INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
One of the most prevalent forms of malignant cancer is colon cancer. It begins to develop as a polyp, which is essentially an outgrowth from the surface of the
colon. Therefore, one of the main purposes of endoscopy and colonoscopy is the early detection of polyps and malignancies. In order to dramatically increase the robustness and efficacy of colorectal cancer screening, as well as improve segmentation, accuracy, lesion detectability, and histological characterization accuracy, DCNN (deep convolutional neural networks) techniques based on U-Net
architecture are applied. Data augmentation is utilised to expand our dataset, giving U-Net access to extra details that lead to accurate detection. The presence of polyps is not consistent, the colour pattern is not uniform, and there is a reflection effect in photos of polyps taken during colonoscopy and endoscopy. Over and under segmentation may result from this.
The segmentation method is based on a model of a polyp's presence, which is defined as a noticeable shape enclosed within a polyp. This model takes these
elements into consideration. An area can be recognised by the presence of edges and valleys. Post-processing techniques including morphological changes to soften segmentation boundaries and grouping neighbouring objects that originally belonged to a large polyp in the output segmentation chart are used to increase the accuracy of polyp detection. Polyp and non-polyp instances are separated for each pixel. The clinician can now identify the polyp with greater ease, speed,
and accuracy. In the development of a CAD (Computer-Aided Diagnosis) system, automated polyp segmentation can be useful. Therefore, we propose an
effective U-Net strategy for DCNN design and method for automated polyp detection.
Keywords:
Colorectal cancer, polyp, DCNN, U-Net, segmentation, data augmentation
Cite Article:
"Automatic Detection of Polyps using UNet", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 3, page no.b442-b446, March-2023, Available :http://www.ijnrd.org/papers/IJNRD2303151.pdf
Downloads:
000118750
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn