Abstract
Anatomical detection of objects of interest or nodules in lung is a not easy task. We present a three-stage method which enables localization and identification of small nodules in medical 3D image space: primitive detector is supervised learned from a small set of annotated abdomen CT slides; the second stage implements the detection to perform multifeatured classification of image space; the last stage regulates the clusters’ allocation with spatial-sensitive analysis of undersampling to achieve better classifier performance. Our main novel contribution is to implement appropriate multivariable imbalancing for improvement of small nodules prediction in CT lung images. The imbalancing task is proposed to apply the outcomes of second learning stage, namely early lung segmentation and initial nodules allocation. In the long term, such method can also be used for object detection with class imbalance in other medical voxel images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Harris, D., Moller, C.C.: The introduction of a clinical practice guideline for the management of suspected appendicitis may influence computed tomography usage. J. Surg. Emerg. Med. (2018)
Burris, N.S., Johnson, K.M., Larson, P.E., Hope, M.D., Nagle, S.K., Behr, S.C., Hope, T.A.: Detection of small pulmonary nodules with ultrashort echo time sequences in oncology patients by using a PET/MR system. Radiology 278(1) (2016)
Ciompi, F., Jacobs, C., Scholten, E.T., et al.: Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images. IEEE Trans. Med. Imaging 34(4), 962–973 (2015)
Kamnitsas, K., Castro, D.C., Folgoc, L.L., Walker, I., Tanno, R., Rueckert, D., Glocker, B., Criminisi, A., Nori, A.: Semi-supervised learning via compact latent space clustering. Mach. Learn. (2018)
Bhateja, V., Patel, H., Krishn, A., Sahu, A., Lay-Ekuakille, A.: Multimodal medical image sensor fusion framework using cascade of wavelet and contourlet transform domains. IEEE Sens. J. 15(12), 6783–6790 (2015)
Shotton, J., Blake, A., Cipolla, R.: Contour-based learning for object. In: ICCV ‘05, vol. 1, pp. 503–510 (2005)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Lemaître, G., Nogueira, F., Aridas, C.K.: Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18–1, 559–563 (2017)
Barber, D.: Bayesian Reasoning and Machine Learning. Cambridge University Press (2012)
Kumar, A., Mukhopadhyay, S., Khandelwal, N.: 3D Texture Analysis of Solitary Pulmonary Nodules Using Co-occurrence Matrix from Volumetric Lung CT Images, pp. 1–4. SPIE (2013)
Kuruvilla, J., Gunavathi, K.: Bayesian reasoning and machine learning. Comput. Meth Prog Bio. 113, 202–209 (2014)
Chen, H., Zhang, J., Xu, Y., Chen, B., Zhang, K.: Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans. Expert Syst. Appl. 39, 11503–11509 (2012)
Lee, M., Boroczky, L., Sungur, K., Cann, A., Borczuk, A., Kawut, S., et al.: Computer-aided diagnosis of pulmonary nodules using a two-step approach for feature selection and classifier ensemble construction. Artif. Intell. Med. 50, 43–53 (2010)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Zhang, F., Song, Y., Cai, W., Lee, M., Zhou, Y., Huang, H., et al.: Lung nodule classification with multilevel patch-based context analysis. IEEE Trans. Biomed. Eng. 61, 1155–1166 (2014)
Orozco, H.M., Villegas, O.O.V., Sánchez, V.G.C., Domínguez, H.D.J.O., Alfaro, M.D.J.N.: Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. Biomed. Eng. Online 14(9) (2015)
ELCAP Public lung image database. http://www.via.cornell.edu/databases/lungdb.html
Armato, S., McLennan, G., Bidaut, L., McNitt-Gray, M., Meyer, C.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38, 915–931 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Anh, D.N., Hoang, N.T. (2020). Learning Validation for Lung CT Images by Multivariable Class Imbalance. In: Satapathy, S., Bhateja, V., Nguyen, B., Nguyen, N., Le, DN. (eds) Frontiers in Intelligent Computing: Theory and Applications. Advances in Intelligent Systems and Computing, vol 1013. Springer, Singapore. https://doi.org/10.1007/978-981-32-9186-7_6
Download citation
DOI: https://doi.org/10.1007/978-981-32-9186-7_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9185-0
Online ISBN: 978-981-32-9186-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)