Ben Glocker: "Causality matters in medical imaging"
Deep Learning and Medical Applications 2020
"Causality matters in medical imaging"
Ben Glocker - Imperial College London, Department of Computing
Abstract: We use causal reasoning to shed new light on key challenges in medical imaging: 1) data scarcity, which is the limited availability of high-quality annotations, and 2) data mismatch, whereby a trained algorithm may fail to generalize in clinical practice. We argue that causal relationships between images, annotations, and data-collection processes can not only have profound effects on the performance of predictive models, but may even dictate which learning strategies should be considered in the first place. Semi-supervision, for example, may be unsuitable for image segmentation - one of the possibly surprising insights from our causal considerations in medical image analysis. We conclude that it is of utmost importance for the success of machine-learning-based image analysis that researchers are aware of and account for the causal relationships underlying their data.
Institute for Pure and Applied Mathematics, UCLA
January 30, 2020
For more information: http://www.ipam.ucla.edu/dlm2020
Видео Ben Glocker: "Causality matters in medical imaging" канала Institute for Pure & Applied Mathematics (IPAM)
"Causality matters in medical imaging"
Ben Glocker - Imperial College London, Department of Computing
Abstract: We use causal reasoning to shed new light on key challenges in medical imaging: 1) data scarcity, which is the limited availability of high-quality annotations, and 2) data mismatch, whereby a trained algorithm may fail to generalize in clinical practice. We argue that causal relationships between images, annotations, and data-collection processes can not only have profound effects on the performance of predictive models, but may even dictate which learning strategies should be considered in the first place. Semi-supervision, for example, may be unsuitable for image segmentation - one of the possibly surprising insights from our causal considerations in medical image analysis. We conclude that it is of utmost importance for the success of machine-learning-based image analysis that researchers are aware of and account for the causal relationships underlying their data.
Institute for Pure and Applied Mathematics, UCLA
January 30, 2020
For more information: http://www.ipam.ucla.edu/dlm2020
Видео Ben Glocker: "Causality matters in medical imaging" канала Institute for Pure & Applied Mathematics (IPAM)
Показать
Комментарии отсутствуют
Информация о видео
3 апреля 2020 г. 3:49:43
00:53:36
Другие видео канала
Deep Learning in Medical Imaging - Ben Glocker, Imperial College LondonDaniel Rueckert: "Deep learning in medical imaging"[MISS 2016] Ben Glocker - Deep Learning for Brain Lesion SegmentationWarp Drive and Aliens: Bryan Gaensler Public LectureIntroducing MRI: MR Imaging of Hemorrhage (52 of 56)Stroke: The BasicsCalcium Imaging Data Cell ExtractionNext steps in health & medicine -- where can technology take us? | Daniel Kraft | TEDxBerlinFrontiers of AI in Medical Imaging for Clinical Decision MakingJustice: What's The Right Thing To Do? Episode 01 "THE MORAL SIDE OF MURDER"Paul Stamets: Mycology and Mushrooms as MedicinesDeep Learning for image segmentation - Ben Glocker - ECR 2018Types of Joints - Medical Imaging Anatomy CourseMarty Lobdell - Study Less Study SmartSchool of Medical Imaging MRI Lab - Shoulder Part INeuroanatomy made ridiculously simpleLecture 5: Optical Imaging of BrainsEKG Interpretation - Master Basics Concepts of ECGShoulder MRI (Approach to MSK MRI Series)The Epic of Gilgamesh, Lecture by Andrew George