Magnifying colonoscopy: interobserver agreement in the assessment of colonic pit patterns and its correlation with histopathological findings

Zanoni, Esdras Camargo Andrade; Cutait, Raul; Averbach, Marcelo; Oliveira, Lix Alfredo Reis de; Teixeira, Cláudio Rolim; Correa, Paulo; Paccos, José Luiz; Rossini, G; Lopes, Luiz H. Câmara

doi:10.1007/s00384-007-0336-5

Cited by 19 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But it needs some exercising to achieve fairly good results (Hurlstone, 2002). Apart from that, similar to the reported inter-observer variability of NBI-based colonoscopy ( κ ≈ 0.57 (Rastogi et al, 2009), κ ≈ 0.63 (Chang et al, 2009), κ ≈ 0.69 (Raghavendra et al, 2010)) inter-observer variability of magnification chromo-endoscopy in the interpretation of pit patterns of colonic lesions has been described ( κ ≈ 0.56 (Zanoni et al, 2007), κ ≈ 0.64 (Chang et al, 2009)). This work aims at allowing computer-assisted pit pattern classification in order to enhance the quality of differential diagnosis.…”

Section: Pit Pattern Classificationsupporting

confidence: 70%

Color treatment in endoscopic image classification using multi-scale local color vector patterns

Häfner¹,

Liedlgruber

Uhl

et al. 2012

Medical Image Analysis

View full text Add to dashboard Cite

Graphical abstractIn this work we propose a novel multi-scale operator which is based on the full color information within an image. In order to evaluate the method, we extract features from endoscopic images using this operator and classify the images according to the respective class of polyps.Highlights► Compared to other LBP-based operators LCVP uses all color information available, yet yielding a more compact descriptor for an image. ► LCVP is up to 7.5 times faster compared to other LBP-based methods evaluated. ► In terms of a classification of polyps the accuracy of LCVP differs insignificantly only from previously developed methods.

show abstract

Section: Pit Pattern Classificationsupporting

confidence: 70%

Color treatment in endoscopic image classification using multi-scale local color vector patterns

Häfner¹,

Liedlgruber

Uhl

et al. 2012

Medical Image Analysis

View full text Add to dashboard Cite

show abstract

“…Vários estudos (6,10,22,23) que envolveram grande número de lesões, analisando o padrão das criptas por meio da magnificação de imagens associada à cromoscopia pelo índigo-carmin ou pela Other 32 lesions out of 41 with negative meshed capillary network were non-neoplastic. Sensitivity, specificity and accuracy were, respectively, 92.7%, 97% and 93.6%.…”

Section: Discussionunclassified

Estudo comparativo entre MBI (FICE®) e a magnificação com índigo-carmin no diagnóstico diferencial de lesões neoplásicas e não-neoplásicas de cólon e reto

Santos¹,

Pereira-Lima

Lopes

et al. 2009

Arq. Gastroenterol.

View full text Add to dashboard Cite

RESUMO -Contexto -O uso da cromoscopia virtual com sistema de imagem multibanda poderia auxiliar no diagnóstico in vivo de neoplasias colônicas. Objetivo -Avaliar a exatidão da magnificação associada à cromoendoscopia eletrônica ou com índigo-carmin na distinção entre lesões neoplásicas e não-neoplásicas do cólon e reto. INTRODUÇÃONos últimos anos, a magnificação de imagens com ou sem o emprego da cromoscopia, tem ganho grande importância como recurso propedêutico para endoscopia digestiva, em especial, da colonoscopia (6,9,11,16,19,20) . Maior precisão diagnóstica requer detecção de pequenas alterações estruturais ou de coloração (8) , que podem ser diagnosticadas por meio da colonoscopia de alta resolução aliada à magnificação de imagens. Esta tecnologia permite o aumento de uma porção da imagem e sua visualização com grande riqueza de detalhes, seja ela obtida óptica ou digitalmente. A imagem endoscópica depende dos comprimentos de onda da luz que são refletidos pelo tubo digestivo. O sistema FICE ® ("Fuji Intelligent Color Enhancement"), por meio de filtros específicos para diferentes combinações de comprimentos de onda entre o vermelho, o verde e o azul, converte imagens ópticas em imagens espectrais altamente contrastadas. Desta forma, o FICE ® se apresenta como verdadeiro método de cromoscopia virtual, dispensando o emprego de corantes, o que levaria a ganho de tempo, redução dos custos e maior praticidade durante a colonoscopia.Neste estudo, pretende-se comparar a precisão diagnóstica desta nova ferramenta com o método clássico de magnificação de imagens aliada à cromoscopia com índigo-carmin na distinção entre lesões neoplásicas e não-neoplásicas do cólon e reto. MÉTODOS

show abstract

“…But it needs some exercising to achieve fairly good results [21]. Apart from that, similar to the reported inter-observer variability of NBI-based colonoscopy ( κ ≈ 0.57 [22], κ ≈ 0.63 [23], κ ≈ 0.69 [24]) inter-observer variability of magnification chromo-endoscopy in the interpretation of pit patterns of colonic lesions has been described ( κ ≈ 0.56 [25], κ ≈ 0.64 [23]). This work aims at allowing computer-assisted pit pattern classification in order to enhance the quality of differential diagnosis.…”

Section: Pit Pattern Classificationmentioning

confidence: 52%

Delaunay triangulation-based pit density estimation for the classification of polyps in high-magnification chromo-colonoscopy

Häfner¹,

Liedlgruber

Uhl

et al. 2012

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

Magnifying colonoscopy: interobserver agreement in the assessment of colonic pit patterns and its correlation with histopathological findings

Abstract: Although the interobserver reproducibility of the colonic pit pattern is good for experienced endoscopists, MC must not be used to replace the histopathological analysis, since it does not differentiate with the necessary safety neoplastic from nonneoplastic lesions.

Cited by 19 publications

References 31 publications

Color treatment in endoscopic image classification using multi-scale local color vector patterns

Color treatment in endoscopic image classification using multi-scale local color vector patterns

Estudo comparativo entre MBI (FICE®) e a magnificação com índigo-carmin no diagnóstico diferencial de lesões neoplásicas e não-neoplásicas de cólon e reto

Delaunay triangulation-based pit density estimation for the classification of polyps in high-magnification chromo-colonoscopy

Contact Info

Product

Resources

About