Artificial intelligence-based detection of pharyngeal cancer using convolutional neural networks.

OBJECTIVES: The prognosis for pharyngeal cancer is relatively poor. It is usually diagnosed in an advanced stage. Although the recent development of narrow-band imaging (NBI) and increased awareness among endoscopists have enabled detection of superficial pharyngeal cancer, these techniques are still not prevalent worldwide. Nevertheless, artificial intelligence (AI)-based deep learning has led to significant advancements in various medical fields. Here, we demonstrate the diagnostic ability of AI-based detection of pharyngeal cancer from endoscopic images in esophagogastroduodenoscopy. METHODS: We retrospectively collected 5403 training images of pharyngeal cancer from 202 superficial cancers and 45 advanced cancers from the Cancer Institute Hospital, Tokyo, Japan. Using these images, we developed an AI-based diagnostic system with convolutional neural networks. We prepared 1912 validation images from 35 patients with 40 pharyngeal cancers and 40 patients without pharyngeal cancer to evaluate our system. RESULTS: Our AI-based diagnostic system correctly detected all pharyngeal cancer lesions (40/40) in the patients with cancer, including three small lesions smaller than 10 mm. For each image, the AI-based system correctly detected pharyngeal cancers in images obtained via NBI with a sensitivity of 85.6%, much higher sensitivity than that for images obtained via white light imaging (70.1%). The novel diagnostic system took only 28 s to analyze 1912 validation images. CONCLUSIONS: The novel AI-based diagnostic system detected pharyngeal cancer with high sensitivity. It could facilitate early detection, thereby leading to better prognosis and quality of life for patients with pharyngeal cancers in the near future.

Extra-ampullary duodenal adenoma: a clinicopathological study.

AIMS: Extra-ampullary duodenal adenoma (EADA) is a rare condition with poorly described clinicopathological details. In this study, we aimed to characterize EADA clinicopathologically. METHODS AND RESULTS: We performed a retrospective review of 44 serial cases of EADA. Each EADA was categorized as either gastric-type (n = 5) or intestinal-type (n = 39). All gastric-type adenomas were located in the first portion of the duodenum and exhibited a pedunculated shape. Gastric-type adenomas were classified into two subtypes: pyloric gland and foveolar. The former consisted of mucin 6 (MUC6)-positive glands covered with MUC5AC-positive cells, whereas nearly all the latter consisted of MUC5AC-positive cells. When EADAs were categorized into high and low grades, approximately 40% (16 of 44) were high-grade. The high-grade adenomas were significantly larger than the low-grade adenomas (19.4 ± 8.6 mm versus 11.8 ± 5.1 mm, P = 0.021), and all adenomas greater than 20 mm in largest diameter were categorized as high-grade adenomas. Among 16 individuals who underwent total colonoscopy before or after duodenal mucosal resection, nine had a colorectal neoplasm, and all nine duodenal lesions were of the intestinal phenotype. CONCLUSIONS: We clarified the clinicopathological characteristics of gastric- and intestinal-type EADAs. EADAs greater than 20 mm at the largest diameter were consistently high-grade, and are thought to have the potential to progress to adenocarcinoma. These findings should be helpful for the clinical management of EADA.