IIITH To Develop Early Oral Cancer Screening Tool
The automated solution, arising out of a collaborative effort with Grace Cancer Foundation and BioCon Foundation, requires just a smart phone. It aims to flag abnormal oral lesions before they progress into advanced stages of cancer.
A blue-coloured bus trundles to a stop at Pangra village in Nizamabad district and sets up a mobile camp. It is a cancer screening bus equipped with a mammography unit, x-ray facilities and other equipment for early detection of oral, breast, and cervical cancers especially for remote rural areas. Run by the Grace Cancer Foundation, an NGO, the bus is staffed with primary healthcare workers who do the preliminary screening for early detection of cancers. Speaking specifically for oral cancer, which is among the top three types of cancers in India, the Foundation’s CEO and Director, Dr. Chinnababu Sunkavalli says that its prognosis remains poor because most patients are diagnosed at advanced stages. Treatment for early-stage cancers typically involves surgery or radiation while a later stage-detection may require treatments such as chemotherapy or immunotherapy and others.
Limitations Of Mobile Camps
While the NGO has been attempting an early screening and detection of cancers via its mobile camps, its efforts are impeded by the sporadic availability of highly skilled medical professionals such as oncologists who can visually examine oral cavities or interpret x-ray test results instantaneously on the bus. “Sending a clinician along with the bus for every visit to remote locations is not a viable option for us,” says Dr. Chinnababu. If an abnormality is detected, a decision needs to be made whether to refer the patient to a health facility for further examination such as a biopsy to confirm if it is cancerous or not. “Rather than sending all patients with suspicious-looking lesions to the district or tertiary hospital for followups, we wanted an AI-based solution on site that could raise an alert on the bus itself,” says Dr. Babu.
When the Foundation approached IIITH, the two brainstormed to arrive at a method where an AI algorithm could flag oral cavity images, taken by simple phone cameras, as malignant or benign. “A project like this needed funding, so iHub-Data stepped in to help us develop a solution for oral cancer screening,” says Dr. Vinod. P.K, who is leading the Cancer initiative at iHub-Data (https://ihub-data.iiit.ac.in). The iHub-Data centre at IIITH is a Technology Innovation Hub that has been established under the National Mission on Interdisciplinary Cyber Physical Systems (NM-ICPS) in the area of data driven technologies. The Hub is focused on putting together large-scale datasets to help develop solutions through applied research. Currently efforts are being directed and amplified in the domains of healthcare and smart mobility. One of the first initiatives In the healthcare domain is centred around image-based early screening and diagnosis of cancer.
An App For Data Collection
The first phase of the project which involves collection of data by the Grace Foundation, has been greatly simplified thanks to the development of an app with the assistance of Product Labs, the market relevant engineering arm of IIITH’s Technology Transfer Office. “The mobile app has now been tested and will be used for the first time for oral cancer screening. I think it is a very useful app that can be used in multiple other public health projects that we are involved in. Apart from recording photographic images of oral cavities, demographic details of the patient and possibly follow-up reports that will come with the image can be maintained on it too,” says Dr. Vinod.
Joining Hands With BioCon
Chancing upon a similar initiative of a tech-based mobile early detection and prevention of oral cancer by the BioCon Foundation, Bangalore, the IIITH team has now joined hands with them too. “They have shared their data that has been collected so far as well as the initial AI model, developed by the Indian Institute of Science (IISc), Bangalore. Our aim is to improve the model’s predictive performance so that it reaches the level expected for usage in a field setting,” says Dr. Vinod. According to Prof. Bapi Raju, the healthcare lead at iHub-Data, “Apart from the photographs of the oral cavity, our model would take into consideration lifestyle, family and medical history, vitals and blood tests, clinical examination, as well as lifestyle information to improve the predictive capability of the AI algorithm.”
With the SOPs for clicking of the required images and training of frontline workers in place, data collection for the project kicked off in November 2021. “Cancers such as oral have favourable outcomes, if they are detected early and treated. Hence the current effort is placing huge emphasis on early screening as well as developing a mobile solution for screening camps in rural settings. The aim is to take the solution to the field and not wait for patients to show up in the secondary and tertiary centres when it might be too late!,” says Prof. Bapi.
Sarita Chebbi is a minimalist runner, practising yogi and baker of all things whole-wheat, and sugar-free. Currently re-learning her ABC’s…the one that goes: A for algorithm, B for Bayesian, C for convolutional (neural network)….