Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress 2023 EHA Congress 2023 ASCO Annual Meeting
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
International Journal of Computer Assisted Radiology and Surgery
Published in: International Journal of Computer Assisted Radiology and Surgery 4/2013

01-07-2013 | Original Article

Discriminative generalized Hough transform for object localization in medical images

Authors: Heike Ruppertshofen, Cristian Lorenz, Georg Rose, Hauke Schramm

Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 4/2013

Login to get access

Abstract

Purpose   This paper proposes the discriminative generalized Hough transform (DGHT) as an efficient and reliable means for object localization in medical images. It is meant to give a deeper insight into the underlying theory and a comprehensive overview of the methodology and the scope of applications. Methods   The DGHT combines the generalized Hough transform (GHT) with a discriminative training technique for the GHT models to obtain more efficient and robust localization results. To this end, the model points are equipped with individual weights, which are trained discriminatively with respect to a minimal localization error. Through this weighting, the models become more robust since the training focuses on common features of the target object over a set of training images. Unlike other weighting strategies, our training algorithm focuses on the error rate and allows for negative weights, which can be employed to encode rivaling structures into the model. The basic algorithm is presented here in conjunction with several extensions for fully automatic and faster processing. These include: (1) the automatic generation of models from training images and their iterative refinement, (2) the training of joint models for similar objects, and (3) a multi-level approach. Results   The algorithm is tested successfully for the knee in long-leg radiographs (97.6 % success rate), the vertebrae in C-arm CT (95.5 % success rate), and the femoral head in whole-body MR (100 % success rate). In addition, it is compared to Hough forests (Gall et al. in IEEE Trans Pattern Anal Mach Intell 33(11):2188–2202, 2011) for the task of knee localization (97.8 % success rate). Conclusion   The DGHT has proven to be a general procedure, which can be easily applied to various tasks with high success rates.
Footnotes
2
Note that there is no automatic identification of vertebrae. Instead, the localization results were allocated to their closest target point and the label of the annotation was used.
 
Literature
1.
Ballard DH (1981) Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognit 13(2):111–122CrossRef
2.
Betke M, Hong H, Thomas D, Prince C, Ko JP (2003) Landmark detection in the chest and registration of lung surfaces with an application to nodule registration. Med Image Anal 7:265–281PubMedCrossRef
3.
Beyerlein P (1998) Discriminative model combination. In: International conference on acoustics, speech, and signal processing, pp 481–484
4.
Brejl M, Sonka M (2000) Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples. IEEE Trans Med Imaging 19:973–985PubMedCrossRef
5.
Brunk M, Ruppertshofen H, Schmidt S, Beyerlein P, Schramm H (2011) Bone age classification using the discriminative generalized Hough transform. In: Bildverarbeitung für die Medizin, pp 284–288
6.
Criminisi A, Shotton J, Robertson D, Konukoglu E (2011) Regression forests for efficient anatomy detection and localization in CT studies. In: Proceedings of the MICCAI 2010 workshop on medical computer vision, vol LNCS 6533, pp 106–117
7.
Cristinacce D, Cootes T, Scott I (2004) A multi-stage approach to facial feature detection. In: British machine vision conference, pp 277–286
8.
Deselaers T, Keysers D, Ney H (2005) Discriminative training for object recognition using image patches. Comput Vis Pattern Recognit 2:157–162
9.
Ecabert O, Thiran JP (2004) Adaptive Hough transform for the detection of natural shapes under weak affine transformations. Pattern Recognit Lett 25:1411–1419CrossRef
10.
Ecabert O, Peters J, Schramm H, Lorenz C, von Berg J, Walker MJ et al (2008) Automatic model-based segmentation of the heart in CT images. IEEE Trans Med Imaging 27(9):1189–1201PubMedCrossRef
11.
Ehrhardt J, Handels H, Strathmann B, Malina T, Plötz W, Pöppl SJ (2003) Atlas-based recognition of anatomical structures and landmarks to support the virtual three-dimensional planning of hip operations. In: Medical image computed computer assisted intervention, vol LNCS 2878, pp 17–24
12.
Engel K, Toennies K (2010) Hierarchical vibrations for part-based recognition of complex objects. Pattern Recognit 43(8):2681–2691CrossRef
13.
Fischer B, Brosig A, Welter P, Grouls C, Günther RW, Deserno TM (2010) Content-based image retrieval applied to bone age assessment. In: SPIE medical, imaging, vol 7624, pp 12–1-12-10
14.
Gall J, Lempitsky V (2009) Class-specific Hough forests for object detection. In: Computer vision and pattern recognition, pp 1022–1029
15.
Gall J, Yao A, Razavi N, Van Gool L, Lempitsky V (2011) Hough forests for object detection, tracking, and action recognition. IEEE Trans Pattern Anal Mach Intell 33(11):2188–2202PubMedCrossRef
16.
Gooßen A, Hermann E, Weber GM, Gernoth T, Pralow T, Grigat RR (2011) Model-based segmentation of pediatric and adult joints for orthopedic measurements in digital radiographs of the lower limbs. Comput Sci Res Dev 26(1–2):107–116CrossRef
17.
Grass M, Koppe R, Klotz E, Proksa R, Kuhn MH, Aerts H et al (1999) Three-dimensional reconstruction of high contrast objects using C-arm image intensifier projection data. Comput Med Imaging Graph 23:311–321PubMedCrossRef
18.
Hahmann F, Ruppertshofen H, Böer G, Stannarius R, Schramm H (2012) Eye localization using the discriminative generalized Hough transform. In: Pattern recognition, vol LNCS 7476, pp 155–614
19.
Heimann T, Münziger S, Meinzer HP, Wolf I (2007) A shape-guided deformable model with evolutionary algorithm initialization for 3D soft tissue segmentation. In: Information processing in medical imaging, vol LNCS 4584, pp 1–12
20.
Heimann T, van Ginneken B, Styner M et al (2009) Comparison and evaluation of methods for liver segmentation from CT datasets. IEEE Trans Med Imaging 28(8):1251–1265PubMedCrossRef
21.
Hu Z, Ojha N, Renisch S, Schulz V, Torres I, Buhl A et al (2009) MR-based attenuation correction for a whole-body sequential PET/MR system. In: IEEE nuclear science symposium conference record, pp 3508–3512
22.
Isgum I, Staring M, Rutten A, Prokop M, Viergever MA, van Ginneken B (2009) Multi-atlas-based segmentation with local decision fusion: application to cardiac and aortic segmentation in CT scans. IEEE Trans Med Imaging 28(7):1000–1010PubMedCrossRef
23.
Jaynes ET (1957) Information theory and statistical mechanics. Phys Rev 106(4):620–630CrossRef
24.
Juang BH, Katagiri S (1992) Discriminative learning for minimum error classification. IEEE Trans Signal Process 40(12):3043–3054CrossRef
25.
Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C (2009) Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 13(3):471–482PubMedCrossRef
26.
Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comp Vis 77(1–3):259–289CrossRef
27.
Lorenz C, von Berg J (2005) Fast automated object detection by recursive casting of search rays. In: Computer assisted radiology and surgery, vol 1281, pp 230–235
28.
Maji S, Malik J (2009) Object detection using a max-margin Hough transform. In: Computer vision and pattern recognition, pp 1038–1045
29.
Okada R (2009) Discriminative generalized Hough transform for object detection. In: International conference on computer vision, pp 2000–2005
30.
Pai A, Narasimhamurthy A, Rao VSV, Vaidya V (2011) Automated localization of vertebra landmarks in MRI images. In: SPIE medical, imaging, vol 7963, pp 3K-1–3K-6
31.
Pauly O, Glocker B, Criminisi A, Mateus D, Möller AM, Nekolla S, Navab N (2011) Fast multiple organ detection and localization in whole-body MR dixon sequences. In: Medical image computing and computer assisted interventions, vol LNCS 6893, pp 239–247
32.
Petersen BTL, Engh MGA (1988) Radiographic assessment of knee alignment after total knee arthroplasty. J Arthroplasty 3(1):62–72CrossRef
33.
Ruppertshofen H, Künne D, Lorenz C, Schmidt S, Beyerlein P, Salah Z et al (2011a) Multi-level approach for the discriminative generalized Hough transform. In: Computer-und roboterassistierte Chirurgie, pp 67–70
34.
Ruppertshofen H, Lorenz C, Schmidt S, Beyerlein P, Salah Z, Rose G, Schramm H (2011b) Discriminative generalized Hough transform for localization of joints in the lower extremities. Comput Sci Res Dev 26(1–2):97–105CrossRef
35.
Ruppertshofen H, Lorenz C, Schmidt S, Beyerlein P, Salah Z, Rose G, Schramm H (2011c) Shape model training for concurrent localization of the left and right knee. In: SPIE medical, imaging, vol 7962, pp 41-1–41-8
36.
Ruppertshofen H, Bülow T, von Berg J, Schmidt S, Beyerlein P, Salah Z, Rose G, Schramm H (2012) A multidimensional model for localization of highly variable objects. In: SPIE medical imaging, vol 8314, p 83142L
37.
Schapire RE (2003) Nonlinear estimation and classification, Springer, chap. The boosting approach to machine learning: an overview, pp 149–172
38.
Schramm H, Ecabert O, Peters J, Philomin V, Weese J (2006) Towards fully automatic object detection and segmentation. In: SPIE medical imaging, vol 6144, pp 11–20
39.
Seim H, Kainmüller D, Heller M, Lamecker H, Zachow S, Hege HC (2008) Automatic segmentation of the pelvic bones from CT data based on a statistical shape model. In: Eurographics workshop on visual computing for biomedicine, pp 93–100
40.
Viola P, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: Computer vision and pattern recognition, pp 511–518
41.
Zheng Y, Barbu A, Georgescu B, Scheuering M, Comaniciu D (2008) Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features. IEEE Trans Med Imaging 27:1668–1681PubMedCrossRef
42.
Zheng Y, Georgescu B, Comaniciu D (2009) Marginal space learning for efficient detection of 2D/3D anatomical structures in medical images. In: Information processing in medical imaging, vol LNCS 5636, pp 411–422
Metadata
Title
Discriminative generalized Hough transform for object localization in medical images
Authors
Heike Ruppertshofen
Cristian Lorenz
Georg Rose
Hauke Schramm
Publication date
01-07-2013
Publisher
Springer Berlin Heidelberg
Published in
International Journal of Computer Assisted Radiology and Surgery / Issue 4/2013
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI
https://doi.org/10.1007/s11548-013-0817-7

Other articles of this Issue 4/2013

International Journal of Computer Assisted Radiology and Surgery 4/2013 Go to the issue

Original Article

A robust method to track colonoscopy videos with non-informative images

Original Article

Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images

Original Article

Measures of divergence of oriented patterns for the detection of architectural distortion in prior mammograms

Original Article

Computer-aided focal liver lesion detection

Original Article

The Medical Imaging Interaction Toolkit: challenges and advances

Original Article

Phantom-based comparison of conventional versus phase-contrast mammography for LCD soft-copy diagnosis