Archives

  • 2022-09
  • 2022-08
  • 2022-07
  • 2022-06
  • 2022-05
  • 2022-04
  • 2021-03
  • 2020-08
  • 2020-07
  • 2020-03
  • 2019-11
  • 2019-10
  • 2019-09
  • 2019-08
  • 2019-07
  • br According to the results it can be concluded that

    2022-09-17


    According to the results, it gamma-Glu-Cys can be concluded that the CAD is suitable to help the doctor for making diagnosis decision. Com-pared with previous study (Zulfanahri et al., 2017; Nugroho et al., 2017a,b), the proposed method also obtains high accuracy. However, this work still has some limitations. The determination of region of interest at the initial process is still manually con-ducted. Moreover, initial window and iteration in using active con-tour at the segmentation process are still manual as well. For the next work, automated processes are necessary to solve these limitations.
    Fig. 14. (a) Output of CAD shows the class of internal characteristics and the final diagnosis, (b) the bigger picture of classification and diagnosis information.
    Table 5
    Training results.
    Component Average of
    Standard Deviation of Accuracy
    Accuracy Sensitivity Specificity PPV NPV
    Please cite this article as: H. A. Nugroho, Zulfanahri, E. L. Frannita et al., Computer aided diagnosis for thyroid cancer system based on internal and external characteristics, Journal of King Saud University – Computer and Information Scienceshttps://doi.org/10.1016/j.jksuci.2019.01.007
    H.A. Nugroho et al. / Journal of King Saud University – Computer and Information Sciences xxx (xxxx) xxx 11
    Table 6
    Confusion matrix for external characteristics.
    External characteristics
    Predicted class
    Malignant
    Benign
    True class Malignant
    Benign
    Table 7
    Confusion matrix for internal characteristics.
    External characteristics
    Predicted class
    Malignant
    Benign
    True class Malignant
    Benign
    Table 8
    Testing results.
    Component
    Average of
    Accuracy Sensitivity Specificity PPV NPV
    4. Conclusion
    The computer-aided diagnosis for thyroid cancer system based on internal and external characteristics has been developed. The system aims to assist the radiologists in analysing important char-acteristics to achieve final diagnosis. The external and internal characteristics have been validated by calculating accuracy, sensi-tivity, specificity, PPV and NPV. The performance analysis on exter-nal characteristics obtains level of accuracy, sensitivity, specificity, PPV and NPV of 97.78%, 100%, 95.45%, 95.83% and 100%, respec-tively. Moreover, for internal characteristics, the results obtained are 94.44%, 95.35%, 90.91%, 97.62% and 83.33%, respectively. The result indicates that the system is reliable in fulfilling the needs of radiologist as the second opinion to diagnose thyroid cancer objectively.
    There are still many steps while performing the system becomes the weakness of current CAD. The next version of the CAD could be less manual and more automatic so the radiologist can understand easily. Besides, combining all the features inside this CAD is a future work that plans to be established.
    Acknowledgements
    The authors would like to acknowledge the Department of Radi-ology, Sardjito Hospital, Yogyakarta for providing the database in this research and also to radiologists for the meaningful sharing knowledge. We would also like to thank the colleagues of Intelli-gent System research group in our Department for inspiring dis-cussion also the Indonesian Endowment Fund for Education (LPDP) and Directorate General of Higher Education, Ministry of Research, Technology and Higher Education for support funding in the study and research programs. Finally, the authors would like to thanks the anonymous reviewers for encouraging reviews and recommendations.
    References
    Delibasis, K.K., Asvestas, P.A., Matsopoulos, G.K., Zoulias, E., Tseleni-balafouta, S., 2009. Computer-aided diagnosis of thyroid malignancy using an artificial immune system classification algorithm. IEEE Trans. Inf. Technol. Biomed. 13