informИнформатикаInformatics1816-03012617-6963UIIP NASBinform-763Research ArticleОБРАБОТКА СИГНАЛОВ, ИЗОБРАЖЕНИЙ, РЕЧИ, ТЕКСТА И РАСПОЗНАВАНИЕ ОБРАЗОВSIGNAL, IMAGE, SPEECH, TEXT PROCESSING AND PATTERN RECOGNITIONИССЛЕДОВАНИЕ ЭФФЕКТИВНОСТИ ЯРКОСТНОЙ ИНФОРМАЦИИ ДЛЯ СЕГМЕНТАЦИИ УЧАСТКОВ АТЕЛЕКТАЗА И РАКОВЫХ ОПУХОЛЕЙ НА ИЗОБРАЖЕНИЯХ ЛЕГКОГО, ПОЛУЧЕННЫХ С ПОМОЩЬЮ КОМПЬЮТЕРНОЙ ТОМОГРАФИИКовалевВ. А.ХоружикС. А.МихайловА. Н.Университет Сюррей ГилфордUnited KingdomГУ «НИИ онкологии и медицинской радиологии им. Н.Н. Александрова», Белорусская медицинская академия последипломного образованияBelarusОтделение медицинских наук НАН Беларуси, Белорусская медицинская академия последипломного образованияBelarus20051701201902(6)93101Copyright © Ковалев В.А., Хоружик С.А., Михайлов А.Н., 20192019Ковалев В.А., Хоружик С.А., Михайлов А.Н.Ковалев В.А., Хоружик С.А., Михайлов А.Н.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://inf.grid.by/jour/article/view/763

Исследуется и количественно оценивается полезность яркостной информации КТ-изобра-жений легкого для сегментации участков ателектаза и раковых опухолей, которые практически неразличимы при визуальном анализе. Проводится анализ статистической значимости межклассовых различий ателектаза и опухоли и осуществляется оценка точности классификации при использовании методов иерархической кластеризации, опорных векторов и метода случайного леса. Показано, что степень полезности яркостной информации изменяется от пациента к пациенту и зависит, главным образом, от размера выборки вокселов.

ReferencesMira J.G., Fullerton G.D., Ezekiel J. Evaluation of computed tomography numbers for treatment planning of lung cancer // International Journal of Radiation Oncology, Biology, Physics.  V. 8. – № 9. – 1982. – P. 1625–1628.Mira J.G., Fullerton G.D., Ezekiel J. Evaluation of computed tomography numbers for treatment planning of lung cancer // International Journal of Radiation Oncology, Biology, Physics.  V. 8. – № 9. – 1982. – P. 1625–1628.Bowden P., Fisher R., Mac Manus M. Measurement of lung tumor volumes using three-dimensional computer planning software // International Journal of Radiation Oncology, Biology, Physics. – V. 53 – № 3. – 2002. – P. 566–573.Bowden P., Fisher R., Mac Manus M. Measurement of lung tumor volumes using three-dimensional computer planning software // International Journal of Radiation Oncology, Biology, Physics. – V. 53 – № 3. – 2002. – P. 566–573.Bradley J., Thorstad W.L., Mutic S. Impact of FDG–PET on radiation therapy volume delineation in non–small–cell lung cancerт // International Journal of Radiation Oncology, Biology, Physics. – V. 59. – № 1. – 2004. – P. 78–86.Bradley J., Thorstad W.L., Mutic S. Impact of FDG–PET on radiation therapy volume delineation in non–small–cell lung cancerт // International Journal of Radiation Oncology, Biology, Physics. – V. 59. – № 1. – 2004. – P. 78–86.Balogh J.B., Caldwell C.B., Ung Y.C. Interobserver variation in contourinig gross tumour volume in carcinoma of the lung associated with pneumonitis and atelectasis: The impact of 18FDG–hybrid pet fusion // International Journal of Radiation Oncology, Biology, Physics. – V. 48. – № 3. – 2000. – P. 128–129.Balogh J.B., Caldwell C.B., Ung Y.C. Interobserver variation in contourinig gross tumour volume in carcinoma of the lung associated with pneumonitis and atelectasis: The impact of 18FDG–hybrid pet fusion // International Journal of Radiation Oncology, Biology, Physics. – V. 48. – № 3. – 2000. – P. 128–129.Venables W.N., Ripley B.D. Modern applied statistics with S, 4th edition. – Berlin: Springer, 2002. – 495 p.Venables W.N., Ripley B.D. Modern applied statistics with S, 4th edition. – Berlin: Springer, 2002. – 495 p.Maindonald J., Braun J. Data analysis and graphics using R: an example-based approach. – Cambridge: Cambridge University Press, 2003. – 400 p.Maindonald J., Braun J. Data analysis and graphics using R: an example-based approach. – Cambridge: Cambridge University Press, 2003. – 400 p.Press W.H., Teukolsky S.A., Vetterling W.T. Numerical recipes in C: the art of scientific computing, 2nd edition. – Cambridge: Cambridge University Press, 2002. – 994 p.Press W.H., Teukolsky S.A., Vetterling W.T. Numerical recipes in C: the art of scientific computing, 2nd edition. – Cambridge: Cambridge University Press, 2002. – 994 p.Breiman L.J., Friedman H., Olshen R.A. Classification and regression trees. – Belmont: Chapman & Hall (reprinted by First CRC Press), 1984. – 368 p.Breiman L.J., Friedman H., Olshen R.A. Classification and regression trees. – Belmont: Chapman & Hall (reprinted by First CRC Press), 1984. – 368 p.Therneau T.M., Atkinson B. Rpart: recursive partitioning in R, package version 3.1-22. – Rochester: Mayo Clinic, College of Medicine, Division of Biostatistics, 2005. – 28 p.Therneau T.M., Atkinson B. Rpart: recursive partitioning in R, package version 3.1-22. – Rochester: Mayo Clinic, College of Medicine, Division of Biostatistics, 2005. – 28 p.Cortes C., Vapnik V. Support-vector network // Machine Learning. – V. 20. – № 3. – 1995. – P. 273–297.Cortes C., Vapnik V. Support-vector network // Machine Learning. – V. 20. – № 3. – 1995. – P. 273–297.Bennett K.P., Campbell C. Support vector machines: Hype or Hallelujah? // ACM Special Interest Group on Knowledge Discovery and Data Mining, Explorations. – V. 2. – № 2. – 2000. – P. 1–13.Bennett K.P., Campbell C. Support vector machines: Hype or Hallelujah? // ACM Special Interest Group on Knowledge Discovery and Data Mining, Explorations. – V. 2. – № 2. – 2000. – P. 1–13.Dimitriadou E., Hornik K., Leisch F. E1071: Miscellaneous functions of the department of statistics, R package version 1.5-7. – TU Wien, Austria, 2005. – 58 p.Dimitriadou E., Hornik K., Leisch F. E1071: Miscellaneous functions of the department of statistics, R package version 1.5-7. – TU Wien, Austria, 2005. – 58 p.Shapire R., Freund Y., Bartlett P. Boosting the margin: A new explanation for the effectiveness of voting methods // The Annals of Statistics. – V. 26. – № 5. – 1998. – P. 1651–1686.Shapire R., Freund Y., Bartlett P. Boosting the margin: A new explanation for the effectiveness of voting methods // The Annals of Statistics. – V. 26. – № 5. – 1998. – P. 1651–1686.Breiman L. Bagging predictors // Machine Learning. – V. 24. – № 2. – 1996. – P. 123–140.Breiman L. Bagging predictors // Machine Learning. – V. 24. – № 2. – 1996. – P. 123–140.Wehrens R., Putter H., Buydens L.M.C. The bootstrap: a tutorial // Chemometrics and intelligent laboratory systems. – V. 54. – 2000. – P. 35–52.Wehrens R., Putter H., Buydens L.M.C. The bootstrap: a tutorial // Chemometrics and intelligent laboratory systems. – V. 54. – 2000. – P. 35–52.Breiman L. Random Forests // Machine Learning. – V. 45. – № 1. – 2001. – P. 5–32.Breiman L. Random Forests // Machine Learning. – V. 45. – № 1. – 2001. – P. 5–32.Breiman L., Cutler A. Wiener M. randomForest: Breiman and Cutler's random forests for classification and regression, R package version 4.5-4, 2005. – 25 p.Breiman L., Cutler A. Wiener M. randomForest: Breiman and Cutler's random forests for classification and regression, R package version 4.5-4, 2005. – 25 p.Cox T.F., Cox M.A. Multidimensional scaling. – London: Chapman & Hall, 1994. – 213 p.Cox T.F., Cox M.A. Multidimensional scaling. – London: Chapman & Hall, 1994. – 213 p.Cailliez F. The analytical solution of the additive constant problem // Psychometrika. – V. 48. – 1983. – P. 343–349.Cailliez F. The analytical solution of the additive constant problem // Psychometrika. – V. 48. – 1983. – P. 343–349.

The authors declare that there are no conflicts of interest present.