Lectures

The following table contains the lecture plan. The Resources column is deliberately extensive, we will most likely not be able to talk about all the methods. Let me know if you have some preferences as to what methods you would like to talk about, I am open to suggestions.

I assume the knowledge of the simple image processing methods such as thresholding or linear filtering. I also assume a basic knowledge of neuronal networks and deep learning (see links below). However, I can of course briefly explain the basic concepts if you let me know.

Number	Date	Topic	Resources
1	21.9.	Segmentation - active contours, level sets	Xu, Prince: ''Snakes, Shapes, and Gradient Vector Flow''. IEEE TIP 1998; Chan, Vese ''Active contours without edges'', IEEE TIP 2001. Malladi et al ''Shape modeling with front propagation: a level set approach.'', IEEE PAMI 1995. Optional: Kybic, Krátký. Discrete curvature calculation for fast level set segmentation. ICIP 2009.. short presentation about active contours, a few slides on levelsets by N.Paragios and some examples by D. Cremers, partial recording from the lecture (sorry the first part is missing)
	28.9.	public holidays svátek
2	5.10.	Segmentation - shape models,	Cootes et al: Active Shape Models - Their Training and Applications, Computer Vision and Image Understanding. 1995. Cootes et al: Active appearance models. IEEE PAMI 2001. Heimann, Meinzer: Statistical shape models for 3D medical image segmentation: A review. MIA 2009. raw lecture slides, Chapter 10 of the Svoboda, Kybic, Hlavac book recording of the lecture
3	12.10.	Segmentations - superpixels, random walker, GraphCuts, graph search, normalized cuts	Achanta et al.: SLIC ''Superpixels Compared to State-of-the-Art Superpixel Methods''. IEEE PAMI 2012. Chen, Pan: ''A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation''. IEEE Reviews in Biomedical Engineering. 2018 Grady: ''Random Walks for Image Segmentation'', IEEE PAMI 2006. Shi, Malik: ''Normalized Cuts and Image Segmentation,'' IEEE PAMI 2000. superpixel lecture notes, normalized cuts lecture notes random walker lecture notes
	19.10.	no lecture
4	26.10.	Segmentation - texture, texture descriptors, textons	Leung, Malik. ''Representing and recognizing the visual appearance of materials using three-dimensional textons''. International Journal of Computer Vision, 2001. M. Unser: ''Texture classification and segmentation using wavelet frames'', IEEE TIP. 1995 Reyes-Aldasoro, Bhalerao, Volumetric Texture Segmentation by Discriminant Feature Selection and Multiresolution Classification, IEEE TMI 2007. Optional: Chapter 15 of the Šonka, Hlaváč, Boyle book and the companion Svoboda, Kybic, Hlavac book. Radim Šára's old lecture on texture (in Czech). Castellano et al: ''Texture analysis of medical images''. Clinical Radiology 2004. Madabhushi, et al. ''Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions''. IEEE TMI 2003. Noble, Boukerroui: ''Ultrasound image segmentation: A survey.'' IEEE TMI 2006. Malik et al. Textons, Contours and Regions: Cue Integration in Image Segmentation ICCV1999, Nava, Kybic "Supertexton-based segmentation in early Drosophila oogenesis." , ICIP2015. Lecture notes: textons, volumetric texture, waveletdescriptors.
5	2.11.	Segmentation - CNN, U-net	Ronneberger et al: U-Net: ''Convolutional Networks for Biomedical Image Segmentation''. MICCAI 2015. Oktay et al: ''Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation.'' IEEE TMI 2018. Optional: Pereira et al: ''Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images'', IEEE TMI 2016 Kamnitsas et al: ''Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation'', MIA 2017 (741 citations) Chung et al: TeTrIS: ''Template Transformer Networks for Image Segmentation With Shape Priors''. IEEE TMI 2019 Ghavami et al: ''Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration.'' MIA, 2019. Lecture notes: CNNs, U-net, Anatomically constrained CNN
6	9.11.	Detection of cells and nuclei	Y. Al-Kofahi et al, “''Improved automatic detection and segmentation of cell nuclei in histopathology images'',” IEEE Trans. Biomed. Eng., vol. 57, no. 4, pp. 841–852, Apr. 2010 Sirinukunwattana et al: ''Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images''. IEEE TMI 2016 Naylor: ''Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map''. Optional: IEEE TMI 2019 Irshan et al: ''Methods for Nuclei Detection, Segmentation, and Classification in Digital Histopathology: A Review—Current Status and Future Potential''. IEEE Reviews in Biomedical Engineering, 2013. Lecture notes: Al-Kofahi et al., Sirinukunwattana et al., Naylor et al.
7	16.11.	Detection of vessels and fibers	Frangi et al: ''Multiscale vessel enhancement filtering''. LNCS 1998 Türetken et al: ''Reconstructing Curvilinear Networks using Path Classifiers and Integer Programming''. IEEE PAMI 2016 Türetken et al:''Automated Reconstruction of Dendritic and Axonal Trees by Global Optimization with Geometric Prior''s. Neurinformatics. 2011 Sironi: ''Multiscale Centerline Detection'', IEEE PAMI 2016. Lecture notes: vessel detection
8	23.11.	Detection of nodules and mammographic lesions	Murphy et al: ''A large scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbour classification''. MIA 2009 Setio et al: ''Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks.'' IEEE TMI 2016 Kooi et al: ''Large scale deep learning for computer aided detection of mammographic lesion.'' MIA, 2017. Optional: Setio et al. ''Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.'' MIA 2017. Lecture notes
9	30.11.	Localization of organs and structures	Sofka el al ''Automatic Detection and Measurement of Structures in Fetal Head Ultrasound Volumes Using Sequential Estimation and Integrated Detection Network (IDN)''. IEEE TMI 2014 Xu et al: ''Efficient Multiple Organ Localization in CT Image Using 3D Region Proposal Network.'' IEEE TMI 2019. lecture notes
10	7.12.	Registration - ICP, coherent point drift, B-splines, rigid registration, multiresolution	Besl, McKay: ''A method for registration of 3D shapes''. IEEE PAMI. 1992 Myronenko, Song: Point Set Registration: ''Coherent Point Drift''. IEEE PAMI, 2010 Lecture notes. Optional: Unser: ''Splines: a perfect fit for signal and image processing'', IEEE SPM, 1999 Unser et al: ''B-Spline Signal Processing: Part I—Theory''. ''Part II / Efficient Design and Applications''. IEEE TSP. 1993
11	14.12.	Registration - rigid, elastic, daemons	P. Thevenaz and M. Unser, ''“Optimization of mutual information for multiresolution image registration,'' IEEE TIP 2000. Jan Kybic and Michael Unser ''Fast Parametric Elastic Image Registration.'' IEEE TIP. 2003 Thirion: ''Image matching as a diffusion process: an analogy with Maxwell’s demons.'' Med. Im. Anal. 1998. lecture notes Optional: Sotiras, Paragios, Davatzikos: ''Deformable image registration: A Survey'', IEEE TMI 2013
		winter holidays
12	11.1.	Registration by CNN	Balakrishnan et al: ''VoxelMorph: A Learning Framework for Deformable Medical Image Registration''. IEEE TMI 2019 X. Yang, R. Kwitt, M. Styner, and M. Niethammer, “Quicksilver: ''Fast predictive image registration-A deep learning approach,''” NeuroImage, 2017. Lecture notes Voxelmorph and Quicksilver. Optional: Sun et al. PWC-Net: ''CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume.'' CVPR 2018

Deep learning (odkazy)

''Vision for robots'' course has very nice slides about deep learning for image processing.
''Pytorch tutorials''
If you want to know everything, read the ''Deep learning book''

Resources

Medical image analysis is a dynamic domain, recent and advanced algorithms are published mainly in the primary literature, i.e. scientific journals. The most relevant are

IEEE Transactions on Medical Imaging
IEEE Transactions on Biomedical Engineering
Medical Image Analysis
IEEE Transactions on Image Processing
International Journal on Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence

These journals can be accessed free of charge thanks to a CTU subscription. Ask the central library in case of problems.

Useful books

Toennies: Guide to Medical Image Analysis, Springer 2012
Deserno: ''Fundamentals of Biomedical Image Processing'', Springer 2011
Yoo: Insight into images. Taylor & Francis, 2004
Birkfellner: Applied Medical Image Processing, CRC Press 2011
Jan: Medical Image Processing, Reconstruction and Restoration, CRC Press 2006
Dhawan: Medical Image Analysis, IEEE Press, 2003
Šonka, Fitzpatrick: Handbook of Medical Imaging: Volume 2, Medical Image Processing and Analysis, SPIE Press, 2000.