Abstract
The field of medical imaging has shown substantial growth over the last decade. Even more dramatic increase was observed in the use of machine learning and data mining techniques within this field. In this paper, we discuss three aspects related to information mining in the domain of medical imaging: the target user groups (for whom), the information to mine (what), and technologies to enable mining (how). Specifically, we focus on three types of information: anatomical, physiological and pathological, and present use cases for each one of them. Furthermore, we introduce representative methods and algorithms that are effective for solving these problems. We conclude the paper by discussing some major trends in the related domains for the coming decade.
- P. Angelini, J. A. Velasco, and S. Flamm. Coronary Anomalies: Incidence, Pathophysiology, and Clinical Relevance. Circulation, 105:2449--2454, 2002.Google ScholarCross Ref
- J. G. Fletcher, F. Booya, R. M. Summers, D. Roy, L. Guendel, B. Schmidt, C H McCollough, and J L Fidler. Comparative Performance of Two Polyp Detection Systems on CT Colonography. American Journal of Roentgenology, 189(2):277--282, 2007.Google ScholarCross Ref
- T. W. Freer and M. J. Ulissey. Screening Mammography with Computer-aided Detection: Prospective Study of 12,860 Patients in a Community Breast Center. Radiology, 220:781--786, 2001.Google Scholar
- R. Guggenberger, P. Eppenberger, D. Markovic, D. Nanz, A. Chhabra, K. P. Pruessmann, and G Andreisek. MR neurography of the median nerve at 3.0T: Optimization of diffusion tensor imaging and fiber tractography. European Journal of Radiology, 81(7):e775--782, 2012.Google ScholarCross Ref
- G. Hermosillo, C. Chefdhotel, K. H. Herrmann, G. Bousquet, L. Bogoni, K. Chaudhuri, D. R. Fischer, C. Geppert, R. Janka, and A. Krishnan. Multi Modality State-of-the-Art Medical Image Segmentation and Registration Methodologies, chapter Image Registration in Medical Imaging: Applications, Methods, and Clinical Evaluation.Google Scholar
- M. F. Kircher, H. Hricak, and S. M. Larson. Molecular imaging for personalized cancer care. Molecular Oncology, 6(2):182--195, 2012.Google ScholarCross Ref
- B. Krishnapuram, J. Stoeckel, V. C. Raykar, R. B. Rao, P. Bamberger, E. Ratner, N. Merlet, I. Stainvas, M. Abramov, and A. Manevitch. Multiple instance learning improves CAD detection of masses in digital mammography. In Proceedings of the 9th international workshop on Digital Mammography, pages 350--357. 2008. Google ScholarDigital Library
- H. B. W. Larsson, T. Y. Lee, N. A. Mayr, G. J. M. Parker, R. E. Port, J. Taylor, and R. M. Weisshoff. Estimating kinetic parameters from dynamic contrast-enhanced t1-weighted mri of diffusable tracer: a common global language for standardized quantities and symbols. Journal of Magnetic Resonance Imaging, 19:223--232, 1999.Google Scholar
- L. Lu, J. Bi, S. Yu, Z. Peng, A. Krishnan, and X. S. Zhou. Hierarchical learning for tubular structure parsing in medical imaging: A study on coronary arteries using 3D CT Angiography. In IEEE 12th International Conference on Computer Vision. 2009.Google ScholarCross Ref
- J. Patterson II, A. Minagar, N. Natarajan, and A. Takalkar. Alzheimer's disease detection with objective statistical evaluation of FDG-PET brain scans: essential methodology for early identification. Future Neurology, 5(2):259--276, 2010.Google ScholarCross Ref
- Z. Peng, Y. Zhan, X. S. Zhou, and A. Krishnan. Robust anatomy detection from CT topograms. In Proceedings of SPIE. 2009.Google Scholar
- V. C. Raykar, B. Krishnapuram, J. Bi, M. Dundar, and R. B. Rao. Bayesian multiple instance learning: Automatic feature selection and inductive transfer. In Proceedings of the 25th International Conference on Machine Learning, pages 808--815. 2008. Google ScholarDigital Library
- V. C. Raykar, S. Yu, L. H. Zhao, G. H. Valadez, C. Florin, L. Bogoni, and L. Moy. Learning from crowds. Journal of Machine Learning Research, 11:1297--1322, April 2010. Google ScholarDigital Library
- G. D. Rubin. Data explosion: the challenge of multidetector-row CT. European Journal of Radiology, 36(2):74--80, 2000.Google ScholarCross Ref
- G. K. Thawait, A. Chhabra, and J. A. Carrino. Spine segmentation and enumeration and normal variants. Radiol Clin North Am, 105:587--98, 2012.Google ScholarCross Ref
- Y. Zhan, M. Dewan, M. Harder, A. Krishnan, and X. S. Zhou. Robust Automatic Knee MR Slice Positioning Through Redundant and Hierarchical Anatomy Detection. IEEE Transactions on Medical Imaging, 30(12):2087--2100, 2011.Google ScholarCross Ref
- Y. Zhan, M. Dewan, and X. S. Zhou. Cross Modality Deformable Segmentation Using Hierarchical Clustering and Learning. In Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention. 2009. Google ScholarDigital Library
- Y. Zhan, M. Dewan, and X. S. Zhou. Robust MR spine detection using hierarchical learning and local articulated model. In International Conference on Medical Image Computing and Computer Assisted Intervention (to appear). 2012. Google ScholarDigital Library
- Y. Zhan, X. S. Zhou, Z. Peng, and A. Krishnan. Active scheduling of organ detection and segmentation in whole-body medical images. In Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention. 2008. Google ScholarDigital Library
- S. Zhang, Y. Zhan, M. Dewan, K. Huang, D. N. Metaxas, and X. S. Zhou. Towards robust and effective shape modeling: Sparse shape composition. Medical Image Analysis, 16(1):265--277, 2012.Google ScholarCross Ref
- X. S. Zhou, A. Gupta, and D. Comaniciu. An information fusion framework for robust shape tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(1):115--129, 2005. Google ScholarDigital Library
Index Terms
- Mining anatomical, physiological and pathological information from medical images
Recommendations
Segmentation of CT Brain Images Using Unsupervised Clusterings
In this paper, we present non-identical unsupervised clustering techniques for the segmentation of CT brain images. Prior to segmentation, we enhance the visualization of the original image. Generally, for the presence of abnormal regions in the brain ...
Feature and Intensity Based Medical Image Registration Using Particle Swarm Optimization
Image registration is an important aspect in medical image analysis, and kinds use in a variety of medical applications. Examples include diagnosis, pre/post surgery guidance, comparing/merging/integrating images from multi-modal like Magnetic Resonance ...
Tracking by means of geodesic region models applied to multidimensional and complex medical images
From surgery to radiotherapy treatment planning, tracking organs or tissues is a fundamental task. The techniques used to achieve this tracking can be classified as: extrinsic and intrinsic. Intrinsic techniques only use image processing methods applied ...
Comments