Improved computer‐aided detection of small polyps in CT colonography using interpolation for curvature estimationa)

Liu, Shiyuan; Kabadi, Suraj; Uitert, Robert Van; Petrick, Nicholas; Deriche, Rachid; Summers, Ronald M.

doi:10.1118/1.3596529

Cited by 15 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shape analysis thus plays important roles in detecting lesions and providing meaningful feature descriptors to reduce false positives in computer-aided diagnosis. Curvature was frequently applied to the detection of colonic polyps (Huang et al, 2005; Liu et al, 2011; Sundaram et al, 2007), pulmonary nodules (Kawata et al, 1999) and liver cancer (Linguraru et al, 2012b). An alternative shape analysis tool is shape index (Koenderink and Doorn, 1992), which is a single-value measurement of local surface geometry according to the principal curvature.…”

Section: Related Workmentioning

confidence: 99%

Computer-aided detection of exophytic renal lesions on non-contrast CT images

Liu

Wang

Linguraru

et al. 2015

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

Renal lesions are important extracolonic findings on computed tomographic colonography (CTC). They are difficult to detect on non-contrast CTC images due to low image contrast with surrounding objects. In this paper, we developed a novel computer-aided diagnosis system to detect a subset of renal lesions, exophytic lesions, by 1) exploiting efficient belief propagation to segment kidneys, 2) establishing an intrinsic manifold diffusion on kidney surface, 3) searching for potential lesion-caused protrusions with local maximum diffusion response, and 4) exploring novel shape descriptors, including multi-scale diffusion response, with machine learning to classify exophytic renal lesions. Experimental results on the validation dataset with 167 patients revealed that manifold diffusion significantly outperformed conventional shape features (p < 1e − 3) and resulted in 95% sensitivity with 15 false positives per patient for detecting exophytic renal lesions. Five-fold cross-validation also demonstrated that our method could stably detect exophytic renal lesions. These encouraging results demonstrated that manifold diffusion is a key means to enable accurate computer-aided diagnosis of renal lesions.

show abstract

Section: Related Workmentioning

confidence: 99%

Computer-aided detection of exophytic renal lesions on non-contrast CT images

Liu

Wang

Linguraru

et al. 2015

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, usually the surface based method tend to smooth the data first, hence some details may be already lost at the first stage. On the contrary, the volume based method put their emphasis on the calculation techniques of curvature for embedding iso-surface [6,7,8]. We conjecture that one of many factors contributing to the variation in detecting small polyps is the implicit assumption made for all the above CADe methods that the polyp is growing out from a flat surface environment.…”

Section: Introductionmentioning

confidence: 95%

A Novel Computer Aided Detection (CADe) Scheme for Colonic Polyps Based on the Structure Decomposition

Wang

Zhang

et al. 2013

Abdominal Imaging. Computation and Clinical Applications

View full text Add to dashboard Cite

Abstract. Accurately detecting small polyps (ranged from 5~8mm) on the colon wall is of great significance for early diagnosis colorectal cancers. However, colon usually consists of the mucosa layers which result in partial volume effect (PVE) on the colon wall. Consequently, the task of computer aided detection (CADe) of polyps turns into too complicated to be reached by simply following solo philosophy. In order to achieve the mission of small polyps' detection, we propose a novel global structure decomposition approach in this paper. That is, the complex colon was separated into much uniform broken parts by means of analysis on second order derivatives of the volume image. Experimentally, we chose 60 patient cases from dataset provided by Wisconsin, and in which we focus on the polyps whose size range from 5~8mm to validate the presented new approach. Compared with previously presented in the literature, the experimental results are much more promising with an average sensitivity of 0.984. Meanwhile, the false positive rate dramatically decreased to 2.2 per dataset after false positive reduction.

show abstract

“…Zhu et al [42] augmented the detection specificity using features extracted from both the gray and color projection images. Liu et al [20] improved the sensitivity of small polyp detection by utilizing image interpolation method for curvature estimation. Mang et al [21] evaluated the stand-alone performance of a polyp detection method with and without fecal tagging, and showed no significant performance differences.…”

Section: Introductionmentioning

confidence: 99%

Adaptive kernel based multiple kernel learning for computer-aided polyp detection in CT colonography

Han

et al. 2015

Geometry, Imaging and Computing

View full text Add to dashboard Cite

Computer-aided detection (CAD) of colonic polyps, as a second reader for computed tomographic colonography (CTC) screening, has earned extensive research interest over the past decades. False positive (FP) reduction in the CAD system plays a crucial role in detecting the polyps. To improve the performance of FP reduction and better assist the physician's diagnosis, we propose an adaptive kernel based multiple kernel learning (MKL) method for CAD of colonic polyps, called AK-MKL. This method builds a more adaptive synthesized classifier by incorporating an adaptive kernel into a set of predefined base kernels for better performance in differentiating true polyps from FPs, which is implemented by learning an optimal combination of a collection of those kernel-based classifiers. Performance evaluation for the presented AK-MKL method was performed on a CTC database, consisting of 25 patients with 50 CT scans. In terms of the AUC (area under the curve of receiver operating characteristic) and accuracy merits, the experimental results showed that our AK-MKL method achieves better performance, compared with two other different methods, i.e., one classifier based on support vector machine (SVM) with only one adaptive kernel (AK-SVM) and the other one based on multiple kernel learning only (MKL).

show abstract

Improved computer‐aided detection of small polyps in CT colonography using interpolation for curvature estimationa)

Cited by 15 publications

References 39 publications

Computer-aided detection of exophytic renal lesions on non-contrast CT images

Computer-aided detection of exophytic renal lesions on non-contrast CT images

A Novel Computer Aided Detection (CADe) Scheme for Colonic Polyps Based on the Structure Decomposition

Adaptive kernel based multiple kernel learning for computer-aided polyp detection in CT colonography

Contact Info

Product

Resources

About