No abstract

Background and Aim Occasionally, colorectal tumors without characteristics of deep submucosal invasion are found to be invasive upon pathological evaluation after endoscopic resection (ER). Because the resection depth for underwater endoscopic mucosal resection (UEMR) has not been clarified, we evaluated the feasibility of UEMR for pathologically invasive colorectal cancer (pT1‐CRC). Methods We retrospectively investigated data on the backgrounds and outcomes of patients with pT1‐CRC who underwent UEMR between January 2014 and June 2019 at our institute. As a reference standard, the backgrounds and outcomes of pT1‐CRCs that had undergone conventional EMR (CEMR) were also investigated. Results Thirty‐one patients (median age, 68 years [range, 32–88 years]; 22 men [71%]) were treated with UEMR. Median lesion size was 17 mm (range, 6–50 mm). The endoscopic complete resection rate was 100%. The overall en bloc resection rate was 77%, and the VM0, HM0, and R0 resection rates were 81%, 58%, and 55%, respectively. In cases of pT1a (invasion <1000 μm)‐CRC (n = 14), the en bloc, VM0, and R0 resection rates were 92%, 100%, and 71%, respectively. Seventeen patients (five with risk factors for lymph node metastasis and 12 without) were followed up, and no local recurrence and distant metastasis were observed during the follow‐up period (median follow‐up period, 18 months [range, 6–62 months]) after UEMR. The outcomes of UEMR seemed to be comparable with those of CEMR (n = 32). Conclusions The VM0 rate of UEMR for pT1‐CRC, especially for pT1a‐CRC, without characteristics of deep submucosal invasion seems feasible.

Objectives: Artificial intelligence (AI) systems have shown favorable performance in the detection of esophageal squamous cell carcinoma (ESCC). However, previous studies were limited by the quality of their validation methods. In this study, we evaluated the performance of an AI system with videos simulating situations in which ESCC has been overlooked. Methods:We used 17,336 images from 1376 superficial ESCCs and 1461 images from 196 noncancerous and normal esophagi to construct the AI system. To record validation videos, the endoscope was passed through the esophagus at a constant speed without focusing on the lesion to simulate situations in which ESCC has been missed. Validation videos were evaluated by the AI system and 21 endoscopists. Results:We prepared 100 video datasets, including 50 superficial ESCCs, 22 noncancerous lesions, and 28 normal esophagi. The AI system had sensitivity of 85.7% (54 of 63 ESCCs) and specificity of 40%. Initial evaluation by endoscopists conducted with plain video (without AI support) had average sensitivity of 75.0% (47.3 of 63 ESCC) and specificity of 91.4%. Subsequent evaluation by endoscopists was conducted with AI assistance, which improved their sensitivity to 77.7% (P = 0.00696) without changing their specificity (91.6%, P = 0.756).Conclusions: Our AI system had high sensitivity for the detection of ESCC. As a support tool, the system has the potential to enhance detection of ESCC without reducing specificity. (UMIN000039645)

Objectives: We aimed to develop an artificial intelligence (AI) system for the real-time diagnosis of pharyngeal cancers.Methods: Endoscopic video images and still images of pharyngeal cancer treated in our facility were collected. A total of 4559 images of pathologically proven pharyngeal cancer (1243 using white light imaging and 3316 using narrow-band imaging/blue laser imaging) from 276 patients were used as a training dataset. The AI system used a convolutional neural network (CNN) model typical of the type used to analyze visual imagery. Supervised learning was used to train the CNN. The AI system was evaluated using an independent validation dataset of 25 video images of pharyngeal cancer and 36 video images of normal pharynx taken at our hospital. Results:The AI system diagnosed 23/25 (92%) pharyngeal cancers as cancers and 17/36 (47%) non-cancers as non-cancers. The transaction speed of the AI system was 0.03 s per image, which meets the required speed for real-time diagnosis. The sensitivity, specificity, and accuracy for the detection of cancer were 92%, 47%, and 66% respectively.Conclusions: Our single-institution study showed that our AI system for diagnosing cancers of the pharyngeal region had promising performance with high sensitivity and acceptable specificity. Further training and improvement of the system are required with a larger dataset including multiple centers.

No abstract