{"title":"Classification of image-enhanced endoscopy in colon tumors.","authors":"One-Zoong Kim","doi":"10.5946/ce.2024.263","DOIUrl":null,"url":null,"abstract":"<p><p>Colorectal cancer accounts for 10% of global cancer cases in each year, making accurate evaluation and resection crucial. Imaging-enhanced endoscopy helps differentiate between hyperplastic polyps and adenomas, guiding treatment decisions. Colon tumors are classified into benign (e.g., serrated and adenomatous polyps) and malignant (e.g., adenocarcinomas). The Paris classification categorizes superficial neoplastic lesions by morphology, while laterally spreading tumors are classified by size and growth pattern. Effective classification aids in determining resectability and appropriate interventions for colon tumors, ultimately improving patient outcomes. Image-enhanced endoscopy improves colon tumor diagnosis using various techniques like dye, optical, and electronic methods. Kudo's pit pattern categorizes lesions based on surface morphology using dye, while Sano, Jikei, and Hiroshima classifications focus on vascular patterns using narrow-band imaging (NBI). The NBI International Colorectal Endoscopic (NICE) classification integrates these methods to identify lesions, especially deep submucosal invasive cancers. The Workgroup Serrated Polyps and Polyposis (WASP) classification targets sessile serrated lesions, and the Japan NBI Expert Team (JNET) classification further refines adenoma categorization with low- and high-grade adenoma. The Colorectal Neoplasia Endoscopic Classification to Choose the Treatment (CONECCT) classification consolidates multiple systems for comprehensive assessment, aiding in treatment decisions and potentially applicable to artificial intelligence for diagnostic validation across imaging modalities like linked color imaging, blue light imaging, or i-scan.</p>","PeriodicalId":10351,"journal":{"name":"Clinical Endoscopy","volume":" ","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Endoscopy","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5946/ce.2024.263","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Colorectal cancer accounts for 10% of global cancer cases in each year, making accurate evaluation and resection crucial. Imaging-enhanced endoscopy helps differentiate between hyperplastic polyps and adenomas, guiding treatment decisions. Colon tumors are classified into benign (e.g., serrated and adenomatous polyps) and malignant (e.g., adenocarcinomas). The Paris classification categorizes superficial neoplastic lesions by morphology, while laterally spreading tumors are classified by size and growth pattern. Effective classification aids in determining resectability and appropriate interventions for colon tumors, ultimately improving patient outcomes. Image-enhanced endoscopy improves colon tumor diagnosis using various techniques like dye, optical, and electronic methods. Kudo's pit pattern categorizes lesions based on surface morphology using dye, while Sano, Jikei, and Hiroshima classifications focus on vascular patterns using narrow-band imaging (NBI). The NBI International Colorectal Endoscopic (NICE) classification integrates these methods to identify lesions, especially deep submucosal invasive cancers. The Workgroup Serrated Polyps and Polyposis (WASP) classification targets sessile serrated lesions, and the Japan NBI Expert Team (JNET) classification further refines adenoma categorization with low- and high-grade adenoma. The Colorectal Neoplasia Endoscopic Classification to Choose the Treatment (CONECCT) classification consolidates multiple systems for comprehensive assessment, aiding in treatment decisions and potentially applicable to artificial intelligence for diagnostic validation across imaging modalities like linked color imaging, blue light imaging, or i-scan.