Digitising surgery with AI

Lecturer: Imanol Luengo (Medtronic)

AI has the potential to impact surgical care. At Digital Surgery, we apply state-of-the-art computer vision technology to understand surgical processes. In this talk, an overview will be given on the challenges and successes on building scalable AI technology for surgery.

(Title TBC)

Lecturer: Annemie Ribbens (icometrix, Belgium)

Clinical Imaging in Drug Development, Where are the Opportunities?

Lecturer: Marius de Groot (GSK)

Medical imaging provides crucial insight into biology and treatment response for drug development. But what makes an imaging technique or biomarker a good fit? In this talk we’ll explore the drug development trajectory and link this to opportunities for medical imaging to impact decision making. This will take us on a journey from mechanistic and proof of concept biomarkers to efficacy endpoints and finally companion diagnostics. What is possible today, and how do we prepare the imaging techniques of tomorrow?

Tomographic image reconstruction with learnt priors

Lecturer: Marta Betcke (UCL CMIC and CIP)

Recent advances in deep learning for tomographic reconstructions have shown a great promise to create accurate and high quality images from subsampled measurements in a time considerably shorter than needed by the established nonlinear regularisation methods such as e.g. Total Variation. This new paradigm also offers a new implicit way of expressing prior knowledge through training on a class of images with expected characteristics.  

Robotics for Healthcare at WEISS

Lecturer: Agostino Stilli (UCL CMIC and WEISS)

This talk will focus on the emerging robotic solutions developed at WEISS in the context of surgery and the associated challenges of realtime imaging processing.

Paediatric Radiotherapy: The Past, Present and Future.

Lecturer: Pei Lim (NHS)

Radiotherapy is an essential component in the management of paediatric cancers. This talk will discuss the current state-of-the-art techniques for paediatric radiotherapy, explore the challenges and future developments in this field.

Imaging the fetus and placenta for diagnosis and therapy

Lecturer: Roz Aughwane (NHS)

In this talk we will explore life before birth and how it can impact on future health. We will discuss how we utilise imaging in diagnosis and therapy for the fetus and placenta, and the challenges presented by the uterine environment. Finally, we will explore some of the exciting research that which is improving our understanding of placental function and will ultimately impact on future patient care.

Computer-assisted interventions

Lecturer: Esther Bonmati Coll (UCL CMIC)

In this lecture I will talk about computer-assisted interventions, and I will briefly explain the different components which are often present in this type of systems. I will also introduce two systems developed at UCL: one for guiding prostate biopsy and another one for guiding endoscopic ultrasound interventions. During the talk we will also see the current challenges and opportunities when using artificial intelligence to solve some of the clinical problems.

Bridging the gap between research and patient care: Quantitative Neuroradiology Initiative

Lecturer: Frederik Barkhof (UCL CMIC and Amsterdam UMC)

MRI is the main imaging modality for the workup in many brain disorders, such as multiple sclerosis (MS), dementia, epilepsy, tumours. In daily Radiology practice, scans are evaluated using visual inspection and the support of rating scales. For research purposes, more sensitive and accurate quantitative image analysis methods have been developed, to determine brain atrophy, MS lesion burden and tumour growth for group analyses, as well as AI-based techniques for pattern recognition and classification. Currently, those sophisticated techniques – developed for group-wise comparisons – are not used in clinical patient care. This translational gap is hard to bridge due to differences between research versus clinical scan quality and lack of PACS environment integration. The Quantitative Neuroradiology Initiative (QNI) aims to bridge this gap by integrating quantification in the clinical workflow to allow patients to benefit from the tools developed by CMIC.