UGC CARE norms ugc approved journal norms IJRTI Research Journal

Click Here

International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (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)

Call For Paper

For Authors

Forms / Download

Published Issue Details

Editorial Board

Other IMP Links

Facts & Figure

Impact Factor : 8.14

Issue per Year : 12

Volume Published : 7

Issue Published : 79

Article Submitted : 5505

Article Published : 3032

Total Authors : 7767

Total Reviewer : 540

Total Countries : 67

Indexing Partner


This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Published Paper Details
Paper Title: A convolution free network for 3D medical image segmentation
Authors Name: Siva Prasad Patnayakuni
Download E-Certificate: Download
Author Reg. ID:
Published Paper Id: IJRTI2208038
Published In: Volume 7 Issue 8, August-2022
Abstract: Profound learning models address the cutting edge in clinical picture division. The vast majority of these models are fully convolutional networks (FCNs), in particular each layer processes the result of the former layer with convolution tasks. The convolution activity partakes in a few significant properties, for example, scanty connections, boundary sharing, and interpretation equivariance. Due to these properties, FCNs have areas of strength for a helpful inductive predisposition for picture demonstrating and examination. In any case, they likewise have specific significant deficiencies, for example, playing out a fixed and pre-decided procedure on a test picture no matter what its substance and trouble in demonstrating long-range cooperation’s. In this work we show that an alternate profound brain network design, dependent completely upon self-consideration between adjoining picture patches and with practically no convolution tasks, can accomplish more exact divisions than FCNs. Our proposed model depends straightforwardly on the transformer network engineering. Given a 3D picture block, our organization separates it into non-covering 3D fixes and processes a 1D installing for each fix. The organization predicts the division map for the block in view of the self-consideration between these fix embeddings. Moreover, to resolve the normal issue of shortage of named clinical pictures, we propose techniques for pre-preparing this model on enormous corpora of unlabeled pictures. Our examinations demonstrate the way that the proposed model can accomplish division correctness’s that are superior to a few best in class FCN designs on two datasets. Our proposed organization can be prepared utilizing just several marked pictures. Besides, with the proposed pre-preparing systems, our organization beats FCNs while named preparing information is little.
Keywords: Fully convolutional networks (FCNs), 3D picture block, datasets, segmentation, medical image.
Cite Article: "A convolution free network for 3D medical image segmentation", International Journal of Science & Engineering Development Research (, ISSN:2455-2631, Vol.7, Issue 8, page no.228 - 236, August-2022, Available :
Downloads: 000177597
ISSN: 2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publication Details: Published Paper ID: IJRTI2208038
Registration ID:183484
Published In: Volume 7 Issue 8, August-2022
DOI (Digital Object Identifier):
Page No: 228 - 236
Country: Nellore, andhra pradesh, India
Research Area: Science & Technology
Publisher : IJ Publication
Published Paper URL :
Published Paper PDF:
Share Article:

Click Here to Download This Article

Article Preview
Click Here to Download This Article

Major Indexing from
Google Scholar ResearcherID Thomson Reuters Mendeley : reference manager : cornell university library Research Gate CiteSeerX DOAJ : Directory of Open Access Journals
DRJI Index Copernicus International Scribd DocStoc

ISSN Details

ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED
Journal Starting Year (ESTD) : 2016

DOI (A digital object identifier)

Providing A digital object identifier by DOI.ONE
How to Get DOI?


Open Access License Policy

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Creative Commons License This material is Open Knowledge This material is Open Data This material is Open Content

Important Details

Social Media

Join RMS/Earn 300


Indexing Partner