Research Article
Design and development of an ‘early prediction machine’ for Colorectal Cancer from pathological images through quantum image processing technique – a theranostic approach
@INPROCEEDINGS{10.4108/eai.16-5-2020.2303948, author={V. Rohith and P. K Krishnan Namboori}, title={Design and development of an ‘early prediction machine’ for Colorectal Cancer from pathological images through quantum image processing technique -- a theranostic approach}, proceedings={Proceedings of the First International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICASISET 2020, 16-17 May 2020, Chennai, India}, publisher={EAI}, proceedings_a={ICASISET}, year={2021}, month={1}, keywords={colorectal cancer hybrid quantum model artificial intelligence deep learning}, doi={10.4108/eai.16-5-2020.2303948} }- V. Rohith
P. K Krishnan Namboori
Year: 2021
Design and development of an ‘early prediction machine’ for Colorectal Cancer from pathological images through quantum image processing technique – a theranostic approach
ICASISET
EAI
DOI: 10.4108/eai.16-5-2020.2303948
Abstract
The Cancer has been reported as a major terminal disease of the world and the number of deaths due to various types of cancer is increasing day by day. More than 30% of the death due to cancer is due to colorectal cancer (CRC) resulted by mutations in the WNT signalling pathway. In most of the cases, early detection of the disease and proper treatment may help in resulting complete cure. Improvements in modern technology with deep neural networks and artificial learning along with image processing enables diagnosis and detection of cancer cells in the early stages. In the present work, the possibility of using ‗quantum processing technique or 'Qubit computing' has been explored to classify malignant and benign cells. The dataset used is pathological images of colorectal cancer processed using a 2-bit quantum circuit. The processing has been carried out using 'IBM Quantum computing (IBM-Q)'. Even with a small dataset and with 4-qubit platform, more than 50% accuracy has been observed. Higher percentage of accuracy may be obtained by optimizing the number of qubits and by using bigdata.