LIVER CANCER DETECTION USING HYBRIDIZED FULLY CONVOLUTIONAL NEURAL NETWORK BASED ON DEEP LEARNING FRAMEWORK.

Liver cancer is one in every of the foremost death factors within the world. Early detection and correct staging of liver disease is a crucial issue in sensible radiology. Liver lesions check with those abnormal tissues that are found within the liver. Liver lesions are a wound or injury within the...

Descripción completa

Detalles Bibliográficos
Publicado en:Turkish Journal of Physiotherapy Rehabilitation Vol. 32; no. 2; pp. 2047 - 2054
Autores principales: SHANMUGAVADIVEL, G., KUMAR, PNANDHA, KUMAR, V. SNAVEEN, PARTHIBAN, V.
Formato: diagnostic images pictorial tables/charts Journal Article
Publicado: Turkish Journal of Physiotherapy & Rehabilitation 2021
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=151006197&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 151006197
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        13008757
        YU1
      jtl: Turkish Journal of Physiotherapy Rehabilitation
      issn: 13008757
      maglogo: N
    pubinfo:
      dt: 2021
      vid: 32
      iid: 2
      pid: 20392
      pub: Turkish Journal of Physiotherapy & Rehabilitation
      place: Kizilay/ Ankara, <Blank>
    artinfo:
      ui:
        151006197
        151006197
        151006197
        151006197
      ppf: 2047
      ppct: 7
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: LIVER CANCER DETECTION USING HYBRIDIZED FULLY CONVOLUTIONAL NEURAL NETWORK BASED ON DEEP LEARNING FRAMEWORK.
      aug:
        au:
          SHANMUGAVADIVEL, G.
          KUMAR, PNANDHA
          KUMAR, V. SNAVEEN
          PARTHIBAN, V.
        affil: Assistant Professor, Department of Electronics and Communication Engineering, M. Kumarasamy College of Engineering, Karur, Tamilnadu
      sug:
        subj:
          Liver Neoplasms Diagnosis
          Neural Networks (Computer)
          Liver Neoplasms Radiography
          Deep Learning
          Conceptual Framework
          Tomography, X-Ray Computed
          Machine Learning
          Image Processing, Computer Assisted
      ab: Liver cancer is one in every of the foremost death factors within the world. Early detection and correct staging of liver disease is a crucial issue in sensible radiology. Liver lesions check with those abnormal tissues that are found within the liver. Liver lesions are a wound or injury within the tissue areas of the body thanks to injury caused by a wound or sickness. These lesions are often known during a CT scan by a distinction in element intensity from different regions of the liver. For correct clinical treatment, physical segmentation of CT scan is tough and a long task. Instead, computerized segmentation may be a terribly difficult task, as well as liver extend by a hundred and fifty slices of a CT image. Segmentation of liver tumors is a crucial necessity task before any surgical intervention. An exact and correct analysis of the lesions allows for the obtainable therapies that may be provided to the patient. It will facilitate decide the simplest treatment approach also as track the progress of the medical aid over associate interval of your time. So as to subsume this challenge, during this project we have a tendency to propose the utilization of advanced machine learning and segmentation techniques named as guided Active Contour(GAC) technique to cluster the lesions. Then using features extraction techniques to extract the options and phase the liver supported similar pixels. And additionally implement Convolutional Neural Network algorithmic rule to classify the liver diseases with improved accuracy rate.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        pictorial
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N