A recent study from The Royal Marsden NHS Foundation Trust in collaboration with The Institute of Cancer Research and Imperial College London (ICL) has suggested that AI could help in identifying the risk of cancer returning in non-small lung cancer (NSCL).
The ongoing study, called ‘Optimising Cancer Treatment surveillance and Ascertaining cause of Pneumonitis USing Artificial Intelligence’ or OCTAPUS-AI, used imaging and clinical data from over 900 NSCLC patients from the UK and Netherlands following curative radiotherapy. It aimed to develop and test machine learning algorithms, in order to gauge how accurately the models could predict the recurrence of cancerous cells.
The imagining data from CT scans was analysed using radiomics technique, through which prognostic information is extracted that cannot be seen by the human eye. Data from the technique can also potentially be linked with biological markers, with the researchers noting that radiomics could be “a useful tool in personalising medicine as well as improving post-treatment surveillance.”
The results, published in npj Precision Oncology, revealed that the researcher’s model was better at identifying patients at a higher risk of recurrence within two years of completing radiotherapy than the traditional TNM staging system. The ‘area under the curve’ (AUC) measurement was used to test the effectiveness of the tool, with an AUC score of one meaning that the system was correct every time, the new model achieved an AUC score of 0.738, whilst the TNM technique scored 0.683.
Dr Sumeet Hindocha, study lead, Clinical Oncology Specialist Registrar at The Royal Marsden NHS Foundation Trust and Clinical Research Fellow at ICL, said: “While at a very early stage, this work suggests that our model could be better at correctly predicting tumour regrowth than traditional methods… Next, we want to explore more advanced machine learning techniques, such as deep learning, to see if we can get even better results. We then want to test this model on newly diagnosed NSCLC patients and follow them to see if the model can accurately predict their risk of recurrence.”
Chief investigator for the OCTAPUS-AI study Dr Richard Lee added: “In the future, we hope this approach will pave the way for predicting recurrence for all cancer types, not just NSCLC. Our model used features specific to this disease but by refining the algorithm, this technology could have much wider application.”
Dr Hindocha’s work is funded by the UKRI Artificial Intelligence for Healthcare Centre for Doctoral Training at ICL, and the study was supported by funding from The Royal Mardsen Cancer Charity and the National Institute for Health and Care Research.
