- Tomorrow's Dose
- Posts
- Edition 8 - AI & Radiotherapy: Uncovering Cardiac Risks and Predicting Cancer Treatment Success
Edition 8 - AI & Radiotherapy: Uncovering Cardiac Risks and Predicting Cancer Treatment Success
Discover how AI is identifying heart risks in lung cancer treatment and revolutionizing chemotherapy predictions.
AI segmentation uncovers connection between lung cancer radiotherapy and heart complications
‘Game changing’ technology which can predict how patients will respond to cancer treatment
European Society of Radiology award won by research radiographer.
Featured follow of the week
Top posts of the week across social
Meet the editor
Want a featured article?
Specialty: Radiotherapy // Sub-Specialty: Prognosis // Body Site: Cardiac
1. AI segmentation uncovers connection between lung cancer radiotherapy and heart complications
Researchers in Massachusetts conducted a retrospective analysis on 748 patients, who were treated with radiation for locally advanced NSCLC. They classified the types of arrhythmias associated with cardiac substructures receiving radiation into a number of subtypes: atrial fibrillation, atrial flutter, other supraventricular tachycardia, bradyarrhythmia, and ventricular tachyarrhythmia or asystole. It was found that about one out of every six patients experienced at least one grade 3 (serious events that likely need intervention or require hospitalization) arrhythmia with a median time of 2.0 years until the first arrhythmia. They also found that almost one-third of patients who experienced arrhythmias also suffered from major adverse cardiac events.
Read Full Article
Paul’s Thoughts:
An interesting part of this study was the use of AI to segment structures such as the pulmonary vein and parts of the conduction system to measure the radiation dose exposure in over 700 patients, saving many months of manual work. As well as AI autocontouring offering a benefit for future patients, this work shows its potential application in retrospective work. I expect we will see more centres applying autocontouring to retrospective data and correlating the dose to those structures with patient outcomes and complications.
Timescale: Early | 3 Years
Specialty: Radiology // Sub-Specialty: Radiomics // Body Site: Gyn
2. ‘Game changing’ technology which can predict how patients will respond to cancer treatment
IRON (Integrated Radiogenomics for Ovarian Neoadjuvant therapy), an AI prediction tool, allows researchers to predict whether chemotherapy would be effective during a study involving 134 women at two centres. Alongside clinical data and patients’ general characteristics – including age and disease status – IRON uses augmented radiomics to scan CT images, measure lesions, and reveal patterns in tumours and tissues that the human eye cannot detect. In the external cohort the integrated radiomics model reduces the prediction error by 8% with respect to the clinical model, achieving an AUC of 0.78 for RECIST 1.1 classification compared to 0.47 for the clinical model.
Read Full Article
Paul’s Thoughts:
Most patients are given chemotherapy to shrink tumours ahead of primary surgery to remove them, however 39% of women do not respond to the chemotherapy, which only serves to delay the surgery. But the IRON tool may allow us to estimate who might benefit from these treatments and who might need alternatives, so changes can be made to the treatment sooner. It also allows us to discover reasons why patients are not responding to chemotherapy.
Timescale: Early | 3 Years
Specialty: Radiology // Sub-Specialty: Radiographer // Body Site: All
3. European Society of Radiology award won by research radiographer.
Ahead of this years’ European Congress of Radiology, hosted by the European Society of Radiology, Ms Walsh’s research project, “R-AI-diographers: Exploring the changing professional role and identity of radiographers in Europe in the era of artificial intelligence (AI)”, was selected by the radiographers’ scientific subcommittee. The project centred on a continent-wide survey investigating radiographers’ thoughts and opinions on the impact of AI implementation on radiographer roles, responsibilities, and professional identities, with over 2,200 participants from 37 different countries.
Read Full Article
Paul’s Thoughts:
It is fantastic to see different disciplines exploring the ways in which AI is, and will, impact their profession. Only with such engagement will it be possible to fully harness the opportunities of AI.
Timescale: Early | 2 Years
A round-up of some of the best posts we found online this week.
Was this email forwarded to you?
Our weekly email brings you the latest health trends and insights, combining top news and opinions into a straightforward, digestible format.
Want an article featured?
Have an insightful link or story about the future of medical health? Reach out below, and we may include it in a future release.
Reply