July 19: Angel Pizarro, Scientific Computing at Amazon Web Services
September 28: Gina Tourassi, University of Tennessee, Knoxville & Paul Fearn, NIH
October 11: Anant Madabhushi, Case Western Reserve University
November 8: Hugo Aerts, Dana Farber Cancer Center / Harvard Medical School
The growing number of uses for artificial intelligence (AI), machine learning (ML) and deep learning (DL) continues to drive the development of cutting-edge technology solutions. Biomedical research and medical care are fields that are poised to be dramatic change as they start to integrate computer vision, predictive modeling, natural language understanding, and recommendation engines within standard practice. In this talk, we will review why AI and ML are hard problems to tackle, describe some cutting edge examples in biomedical research and other industries that are applying these techniques to create materially better solutions, and then dive into the details of the family of intelligent services at AWS that provide cloud-native machine learning and deep learning technologies to address a wide range of research needs. We will focus specifically on deep learning applications and products, such as the AWS Deep Learning AMI lets you run deep learning in the cloud, at any scale. Whether you’re just getting started with AI or you’re a deep learning expert, this session will provide a meaningful overview of how to improve scale and efficiency with the AWS Cloud.
Modern information systems, storage devices and recording formats have led to unprecedented growths in scientific and social data. These advancements have resulted in the Big Data (BD) paradigm – enormous data collection for processing and analyses that can provide new information not otherwise gleaned from smaller disparate data collections.
This presentation will discuss the Open Archival Information System (OAIS) reference model, to address challenges posed by BD. Examples from Earth Observing Systems and Biomedical research systems will be shown to elucidate the OAIS. An integrated reference architecture for BD life cycle management will be presented.
Intelligent biomedical archives (IBA) concept and characteristics that differentiate IBA from traditional archives will be highlighted. A functional view of the IBA will be presented for increasing transformation of data to knowledge. Scenario-based examples from biomedical research will be provided to stimulate discussion on approaches to operationalize IBA. A vision for developing true knowledge building systems for biomedical research will be shared.
This session will address the role of computer-aided diagnosis and machine learning in the practice of radiology. The debate format will address the question of whether computers will replace radiologists in 20 years. The session will include information on state-of-the-art machine learning methods, computer-aided diagnosis results, and prognostications on these tools. Impediments to computers replacing radiologists will also be described.
Pediatric cancers are the leading cause of disease-related death in children, but are defined as a rare disease when contrasted to adult tumors. Because of this classification, pediatric cancer discovery efforts are challenging due to a more limited basic and translational data-driven research infrastructure. As such, harnessing the potential for accelerated discovery through large-scale molecular/genomic data-generation and analysis platforms requires new approaches and tools for collaborative discovery on behalf of the rare disease patient-community. The Children’s Hospital of Philadelphia and its partnered consortia-based institutions have piloted a series of data-focused initiatives which span biospecimen-driven pediatric cancer research, clinical trials, data storage, analysis, and visualization platform-development. Covered in the presentation will be our experiences over the past five years in these efforts and the partnered development of CAVATICA, a data analysis platform designed to both facilitate the rapid integration and analysis of genomic data from multiple diseases affecting children and enable transdisciplinary discovery via interoperability with the Genomic Data Commons and other NIH data repositories.
- EDIT THE CALENDAR
Customise the different types of events you'd like to manage in this calendar.#legIndex/#totalLegs
- RESTRICT THE CALENDAR
Optionally, restrict who can view or add events to the team calendar.#legIndex/#totalLegs
- SHARE WITH YOUR TEAM
Grab the calendar's URL and email it to your team, or paste it on a page to embed the calendar.#legIndex/#totalLegs
- ADD AN EVENT
The calendar is ready to go! Click any day on the calendar to add an event or use the Add event button.#legIndex/#totalLegs