This study will assess the utility of radiomics and artificial intelligence approaches to new lung nodules in patients who have undergone radical treatment for a previous cancer.
Improvements in cancer detection and diagnosis have led to increasing numbers of patients being diagnosed with early stage cancer and potentially receiving curative therapy with improved survival outcomes. Recent retrospective studies in cancer survivors have demonstrated such patients possess an increased risk of further cancer in their lifetime compared to the general population, in part potentially due to shared lifestyle risk factors (e.g. smoking), genetic cancer pre-disposition or downstream oncogenic side effects of anti-cancer therapies (eg. radiotherapy). Lung cancer remains the leading cause of cancer related deaths worldwide and the lungs also represent a common site for metastatic disease in patients with non-pulmonary malignancy. Furthermore, lung cancer is one of the most common second primary malignancy in patients with a prior history of treated cancer. Therefore, discerning the significance of a pulmonary nodule in the context of a previous cancer remains a clinical challenge given it may possess the potential to represent benign disease, metastatic relapse or new primary malignancy. This study will assess the utility of radiomics and artificial intelligence approaches to new lung nodules in patients who have undergone radical treatment for a previous cancer. This will entail use of machine learning (ML) approaches and later, exploration of deep-learning/convolutional neural network approaches to nodule interpretation for differentiation of benign, metastatic and new primary lung cancer nodules/lesions. Development of a ML classifier or deep learning based tool may help guide which patients would benefit from earlier investigations including additional imaging, biopsy sampling and lead to earlier cancer diagnosis, leading to better patient outcomes in this unique cohort. This is a retrospective study analysing data already collected routinely as part of patient care. All data will be anonymised prior to any analysis, no patient directed/related interventions will be employed and consent-waiver for study inclusion will be exercised.
Study Type
OBSERVATIONAL
Enrollment
1,000
First nodule detection CT scans as per eligibility criteria will be used as input into in-house software to extract multiple radiomic features and used to develop a machine learning based classifier to differentiate nodule aetiology. Scans will also be used as input in to a deep learning/convolutional neural network models to perform automated imaging classification.
The Royal Marsden NHS Foundation Trust (Chelsea Site)
London, United Kingdom
RECRUITINGRoyal Brompton Hospital
London, United Kingdom
RECRUITINGDevelopment of a CT-thorax based radiomics ML classifier model to predict cancer risk in new lung nodules after previous radically treated cancer.
The study aims to identify distinct clusters of radiomics variables to generate a radiomics predictive vector (RPV), which can be used to stratify benign vs malignant nodules in patients who have previously received radical treatment for a malignancy. The RPV will be used in multivariate analysis and compared to existing risk models used in clinical practice.
Time frame: 2 years
Development of the CT-thorax based ML classifier model to predict whether a new malignant nodule represents metastatic lung disease (new cancer vs previous cancer recurrence) or a new primary lung malignancy.
The study aims to identify distinct clusters of radiomic variables to generate a radiomics predictive vector (RPV) which is able to differentiate metastatic lung nodules from new primary lung cancer in patients who have previously received radical treatment for a cancer. No current models exist in clinical practice which address this diagnostic challenge.
Time frame: 2 years
To evaluate performance the developed CT-thorax based ML classifier model in an independent external validation cohort.
The investigators aim to assess performance of the derived radiomics predictive vector (RPV) on an external independent post-cancer lung nodule dataset to evaluate generalisability and potential real-world performance.
Time frame: 2 years
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.