As featured recently in a special issue of Cancer Biomarkers, lead researchers from a series of Shanghai-based universities showed how Artificial Intelligence (AI) algorithms when analysing radiomics data can help better detect the formation and movement of cancer in a patient. Lead investigators were Shaoli Song, PhD, from Shanghai Medical College and Lisheng Wang, PhD, from Shanghai Jiao Tong University.
The challenge of detecting cancer, including its relapse and metastasis, is a monumental one as large sets of data need to be considered. But early detection is key. Early diagnosis of cancer can give the best chance for successful treatment. When cancer care is delayed or inaccessible there is a lower chance of survival, greater problems associated with treatment and higher costs of care.
To overcome such challenges, the Chinese team of scientists combined radiomic data from preoperative positron emission tomography (PET) and CT images in patients with early-stage uterine cervical squamous cell carcinoma. Then, they used AI algorithms to develop a prognostic signature capable of predicting disease-free survival. In short, by using AI, they can better predict to what extent the advances of cancer is halted.
In cancer, disease-free survival (DFS) is the length of time after primary treatment for cancer ends that the patient survives without any signs or symptoms of that cancer. In a clinical trial, measuring DFS is one way to see how well a new treatment works.
This model could provide more accurate information about potential relapse and metastasis, and could be helpful in decision-making.
Radiomics is an emerging field where features are extracted from medical imaging using various techniques. In this sense, it uses Deep Learning (DL) and Machine Learning (ML). Radiomic features can quantify tumour intensity, shape, and heterogeneity and have been applied to oncologic detection, diagnosis, therapeutic response, and prognosis.
Indeed, the combination of AI, DL and ML working together have transformed many industries and areas of science. Now, these tools are being applied to address the challenges of cancer biomarker discovery, where the analysis of vast amounts of imaging and molecular data is beyond the ability of traditional statistical analyses and tools.
The challenge of overwhelming data has been echoed by other scientists in the field of cancer biomarker discovery. Karin Roadlan, PhD, Oregon Health and Science University, USA, detailed that the biomarker field is blessed with a plethora of imaging and molecular-based data. But at the same time, it is plagued with so much data that no one individual can comprehend it all.
And that certainly looks like a job tailor-fit for AI. Roadlan affirmed saying that AI offers a solution to that problem, and has the potential to uncover novel interactions that more accurately reflect the biology of cancer and other diseases.
Already, the technology looks promising, and the Cancer Biomarkers noted that. ML, DL with AI has been instrumental in identifying early-stage cancers, inferring the site of specific cancer, and aiding in the assignment of appropriate therapeutic options for each patient. Further, such digital technologies have helped characterise the tumour microenvironment and predict the response to immunotherapy.
China is at the forefront of massive digital transformation. It is certainly is in the process of putting all the pieces together to move its digital economy forward. And its digital strengths as a nation have been showcased to the world.
As reported on OpenGov Asia, the 2022 Beijing Paralympics is a testament to this. Emerging digital technologies have allowed physically-challenged athletes and audiences to participate better in the event.
