Archives

  • 2018-07
  • 2020-07
  • 2020-08
  • br A Critical assessment of

    2020-08-18


    A Critical assessment of ANN was carried out in Dande et al. [10] which results in an increase in the efficacy and specificity of the diagnostic techniques, but it fails to minimize the computa-tional complexity. Tumor tissue based on pathological evaluation is considered to be one of the most pivotal for early diagnosis in cancer patients. However, the automated image analysis methods have the potential to improve the accuracy of disease diagnosis and to minimize human errors. Khosravia et al. [11] proposed different computational methods using convolutional neural net-works (CNN), where a stand-alone pipeline was constructed in an effective manner to classify several histopathology images across different types of cancer. But, it fails to minimize the computation cost while classifying the various types of cancer.
    Sharma et al. [18] proposed a two-stage hybrid ensemble clas-sification technique to increase the prediction accuracy of chronic kidney disease with ML technique. It improves the disease diag-nosis, but the multistage classification was not performed with minimum time. Early diagnoses of lung cancers and differentia-tion between the tumor types and non-tumor types have been required to improve the patient survival rate. In Hosseinzadeh et al. [13], a diagnostic system with structural and physicochemi-cal attributes of proteins via feature extraction, feature selection, and prediction models was designed. Then, the ML models were
    Table 1
    Comparison of the proposed approach with the state-of-the-art approaches.
    Author Year Approach Objective Pros Cons
    Das et al. [4] 2010 Ensemble learning methods To classify the Valvular Minimize the classification Classification accuracy rate
    heart disease time remained unsolved
    Ghorai et al. [3] 2011 Nonparallel Plane Proximal Perform cancer classification Provides better classification Valvular WY-14643 disorders
    Classifier (NPPC) with higher accuracy in a accuracy with lesser classification was difficult
    Computer Aided Diagnosis computation time
    Baz et al. [12] 2012 Computer-aided diagnosis Lung cancer diagnosis Achieve better detection Accurate feature selection
    (CAD) system
    and diagnosis of lung was not performed
    nodules
    Hosseinzadeh et al. [13] 2013 Machine learning models Predict and detect the type Provide more accurate The false positive rate was
    of lung tumors results in lung tumor not minimized
    detection
    Adetiba et al. [8] 2015 Radial Basis Function Neural Classifies the Lung Cancer Improve classification, Performance of feature
    Network with Affine
    accuracy and achieves, and extraction was not
    Transforms
    low mean square error improved
    Kumar et al. [14] 2016 Evolutionary algorithms Lung cancer detection Detect the lung cancer The error rate was not
    accurately with minimum minimized
    time
    Huda et al. [6] 2016 Global optimization based Tumor classification with Increases the imbalanced Classification time was not
    hybrid wrapper-filter the imbalanced healthcare healthcare data minimized
    feature selection with data classification
    ensemble classification
    Podolsky et al. [15] 2016 Machine learning algorithm Lung cancer diagnosis Increase the accuracy of Classification time remained
    predicting cancer unsolved
    susceptibility and Minimize
    false positive
    Zhou et al. [16] 2017 Multi-modality and Extract numbers of Increase the disease Failed to minimize the
    multi-classifier radiomics quantitative features and prediction accuracy with disease prediction time.
    predictive models disease prediction the features
    Kang et al. [17] 2017 Multi-view convolutional lung nodule classification Increases the classification Failed to attain accurate
    neural networks (MV-CNN)
    accuracy and minimizes the disease prediction with
    time features
    Dande et al. [10] 2017 Artificial Neural Network Diagnosis and evaluation of Increase the efficacy and Failed to minimize the
    medical conditions specificity of disease computational complexity
    diagnosis
    Costaa et al. [5] 2018 Generalized mixture (GM) Increase the classification Handles single-label Multi-label classification
    functions accuracy of a stability classification classification problems problem remained
    system
    unaddressed
    Hussein et al. [7] 2018 Proportion-Support Vector Categorizes the Lung Improve the diagnosing Failed to minimize the error
    Machine (SVM) Nodules accuracy rate
    Jain et al. [9] 2018 Feature selection and Enhancing the accuracy of Classification systems for The classification time was
    parallel classification classification systems effective disease prediction not minimized