Learning Effect of Diagnosing Depth of Invasion Using Non-Extension Sign in Early Gastric Cancer

Absence of the Nonextension Sign as a Marker for Endoscopic Submucosal Dissection Suitability

Early gastric cancer is defined as gastric cancer confined to the mucosa or submucosa, irrespective of lymph node metastasis. Endoscopic submucosal dissection is a standard treatment of early gastric cancer. The nonextension sign consists of a protrusion of the surrounding mucosa into the lumen, resembling a trapezoidal shape. This phenomenon occurs when massive submucosal invasion by a cancer increases the thickness and rigidity of the gastric wall and may be useful to differentiate between mucosal or microinvasive submucosal and invasive submucosal cancers. Our case demonstrates the usefulness of the absence of the conventional endoscopic nonextension sign as a marker to decide the adequate approach for mucosal lesions.

Current Evidence and Future Perspective of Accuracy of Artificial Intelligence Application for Early Gastric Cancer Diagnosis With Endoscopy: A Systematic and Meta-Analysis

Background & Aims: Gastric cancer is the common malignancies from cancer worldwide. Endoscopy is currently the most effective method to detect early gastric cancer (EGC). However, endoscopy is not infallible and EGC can be missed during endoscopy. Artificial intelligence (AI)-assisted endoscopic diagnosis is a recent hot spot of research. We aimed to quantify the diagnostic value of AI-assisted endoscopy in diagnosing EGC.

Method: The PubMed, MEDLINE, Embase and the Cochrane Library Databases were searched for articles on AI-assisted endoscopy application in EGC diagnosis. The pooled sensitivity, specificity, and area under the curve (AUC) were calculated, and the endoscopists' diagnostic value was evaluated for comparison. The subgroup was set according to endoscopy modality, and number of training images. A funnel plot was delineated to estimate the publication bias.

Result: 16 studies were included in this study. We indicated that the application of AI in endoscopic detection of EGC achieved an AUC of 0.96 (95% CI, 0.94–0.97), a sensitivity of 86% (95% CI, 77–92%), and a specificity of 93% (95% CI, 89–96%). In AI-assisted EGC depth diagnosis, the AUC was 0.82(95% CI, 0.78–0.85), and the pooled sensitivity and specificity was 0.72(95% CI, 0.58–0.82) and 0.79(95% CI, 0.56–0.92). The funnel plot showed no publication bias.

Conclusion: The AI applications for EGC diagnosis seemed to be more accurate than the endoscopists. AI assisted EGC diagnosis was more accurate than experts. More prospective studies are needed to make AI-aided EGC diagnosis universal in clinical practice.

Clinical significance of endoscopic ultrasonography in diagnosing invasion depth of early gastric cancer prior to endoscopic submucosal dissection

BACKGROUND AND AIM

Endoscopic ultrasonography is a reliable diagnostic modality for determining indications of endoscopic submucosal dissection for early gastric cancer. We aimed to clarify the clinical significance of endoscopic ultrasonography in the invasion depth diagnosis of early gastric cancer.

METHODS

We retrospectively assessed 1598 consecutive patients with 2001 early gastric cancers who underwent EUS before ESD or surgery between October 2010 and April 2019 at our institution. Lesions were classified according to endoscopic ultrasonography-determined invasion depth as EUS-M/SM1 (lesions confined to sonographic layers 1 and 2 or lesions with changes in sonographic layer 3; depth, < 1 mm) and EUS-SM2 (lesions with changes in sonographic layer 3; depth, ≥ 1 mm). We evaluated the invasion depth determination accuracy of endoscopic ultrasonography and analyzed the clinicopathological features of misdiagnosed early gastric cancer cases.

RESULTS

The invasion depth determination accuracy was as follows: EUS-M/SM1: pathological T1a/T1b1 early gastric cancer, 97%; EUS-SM2: pathological T1b2 early gastric cancer, 79%. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 95%, 98%, 69%, 97%, and 79%, respectively. In EUS-M/SM1 early gastric cancer, tumor size of ≥ 15 mm, presence of ulceration, and undifferentiated histological type were significantly associated with endoscopic ultrasonography accuracy. In EUS-SM2 early gastric cancer, tumor size of ≥ 30 mm was significantly associated with endoscopic ultrasonography accuracy.

CONCLUSIONS

Endoscopic ultrasonography is a useful modality in accurately determining the invasion depth of early gastric cancer before endoscopic submucosal dissection.