A group of scientists from the Institute of Advanced Study in Science and Technology (IASST) in Guwahati has developed a classification method based on artificial intelligence to evaluate hormone status for prognosis of breast cancer.
The research team of IASST has come up with the novel deep learning (DL)-based quantitative evaluation method for indicating estrogen or progesterone status with the help of Immunohistochemistry (IHC) specimen related to the prognosis of breast cancer.
Ready for a challenge? Click here to take our quiz and show off your knowledge!
Breast cancer is the most common invasive cancer accounting for 14 per cent of cancers amongst Indian women, both in rural and urban India.
In India, the post-cancer survival rate related to breast cancer is reported to be 60 per cent, which is approximately 80 per cent of Indian patients below 60 years of age. Such alarming numbers could be reduced if the cancer is diagnosed at an early stage.
The software – IHC-Net when loaded onto a system, can semantically segment the exact positive and negative nuclei from breast tissue images.
Ready for a challenge? Click here to take our quiz and show off your knowledge!
The framework by the IASST’s team of scientists is a reliable alternative to manual methods for automatic grading systems used to determine the scoring of estrogen receptor status for predicting the progression of breast cancer.
The study led by Dr Lipi B Mahanta, was done in collaboration with Dr Lopamudra Kakoti from the Dr B Borooah Cancer Institute. The research team also included Elima Hussain, Navarun Das and Dr Manish Chowdhury.
The computer-aided diagnosis method using recent artificial intelligence technology to evaluate the hormone status for prognosis of breast cancer, involves an algorithm that indicates whether or not the tumour has hormone receptors on the surface of cancer cells.
This will help doctors in carrying out hormonal therapy for breast cancer with ease and precision in a short time.
An ensemble method was also used for integrating the decision of three machine learning (ML) models which will give the final Allred cancer score.