CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames

Maroulis, Dimitris; Iakovidis, Dimitris K.; Karkanis, S.A.; Karras, D.A.

doi:10.1016/s0169-2607(02)00007-x

Cited by 122 publications

(76 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Given a colonoscopy image, the "true" features associated with the physical surface properties of the tissue are not exactly known to the system developer. Usually, one or more feature-extraction models [4,16,20] are used to provide values for each feature's parameters. The findings are then used to infer the correct interpretation.…”

Section: Methodsmentioning

confidence: 99%

“…Automated classification and identification of colonic carcinoma using microscopy images have been proposed by [21], but the use of clinical endoscopy video frames for the identification of colonic tumors has been considered only in limited instances [4,17,18,22,23]. Along this line of research, this paper makes use of texture information for the detection of malignant regions in colonoscopy images by employing some quantitative description of a texture.…”

Section: Texture Classificationmentioning

confidence: 99%

“…The emergence of grid protocols in conjunction with distributed computing offers CPU and data handling capabilities to users and could provide decision support in clinical diagnosis [2]. Minimally invasive, image-guided diagnostic procedures and surgery are particularly benefited from advanced software and hardware infrastructures [3,4]. In this context, the integration of navigation systems with high tracking accuracy and manoeuvrability, real-time services, such as analysis of imaging data and classification, parallelization of computational methods, detection of similarities with data stored in collaborating sites, comparison of patient's images against the norm, information sharing, and e-collaboration with other experts would definitely increase the efficiency of typical diagnostic procedures and surgeries [3][4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…Colonoscopic diagnosis is a particular challenging area, involving the extraction and interpretation of patterns from complex medical video sequences under variable perceptual conditions (resolution change, shadings, shadows, lighting condition variations, reflections etc. ), hypothesis generation, and reasoning in relation to previous experiences of the medical experts [4,[16][17][18]. When one considers that abnormalities are hard enough to diagnose, the problem is exaggerated greatly when the physicians do not know what they are looking for.…”

Section: Introductionmentioning

confidence: 99%

“…The use of intelligent approaches for the detection of lesions in colonoscopy has to meet a number of challenges [4,18]: the time varying nature of the process, changes in the perceptual direction of the physician, variations in the diffused light conditions. For example, though one can use bright lights, the effect in a tight organ is that light tends to diffuse which leads to some areas being clearly lit and others not so; thus potentially hiding abnormalities.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Distributed computing methodology for training neural networks in an image-guided diagnostic application

Plagianakos

Magoulas

Vrahatis

2006

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Distributed Computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a Parallel Virtual Machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the Parallel Virtual Machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Texture Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Distributed computing methodology for training neural networks in an image-guided diagnostic application

Plagianakos

Magoulas

Vrahatis

2006

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

Artificial Intelligence in Gastroenterology

Walradt¹,

Berzin²

2023

AI in Clinical Medicine

View full text Add to dashboard Cite

Automatic detection of small bowel tumors in wireless capsule endoscopy images using ensemble learning

et al. 2019

View full text Add to dashboard Cite

PurposeWireless Capsule Endoscopy (WCE) is a minimally invasive diagnosis tool for lesion detection in the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the significant amount of acquired data leads to difficulties in the diagnosis by the physicians; which can be eased with computer assistance. This paper addresses a method for the automatic detection of tumors in WCE by using a two‐step based procedure: region of interest selection and classification.MethodsThe first step aims to separate abnormal from normal tissue by using automatic segmentation based on a Gaussian Mixture Model (GMM). A modified version of the Anderson method for convergence acceleration of the expectation–maximization (EM) algorithm is proposed. The proposed features for both segmentation and classification are based on the CIELab color space, as a way of bypassing lightness variations, where the L component is discarded. Tissue variability among subjects, light inhomogeneities and even intensity differences among different devices can be overcome by using simultaneously features from both regions. In the second step, an ensemble system with partition of the training data with a new training scheme is proposed. At this stage, the gating network is trained after the experts have been trained decoupling the joint maximization of both modules. The partition module is also used at the test step, leading the incoming data to the most likely expert allowing incremental adaptation by preserving data diversity.ResultsThis algorithm outperforms others based on texture features selected from Wavelets and Curvelets transforms, classified by a regular support vector machine (SVM) in more than 5%.ConclusionsThis work shows that simpler features can outperform more elaborate ones if appropriately designed. In the current case, luminance was discarded to cope with saturated tissue, facilitating the color perception. Ensemble systems remain an open research field. In the current case, changes in both topology and training strategy have led to significant performance improvements. A system with this level of performance can be used in current clinical practice.

show abstract

CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames

Cited by 122 publications

References 33 publications

Distributed computing methodology for training neural networks in an image-guided diagnostic application

Distributed computing methodology for training neural networks in an image-guided diagnostic application

Artificial Intelligence in Gastroenterology

Automatic detection of small bowel tumors in wireless capsule endoscopy images using ensemble learning

Contact Info

Product

Resources

About