Artificial intelligence-based diagnosis of the depth of laryngopharyngeal cancer

Kohei Yumii; Tsutomu Ueda; Daisuke Kawahara; Nobuyuki Chikuie; Takayuki Taruya; Takao Hamamoto; Sachio Takeno

doi:10.1016/j.anl.2023.09.001

Artificial intelligence-based diagnosis of the depth of laryngopharyngeal cancer

Auris Nasus Larynx. 2024 Apr;51(2):417-424. doi: 10.1016/j.anl.2023.09.001. Epub 2023 Oct 12.

Authors

Kohei Yumii¹, Tsutomu Ueda², Daisuke Kawahara³, Nobuyuki Chikuie¹, Takayuki Taruya¹, Takao Hamamoto¹, Sachio Takeno¹

Affiliations

¹ Department of Otorhinolaryngology, Head and Neck Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, 1-2-3 Kasumi Minami-ku, Hiroshima, Japan.
² Department of Otorhinolaryngology, Head and Neck Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, 1-2-3 Kasumi Minami-ku, Hiroshima, Japan. Electronic address: uedatsu@hiroshima-u.ac.jp.
³ Department of Radiation Oncology, Graduate School of Biomedical Health Sciences, Hiroshima University, Hiroshima, Japan.

PMID: 37838567
DOI: 10.1016/j.anl.2023.09.001

Abstract

Objective: Transoral surgery (TOS) is a widely used treatment for laryngopharyngeal cancer. There are some difficult cases of setting the extent of resection in TOS, particularly in setting the vertical margins. However, positive vertical margins require additional treatment. Further, excessive resection should be avoided as it increases the risk of bleeding as a postoperative complication and may lead to decreased quality of life, such as dysphagia. Considering these issues, determining the extent of resection in TOS is an important consideration. In this study, we investigated the possibility of accurately diagnosing the depth of laryngopharyngeal cancer using radiomics, an image analysis method based on artificial intelligence (AI).

Methods: We included esophagogastroduodenoscopic images of 95 lesions that were pathologically diagnosed as squamous cell carcinoma (SCC) and treated with transoral surgery at our institution between August 2009 and April 2020. Of the 95 lesions, 54 were SCC in situ, and 41 were SCC. Radiomics analysis was performed on 95 upper gastrointestinal endoscopic NBI images of these lesions to evaluate their diagnostic performance for the presence of subepithelial invasion. The lesions in the endoscopic images were manually delineated, and the accuracy, sensitivity, specificity, and area under the curve (AUC) were evaluated from the features obtained using least absolute shrinkage and selection operator analysis. In addition, the results were compared with the depth predictions made by skilled endoscopists.

Results: In the Radiomics study, the average cross-validation was 0.833. The mean AUC for cross-validation calculated from the receiver operating characteristic curve was 0.868. These results were equivalent to those of the diagnosis made by a skilled endoscopist.

Conclusion: The diagnosis of laryngopharyngeal cancer depth using radiomics analysis has potential clinical applications. We plan to use it in actual surgery in the future and prospectively study whether it can be used for diagnosis.

Keywords: Artificial intelligence (AI); Deep learning; Diagnosis of depth; Head and neck cancer; Radiomics; Transoral surgery.

MeSH terms

Artificial Intelligence*
Carcinoma, Squamous Cell* / diagnostic imaging
Carcinoma, Squamous Cell* / surgery
Endoscopy
Humans
Quality of Life
ROC Curve
Retrospective Studies