Abstract
Two dominant classes of modern approaches for the detection and classification of focal lesions are a bag of visual words and end-to-end learning machines. In this study, we reviewed and compared these approaches for lung nodule detection, colorectal polyp detection, and lung nodule classification in CT images. Specifically, we considered massive-training artificial neural networks (MTANNs) and convolutional neural networks (CNNs) as representatives of end-to-end learning machines, and Fisher vectors as a representative of the bag of visual words. We first compared CNNs with Fisher vectors in nodule detection, nodule classification, and polyp detection, concluding that the best performing CNN model achieved comparable performance to that of Fisher vectors. We also analyzed the performance of CNNs with varying depths for the 3 studied applications. Our experiments showed that the CNN architectures with 3 or 4 convolutional layers were more effective than shallower architectures, but we did not observe a further performance gain by using deeper architectures. We then compared CNNs with MTANNs, concluding that MTANNs outperformed CNNs for nodule detection and classification particularly given limited training data. Specifically, for nodule detection, the MTANNs generated 0.08 false positives per section at 100% sensitivity, which was significantly (p < 0.05) lower than the best performing CNN model with 0.67 false positives per section at the same level of sensitivity. We showed that the best performing CNN model achieved comparable performance to that of Fisher vectors in the 3 studied applications, and that MTANNs outperformed CNNs in nodule detection and classification, especially given limited training data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Suzuki, K., Armato III, S.G., Li, F., Sone, S., Doi, K.: Massive training artificial neural network (mtann) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. Med. Phys. 30(7), 1602–1617 (2003)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Perronnin, F., Sánchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Computer Vision–ECCV 2010, pp. 143–156. Springer (2010)
Suzuki, K., Horiba, I., Sugie, N.: Efficient approximation of neural filters for removing quantum noise from images. IEEE Trans. Signal Process. 50(7), 1787–1799 (2002)
Suzuki, K., Horiba, I., Sugie, N., Nanki, M.: Neural filter with selection of input features and its application to image quality improvement of medical image sequences. IEICE Trans. Inf. Syst. 85(10), 1710–1718 (2002)
Suzuki, K., Li, F., Sone, S., et al.: Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose ct by use of massive training artificial neural network. IEEE Trans. Med. Imag. 24(9), 1138–1150 (2005)
Suzuki, K., Yoshida, H., Näppi, J., Dachman, A.H.: Massive-training artificial neural network (mtann) for reduction of false positives in computer-aided detection of polyps: suppression of rectal tubes. Med. Phys. 33(10), 3814–3824 (2006)
Suzuki, K., Yoshida, H., Näppi, J., Armato III, S.G., Dachman, A.H.: Mixture of expert 3d massive-training anns for reduction of multiple types of false positives in cad for detection of polyps in ct colonography. Med. Phys. 35(2), 694–703 (2008)
Suzuki, K., Rockey, D.C., Dachman, A.H.: Ct colonography: advanced computer-aided detection scheme utilizing mtanns for detection of missed polyps in a multicenter clinical trial. Med. Phys. 37(1), 12–21 (2010)
Suzuki, K., Zhang, J., Xu, J.: Massive-training artificial neural network coupled with laplacian-eigenfunction-based dimensionality reduction for computer-aided detection of polyps in ct colonography. IEEE Trans. Med. Imag. 29(11), 1907–1917 (2010)
Xu, J.-W., Suzuki, K.: Massive-training support vector regression and gaussian process for false-positive reduction in computer-aided detection of polyps in ct colonography. Med. Phys. 38(4), 1888–1902 (2011)
Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
Fukushima, K.: Neocognitron capable of incremental learning. Neural Netw. 17(1), 37–46 (2004)
Deutsch, S.: A simplified version of kunihiko fukushima’s neocognitron. Biol. Cybern. 42(1), 17–21 (1981)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Le Cun, B.B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems. Citeseer (1990)
Tajbakhsh, N., Gotway, M.B., Liang, J.: Computer-aided pulmonary embolism detection using a novel vessel-aligned multi-planar image representation and convolutional neural networks. In: Medical Image Computing and Computer-Assisted Intervention MICCAI 2015 (2015)
Shen, W., Zhou, M., Yang, F., Yang, C., Tian, J.: Multi-scale convolutional neural networks for lung nodule classification. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M.J. (eds.), Information Processing in Medical Imaging. Lecture Notes in Computer Science, vol. 9123, pp. 588–599. Springer International Publishing (2015)
Roth, H., Lu, L., Seff, A., Cherry, K., Hoffman, J., Wang, S., Liu, J., Turkbey, E., Summers, R.: A new 2.5d representation for lymph node detection using random sets of deep convolutional neural network observations. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.), Medical Image Computing and Computer-Assisted Intervention MICCAI 2014. Lecture Notes in Computer Science, vol. 8673, pp. 520–527. Springer International Publishing (2014)
Tajbakhsh, N., Gurudu, S.R., Liang, J.: A comprehensive computer-aided polyp detection system for colonoscopy videos. In: Information Processing in Medical Imaging, pp. 327–338. Springer (2015)
Zhang, W., Li, R., Deng, H., Wang, L., Lin, W., Ji, S., Shen, D.: Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage 108, 214–224 (2015)
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., Larochelle, H.: Brain tumor segmentation with deep neural networks (2015). arXiv:1505.03540
Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., Hurst, R.T., Kendall, C.B., Gotway, M.B., Liang, J.: Convolutional neural networks for medical image analysis: Fine tuning or full training? IEEE Trans. Med. Imag. 35, 1299–1312 (2016)
Tajbakhsh, N., Gurudu, S.R., Liang, J.: Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 79–83. IEEE (2015)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005, vol. 2, pp. 524–531. IEEE (2005)
Song, Y., Cai, W., Zhang, F., Huang, H., Zhou, Y., Feng, D.D.: Bone texture characterization with fisher encoding of local descriptors. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 5–8. IEEE (2015)
Kwitt, R., Hegenbart, S., Rasiwasia, N., Vécsei, A., Uhl, A.: Do we need annotation experts? a case study in celiac disease classification. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014, pp. 454–461. Springer (2014)
Twinanda, A.P., De Mathelin, M., Padoy, N.: Fisher kernel based task boundary retrieval in laparoscopic database with single video query. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014, pp. 409–416. Springer (2014)
Manivannan, S., Wang, R., Trucco, E.: Inter-cluster features for medical image classification. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014, pp. 345–352. Springer (2014)
Lowe, D.G.: Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer vision, 1999, vol. 2, pp. 1150–1157. IEEE (1999)
Sone, S., Takashima, S., Li, F., Yang, Z., Honda, T., Maruyama, Y., Hasegawa, M., Yamanda, T., Kubo, K., Hanamura, K., et al.: Mass screening for lung cancer with mobile spiral computed tomography scanner. The Lancet 351(9111), 1242–1245 (1998)
Li, F., Sone, S., Abe, H., MacMahon, H., Armato, S.G., Doi, K.: Lung cancers missed at low-dose helical ct screening in a general population: comparison of clinical, histopathologic, and imaging findings 1. Radiology 225(3), 673–683 (2002)
Näppi, J., Yoshida, H.: Feature-guided analysis for reduction of false positives in cad of polyps for computed tomographic colonography. Med. Phys. 30(7), 1592–1601 (2003)
Yoshida, H., Näppi, J.: Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps. IEEE Trans. Med. Imag. 20(12), 1261–1274 (2001)
Egan, J.P., Greenberg, G.Z., Schulman, A.I.: Operating characteristics, signal detectability, and the method of free response. J. Acoust. Soc. Am. 33(8), 993–1007 (1961)
Chakraborty, D.P., Berbaum, K.S.: Observer studies involving detection and localization: modeling, analysis, and validation. Med. Phys. 31(8), 2313–2330 (2004)
Zhai, X., Chakraborty, D.: RJafroc: Analysis of Data Acquired Using the Receiver Operating Characteristic Paradigm and Its Extensions (2015). R package version 0.1.1
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., Mller, M.: Proc: an open-source package for r and s+ to analyze and compare roc curves. BMC Bioinform. 12(77) (2011)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding (2014). arXiv:1408.5093
Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms (2008). http://www.vlfeat.org/
Edwards, D.C., Kupinski, M.A., Metz, C.E., Nishikawa, R.M.: Maximum likelihood fitting of froc curves under an initial-detection-and-candidate-analysis model. Med. Phys. 29(12), 2861–2870 (2002)
van Ginneken, B., Setio, A.A., Jacobs, C., Ciompi, F.: Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 286–289, April 2015
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep fisher networks for large-scale image classification. In: Advances in Neural Information Processing Systems, pp. 163–171 (2013)
Sydorov, V., Sakurada, M., Lampert, C.: Deep fisher kernels-end to end learning of the fisher kernel gmm parameters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1402–1409 (2014)
Perronnin, F., Larlus, D.: Fisher vectors meet neural networks: A hybrid classification architecture. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3743–3752 (2015)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Computer Vision–ECCV 2014, pp. 818–833. Springer (2014)
Eigen, D., Rolfe, J., Fergus, R., LeCun, Y.: Understanding deep architectures using a recursive convolutional network (213). arXiv:1312.1847
Li, Q., Li, F., Shiraishi, J., Katsuragawa, S., Sone, S., Doi, K.: Investigation of new psychophysical measures for evaluation of similar images on thoracic computed tomography for distinction between benign and malignant nodules. Med. Phys. 30(10), 2584–2593 (2003)
Margeta, J., Criminisi, A., Cabrera Lozoya, R., Lee, D.C., Ayache, N.: Fine-tuned convolutional neural nets for cardiac mri acquisition plane recognition. Comput. Methods Biomech. Biomed. Eng. Imag. Vis., 1–11 (2015)
Bar, Y., Diamant, I., Wolf, L., Greenspan, H.: Deep learning with non-medical training used for chest pathology identification, vol. 9414, pp. 94140V–94140V–7 (2015)
Kobetski, M., Sullivan, J.: Improved boosting performance by explicit handling of ambiguous positive examples. In: Pattern Recognition Applications and Methods. Advances in Intelligent Systems and Computing, vol. 318, pp. 17–37 (2015)
Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Advances in Neural Information Processing Systems, pp. 2654–2662 (2014)
Suzuki, K., Doi, K.: How can a massive training artificial neural network (mtann) be trained with a small number of cases in the distinction between nodules and vessels in thoracic ct? 1. Acad. Radiol. 12(10), 1333–1341 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this chapter
Cite this chapter
Tajbakhsh, N., Suzuki, K. (2018). A Comparative Study of Modern Machine Learning Approaches for Focal Lesion Detection and Classification in Medical Images: BoVW, CNN and MTANN. In: Suzuki, K., Chen, Y. (eds) Artificial Intelligence in Decision Support Systems for Diagnosis in Medical Imaging. Intelligent Systems Reference Library, vol 140. Springer, Cham. https://doi.org/10.1007/978-3-319-68843-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-68843-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68842-8
Online ISBN: 978-3-319-68843-5
eBook Packages: EngineeringEngineering (R0)