Search Courses

Machine Learning in Dosimetry: Why We Shouldn’t Fear A.I.

Course Details

MDCB Credits: 1.00

ARRT Credits: 1.00

Available Until: 10/31/2020

Non-Member Price: $35.00

Member Price: $20.00

Member PLUS Price: $20.00

Add to My Course Library

Once you have exceeded your annual free credit allowance you will be prompted to pay a per-credit fee.

Courses purchased using your credit allowance are non-refundable and need to be completed before their expiration date

View your annual credit allowance here.

Presented by Mark Gooding, DPhil
Chief Scientist
Mirada Medical Ltd

Recorded June 19, 2019
From the AAMD 43rd Annual Meeting

NOTE: If you earned CE Credits for this session during the AAMD 43rd Annual Meeting, you will not be eligible to earn CE Credits for it again.

Artificial Intelligence (AI) is often in the news at the moment, whether it is computers beating humans at games such as Go, autonomous cars taking to the streets, or social media chatbots starting to behave inappropriately. The same is true in healthcare with AI being heralded for a wide range of clinical applications such as lung nodule CAD, image segmentation and treatment personalization.

Unsurprisingly, AI is also emerging in the field of radiotherapy, with great performance being seen in applications ranging from basic tasks such as scheduling, through contouring and planning, all the way to decision support. At the same time, many famous people speak warnings of the potential dangers of uncontrolled AI, regulatory authorities being to struggle an emerging type of device, and at a basic level, we ourselves may fear a technology that we do not understand. The purpose of this session is to provide that understanding and look to how we can adopt AI to our benefit rather than fear it.

In this session we will explore the basic principles of machine learning and AI with tangible examples rather than math, learning the strengths and weaknesses of AI compared to other technology solutions to similar tasks. We will consider current and near-future applications in radiotherapy, looking at the potential benefits that AI may bring and the changes that could cause. Looking at clinical implementation, we will consider what approaches we might adapt to the validation of AI-based technology.

Learner Outcomes:

  1. The basic principles of Machine Learning and AI 
  2. The strength and limitations of AI compared to other technology solutions 
  3. How AI is being deployed in radiotherapy applications 
  4. Approaches to validation of AI in radiotherapy

Presenter:
Dr. Mark Gooding obtained his DPhil in Medical Imaging from University of Oxford in 2004. He was employed as a postdoctoral researcher both in university and NHS settings, where his focus was largely around women’s health. In 2009, he joined Mirada Medical, motivated by a desire to see technical innovation translated into clinical practice. While there, he has worked on a broad spectrum of clinical applications, developing algorithms and products for both diagnostic and therapeutic purposes., If given a free choice of research topic, his passion is for improving image segmentation, but in practice, he is keen to address any technical challenge. Dr Gooding now leads the science team at Mirada, where in addition to the commercial work he continues to collaborate both clinically and academically