• K. Tejaswani

Colon cancer is called as colorectal cancer is one of the world’s deadliest cancer disease at high mortality rate which affecting people of all age and gender. In the change of atmosphere, climate, and lifestyle it puts the people health at risk. For diagnosing the colon cancer computed tomography scans are very useful. The main goal of the study is to detect colon nodules and distinguish colon images. The deep learning approaches use to detect the position of cancerous colon nodule and we incorporate properly educate this approach for detect and classification of clinical CT images that this technique is long been discovered to identify and convinced medical field. Each of the computer tomography slice segment from the radiologist markings. This project compares the output of deep learning techniques with computer aided diagnosis method. In multi-stage system detects nodules in 3D colon CAT scans, decide whether or not each nodule is malignant, and assigns a cancer likelihood based on the findings. The proposed model helps to extract the grater accurate image features and signifies improvement of overall accuracy of classification. If histopathologist is not well trained it generates wrong diagnosis. For getting better result, histopathology images can help to identify malignant tumors and cancer subtypes. The model trains separately with various images and partitioned in 80% in train phase and 20% in test phase.

Colon cancer, Deep Learning, Computed Tomography, Computer-Aided Diagnosis, Histopathology images.

"Colon Cancer Detection using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 5, page no.d610-d614, May-2021, Available :http://www.jetir.org/papers/JETIR2105470.pdf

"Colon Cancer Detection using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 5, page no. ppd610-d614, May-2021, Available at : http://www.jetir.org/papers/JETIR2105470.pdf