Regression Forests for Efficient Anatomy Detection and Localization in CT Studies

Criminisi, Antonio; Shotton, Jamie; Robertson, Duncan; Konukoğlu, Ender

doi:10.1007/978-3-642-18421-5_11

Cited by 202 publications

(170 citation statements)

References 14 publications

Supporting

Mentioning

169

Contrasting

Order By: Relevance

“…The distance between the predicted bounding box center and the ground truth was also used to assess the detection accuracy. These results are given in Table 1 and compared to those reported in [13]. The refinement step (Section 2.3), for a low extra time cost, greatly increases the accuracy of the bounding box detection (e.g.…”

Section: Experiments and Resultsmentioning

confidence: 88%

“…Regression-based techniques do not require an exhaustive search of parameters. Other regressors such as regression forests and random ferns have also been proposed [13,14].…”

Section: Background On Organ Detectionmentioning

confidence: 99%

“…First, we find a coarse positioning based on contextual information adapting the approach proposed by Criminisi et al [13]. Then, the position of each box is refined based on local information.…”

Section: Coarse Localization Of the Kidneysmentioning

confidence: 99%

“…A random forest is trained on CT scans with known kidney bounding boxes to predict for each voxel the relative position and size of the kidneys. Since CT intensities (expressed in Hounsfield units) have direct physical meaning, as explained in [13], the features used are the mean intensities over displaced, asymmetric cuboidal regions. To allow a much faster training, we used residual sum of squares (RSS) instead of the information gain for the node optimization in the training stage.…”

Section: Coarse Localization Of the Kidneysmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests

Cuingnet

Prevost

Lesage

et al. 2012

Lecture Notes in Computer Science

123

101

View full text Add to dashboard Cite

Abstract. Kidney segmentation in 3D CT images allows extracting useful information for nephrologists. For practical use in clinical routine, such an algorithm should be fast, automatic and robust to contrast-agent enhancement and fields of view. By combining and refining state-of-theart techniques (random forests and template deformation), we demonstrate the possibility of building an algorithm that meets these requirements. Kidneys are localized with random forests following a coarseto-fine strategy. Their initial positions detected with global contextual information are refined with a cascade of local regression forests. A classification forest is then used to obtain a probabilistic segmentation of both kidneys. The final segmentation is performed with an implicit template deformation algorithm driven by these kidney probability maps. Our method has been validated on a highly heterogeneous database of 233 CT scans from 89 patients. 80 % of the kidneys were accurately detected and segmented (Dice coefficient > 0.90) in a few seconds per volume.

show abstract

Section: Experiments and Resultsmentioning

confidence: 88%

“…Regression-based techniques do not require an exhaustive search of parameters. Other regressors such as regression forests and random ferns have also been proposed [13,14].…”

Section: Background On Organ Detectionmentioning

confidence: 99%

Section: Coarse Localization Of the Kidneysmentioning

confidence: 99%

Section: Coarse Localization Of the Kidneysmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests

Cuingnet

Prevost

Lesage

et al. 2012

Lecture Notes in Computer Science

123

101

View full text Add to dashboard Cite

show abstract

“…Contextual reasoning is enabled via long-range spatial features, like the ones used in [14,15]. This way, the presence of organs such as kidneys, liver, or lungs provide strong indications about the presence of certain vertebrae.…”

Section: Vertebrae Localization and Identificationmentioning

confidence: 99%

Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans

Glocker

Feulner

Criminisi

et al. 2012

Lecture Notes in Computer Science

Self Cite

141

127

View full text Add to dashboard Cite

Abstract. This paper presents a new method for automatic localization and identification of vertebrae in arbitrary field-of-view CT scans. No assumptions are made about which section of the spine is visible or to which extent. Thus, our approach is more general than previous work while being computationally efficient. Our algorithm is based on regression forests and probabilistic graphical models. The discriminative, regression part aims at roughly detecting the visible part of the spine. Accurate localization and identification of individual vertebrae is achieved through a generative model capturing spinal shape and appearance. The system is evaluated quantitatively on 200 CT scans, the largest dataset reported for this purpose. We obtain an overall median localization error of less than 6mm, with an identification rate of 81%.

show abstract

Learning‐based deformable image registration for infant MR images in the first year of life

Wei

Gao

et al. 2017

Medical Physics

View full text Add to dashboard Cite

Purpose Many brain development studies have been devoted to investigate dynamic structural and functional changes in the first year of life. To quantitatively measure brain development in such a dynamic period, accurate image registration for different infant subjects with possible large age gap is of high demand. Although many state-of-the-art image registration methods have been proposed for young and elderly brain images, very few registration methods work for infant brain images acquired in the first year of life, because of (1) large anatomical changes due to fast brain development and (2) dynamic appearance changes due to white matter myelination. Methods To address these two difficulties, we propose a learning-based registration method to not only align the anatomical structures but also alleviate the appearance differences between two arbitrary infant MR images (with large age gap) by leveraging the regression forest to predict both the initial displacement vector and appearance changes. Specifically, in the training stage, two regression models are trained separately, with (1) one model learning the relationship between local image appearance (of one development phase) and its displacement toward the template (of another development phase) and (2) another model learning the local appearance changes between the two brain development phases. Then, in the testing stage, to register a new infant image to the template, we first predict both its voxel-wise displacement and appearance changes by the two learned regression models. Since such initializations can alleviate significant appearance and shape differences between new infant image and the template, it is easy to just use a conventional registration method to refine the remaining registration. Results We apply our proposed registration method to align 24 infant subjects at five different time points (i.e., 2-week-old, 3-month-old, 6-month-old, 9-month-old, and 12-month-old), and achieve more accurate and robust registration results, compared to the state-of-the-art registration methods. Conclusions The proposed learning-based registration method addresses the challenging task of registering infant brain images and achieves higher registration accuracy compared with other counterpart registration methods.

show abstract

Regression Forests for Efficient Anatomy Detection and Localization in CT Studies

Cited by 202 publications

References 14 publications

Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests

Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests

Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans

Learning‐based deformable image registration for infant MR images in the first year of life

Contact Info

Product

Resources

About