Convex Multi-class Image Labeling by Simplex-Constrained Total Variation

Lellmann, Jan; Kappes, Jörg Hendrik; Yuan, Jing; Becker, Florian; Schnörr, Christoph

doi:10.1007/978-3-642-02256-2_13

Cited by 117 publications

(180 citation statements)

References 35 publications

Supporting

Mentioning

178

Contrasting

Order By: Relevance

“…Recently, convex relaxation approaches were proposed, e.g. [3,[18][19][20][21][22]. Comparing to level set methods, Great advantages in numerics can be achieved, e.g.…”

Section: Introductionmentioning

confidence: 99%

“…the convex relaxed Potts model. In [18,22], such convex minimization problem is computed directly through the minimization over the labeling functions, i.e. tackle the minimal cut problem in a direct way, extra computation load is introduced to explore the pointwise simplex constraint within each iteration.…”

Section: Introductionmentioning

confidence: 99%

“…We also propose a fast max-flow based algorithm for computing continuous mincuts. Experiments show that our max-flow algorithm is much more efficient than the state of art of computational methods [18,22].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Continuous Max-Flow Approach to Potts Model

Yuan

Bae

Tai

et al. 2010

Lecture Notes in Computer Science

Self Cite

141

209

View full text Add to dashboard Cite

Abstract. We address the continuous problem of assigning multiple (unordered) labels with the minimum perimeter. The corresponding discrete Potts model is typically addressed with a-expansion which can generate metrication artifacts. Existing convex continuous formulations of the Potts model use TV-based functionals directly encoding perimeter costs. Such formulations are analogous to 'min-cut' problems on graphs. We propose a novel convex formulation with a continous 'max-flow' functional. This approach is dual to the standard TV-based formulations of the Potts model. Our continous max-flow approach has significant numerical advantages; it avoids extra computational load in enforcing the simplex constraints and naturally allows parallel computations over different labels. Numerical experiments show competitive performance in terms of quality and significantly reduced number of iterations compared to the previous state of the art convex methods for the continuous Potts model.

show abstract

“…Recently, convex relaxation approaches were proposed, e.g. [3,[18][19][20][21][22]. Comparing to level set methods, Great advantages in numerics can be achieved, e.g.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Continuous Max-Flow Approach to Potts Model

Yuan

Bae

Tai

et al. 2010

Lecture Notes in Computer Science

Self Cite

141

209

View full text Add to dashboard Cite

show abstract

“…In particular, the authors prompted to the relation with the Chan-Vese model [5]. Multi-label segmentations using the above approach or its relatives were proposed in [1,17,18,23,29]. Later, we will choose s(j) in dependence on f and r, e.g., as in (6) and on the knowledge of the layer conditions.…”

Section: Optimization Of the Labelsmentioning

confidence: 99%

“…In this paper we propose to segment images with separating layers by modifying recently proposed convex relaxation methods for image multi-labeling [1,17,18,23,29] with respect to the layer structure. More precisely, our aim is twofold: Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of images with separating layers by fuzzy c-means and convex optimization

Shafei

Steidl

2012

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Ensemble learning and tensor regularization for cone‐beam computed tomography‐based pelvic organ segmentation

et al. 2022

View full text Add to dashboard Cite

Purpose Cone‐beam computed tomography (CBCT) is a widely accessible low‐dose imaging approach compatible with on‐table patient anatomy observation for radiotherapy. However, its use in comprehensive anatomy monitoring is hindered by low contrast and low signal‐to‐noise ratio and a large presence of artifacts, resulting in difficulty in identifying organ and structure boundaries either manually or automatically. In this study, we propose and develop an ensemble deep‐learning model to segment post‐prostatectomy organs automatically. Methods We utilize the ensemble logic in various modules during the segmentation process to alleviate the impact of low image quality of CBCT. Specifically, (1) semantic attention was obtained from an ensemble 2.5D You‐only‐look‐once detector to consistently define regions of interest, (2) multiple view‐specific two‐stream 2.5D segmentation networks were developed, using auxiliary high‐quality CT data to aid CBCT segmentation, and (3) a novel tensor‐regularized ensemble scheme was proposed to aggregate the estimates from multiple views and regularize the spatial integrity of the final segmentation. Results A cross‐validation study achieved Dice similarity coefficient and mean surface distance of 0.779 ±$\pm$ 0.069 and 2.895 ±$\pm$ 1.496 mm for the rectum, and 0.915 ±$\pm$ 0.055 and 1.675 ±$\pm$ 1.311 mm for the bladder. Conclusions The proposed ensemble scheme manages to enhance the geometric integrity and robustness of the contours derived from CBCT with light network components. The tensor regularization approach generates organ results conforming to anatomy and physiology, without compromising typical quantitative performance in Dice similarity coefficient and mean surface distance, to support further clinical interpretation and decision making.

show abstract

Convex Multi-class Image Labeling by Simplex-Constrained Total Variation

Cited by 117 publications

References 35 publications

A Continuous Max-Flow Approach to Potts Model

A Continuous Max-Flow Approach to Potts Model

Segmentation of images with separating layers by fuzzy c-means and convex optimization

Ensemble learning and tensor regularization for cone‐beam computed tomography‐based pelvic organ segmentation

Contact Info

Product

Resources

About