Subscribe to RSS
DOI: 10.1055/a-1488-6297
Green-colored areas in laterally spreading tumors on narrow-band imaging: a future target for artificial-intelligence-assisted detection of malignancies?
Accurate real-time characterization of colorectal lesions during endoscopy is crucial for histological prediction, allowing the choice of the most appropriate treatment [1]. Polyps are characterized on the basis of an evaluation of their macroscopic appearance, vascular pattern, and pit pattern with magnification, under both white-light and virtual chromoendoscopy such as narrow-band imaging (NBI) [2]. However, colorectal lesions are not homogeneous: a malignant component can sometimes occupy only a small area of the whole lesion and be relatively difficult to detect, especially for inexperienced endoscopists.
We report on four colorectal lesions with focal malignancies ([Video 1]). The first lesion was a 4-cm granular laterally spreading tumor (LST-G) in the sigmoid with a 5-mm area classified as Kudo Vn, Sano IIIa. The second lesion was a 3-cm pseudo-depressed nongranular LST in the sigmoid with a 5-mm area classified as Kudo Vn. The third lesion was a pseudo-depressed polyp in the right colon with a central area classified as Kudo Vi. The fourth lesion was a LST-G of the cecum with a 15-mm nodule classified as Kudo Vi, Sano IIIa. The four lesions were resected by endoscopic submucosal dissection and the suspect areas were identified as adenocarcinoma invading the submucosa to depths of, respectively, 3500 μm, 900 μm, and more than 1500 μm. In all four lesions, we detected with NBI a green-colored area (also visualized as a reddish area in TXI mode; Olympus, Tokyo, Japan) that corresponded to the area where invasive cancer was found ([Fig. 1], [Fig. 2], [Fig. 3], [Fig. 4]).
Video 1 Endoscopic examination of the four colorectal lesions with focal malignancies.
Quality:
These cases show that the malignant component within a large colorectal lesion can have a green-colored area that is easily detectable on a distant view of the lesion, without the need to analyze the entire surface under magnification. Targeting such areas before analyzing them more closely could be a way to improve prediction for inexperienced endoscopists, and the green coloration could be a red flag in artificial-intelligence-assisted support for endoscopists in detecting malignancies.
Endoscopy_UCTN_Code_TTT_1AQ_2AB
Endoscopy E-Videos is a free access online section, reporting on interesting cases and new techniques in gastroenterological endoscopy. All papers include a high
quality video and all contributions are
freely accessible online.
This section has its own submission
website at
https://mc.manuscriptcentral.com/e-videos
Publication History
Article published online:
12 May 2021
© 2021. Thieme. All rights reserved.
Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany
-
References
- 1 Fabritius M, Gonzalez J-M, Becq A. et al. A simplified table using validated diagnostic criteria is effective to improve characterization of colorectal polyps: the CONECCT teaching program. Endosc Int Open 2019; 07: E1197-E1206
- 2 Sano Y, Tanaka S, Kudo S. et al. Narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors proposed by the Japan NBI Expert Team: Japan NBI Expert Team classification. Digest Endosc 2016; 28: 526-533