Open Access
CC BY 4.0 · Endoscopy 2023; 55(S 01): E1240-E1241
DOI: 10.1055/a-2208-3412
E-Videos

Endoscopic submucosal dissection for a small high grade intraepithelial neoplasia in the hypopharynx detected incidentally by artificial intelligence

Authors

  • Ruide Liu

    1   Department of Gastroenterology and Hepatology, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)
  • Xianglei Yuan

    1   Department of Gastroenterology and Hepatology, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)
  • Shuang Liu

    1   Department of Gastroenterology and Hepatology, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)
  • Bing Hu

    1   Department of Gastroenterology and Hepatology, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)

Supported by: National Natural Science Foundation of China Grant No: 82170675
Supported by: 1·3·5 project for disciplines of excellence, West China Hospital, Sichuan University Grant No: ZYJC21011
 

Hypopharyngeal carcinoma, a malignant tumor with a poor prognosis, is usually diagnosed at an advanced stage owing to underdiagnosis. Limited knowledge of hypopharyngeal lesions and rapid access to the esophagus during endoscopy might contribute to this delayed diagnosis [1]. Previous studies have shown the potential of artificial intelligence (AI)-based systems for high sensitivity detection of early pharyngeal cancer [2]. Here, we present a case in which a hypopharyngeal precancerous lesion was incidentally detected using AI and successfully treated by endoscopic submucosal dissection (ESD).

A 58-year-old man was referred to our hospital for endoscopic treatment of an esophageal mucosal lesion. He had experienced hoarseness and throat discomfort for 2 years. Enhanced computed tomography of the head and neck showed no obvious thickening or abnormal enhancement in the pharynx, nor any enlarged cervical lymph nodes ([Fig. 1] a). During endoscopic treatment for the esophageal lesion, with the assistance of an AI system, a suspected hypopharyngeal precancerous lesion, approximately 0.7 cm in size, was detected in the corniculate tubercle of the hypopharynx ([Fig. 1] b,c, [Video 1]). Given the previous success of ESD in treating early hypopharyngeal cancer, the patient agreed to undergo the procedure, which was successfully performed [3] [4] ([Fig. 1] d). Histopathology revealed a high grade squamous intraepithelial neoplasia measuring 0.7×0.3 cm ([Fig. 2]).

Zoom
Fig. 1 Preoperative images and the postoperative specimen. a Computed tomography showed that there was no obvious thickening or abnormal enhancement in the pharynx, nor any enlarged cervical lymph nodes. b Artificial intelligence system incidentally detected a small mucosal lesion of approximately 0.7 cm under white-light imaging. c The same lesion under narrow-band imaging. d The resected specimen measured 1.0 × 1.2  cm.
Endoscopic submucosal dissection for a small, high grade intraepithelial neoplasia in the hypopharynx detected incidentally by artificial intelligence.Video 1

Zoom
Fig. 2 Histopathology of the specimen showed a high grade squamous intraepithelial neoplasia (hematoxylin and eosin ×200).

Subsequent follow-up endoscopy at 1 year showed no residual lesion or recurrence.

The potential for synchronous or metachronous head–neck cancer in patients with esophageal squamous cell carcinoma (ESCC) underscores the significance of careful examination of the pharynx during endoscopy in such patients [5]. Previous AI systems have primarily focused on detecting early hypopharyngeal cancer, leaving uncertainty about their capacity to identify hypopharyngeal precancerous lesions. While our team’s AI system was originally developed for ESCC and precancerous lesions, it has demonstrated efficacy in detecting similar squamous epithelial precancerous lesions in the hypopharynx. Nevertheless, further clinical studies are essential to validate its effectiveness.

Endoscopy_UCTN_Code_CCL_1AB_2AB

E-Videosis an open access online section of the journal Endoscopy, reporting on interesting cases and new techniques in gastroenterological endoscopy. All papers include a high-quality video and are published with a Creative Commons CC-BY license. Endoscopy E-Videos qualify for HINARI discounts and waivers and eligibility is automatically checked during the submission process. We grant 100% waivers to articles whose corresponding authors are based in Group A countries and 50% waivers to those who are based in Group B countries as classified by Research4Life (see: https://www.research4life.org/access/eligibility/).

This section has its own submission website athttps://mc.manuscriptcentral.com/e-videos.


Conflict of Interest

The authors declare that they have no conflict of interest.


Correspondence

Bing Hu, MD
Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University
Guo Xue Alley 37
610041 Chengdu
China   

Publication History

Article published online:
12 December 2023

© 2023. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/).

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany


Zoom
Fig. 1 Preoperative images and the postoperative specimen. a Computed tomography showed that there was no obvious thickening or abnormal enhancement in the pharynx, nor any enlarged cervical lymph nodes. b Artificial intelligence system incidentally detected a small mucosal lesion of approximately 0.7 cm under white-light imaging. c The same lesion under narrow-band imaging. d The resected specimen measured 1.0 × 1.2  cm.
Zoom
Fig. 2 Histopathology of the specimen showed a high grade squamous intraepithelial neoplasia (hematoxylin and eosin ×200).