Automatic Detection of Polyps using UNet

Automatic Detection of Polyps using UNet

Registration ID: IJNRD_188636

Published ID: IJNRD2303151

DOI: Click Here to Get

Lukalapu Kusuma , K Nikita , Sanjana Das

Colorectal cancer, polyp, DCNN, U-Net, segmentation, data augmentation

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.

Published Paper   E-Certificate

"Automatic Detection of Polyps using UNet", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.8, Issue 3, page no.b442-b446, March-2023, Available :https://ijnrd.org/papers/IJNRD2303151.pdf

Volume 8 Issue 3, March-2023

Pages : b442-b446

Paper Reg. ID: IJNRD_188636

Published Paper Id: IJNRD2303151

Downloads: 000121139

Research Area: Computer Engineering 

Country: Hyderabad, Telangana, India

Published Paper PDF: https://ijnrd.org/papers/IJNRD2303151.pdf

Published Paper URL: https://ijnrd.org/viewpaperforall?paper=IJNRD2303151

Journal Name: INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT(IJNRD)

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

Publisher: IJNRD (IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition

Call For Paper - Volume 10 | Issue 8 | August 2025

IJNRD is Scholarly open access journals, Peer-reviewed, and Refereed Journals, High 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) with Open-Access Publications.

INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (IJNRD) aims to explore advances in research pertaining to applied, theoretical and experimental Technological studies. The goal is to promote scientific information interchange between researchers, developers, engineers, students, and practitioners working in and around the world. IJNRD will provide an opportunity for practitioners and educators of engineering field to exchange research evidence, models of best practice and innovative ideas.

Indexing In Google Scholar, SSRN, ResearcherID-Publons, Semantic Scholar | AI-Powered Research Tool, Microsoft Academic, Academia.edu, arXiv.org, Research Gate, CiteSeerX, ResearcherID Thomson Reuters, Mendeley : reference manager, DocStoc, ISSUU, Scribd, and many more

How to submit the paper?

Important Dates for Current issue

Paper Submission Open For: August 2025

Current Issue: Volume 10 | Issue 8

Last Date for Paper Submission: Till 31-Aug-2025

Notification of Review Result: Within 1-2 Days after Submitting paper.

Publication of Paper: Within 01-02 Days after Submititng documents.

Frequency: Monthly (12 issue Annually).

Journal Type: International Peer-reviewed, Refereed, and Open Access Journal.

Subject Category: Research Area