CT Liver Tumor Segmentation using a Hybrid Deep Convolutional Neural Network RA-UNet

Convolutional Neural Networks (CNNs) have currently acquired focus from researchers to address computer vision and medical image processing problems. Popular though they may be, most methods can only handle 2D pictures, but in medical liver tumor segmentation 3D volumes are normally analyzed in clinical data. Here, we offer a technique for segmenting 3D images using a fully convolutional neural network that has been trained on volumetric data. Our CNN is taught to predict segmentation for the entire volume simultaneously after being trained from scratch on prostate Magnetic Resonance Imaging (MRI) data. Liver cancer is second among male cancers in terms of mortality and sixth among female cancers in terms of mortality. Diagnosing, treating and assessing the efficacy of liver cancer all rely on accurate segmentation of hepatic lesions. As a standardized benchmark, LiTS (Liver Tumor Segmentation Challenge) allows researchers to evaluate and compare several automated liver lesion segmentation approaches. Computed tomography (CT) allows for early diagnosis, which is key to a high recovery rate. However, manually reviewing CT slices for thousands or millions of patients is difficult, tiring, costly, time-consuming, and prone to mistakes. Thus, we need a trustworthy, easy, and precise approach to automating this procedure. This work contains convolutional neural networks (CNNs) to solve all those problems; specifically, a trained RA-UNet(or) Res U-Net model using the 3D-IRCADb01 dataset, which includes CT slices from patients and masks for liver, tumors, and other organs. RA-UNet model combines the U-Net and ResNet models, instead of using convolutional blocks, it employs Residual blocks A second CNN was trained to segment the tumours based on the output of the first CNN after a first Cascaded Convolutional Neural Network (CNN) was used to segment the liver and extract the ROI. The dice coefficient was 95%, while the True Value Accuracy was 99%.

  • Research Type: Applied Research
  • Paper Type: Experimental Research Paper
  • Vol.6 , Issue 3 , Pages: 1 - 10, May 2024
  • Published on: 10 May, 2024
  • Issue Type: Regular
  • Cite Score
    :

    100

  • No. of authors
    :

    75

  • No. of Downloads
    :

    43

  • Cite Score
    :

    100

  • No. of authors
    :

    75

  • No. of Downloads
    :

    43

  • Cite Score
    :

    100

  • No. of authors
    :

    75

  • No. of Downloads
    :

    43

About Authors:
P. GANGADHARA REDDY
India
Aditya College of Engineering

Dr. P.GANGADHARA REDDY is working as Associate Professor in the Department of ECE, at Aditya College of Engineering, Madanepalle, AP, India."


Copyright © 2024, This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC-BY-NY-SA). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Corresponding Author: P. GANGADHARA REDDY, gangadharareddy.p@gmail.com

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Conflict of interest: The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher’s note: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Global Readers View
  • No. of Readers
    131
  • No. of Reaction
    0
  • No. of Comments
    0
  • No. of Downloads
    4

Or share your Opinion

Edited by:
  • Editor-In-Chief
    IJRDES
Reviewed by:
  • KUPPIREDDY KRISHNA REDDY
    KUPPIREDDY KRISHNA REDDY
    India
    MOTHER THERESA INSTITUTE OF ENGINEERING & TECHNOLOGY
  • Thatigutla Amaranatha Reddy
    Thatigutla Amaranatha Reddy
    India
    Aditya College of Engineering
  • YEGIREDDI RAMESH
    YEGIREDDI RAMESH
    India
    Aditya Institute of Technology and Management
Similar Papers
Authors’ other publications
  • 64 - BIT Implementation o...
    15 Sep, 2024

    The Inter-Integrated Circuit (I2C) protocol is a versatile communication standard used in embedded systems and integrated circuits. Two...

  • Management of Traffic By...
    17 Jul, 2024

    An integrated system for traffic management that combines environmental monitoring and pollutant detection using Raspberry Pi. The system...

  • High Speed Carry Look Ahe...
    16 Jan, 2024

    An integrated system for traffic management that combines environmental monitoring and pollutant detection using Raspberry Pi. The system...

  • Performance Trade-offs in...
    19 Jan, 2024

    Designers of RF (Radio Frequency) circuits must exercise caution throughout the different phases of system design. Prior to...

×