Assessment and management of the malignant colorectal polyp

Neilson, Laura J; Rutter, Matthew D.; Saunders, Brian P.; Plumb, Andrew; Rees, Colin

doi:10.1136/flgastro-2015-100565

Cited by 20 publications

(21 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Given that the first two categories are not associated with malignancy and Types III and IV have a low risk of containing carcinoma, we decided to group them as nonmalignant. Type V polyps otherwise has a 56% risk of malignancy, so we can confidently label that type as the only one malignant in our test environment [8]. These polyp types can be seen in Figure 1.…”

Section: Methodsmentioning

confidence: 81%

See 1 more Smart Citation

Kudo’s Classification for Colon Polyps Assessment Using a Deep Learning Approach

et al. 2020

View full text Add to dashboard Cite

Colorectal cancer (CRC) is the second leading cause of cancer death in the world. This disease could begin as a non-cancerous polyp in the colon, when not treated in a timely manner, these polyps could induce cancer, and in turn, death. We propose a deep learning model for classifying colon polyps based on the Kudo’s classification schema, using basic colonoscopy equipment. We train a deep convolutional model with a private dataset from the University of Deusto with and without using a VGG model as a feature extractor, and compared the results. We obtained 83% of accuracy and 83% of F1-score after fine tuning our model with the VGG filter. These results show that deep learning algorithms are useful to develop computer-aided tools for early CRC detection, and suggest combining it with a polyp segmentation model for its use by specialists.

show abstract

Section: Methodsmentioning

confidence: 81%

“…Type III and IV have a low risk factor of being carcinogenic. Type V has a 56% of being malignant [8,9].…”

Section: Introductionmentioning

confidence: 99%

Kudo’s Classification for Colon Polyps Assessment Using a Deep Learning Approach

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Colorectal cancer is the third most prevalent cancer in men, and the second most common in women worldwide, being the second leading cause of cancer death in Europe. [1][2][3] More than 95% of colorectal cancers arise through the adenoma-carcinoma transformation sequence, over an estimated period of 10-20 years. This supports screening of colorectal cancer, allowing the detection of advanced adenomas and future colorectal cancers through more timely intervention.…”

Section: Introductionmentioning

confidence: 99%

Surgical treatment of malignant colon polyps

Ramos

Gonçalves

Silva³

et al. 2018

Journal of Coloproctology

View full text Add to dashboard Cite

Background In the therapeutic decision about the malignant colon polyp, several factors predicting residual disease after the endoscopic resection guide the decision of surveillance or surgical intervention. This is a challenging decision, because even in the presence of high-risk predictors currently used, only 15–30% of the patients will have residual disease in the surgical specimen. Objective To evaluate patients with a diagnosis of malignant colon polyp at the Hospital Center of São João, who were indicated for surgical treatment, studying the predictors of residual disease in the surgical specimen. Methods A retrospective study was carried out, based on the patients with malignant colon polyp diagnosed and treated at the Hospital Center of São João in the city of Porto, Portugal, between 2009 and 2016. The endoscopic, anatomopathological, surgical and follow-up data were reviewed. Results Of the total number of patients in the study ( n = 96), 59 (61.5%) were indicated for surgery after a multidisciplinary discussion. Of this group, 21 patients (35.6%) had residual disease in the surgical specimen, with presence of lymph node invasion in 8 patients (13.6%). The presence of malignancy in the surgical resection specimen was statistically significantly associated with: size of the resected polyp ( p = 0.023); sessile polyp ( p = 0.007); piecemeal resection ( p = 0.002). Conclusions The persistence of malignancy in the surgical specimen was associated with larger sessile polyps and piecemeal removal. A significant number of patients did not show malignancy in the surgical resection specimen, with more markers being required to better stratify patients.

show abstract

“…The term "malignant polyp" refers to an adenoma with a benign endoscopic appearance [1] and a histology report that suggests malignancy invading into the submucosa [1][2][3]. A malignant polyp is therefore classified as an early carcinoma.…”

Section: Introductionmentioning

confidence: 99%

Complete endoscopic mucosal resection of malignant colonic sessile polyps and clinical outcome of 51 cases.

Paspatis¹

2017

Preprint

View full text Add to dashboard Cite

Background Meta-analyses and guidelines recommend that deep submucosal invasion (>1 mm) of malignant sessile colonic polyps is an important risk factor for lymph node metastasis. However, existing data are based on small retrospective studies with marked heterogeneity. We herein aimed to investigate the long-term outcomes of patients who underwent complete endoscopic mucosal resection (EMR) of malignant colonic sessile polyps invading the submucosal layer.Methods Endoscopy records for the period 2000-2016 were reviewed retrospectively. All enrolled patients exhibited an endoscopically resected malignant colonic sessile polyp. All patients were advised to undergo surgery, but some opted for conservative treatment and endoscopic follow up.Results Fifty-one patients with confirmed infiltrative submucosal adenocarcinoma in sessile colonic polyps that had undergone complete EMR were detected. A total of 32 (62.7%) patients opted for surgery after EMR and 19 (37.3%) chose endoscopic follow up. In 44 (86.3%) patients the submucosal invasion was >1 mm. Residual malignant disease was identified in the surgical pathological specimen of only 1 patient. During a median follow up of 23.41 months (interquartile range 33.45, range 1.84-144.92), no local recurrences or lymph node metastasis were identified. Forty-nine patients are alive without evidence of disease and 2 died of other causes (without evidence of local or metastatic disease at last follow up). ConclusionOur data suggest that complete EMR of cancerous colonic sessile polyps, even in cases of submucosal invasion >1 mm carries a low risk of recurrence and therefore may need further evaluation as an alternative strategy to surgical resection.

show abstract

Assessment and management of the malignant colorectal polyp

Abstract: Colorectal cancer is the second most common cancer affecting men and women in England.

Cited by 20 publications

References 34 publications

Kudo’s Classification for Colon Polyps Assessment Using a Deep Learning Approach

Kudo’s Classification for Colon Polyps Assessment Using a Deep Learning Approach

Surgical treatment of malignant colon polyps

Complete endoscopic mucosal resection of malignant colonic sessile polyps and clinical outcome of 51 cases.

Contact Info

Product

Resources

About