Endoscopic Submucosal Dissection for Upper Gastrointestinal Neoplasia-a North American Perspective

Esophagectomy versus observation following endoscopic submucosal dissection of pT1b esophageal adenocarcinoma

BACKGROUND

Management following endoscopic submucosal dissection (ESD) of pT1b esophageal adenocarcinoma (EAC) remains controversial. This study compared pathological and survival outcomes of patients after endoscopic resection (ER) of pT1b EAC followed by either en bloc esophagectomy or observation.

METHODS

From 1/12 to 12/22, all patients with pT1b EAC treated with ER were identified from a prospectively maintained departmental database. ESD was curative (all of: Submucosal invasion < 500 μm; G1/2, LVI/PNI-; deep margin-) or non-curative (one or more of Submucosal invasion ≥ 500 μm; G3; LVI/PNI+; deep margin+). Patients were allocated to observation (OBS) or esophagectomy (SURG) based on patient factors/preference and pathological variables.

RESULTS

56/171 ERs met the inclusion criteria. ER was curative in 8/56 (14%) and non-curative in 48/56 (86%). OBS was undertaken after 8/27 (30%) curative and 19/27 (70%) non-curative resections. All 29 SURG patients had non-curative ERs and were younger, had lower Charlson comorbidity scores and had more deep margin + lesions than OBS patients. Post-esophagectomy, 15/29 (52%) had no residual disease within the surgical specimen while pT+N-/pT-N+/pT+N+ occurred in 5/3/6 (17%/10%/21%) patients. Of those with residual disease in the surgical specimen, 12/14 (86%) had deep margin + ERs; however, only ESD instead of EMR was independently associated with a lower risk of residual disease (OR 0.431, 95% CI - 0.016 to 1.234, p = 0.045). OBS and SURG patients had equivalent overall survival outcomes and recurrence was low in both groups even following non-curative ER. Follow-up was 28 months (0-102) and 30 months (0-97), respectively.

CONCLUSION

In select patients, including some of those with a non-curative ESD resection of pT1B EAC, surveillance alone may be appropriate. Alternatives beyond traditional pathological features is needed to direct patient care more accurately.

Deep Learning-Based Ultrasound Combined with Gastroscope for the Diagnosis and Nursing of Upper Gastrointestinal Submucous Lesions

The study focused on the diagnostic value of deep learning-based ultrasound combined with gastroscope examination for upper gastrointestinal submucous lesions and nursing. A total of 104 patients with upper gastrointestinal submucous lesions diagnosed in hospital were selected as the research subjects. In this study, the feed forward denoising convulsive neural network (DnCNN) was improved, and the n-DnCNN model was designed and applied to ultrasonic image processing. The peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of Gaussian filtering, NL-means, and DnCNN were then compared with n-DnCNN. Subsequently, the distribution and types of submucosal lesions in different parts of the upper digestive tract were analyzed by ultrasound combined with gastroscope and gastroscope examination alone, and the diagnostic performance of this method was evaluated. The results showed that the average PSNR and SSIM of the n-DnCNN model were 33.01 dB and 0.87, respectively, which were significantly higher than GF, NL-means, and DnCNN algorithms, and the difference was statistically significant ( $P<0.05$ ). Of the 116 lesions detected, 49 were located in the esophagus (42.24%), 52 in the stomach (44.83%), and 15 in the duodenum (12.93%). Of the 49 esophageal submucosal lesions, 6.12% were located in the upper esophagus, 55.1% in the middle esophagus, and 38.79% in the lower esophagus, and the difference was statistically significant ( $P<0.05$ ). Of the gastric submucosal lesions, the lesions in the gastric cardia were significantly less than in other parts, and the difference was statistically significant ( $P<0.05$ ). The accuracy of ultrasound combined with gastroscope in the diagnosis of upper gastrointestinal submucous episodes was 82.32%, higher than that of gastroscope examination, and the difference was statistically significant ( $P<0.05$ ). In conclusion, the n-DnCNN model has a good noise reduction effect, and the obtained image is of high quality. Ultrasound combined with gastroscope examination can effectively improve the accuracy of diagnosis of upper gastrointestinal submucous lesions.