Scientists of the Indian Institute of Technology, Kharagpur (IIT-KGP), have developed a highly accurate and portable, yet, user-friendly and non-invasive device for detecting oral cancer. The device is very affordable, and hence, would prove to be very useful in resource-constrained clinical settings.
This research work was undertaken under the guidance of Professor Suman Chakraborty of the Department of Mechanical Engineering. The findings of the research were published in the prestigious Proceedings of the National Academy of Sciences (PNAS), USA titled ‘Portable, handheld, and affordable blood perfusion imager for screening of subsurface cancer in resource-limited settings’. It has also been selected for an eminent print journal named In This Issue.
Significance of the Innovation
Cancer of the oral cavity has remained one of the major causes of morbidity and mortality in socially-challenged communities. There is an average 80 per cent chance of five-year survival rate if diagnosed at an early stage. The survival rate would drop to 65 per cent or less, in more advanced stages.
Most oral cancers remain undetected until they have reached an advanced stage. In resource-limited settings, there would be serious lacking of accurate and affordable diagnostic tools to arrive at a conclusion on the stage in the first clinical examination of the patient.
It is very difficult to find the overlapping features of oral cancer, such as oral squamous cell carcinoma, etc., with certain common precancerous conditions (oral sub-mucosal fibrosis, oral leucoplakia, oral erythroplakia, and oral lichen planus) in addition to several other types of mouth sores and ulcers.
In case of non-availability of high-end resources, the clinician is compelled to rely more on sensibly recognisable features during the clinical examination of the at-risk oral sites (buccal mucosa, tongue, gum, palate, etc.) along with the medical history of the patient.
Therefore, this affordable non-invasive portable device would save millions of lives as diagnostic results would be available in the first examination process. It would be able to detect cancer of superficial locations in the body, with very little margin of error.
The Device
This device is user-friendly, portable, and has a blood perfusion imager (BPI). The BPI, which combines a miniature far-infrared (FIR) camera and a humidity sensor, is electronically controlled and interfaced with a combined physics-based and data-driven software engine.
The device consists of a probing unit for screening and a processing unit for obtaining blood perfusion data and disease recognition. The probing unit comprises a holder and sensor housing. The holder is used for guiding the sensor housing to the measurement site. The sensor housing helps maintain a stable environment for sensors to minimise the effect of breathing. The sensor housing comprises an on-chip long-wave infrared (IR) camera for measuring tissue temperature as well as a fully-calibrated digital humidity sensor for measuring ambient temperature and relative humidity inside the mouth. The IR camera sensor array would capture the spectral radiance in the wavelength range of 8–14 µm (micrometre). The device uses additional signal-processing electronics to convert the radiometric values into temperature value, with thermal sensitivity less than 50 millikelvin, and for imaging at a rate of 8.7 Hertz.
Working of the device The handheld unit consists of various sensors and controllers, and feeds the measured data to a highly efficient computer simulation engine which classifies normal, pre-cancer, and cancer cases in the oral cavity. As the results are highly accurate, there is no need to refer the patient to specialised medical centres for resource-intensive diagnostic procedures. This technology would overcome the challenges of cancer screening in resource-limited settings, where other forms of complementary diagnostics are not commonly available.
The device uses a simple and automated touch-free approach of estimating blood flow variations in different regions of the potentially diseased tissue, specifically correlating with the diseased condition. This technology has been proven to be superior as compared to thermal imaging-based screening technologies currently available. It is superior because the temperature in the tissue itself varies with the surrounding conditions.
Scientists have also infused a machine learning-based classification approach with physics-based analytics, based on thermal images obtained from portable devices. In its early stage, oral cancer is known to manifest an increase in blood flow. However, full-grown oral cancer reveals a decrease in blood flow, similar to pre-cancer or normal cases. This data-science augmented interpretation algorithm has minimised inevitable instances of misclassification due to similar common deceptive features among other medical conditions. In borderline cases, this may be compounded by obvious inter-patient variability, which may lead to wrong clinical decisions. This new technology would help in delivering a judicious amalgamation of data analytics and physics-based approach towards disease modelling and detection technology.
Clinical trials Experts from the Guru Nanak Institute of Dental Sciences and Research, in West Bengal, had supervised the clinical trials of this technology. In the first phase of the clinical trials, they have established the efficacy of the new method in differentiating cancerous and precancerous stages of suspected oral abnormalities, as verified by high-standard biopsy reports. The next phase would see field deployments in Odisha.
Affordability and diagnosis The estimated cost of this portable device is US $500 (which is approximately Rs 37,000/-), and could be accommodated in a resource-limited setting. The optical coherence tomography (OCT) machine costs at least US $35,000 (which is approximately Rs 26,00,000/-). The CT scan, MRI, etc., are still comparatively more expensive. Additionally, such complex machines need high-end lab infrastructure, along with support resources, which are needed for their operation and maintenance.
Diagnosis could be arrived at within 5–10 minutes after taking the image with the new device.
The patent for this new technology has already been filed and the technology has been made available for ready licensing to companies for commercial adaptation. However, it may be subjected to more extensive statutory field trials before clinical use.
Reason behind this innovation The non-availability of diagnostic technologies and its challenges have been exposed by the ongoing COVID-19 pandemic. The need for diagnostic technologies, that are accurate, economical, user-friendly and amenable, has become inevitable. Absence of these easy methods of detection led to lapse in detection in early stages of the disease. Therefore, many cases reached a more advanced and irrecoverable state. Poor oral hygiene due to different forms of addiction inherent to the lifestyles of socially and economically challenged populations, have triggered an intense urge of developing this technology. This new technology would offer an amalgamated approach, with a trade-off between the scientific standards of high-end laboratory-based tests, along with the elegance of common rapid tests. This invention might change the future of diagnostics, targeting specific public health measures towards catering the undeserved.
© Spectrum Books Pvt Ltd.