• S.Sunitha

Among the recognized types of malignant tumors, one that cannot be detected early and presents no symptoms is intestinal cancer. Wireless capsule endoscopy is a clinical investigation for detecting stomach cancer and other stomach related ailments. Due to the stomach's structure and color, detecting stomach cancer in its early stages with WCE images is a challenging and time-demanding medical procedure. This research aims to automate the process detection of malignancy in WCE images with high accuracy. Convolutional Neural Networks and Machine Learning techniques are used in this study to detect stomach cancer early. Automatic feature extraction from WCE images is performed using a Multi-Layer CNN (ML-CNN) feature extractor. Additional color and texture features are extracted from WCE images using Correlated Feature Extraction (CFE). The features retrieved using the Multi-Layer CNN (ML-CNN) technique are classified using RF into two categories. MAE and RMSE are used to demonstrate the efficacy of the suggested strategy based on training and detection of stomach cancer. The classification accuracy of the proposed Multi-Layer CNN (ML-CNN) technique is 95%, which is superior to other existing approaches.

Wireless Capsule Endoscopy, Image Segmentation, Image Pre-Processing, CNN, Polyp Detection, Deep Learning.

"Automated Stomach Cancer Detection System Using Multi-Layer CNN and Random Forest ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 2, page no.a728-a734, February-2022, Available :http://www.jetir.org/papers/JETIR2202089.pdf

"Automated Stomach Cancer Detection System Using Multi-Layer CNN and Random Forest ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 2, page no. ppa728-a734, February-2022, Available at : http://www.jetir.org/papers/JETIR2202089.pdf