Variational Image Segmentation for Endoscopic Human Colonic Aberrant Crypt Foci

Figueiredo, Isabel N.; Figueiredo, Pedro; Stadler, Georg; Ghattas, Omar; Araújo, Adérito

doi:10.1109/tmi.2009.2036258

Cited by 16 publications

(15 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…169 In the last three decades, induction of aberrant crypt foci (ACF) in rat colon has been widely accepted as the pre-neoplastic lesions for modeling colorectal cancer. [172][173][174][175][176][177] Although 2 studies showed that senna promoted formation of carcinogen-induced ACF in rat colon when given at high doses, 178,179 other studies failed to show any effects of senna in initiating ACF per se or promoting existing ACF. 180,181 In fact, one study even demonstrated a reduction of ACF in rat colon after long-term usage of senna.…”

Section: Fluidsmentioning

confidence: 99%

Chronic Constipation: An Evidence-Based Review

Leung¹,

Riutta²,

Kotecha³

et al. 2011

The Journal of the American Board of Family Medicine

273

168

View full text Add to dashboard Cite

Background: Chronic constipation is a common condition seen in family practice among the elderly and women. There is no consensus regarding its exact definition, and it may be interpreted differently by physicians and patients. Physicians prescribe various treatments, and patients often adopt different over-the-counter remedies. Chronic constipation is either caused by slow colonic transit or pelvic floor dysfunction, and treatment differs accordingly.Methods: To update our knowledge of chronic constipation and its etiology and best-evidence treatment, information was synthesized from articles published in PubMed, EMBASE, and Cochrane Database of Systematic Reviews. Levels of evidence and recommendations were made according to the Strength of Recommendation taxonomy.Results

show abstract

Section: Fluidsmentioning

confidence: 99%

Chronic Constipation: An Evidence-Based Review

Leung¹,

Riutta²,

Kotecha³

et al. 2011

The Journal of the American Board of Family Medicine

273

168

View full text Add to dashboard Cite

show abstract

“…Basically there are two directions for improvement which deal with the limitations of the original Chan-Vese model. The first one is to employ more complicated and flexible probabilistic region models [3], [10], [20], [22], [28], [40]. Another direction is to use texture features [40], [42], [43] to detect the texture-induced edges.…”

Section: Related Workmentioning

confidence: 99%

“…The total energy incorporating both the boundary and the region based information is then defined by (20) The first term is the boundary-based force where the boundary classification information is incorporated. The second term is the region-based force where the region classification information is incorporated.…”

Section: Unifying Region and Boundary-based Informationmentioning

confidence: 99%

Boosting Active Contours for Weld Pool Visual Tracking in Automatic Arc Welding

Liu

Fan

Olsen

et al. 2017

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Abstract-Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.Note to Practitioners-Welding quality is highly dependent on the human welder's experiences and skills in the gas tungsten arc welding process. In particular, detecting the shape of the nonrigid molten metal during welding plays an important role in improving the welding quality since it provides a prime feedback mechanism for welding control. However, this is a challenging task due to a number of reasons, e.g., strong interference and changing working environment. Applying classical image processing algorithms directly, such as active contour models (ACM), cannot guarantee satisfactory performance due to the above-mentioned reasons. Actually, in practice, ACM more often than not failed to capture the welding pool boundary. In this work, we integrate an applicationdependent prior to the definition of the energy functional of a traditional ACM, thus allowing us to use machine learning techniques to improve the performance of traditional ACM. In density estimation of the prior, AdaBoost is utilized to select features that are most suitable for Gaussian Bayesian classifiers to differentiate wanted boundaries and unwanted ones (e.g., spurious boundaries caused by interfering noise). The proposed approach improves the performance of the traditional ACM and captures the boundary of the

show abstract

“…They assumed that polyps appear as convex objects in a image, and introduced active rays to obtain a smoother contour. Figueiredo et al [19] proposed a segmentation method for assessing the aberrant crypt foci captured by an endoscope. They used variational level sets and active contours without the edge model of Chan and Vase [20].…”

Section: Related Workmentioning

confidence: 99%

Discriminative Subtree Selection for NBI Endoscopic Image Labeling

Hirakawa

Tamaki

Kurita

et al. 2017

Computer Vision – ACCV 2016 Workshops

View full text Add to dashboard Cite

Abstract. In this paper, we propose a novel method for image labeling of colorectal Narrow Band Imaging (NBI) endoscopic images based on a tree of shapes. Labeling results could be obtained by simply classifying histogram features of all nodes in a tree of shapes, however, satisfactory results are difficult to obtain because histogram features of small nodes are not enough discriminative. To obtain discriminative subtrees, we propose a method that optimally selects discriminative subtrees. We model an objective function that includes the parameters of a classifier and a threshold to select subtrees. Then labeling is done by mapping the classification results of nodes of the subtrees to those corresponding image regions. Experimental results on a dataset of 63 NBI endoscopic images show that the proposed method performs qualitatively and quantitatively much better than existing methods.

show abstract

Variational Image Segmentation for Endoscopic Human Colonic Aberrant Crypt Foci

Cited by 16 publications

References 37 publications

Chronic Constipation: An Evidence-Based Review

Chronic Constipation: An Evidence-Based Review

Boosting Active Contours for Weld Pool Visual Tracking in Automatic Arc Welding

Discriminative Subtree Selection for NBI Endoscopic Image Labeling

Contact Info

Product

Resources

About