A Two-Level Approach Towards Semantic Colon Segmentation: Removing Extra-Colonic Findings

Lü, Le; Wolf, Matthias; Liang, Jianming; Dündar, Murat; Bi, Jinbo; Salganicoff, Marcos

doi:10.1007/978-3-642-04271-3_122

Cited by 14 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For centerline based schemes, > 40% polyps are non-retrievable or can not be directly handled by [1][2][3][4], mainly due to collapsed colon segmentation in at least one prone or supine volume of 31% training, or 36% testing cases. [13]reports that ∼ 40% volumes have collapsed colon segments in a clinical dataset. Note that, by normalizing against the polyp retrieval upper bounds (55 ∼ 59% for geometric and 93 ∼ 94% for metric learning) respectively, in Fig.…”

Section: Resultsmentioning

confidence: 99%

Robust Large Scale Prone-Supine Polyp Matching Using Local Features: A Metric Learning Approach

Liu

Lü

et al. 2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Computer aided detection (CAD) systems have emerged as noninvasive and effective tools, using 3D CT Colonography (CTC) for early detection of colonic polyps. In this paper, we propose a robust and automatic polyp prone-supine view matching method, to facilitate the regular CTC workflow where radiologists need to manually match the CAD findings in prone and supine CT scans for validation. Apart from previous colon registration approaches based on global geometric information [1][2][3][4], this paper presents a feature selection and metric distance learning approach to build a pairwise matching function (where true pairs of polyp detections have smaller distances than false pairs), learned using local polyp classification features [5][6][7]. Thus our process can seamlessly handle collapsed colon segments or other severe structural artifacts which often exist in CTC, since only local features are used, whereas other global geometry dependent methods may become invalid for collapsed segmentation cases. Our automatic approach is extensively evaluated using a large multi-site dataset of 195 patient cases in training and 223 cases for testing. No external examination on the correctness of colon segmentation topology [2] is needed. The results show that we achieve significantly superior matching accuracy than previous methods [1][2][3][4], on at least one order-of-magnitude larger CTC datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust Large Scale Prone-Supine Polyp Matching Using Local Features: A Metric Learning Approach

Liu

Lü

et al. 2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The labeled vessel tree may enable automated distinction between the colon and small bowel. Other methods [30–31] have been proposed to model vessel trees. Lu et al [30] used a hierarchical machine learning approach to label and segment generic tubular structures in medical images.…”

Section: Discussionmentioning

confidence: 99%

“…Other methods [30–31] have been proposed to model vessel trees. Lu et al [30] used a hierarchical machine learning approach to label and segment generic tubular structures in medical images. Statistical machine learning methods have their merits to handle uncertain problems, such as missing arteries because of vessel segmentation limitations.…”

Section: Discussionmentioning

confidence: 99%

Mesenteric Vasculature-Guided Small Bowel Segmentation on 3-D CT

Zhang

Liu

Yao

et al. 2013

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Due to its importance and possible applications in visualization, tumor detection and pre-operative planning, automatic small bowel segmentation is essential for computer-aided diagnosis of small bowel pathology. However, segmenting the small bowel directly on CT scans is very difficult because of the low image contrast on CT scans and high tortuosity of the small bowel and its close proximity to other abdominal organs. Motivated by the intensity characteristics of abdominal CT images, the anatomic relationship between the mesenteric vasculature and the small bowel, and potential usefulness of the mesenteric vasculature for establishing the path of the small bowel, we propose a novel mesenteric vasculature map-guided method for small bowel segmentation on high-resolution CT angiography scans. The major mesenteric arteries are first segmented using a vessel tracing method based on multi-linear subspace vessel model and Bayesian inference. Second, multi-view, multi-scale vesselness enhancement filters are used to segment small vessels, and vessels directly or indirectly connecting to the superior mesenteric artery are classified as mesenteric vessels. Third, a mesenteric vasculature map is built by linking vessel bifurcation points, and the small bowel is segmented by employing the mesenteric vessel map and fuzzy connectness. The method was evaluated on 11 abdominal CT scans of patients suspected of having carcinoid tumors with manually labeled reference standard. The result, 82.5% volume overlap accuracy compared with the reference standard, shows it is feasible to segment the small bowel on CT scans using the mesenteric vasculature as a roadmap.

show abstract

“…Air compartments can be effectively extracted using a generic 3D region growing algorithm and the air intensity range. However they may be from lung and other extra-colonic regions (e.g., small intestine, stomach) and we eliminate extra-colonic air findings, via robust component-level structure parsing using geometric features and rank-one SVM classification [4]. On the other hand, when searching tagging materials, we need to avoid the bone tissue voxels since they have similar Hounsfield units or CT intensity values.…”

Section: Bounding Box Generation Of Tagging Roismentioning

confidence: 99%

A New Algorithm of Electronic Cleansing for Weak Faecal-Tagging CT Colonography

Lü

Jian

et al. 2013

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. CT Colonography (CTC) has emerged as a mainstream clinical practice of colonic cancer screening and diagnosis. One of the most critical problems is to increase compliance with CTC examinations via minimal bowel preparation (i.e., weak faecal-tagging), which nevertheless causes much lower signal-noise-ratio than conventional preparation.In this paper, we present a new algorithm pipeline of electronically cleansing tagging materials in CTC under reduced oral contrast dose. Our method has the following steps: 1, robust structure parsing to generate a list of volume regions of interest (ROIs) of tagging material (avoiding bone erosion); 2, effectively locating local tagging-air (AT) transitional surface regions; 3, a novel discriminative-generative algorithm to learn the higher-order image appearance model in AT using 3D Markov Random Fields (MRF); 4, accurate probability density function based voxel labeling corresponding to semantic classes. Validated on 26 weak faecaltagging CTC cases from 3 medical sites, our method yields better visualization clarity and readability compared with the previous approach [1]. The whole system computes efficiently (e.g., < 40 seconds for CT images of 512 × 512 × 1000+).

show abstract

A Two-Level Approach Towards Semantic Colon Segmentation: Removing Extra-Colonic Findings

Cited by 14 publications

References 10 publications

Robust Large Scale Prone-Supine Polyp Matching Using Local Features: A Metric Learning Approach

Robust Large Scale Prone-Supine Polyp Matching Using Local Features: A Metric Learning Approach

Mesenteric Vasculature-Guided Small Bowel Segmentation on 3-D CT

A New Algorithm of Electronic Cleansing for Weak Faecal-Tagging CT Colonography

Contact Info

Product

Resources

About