THE INNOVATION

Breast cancer is the leading cause of cancer deaths in women today. According to WHO, one in every 12 women have the risk of a breast abnormality. Indian women have only about 50% chance of survival. Early diagnosis is very critical to decrease mortality rates. Most common methods used for cancer screening today is Clinical Examination, Mammography and Ultrasound. Among them mammography is considered as a gold standard for breast cancer screening. It uses X-rays to screen the breast region and digitizes the density difference in image format. Typically, cancerous tumor has high density compared to surrounding region and can be easily distinguished from other regions. But mammography has following disadvantages:
a) High cost b) Low Sensitivity towards Younger Women c) Risk of Radiation d) Fear and Pain due to compression of breast e) Privacy f) Need for experienced technicians.
Among other modalities, clinical breast exam can detect lumps but only when they are large enough to be palpable and result in many false positives as not all lumps are cancerous.
NIRAMAI team has pioneered Thermalytix, a technique that uses their patented artificial intelligence algorithms over thermal images of the subject to enable a non-contact, non-invasive, end-to-end privacy aware breast cancer screening solution that requires minimal skills to operate. The solution is a low cost, portable cancer screening tool that can detect early stage cancer with an ability to see abnormal cell activity much earlier than palpable lumps.
The core solution is a cloud-hosted computer aided diagnostic software developed by NIRAMAI. The sensing used by NIRAMAI uses Thermography which shows the earliest signs for breast cancer screening based on the fact that the metabolism in the tumour will be higher than the neighboring tissues. Additionally, the blood vessel activity surrounding a developing cancer is has a typical thermal pattern and will be almost always higher than in normal breast tissue. Since breast tissue is part of the skin, vascular alterations due to cancer result in temperature changes on the surface of the breast which can be captured with infrared thermography. Thermal abnormalities identified with thermal imaging are among the earliest signs of a pre-cancerous or cancerous lesion of the breast. While every malignancy will show a hotspot, not all hotspots in thermal images are cancerous. So, NIRAMAI has developed an artificial intelligence model that was trained using historic data to analyse the images to differentiate cancer versus noncancerous tissue. Since thermal cameras are small, they are very portable and can be used for screening in rural camps. The first version of this automated diagnostics software to identify suspicious malignancy has shown good accuracy (over 90%) on 8500 plus subjects.