Scientists at the Institute of Advanced Study in Science and Technology (IASST) have developed an artificial intelligence (AI)-based algorithm to help the rapid diagnosis and prediction of the oral squamous cell carcinoma.
IASST is located in Guwahati and is an autonomous institute under the Department of Science and Technology (DST).
The framework was developed by the research group at IASST’s Central Computational and Numerical Sciences Division, led by Dr Lipi B. Mahanta.
It will also help with the grading of the oral squamous cell carcinoma.
According to a press release, an indigenous dataset was developed by the scientists through collaborations due to the unavailability of a benchmark oral cancer dataset for the study.
Exploring different state-of-the-art AI techniques and playing with their proposed method, the scientists have gained unprecedented accuracy in oral cancer grading, the release noted.
The study was conducted by applying two approaches through the application of transfer learning using a pre-trained deep convolutional neural network (CNN).
Four candidate pre-trained models, namely Alexnet, VGG-16, VGG-19, and Resnet-50, were chosen to find the most suitable model for the classification problem, and a proposed CNN model developed to fit the problem.
Although the highest classification accuracy of 92.15% was achieved by the Resnet-50 model, the experimental findings highlight that the proposed CNN model outperformed the transfer learning approaches, displaying an accuracy of 97.5%. The work has been published in the journal Neural Networks.
As of now, the group is set to convert the algorithm into proper software to carry out field trials. This is the next challenge that the group is prepared to meet, considering the ever-present gap between the health and IT sectors, the release said.
Dr Mahanta intends for all the advanced infrastructural support to meet these challenges and believes that the software needs to be actively tested in hospitals to make it robust, more accurate, and real-time worthy.
Around 16.1% of all cancers among men and 10.4% among women are oral cancer. Oral cavity cancers are also known to have a high recurrence rate compared to other cancers due to a high consumption of betel nut and tobacco in the country,
This cancer group is characterised by epithelial squamous tissue differentiation and aggressive tumour growth, disrupting the basement membrane of the inner cheek region. Thus, it can be graded by Broder’s histopathological system as well-differentiated SCC (WDSCC), moderately differentiated SCC (MDSCC), and poorly differentiated SCC (PDSCC).
The cellular morphometry highlighting the tumour growth displays a very minute histological difference separating the three classes, which is hard to capture by the human eye.
The release explained that it has remained elusive due to its highly similar histological features, which even pathologists find difficult to classify.
The advent of deep learning in AI holds an extraordinary prospect in digital image analysis to serve as a computational aid in the diagnosis of cancer, thus providing help in timely and effective prognosis and multi-modal treatment protocols for cancer patients and reducing the operational workload of pathologists while enhancing management of the disease.
Another institute in the country has formed a rare-earth-based magnetocaloric material that can be effectively used for cancer treatment. The magnetocaloric materials (certain materials where the application and removal of a magnetic field causes the materials to become warmer or cooler) was developed by the International Advanced Research Centre for Powder Metallurgy and New Materials (ARCI).