Contact : 9561854529 Email : submitpaper@ijaea.com editorinchief.ijaea@gmail.com Working Hours: 9am to 9PM

International Journal of Advanced Engineering Application

ISSN: 3048-6807

Submit Paper Apply for Reviewer

Forecasting Radiological Panel Opinions Through Ensemble Machine Learning Classifiers

Author(s):Joao M. Santos1, Ana P. Silva2, and Carlos F. Mendes3

Affiliation: 1Department of Electrical Engineering, Agostinho Neto University, Luanda, Angola 2Department of Computer Science, Agostinho Neto University, Luanda, Angola 3Department of Civil Engineering, Agostinho Neto University, Luanda, Angola

Page No: 33-42

Volume issue & Publishing Year: Volume 2 Issue 1,Jan-2025

Journal: International Journal of Advanced Engineering Application (IJAEA)

ISSN NO: 3048-6807

DOI: https://doi.org/10.5281/zenodo.17673638

Download PDF

Article Indexing:

Abstract:
This paper explores the use of an ensemble of machine learning classifiers combined with active learning strategies to predict radiologists' assessments of lung nodule characteristics in the Lung Image Database Consortium (LIDC). The study focuses on modeling and predicting agreement among radiologists� semantic ratings across seven key nodule characteristics: spiculation, lobulation, texture, sphericity, margin, subtlety, and malignancy. These characteristics are essential in evaluating and diagnosing pulmonary nodules.The proposed approach utilizes an ensemble of classifiers, functioning as a simulated "computer panel of experts," to analyze 64 image features extracted from the nodules. These features span four critical categories: shape, intensity, texture, and size. By leveraging active learning, the system initiates the training phase with nodules where radiologists� semantic ratings are consistent. The system then progressively learns to classify nodules with varying degrees of disagreement among radiologists, effectively addressing uncertainty and variability in expert interpretations. The results demonstrate that the ensemble approach outperforms individual classifiers in terms of classification accuracy, showcasing its ability to synthesize diverse perspectives and make more reliable predictions. This enhanced predictive capability underscores the potential of machine learning to serve as a supportive tool in radiological diagnostics. By acting as a "second read" for physicians, the proposed system can improve consistency in radiological interpretations, reduce diagnostic variability, and ultimately enhance patient care. The findings highlight the promising role of advanced computational methods in augmenting human expertise in medical imaging analysis.

Keywords: Ensemble learning; Active learning; Lung nodule classification; LIDC database; Radiological assessment; Semantic characteristics; Nodule spiculation; Nodule lobulation; Nodule texture; Nodule sphericity; Nodule margin; Nodule subtlety; Malignancy prediction; Machine learning in radiology; Image feature analysis

Reference:

  • [1] S. G. Armato III, G. McLennan, M. F. McNitt-Gray, C. R. Meyer, D. Yankelevitz, D. R. Aberle, C. I. Henschke, E. A. Hoffman, E. A. Kazerooni, H. MacMahon, A. P. Reeves, B. Y. Croft, and L. P. Clarke, “Lung Image Database Consortium: Developing a resource for the medical imaging research community,” Radiology, vol. 232, pp. 739–748, 2004.
  • [2] D. Raicu, D. Zinovev, J. Furst, and E. Varutbangkul, “Semi-supervised learning approaches for predicting lung nodules semantic characteristics,” Intell. Decis. Technol., vol. 3, no. 2, 2009.
  • [3] O. Chapelle, B. Schölkopf, and A. Zien, Semi-Supervised Learning. MIT Press, Cambridge, MA, USA, 2006.
  • [4] J. Cohen, “Weighted kappa: Nominal scale agreement with provision for scaled disagreement or partial credit,” Psychol. Bull., vol. 70, pp. 213–220, 1968.
  • [5] M. F. McNitt-Gray, E. M. Hart, N. Wyckoff, J. W. Sayre, J. G. Goldin, and D. R. Aberle, “A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution CT: Preliminary results,” Med. Phys., vol. 26, pp. 880–888, 1999.
  • [6] M. F. McNitt-Gray, N. Wyckoff, J. W. Sayre, J. G. Goldin, and D. R. Aberle, “The effects of co-occurrence matrix based texture parameters on the classification of solitary pulmonary nodules imaged on computed tomography,” Comput. Med. Imaging Graph., vol. 23, pp. 339–348, 1999.
  • [7] S. C. B. Lo, L. Y. Hsu, M. T. Freedman, Y. M. F. Lure, and H. Zhao, “Classification of lung nodules in diagnostic CT: An approach based on 3-D vascular features, nodule density distributions, and shape features,” in Proc. SPIE Med. Imaging Conf., San Diego, CA, pp. 183–189, Feb. 2003.
  • [8] S. G. Armato III, M. B. Altman, J. Wilkie, S. Sone, F. Li, K. Doi, and A. S. Roy, “Automated lung nodule classification following automated nodule detection on CT: A serial approach,” Med. Phys., vol. 30, pp. 1188–1197, 2003.
  • [9] S. Takashima, S. Sone, F. Li, Y. Maruyama, M. Hasegawa, and M. Kadoya, “Indeterminate solitary pulmonary nodules revealed at population-based CT screening of the lung: Using first follow-up diagnostic CT to differentiate benign and malignant lesions,” Am. J. Roentgenol., vol. 180, pp. 1255–1263, 2003.
  • [10] S. Takashima, S. Sone, F. Li, Y. Maruyama, M. Hasegawa, T. Matsushita, F. Takayama, and M. Kadoya, “Small solitary pulmonary nodules (<1 cm) detected at population-based CT screening for lung cancer: Reliable high-resolution CT features of benign lesions,” Am. J. Roentgenol., vol. 180, pp. 955–964, 2003.
  • [11] S. Shah, M. McNitt-Gray, S. Rogers, J. Goldin, D. Aberle, R. Suh, K. DeZoysa, and M. Brown, “Computer-aided lung nodule diagnosis using a simple classifier,” Int. Congr. Ser., vol. 6, pp. 952–955, 2004.
  • [12] R. C. Holte, “Very simple classification rules perform well on most commonly used datasets,” Mach. Learning, vol. 11, pp. 63–91, 1993.
  • [13] C. C. Samuel, V. Saravanan, and D. M. R. Vimala, “Lung nodule diagnosis from CT images using fuzzy logic,” in Proc. Int. Conf. Comput. Intell. Multimedia Appl., Sivakasi, Tamilnadu, India, pp. 159–163, Dec. 2007.
  • [14] I. Sluimer, A. Schilham, M. Prokop, and B. van Ginneken, “Computer analysis of computed tomography scans of the lung: A survey,” IEEE Trans. Med. Imaging, vol. 4, pp. 385–405, 2006.
  • [15] J. G. Goldin, M. S. Brown, and I. Petkovska, “Computer-aided diagnosis in lung nodule assessment,” J. Thorac. Imaging, vol. 23, pp. 97–104, 2008.
  • [16] J. Gurney, “Determining the likelihood of malignancy in solitary pulmonary nodules with Bayesian analysis. Part I. Theory,” Radiology, vol. 186, pp. 405–413, 1993.
  • [17] J. Gurney, D. Lyddon, and J. McKay, “Determining the likelihood of malignancy in solitary pulmonary nodules with Bayesian analysis. Part II. Application,” Radiology, vol. 186, pp. 415–422, 1993.
  • [18] Y. Matsuki, K. Nakamura, H. Watanabe, T. Aoki, H. Nakata, S. Katsuragawa, and K. Doi, “Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: Evaluation with receiver operating characteristic analysis,” Am. J. Roentgenol., vol. 178, pp. 657–663, 2002.
  • [19] M. Aoyama, Q. Li, S. Katsuragawa, F. Li, S. Sone, and K. Doi, “Computerized scheme for determination of the likelihood measure of malignancy for pulmonary nodules on low-dose CT images,” Med. Phys., vol. 30, pp. 387–394, 2003.
  • [20] C. Kahn, D. Channin, and D. Rubin, “An ontology for PACS integration,” J. Digit. Imaging, vol. 12, pp. 316–327, 2006.
  • [21] A. S. Barb, C. R. Shyu, and Y. P. Sethi, “Knowledge representation and sharing using visual semantic modeling for diagnostic medical image databases,” IEEE Trans. Inf. Technol. Biomed., vol. 9, pp. 538–553, 2005.
  • [22] S. Ebadollahi, A. Coden, M. A. Tanenblatt, S. F. Chang, T. F. Syeda-Mahmood, and A. Amir, “Concept-based electronic health records: Opportunities and challenges,” in Proc. ACM Multimedia, pp. 997–1006, 2006.
  • [23] S. Ebadollahi, D. E. Johnson, and M. Diao, “Retrieving clinical cases through a concept space representation of text and images,” SPIE Med. Imaging Symp., 2008.
  • [24] K. Nie, J. H. Chen, H. J. Yu, Y. Chu, O. Nalcioglu, and M. Y. Su, “Quantitative analysis of lesion morphology and texture features for diagnostic prediction in breast MRI,” Acad. Radiol., vol. 15, pp. 1513–1525, 2008.
  • [25] G. P. Liney, M. Sreenivas, P. Gibbs, R. Garcia-Alvarez, and L. W. Turnbull, “Breast lesion analysis of shape technique: Semi-automated vs. manual,” in Proc. SPIE Med. Imaging, Feb. (year not specified).
  • [26] D. S. Raicu, E. Varutbangkul, J. G. Cisneros, J. D. Furst, D. S. Channin, and S. G. Armato III, “Semantics and image content integration for pulmonary nodule interpretation in thoracic computed tomography,” in Proc. SPIE Med. Imaging Conf., San Diego, CA, Feb. 2007.
  • [27] D. S. Raicu, E. Varutbangkul, J. D. Furst, and S. G. Armato III, “Modeling semantics from image data: Opportunities from LIDC,” Int. J. Biomed. Eng. Technol., pp. 1–22, 2008.
  • [28] P. Opulencia, D. S. Channin, D. S. Raicu, and J. D. Furst, “Mapping LIDC, RadLex, and lung nodule image features,” J. Digit. Imaging, 2009.
  • [29] J. Cohen, “A coefficient of agreement for nominal scale,” Educ. Psychol. Meas., vol. 20, pp. 37–46, 1960.
  • [30] J. L. Fleiss, “Measuring nominal scale agreement among many raters,” Psychol. Bull., vol. 76, pp. 378–382, 1971.
  • [31] J. R. Landis and G. G. Koch, “An application of hierarchical Kappa-type statistics in the assessment of majority agreement among multiple observers,” Biometrics, vol. 33, pp. 363–374, 1977.
  • [32] J. R. Landis and G. G. Koch, “The measurement of observer agreement for categorical data,” Biometrics, vol. 33, pp. 159–174, 1977.
  • [33] H. C. Kraemer, “Extension of the kappa coefficient,” Biometrics, vol. 36, pp. 207–216, 1980.
  • [34] J. L. Fleiss, “Measuring nominal scale agreement among many raters,” Psychol. Bull., vol. 76, pp. 378–382, 1971.
  • [35] A. J. Viera and J. M. Garrett, “Understanding interobserver agreement: The Kappa statistic,” Fam. Med., vol. 5, pp. 360–363, 2005.
  • [36] M. F. McNitt-Gray, S. G. Armato III, C. R. Meyer, A. P. Reeves, G. McLennan, R. C. Pais, J. Freymann, M. S. Brown, R. M. Engelmann, P. H. Bland, G. E. Laderach, C. Piker, J. Guo, Z. Towfic, D. P. Qing, D. F. Yankelevitz, D. R. Aberle, E. J. van Beek, H. MacMahon, E. A. Kazerooni, B. Y. Croft, and L. P. Clarke, “The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation,” Acad. Radiol., vol. 12, pp. 1464–1474, 2007.
  • [37] C. Philips, D. Li, J. Furst, and D. Raicu, “An analysis of co-occurrence and Gabor texture classification in 2D and 3D,” in Proc. CARS, Barcelona, Spain, 2008.
  • [38] P. Melville and R. Mooney, “Constructing diverse classifier ensembles using artificial training examples,” in Proc. 18th Int. Joint Conf. Artif. Intell., Acapulco, Mexico, pp. 505–510, 2003.
  • [39] P. Melville and R. Mooney, “Diverse ensembles for active learning,” in Proc. Int. Conf. Mach. Learn., Banff, Alberta, Canada, pp. 584–591, July 2004.
  • [40] T. M. Mitchell, Machine Learning. McGraw-Hill, New York, NY, USA, 1997.
  • [41] S. Siena, O. Zinoveva, and D. Raicu, “Area and shape-dependent variability metric for evaluating panel segmentations of lung nodules in LIDC data,” in Proc. SPIE Med. Imaging Conf., San Francisco, CA, Feb. 2010