The utilisation of medical imaging biomarkers to better understand the efficacy of cancer drugs, aided by the power of AI.
Oncology clinical trials would benefit greatly from new biomarkers that could help to better understand the efficacy of drug treatments. Growth rate (‘g’) of tumour derived by appropriate tumour growth rate (TGR) modelling, as well as quantitative estimation of tumour heterogeneity through radiomics are two processes that offer such oncological imaging biomarkers.
Response evaluation criteria in solid tumours (RECIST) 1.1 and other similar criteria for tumour burden assessments have been used conventionally for the investigation of tumour inhibitory effect of cancer drugs. A large sample size is commonly required for both a reliable estimation of overall survival from such criteria, and to differentiate from the control arm. However, the ‘g’ value obtained through effective TGR modelling may provide a more efficient alternative to understanding drug efficacy using a lower sample size.
Radiomics is the extraction of quantitative metrics from medical images that characterise tumour heterogeneity. Radiomic features (both cross sectional and longitudinal changes) have been associated with tumour aggressiveness and may predict clinical and clinical trial end points like survival.
In this webinar, we will discuss the basics of TGR modelling from tumour imaging data, as well as radiomics. We will also look at how AI can be harnessed for a more automated tumour volume detection, and how this can aid with simultaneous assessment of both ‘g’ as well as radiomics features.
What you will learn:
- The need for reliable estimation of inhibitory effect of oncological drugs using lower sample size.
- Various models for estimation of tumour growth rate (‘g’), including exponential models.
- The value and pitfalls of tumour characterisation using radiomics.
- The advantages of volumetric assessment of tumour size when compared to conventional line measurements.
- How the power of AI can be harnessed to facilitate better extraction of tumour volume.
Paul McCracken, PhD
Vice President, Global Head of Medical Imaging, ICON
Dr. McCracken is the Global Head of ICON Medical Imaging. Paul has over 20 years’ experience in imaging and pharmaceuticals, with a strong track record of applying imaging and biomarkers to drug discovery and development across a range of therapeutic areas.
Ramkumar Krishnamurthy, PhD
Medical Imaging Scientist II, ICON
Ramkumar is a Medical Imaging Scientist and MRI Physicist with over 15 years clinical imaging experience, including body and cardiovascular imaging. He was also the technical manager for the advanced imaging clinical lab for many years, working with advanced processing of imaging data, including tumor imaging metrics.
Meena Makary, PhD
Medical Imaging Scientist II, ICON
Meena is a Medical Imaging Scientist with over 8 years of clinical imaging experience including multimodal neuroimaging and AI. Prior to ICON, he completed his postdoctoral fellowships at Yale and Harvard Universities for 4 years focusing on understanding the neural basis of several psychiatric and neurodegenerative disorders. At ICON, Dr. Makary is working on developing advanced imaging analysis tools and AI algorithms.
Studying ‘g’ and radiomics features at initial phases of drug trials may help the study team gain early insight into drug efficacy. This webinar will be helpful for all who are involved in the study design of drug trials, especially:
- Medical Directors
- Imaging Scientists
- Operational Leaders