Biomedical Image Segmentation and Analysis Using Machine Learning and Computational Intelligence Techniques
Leonardo Rundo – leonardo.rundo@disco.unimib.it
Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy
Institute of Molecular Bioimaging and Physiology, Italian National Research Council, Cefalú (PA), Italy
Andrea Tangherloni – andrea.tangherloni@disco.unimib.it
Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy
Synopsis
Nowadays, the amount of heterogeneous biomedical data is increasing more and more thanks to advancements in imaging acquisition modalities and High Throughput technologies [Peng 2008, Shamir 2010]. This huge information ensemble could overwhelm analytic capabilities concerning both physicians in their decision-making tasks and biologists in investigating complex biological systems [Meijering 2016]. With particular reference to biomedical images, medical imaging comprises minimally invasive techniques for acquiring biomedical images that provide detailed information about the anatomy and physiology of the imaged organs [Duncan 2000], while live-cell microscopy imaging allows for the visualization and analysis of living specimens’ dynamic processes [Meijering 2012].
Quantitative imaging methods provide scientifically and clinically relevant data in prediction, prognostication or response assessment [Yankeelov 2016], by also exploiting radiomics approaches [Aerts 2014]. In this regard, Computational Intelligence and Machine Learning can significantly improve traditional image processing techniques [Wang 2012]. Therefore, computational approaches for medical and biological image analysis play a key role in radiology and laboratory applications [Wernick 2010]. However, conventional Machine Learning and Computational techniques must be adapted and tailored to address the unique challenges regarding biomedical images [Kraus 2017, Shen 2017].
In this talk, the challenges and the characteristics of the most recent methods will be introduced and discussed by means of several practical applications, focusing on image segmentation and registration in cancer imaging [Brady 2016]. As a matter of fact, medical image segmentation, which consists in detecting and delineating Regions of Interests (e.g., organs or pathological areas), is one of the most critical clinical tasks. Novel methods for computer-assisted Magnetic Resonance image segmentation, mainly based on unsupervised Fuzzy C-Means clustering techniques, will be presented [Militello 2015, Rundo 2017b, Rundo 2017c]. In the context of multispectral and multimodal image processing [Rundo 2017a, Rundo 2017d], image registration represents a fundamental step because it enables to integrate different images into a single representation (i.e., the same reference system) [Maes 1997]. In particular, biomedical image registration approaches using Particle Swarm Optimization [Kennedy 1995] will be investigated [Wachowiak 2004, Rundo 2016]. To conclude, a recent medical image enhancement method based on Genetic Algorithms [Holland 1992] will be briefly described.
References
[Aerts 2014] Aerts H.J., Velazquez E.R., Leijenaar, R.T., et al., Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach, Nat. Commun. 5, 4006, 2014.
[Brady 2016] Brady M., Highnam R., Irving B., et al., Oncological image analysis, Med. Image Anal. 33, 7-12, 2016.
[Duncan 2000] Duncan J.S. and Ayache N., Medical image analysis: progress over two decades and the challenges ahead, IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 85-106, 2000.
[Holland 1992] Holland J., Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence, MIT Press, 1992.
[Kennedy 1995] Kennedy J. and Eberhart R.C., Particle swarm optimization, in: Proc. IEEE International Conference on Neural Networks, vol. 4, pp. 1942-1948, 1995.
[Kraus 2017] Kraus O.Z., Grys B.T., Ba J., et al., Automated analysis of high‐content microscopy data with deep learning, Mol. Syst. Biol. 13(4), 924, 2017.
[Maes 1997] Maes F., Collignon A., Vandermeulen D., et al., Multimodality image registration by maximization of mutual information, IEEE Trans. Med. Imaging 16(2), 187-198, 1997.
[Meijering 2012] Meijering E., Cell segmentation: 50 years down the road, IEEE Signal Process. Mag. 29(5), 140-145, 2012.
[Meijering 2016] Meijering E., Carpenter A.E., Peng H., et al., Imagining the future of bioimage analysis, Nat. Biotech. 34, 1250-1255.
[Militello 2015] Militello C., Rundo L., Vitabile S., et al., Gamma Knife treatment planning: MR brain tumor segmentation and volume measurement based on unsupervised Fuzzy C-Means clustering, Int. J. Imaging Syst. Technol. 25(3), 213-225, 2015.
[Peng 2008] Peng H., Bioimage informatics: a new area of engineering biology, Bioinform. 24(17), 1827-1836.
[Rundo 2016] Rundo L., Tangherloni A., Militello C., et al., Multimodal medical image registration using particle swarm optimization: a review, in: Proc. 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1-8.
[Rundo 2017a] Rundo L., Militello C., Russo G., et al., Automated prostate gland segmentation based on an unsupervised Fuzzy C-Means clustering technique using multispectral T1w and T2w MR imaging, Information 8(2), 49, pp. 1-28, 2017.
[Rundo 2017b] Rundo L., Militello C., Russo G., et al., GTVcut for Neuro-radiosurgery treatment planning: an MRI brain cancer seeded image segmentation method based on a cellular automata model, Nat. Comput., 2017 [In Press].
[Rundo 2017c] Rundo L., Militello C., Tangherloni A., et al., NeXt for Neuro-radiosurgery: A fully automatic approach for necrosis extraction in brain tumor MRI using an unsupervised machine learning technique, Accepted by: Int. J. Imaging Syst. Technol., 2017.
[Rundo 2017d] Rundo L., Stefano A., Militello C., et al., A fully automatic approach for multimodal PET and MR image segmentation in Gamma Knife treatment planning, Comput. Methods Programs Biomed. 144, 77-96, 2017.
[Shamir 2010] Shamir L., Delaney J.D., Orlov N., et al., Pattern recognition software and techniques for biological image analysis, PLoS Comput. Biol. 6(11), e1000974, 2010.
[Shen 2017] Shen D., Wu G., Suk H.I., Deep learning in medical image analysis, Annual Review of Biomedical Engineering 19, 221-248, 2017.
[Wachowiak 2004] Wachowiak M.P., Smolíková R., Zheng Y., et al., An approach to multimodal biomedical image registration utilizing particle swarm optimization, IEEE Trans. Evol. Comput., vol. 8, no. 3, pp. 289-301, 2004
[Wang 2012] Wang S. and Summers R.M., Machine learning and radiology, Med. Image Anal. 16(5), 933-951, 2012.
[Wernick 2010] Wernick M.N., Yang Y., Brankov J.G., et al., Machine learning in medical imaging, IEEE Signal Process. Mag. 27(4), 25-38, 2010.
[Yankeelov 2016] Yankeelov T.E., Mankoff D.A., Schwartz L.H., et al., Quantitative imaging in cancer clinical trials, Clin. Cancer Res. 22(2), 284-290, 2016.
