology
Jakob Nikolas kather is a professor at Technical University Dresden, leading the department of Clinical Artificial Intelligence at Else Kroener Fresenius Center for Digital Health. As a physician, he specializes in Internal Medicine and gastrointestinal oncology. As a researcher, he focuses on deep learning for immunotherapy biomarkers in cancer.
Prateek Prasanna: Augmenting Radiologist's Knowledge into AI
Prateek Prasanna is an assistant professor in the Biomedical Informatics department at Stony Brook University, New York. He directs the Imaging Informatics for Precision Medicine Lab. His research interests lie at the intersection of medical image analysis and machine learning. We talked about the following papers:
Sailesh Conjeti: MLOps for Healthcare AI
Sailesh Conjeti is on a mission to bring AI-based solutions to Healthcare and translating them to clinical use to make a difference. He is the Functional Lead of Data Science at Siemens Healthineers. You can read his blogposts at https://www.saileshconjeti.com/blog.
Ismini Lourentzou: Chest ImaGenome
Ismini Lourentzou is an Assistant Professor of Computer Science at Virginia Tech. Prior to VT, she spent a year as research scientist (Research Staff Member) at IBM Almaden Research Center, working on Machine Learning, Natural Language Processing and Information Retrieval problems. Her research interests are broadly defined at the intersection of Data Science, Big Data, Machine Learning, and Artificial Intelligence.
Chest ImaGenome Dataset for Clinical Reasoning: https://openreview.net/forum?id=H-d5634yVi
Matthias Unberath: Forgotten Humans of Explainable AI
Mathias Unberath is an assistant professor in the Department of Computer Science, and is affiliated with the Laboratory for Computational Sensing and Robotics and the Malone Center for Engineering in Healthcare. With his group—the Advanced Robotics and Computationally AugmenteD Environments (ARCADE) Lab—he advances healthcare by creating collaborative intelligent systems that support clinical workflows. Through synergistic research on imaging, computer vision, machine learning, and interaction design, he builds human-centered solutions that are embodied in emerging technology such as mixed reality and robotics.
Pre-print of the paper we discussed: https://arxiv.org/pdf/2112.12596v1.pdf
Taufique Joarder: Policy Questions of Healthcare AI
Taufique Joarder is a health policy and systems researcher and a university faculty. He has thirteen years of national and international experience and a doctorate in public health with expertise in health policy and systems research, teaching and training as well as extensive publishing. His background also includes higher leadership positions in NGOs/CSOs, faculty positions, policy-relevant engagements in Bangladesh and abroad, and extensive media involvement (as an expert, guest discussant, moderator, and TV anchor).
Stephen Aylward: The case of Open-source software
Stephen Aylward, Ph.D., is the senior director of strategic initiatives and founder of Kitware’s North Carolina office. He helps drive multiple research and open source software development projects at Kitware. Over the past 25+ years, Stephen has conducted medical image analysis research covering nearly every aspect of health care, including screening, diagnosis, treatment planning, guidance, and outcome assessment for mammography, neurosurgery, partial liver transplantation, retinopathy of prematurity, stroke, traumatic brain injury, pre-clinical cancer studies, and others. He has also been instrumental in the creation of the Insight Toolkit (ITK), major updates to 3D Slicer, and the development of new technologies and the VTK.js library for web-based scientific visualization.
Lena Maier-Hein: What does it mean to win a Biomedical Challenge?
Lena Maier-Hein is the head of the Computer Assisted Medical Interventions (CAMI) department at the German Cancer Research Center (DKFZ) in Heidelberg, Germany. Her research focuses on Surgical Data Science and rankings of biomedical challenges.
Russ Taylor: The role of AI in Robotic Surgery
Russ Taylor is the father of robotic surgery. Hi is the John C. Malone Professor in the Department of Computer Science, and the director of the Laboratory for Computational Sensing and Robotics. His research has focused on all aspects of computer-integrated interventional medicine. Broadly, this research has included:
- Medical robotics
- Medical imaging & modeling and
- Complete systems for surgical assistance, image-guided surgery, and "Surgical CAD/CAM".
An underlying theme has been the basic insight that information-based technologies can have just as profound an impact on computer-integrated medicine as it has had on computer-integrated manufacturing.
Ilker Hacihaliloglu: Ultrasound for all
Ilker is interested in the extraction of relevant information from three dimensional (3D) medical images by developing state of the art computational algorithms for image guided surgery and therapy applications. The main objective of his research is to study and model medical procedures and introduce advanced computer integrated solutions to improve their quality, efficiency, and safety.
Frank Xu: Baidu's AI, WHO's Digital Health & other stories
Frank (Yanwu) Xu, is an Intelligent Healthcare Scientist (research lead) at Baidu, an Adjunct Professor at Ningbo Institute of Materials Technology & Engineering, the Chinese Academy of Sciences (CAS), and an Adjunct Principal Investigator at Singapore Eye Research Institute. Frank is also serving the World Health Organization (WHO) as a technical advisory group member of Digital Health and an expert group member of Data Principles and Sharing Policies.
Lorenzo Righetto: Publishing MICCAI research into Nature Communications
Lorenzo Righetto is an associate Editor of Nature Communications where he handles manuscripts in the area of digital medicine and computational health. Lorenzo joined Nature Communications in January 2020. Lorenzo is based in the London office.
Karsten Ridder: Communication is key for AI-ready Healthcare
Karsten Ridder is a practicing radiologist from Dortmund, Germany with a special focus on Women's Health Imaging and Cardiovascular Imaging. He received numerous awards for his clinical research and innovation, including German Medical Award for Innovation in 2021.
Shuo Li: Will MICCAI 2022 be virtual?
Julia Schnabel: MICCAI goes to Africa
Julia Schnabel is the Professor for Computational Imaging and AI in Medicine at TUM (TUM Liesel Beckmann Distinguished Professorship), jointly with Helmholtz Center Munich (Helmholtz Distinguished Professorship). Her research focuses on intelligent imaging solutions and computer aided evaluation, including complex motion modelling, image reconstruction, image quality control, image segmentation and classification, applied to multi-modal, quantitative and dynamic imaging. She is the co-general chair of MICCAI 2024, the first MICCAI in Africa. She often Tweets @ja_schnabel.
Anant Madabhushi: When MICCAI scientist meets Real Clinicians
Anant Madabhushi is the Donnell Institute Professor of Biomedical Engineering at Case Western Reserve University (CWRU) in Cleveland and director of the university's Center for Computational Imaging and Personalized Diagnostics (CCIPD). He is a Research Scientist at the Louis Stokes Cleveland Veterans Administration (VA) Medical Center and has affiliate appointments both at University Hospitals and Cleveland Clinic. He holds secondary appointments in the departments of Urology, Radiology, Pathology, Radiation Oncology, General Medical Sciences, Computer & Data Sciences, and Electrical, Computer and Systems Engineering at CWRU. We talked about his research on translation of AI to clinical oncology. He tweets regularly @anantm.
Leo Joskowicz: Shaping up AI and MICCAI
Leo Joskowicz is a pioneer of Computer Assisted Intervention and the President of MICCAI society. He is a professor at the School of Engineering and Computer Science at the Hebrew University of Jerusalem. In this episode, we explore his interest in Geometry, Shape and making MICCAI society a home to all scientists working in medical imaging problems, no matter their geographical location.
Dan Stoyanov: Surgical Data Science 101
Dan Stoyanov is a Professor of Robot Vision in the Department of Computer Science at University College London, Director of the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), Royal Academy of Engineering Chair in Emerging Technologies and a Fellow of the Institution of Engineering and Technology. Dan is also Chief Scientific Officer at Digital Surgery Ltd and Co-Founder of Odin Medical, both companies specializing in developing AI products for interventional healthcare. You can follow Dan on Twitter @DanStoyanov.
John Mongan: To buy or not to buy radiology AI
John Mongan is the Associate Chair for Translational Informatics, Director of the Center for Intelligent Imaging and an Associate Professor of Clinical Radiology (Abdominal Imaging and Ultrasound section) in the Department of Radiology and Biomedical Imaging at the University of California, San Francisco. His research focuses on AI in medical imaging. In this session, we discussed the business case of Radiology AI and his Checklist for Artificial Intelligence in Medical Imaging (CLAIM).
You can find him in Twitter @MonganMD.
Qi Dou: Federated Learning for radiology
Qi Dou is an Assistant Professor from The Chinese University of Hong Kong. Her research focus is on the interdisciplinary field of medical image analysis, artificial intelligence and robotics. In this episode, we talked about the importance of Federated Learning in medical imaging and in particular, her paper Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study. You can find her in Twitter @QiDou_.
Andreas Maier: Known operator learning for medical imaging
Professor Andreas Maier leads the Pattern Recognition Lab of Friedrich-Alexander-Universität of Erlangen-Nürnberg. In this episode, we discussed his research on Known Operator Learning and in particular his paper Learning with known operators reduces maximum error bounds. You can find him in Twitter @maier_ak.
Alex Frangi: Unlocking In-silico clinical trials
Professor Alex Frangi is Diamond Jubilee Chair in Computational Medicine and Royal Academy of Engineering Chair in Emerging Technologies at the University of Leeds, Leeds, UK, with joint appointments at the School of Computing and the School of Medicine. He directs the CISTIB Center for Computational Imaging and Simulation Technologies in Biomedicine. In this episode, we discuss computational medicine, the promises of in-silico trials and his new paper In-silico trial of intracranial flow diverters replicates and expands insights from conventional clinical trials.
Yuri Tolkach: Silent Failures of Deep Digital Pathology
Dr. Yuri Tolkach, a pathologist and researcher from Uniklinik Köln, is breaking new grounds in digital pathology with probing questions about the usability of deep learning. In this episode, we discussed in great details his recent article on Quality control stress test for deep learning-based diagnostic model in digital pathology.
Marius Linguraru: Making babies fitter - within MICCAI and beyond
Marius Linguraru is a principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children's National Hospital in Washington, D.C. Dr. Linguraru is also professor of Radiology and Pediatrics and secondary professor of Biomedical Engineering at George Washington University. He co-founded PediaMetrix Inc., a company focused on infant well-being by creating solutions to improve the management of conditions of early childhood. Finally Dr. Linguraru is a board member of MICCAI society with a focus on early career development of young researchers. In this episode we discussed in depth about his research on pediatric health and his activities for the MICCAI society.
Arijit Patra: Big-Pharmas need imaging AI, and they don't know it yet!
Arijit Patra, a senior machine learning scientist from AstraZeneca, discusses how AI can significantly speed-up pre-clinical imaging. He also discussed his PhD thesis on continual learning for fetal ultrasound imaging.
Indranil Mallick: Why Indian healthcare needs AI post COVID? Reflections of a Radiation Oncologist
Indranil Mallick, a practicing oncologist from India, asserts the necessity of AI in Radiation Oncology. His reflections of practicing Oncology through the two waves of the pandemic in India is a reminder, how varied the demands are of the AI-readiness of healthcare across the globe.
Michal Rosen-Zvi: Underwhelming maturity of Radiology AI in COVID-19 imaging
Michal Rosen-Zvi, director of IBM Research's healthcare informatics, talks about her perspective on the usefulness of radiology AI during the pandemic. In particular, we discussed her recently published article On the role of artificial intelligence in medical imaging of COVID-19.
With multiple articles describing similar concerns, this is a timely episode about a very relevant topic. Further reading:
Daniel Pinto dos Santos: Get your radiology report structured, have some ECLAIRS!
We chatted with the radiologist Dr. Daniel Pinto dos Santos about his research in deep learning for radiology. We focused on two of his recent articles. You can read both open-access article right here:
Terry Peters: Beware of the nasty surprises from healthcare AI
Prof. Terry Peters tackles problems related to Image-guided interventions with a special focus on intra-operative navigation. While majority of MICCAI society is whole-heartedly embracing AI, Prof. Peters, a MICCAI fellow, voices his skepticism in some of the research directions. He cautions about proper standardization and interpretability of healthcare AI. Very important lessons for the majority of young members within MICCAI society.