Artificial intelligence used to predict oral cancer survival chances
COVENTRY, UK: The impact artificial intelligence is having on the healthcare industry is becoming more and more evident on a daily basis. In dentistry, some of the advances have helped to improve outcomes and increase productivity. Now in a recent pilot study, researchers in the UK have developed an algorithm that helps predict the chances of a patient surviving oral cancer. The study, which focuses on patients from Pakistan, may be hugely influential in helping a country with almost 13,000 new cases of oral cancer every year.
Collaborating on the study were researchers from the Shaukat Khanum Memorial Cancer Hospital and Research Centre (SKMCH&RC) in Lahore in Pakistan and the Department of Computer Science at the University of Warwick (UW) in Coventry in the UK. Scans from 70 patients with oral cancer who had been treated with radiation therapy and had undergone head and neck surgery were used to gather information, with scientists from SKMCH&RC then sending tissue samples from these patients to the team at UW. With a state-of-the-art imaging machine, the researchers at UW were able to digitally produce high-resolution images of the samples on a microscopic scale. They then developed an algorithm that could predict survival rates by measuring tumour-infiltrating lymphocytes (TILs).
“We are only beginning to unravel the remarkable potential of wealth of information present in pathology image data. This pilot study shows that with the help of modern cancer image analytics algorithms, we can precisely calculate the score of abundance of TILs in oral cancers in an objective manner and then use that score for risk stratification in terms of disease-free survival,” said lead researcher Prof. Nasir Rajpoot from the Department of Computer Science at UW.
According to the study, the level of TILs found in a scan indicate the patient’s immunity to the cancer and response to treatment, and the density and spatial arrangement of TILs correlate with the chances of overall survival and disease-free survival. Speaking about the study, Dr Asif Loya, Medical Director at SKMCH&RC, said, “There is little known about the histological signatures corresponding to patient subgroups with differing outcomes in this part of the world. Histologic risk assessment is strongly predictive of local disease-free and overall survival in oral squamous cell carcinoma thus there is need for a validated scoring system to be used as an aid in treatment decision-making in these cancers in our patients.”
The study, titled “A novel digital score for abundance of tumour infiltrating lymphocytes predicts disease free survival in oral squamous cell carcinoma”, was published on 16 September 2019 in Scientific Reports.