Echoendoscopy in Preoperative Evaluation of Esophageal Adenocarcinoma and Gastroesophageal Junction: Systematic Review and Meta-analysis

Klamt, Alexandre Luis; Neyeloff, Jeruza Lavanholi; Santos, Luís Alberto Loureiro dos; Mazzini, Guilherme S.; Campos, Vinícius Jardim; Gurski, Richard Ricachenevsky

doi:10.1016/j.ultrasmedbio.2021.03.013

Cited by 15 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At present, the effectiveness of AI-NBI in the diagnosis of gastrointestinal tumors such as gastric cancer and colorectal cancer has been demonstrated [ 22 ]; scholars Barragán-Montero et al showed that the accuracy of IMRI deep learning-based AI system in diagnosing esophageal cancer was superior to that of 4 endoscopists [ 23 ] and that this technique could further determine the depth of invasion of early esophageal carcinoma, proving that AI system can compensate for the shortcomings of incomplete visual capture in humans and assist endoscopists in DEN for precise diagnosis. Scholars Pham et al constructed an AI model based on CNN and found that its sensitivity for detecting melanoma was 98.0% and the detection rate was significantly higher than endoscopists [ 24 ], and this study also found that the diagnosis rate of AI-NBI was 0.02 ± 0.01 s, significantly faster than that of physicians ( P < 0.001).…”

Section: Discussionmentioning

confidence: 99%

Efficacy of Digestive Endoscope Based on Artificial Intelligence System in Diagnosing Early Esophageal Carcinoma

Zhao

Liu

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Objective. To explore the efficacy of digestive endoscopy (DEN) based on artificial intelligence (AI) system in diagnosing early esophageal carcinoma. Methods. The clinical data of 300 patients with suspected esophageal carcinoma treated in our hospital from January 2018 to January 2020 were retrospectively analyzed; among them, 198 were diagnosed with esophageal carcinoma after pathological examination, and 102 had benign esophageal lesion. An AI system based on convolutional neural network (CNN) was adopted to assess the DEN images of patients with early esophageal carcinoma. A total of 200 patients (148 with early esophageal carcinoma and 52 with benign esophageal lesion) were selected as the learning group for the Inception V3 image classification system to learn; and the rest 100 patients (50 with early esophageal carcinoma and 50 with benign esophageal lesion) were included in the diagnosis group for the Inception V3 system to assist the narrow-band imaging (NBI) with diagnosis. The diagnosis results from Inception V3-assisted NBI were compared with those from imaging physicians, and the diagnostic efficacy diagram was drawn. Results. The diagnosis rate of AI-NBI was significantly faster than that of physician diagnosis ( 0.02 ± 0.01 vs. 5.65 ± 0.32 s (mean rate of two physicians), P < 0.001 ); between AI-NBI diagnosis and physician diagnosis, no statistical differences in sensitivity (90.0% vs. 92.0%), specificity (92.0% vs. 94.0%), and accuracy (91.0% vs. 93.0%) were observed ( P > 0.05 ); and according to the ROC curves, AUC (95% CI) of AI-NBI diagnosis = 0.910 (0.845-0.975), and AUC (95% CI) of physician diagnosis = 0.930 (0.872-0.988). Conclusion. CNN-based AI system can assist NBI in screening early esophageal carcinoma, which has a good application prospect in the clinical diagnosis of early esophageal carcinoma.

show abstract

Section: Discussionmentioning

confidence: 99%

Efficacy of Digestive Endoscope Based on Artificial Intelligence System in Diagnosing Early Esophageal Carcinoma

Zhao

Liu

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Both ET and carcinoma manifest as hypoechoic masses encroaching into various layers of the esophageal wall. Nevertheless, esophageal carcinoma is a hypoechoic mass derived from the epithelial layer, infiltrating from the inside to the outside [ 38 , 39 ]. Most ET is secondary to mediastinal lymph nodes, which are invaded externally.…”

Section: Manifestations Of Et According To Eusmentioning

confidence: 99%

Role of Endoscopy in Esophageal Tuberculosis: A Narrative Review

Zong

Zhao

et al. 2022

JCM

View full text Add to dashboard Cite

Esophageal tuberculosis (ET) is a rare infectious disease of the gastrointestinal tract. Awareness of ET is deficient due to its low incidence. Unexplained dysphagia and upper gastrointestinal bleeding are the most common symptoms of ET. The prognosis is generally good if patients are diagnosed properly and receive anti-tubercular treatment promptly. However, ET is difficult to differentiate from other diseases. Endoscopic techniques such as esophagogastroduodenoscopy (EGD), endoscopic ultrasonography (EUS), contrast-enhanced harmonic endoscopic ultrasonography (CH-EUS), elastography, and endoscopic ultrasound--guided fine-needle aspiration (EUS-FNA) improve the diagnosis of ET. Thus, the characteristics of ET and other difficult-to-detect diseases according to EGD and EUS were summarized. Intriguingly, there is no literature relevant to the application of CH-EUS and elastography in ET. The authors’ research center was first in introducing CH-EUS and elastography into the field of ET. The specific manifestation of ET based on CH-EUS was discovered for the first time. Correlative experience and representative cases were shared. The role of endoscopy in acquiring esophageal specimens and treatment for ET was also established. In this review, we aim to introduce a promising technology for the diagnosis and treatment of ET.

show abstract

“…In fact, for node (N) staging, sensitivity is 77.3% and specificity 67.4%, with an accuracy of 77.9%. 9 Baseline SUV max of 18‐fluorine‐fluorodeoxyglucose positron emission tomography/computed tomography ( 18 F‐FDG PET/CT) exhibits a high predictive value of the preoperative CT stage, as it can predict a locally advanced tumor with high accuracy. 10 Preoperative staging of esophageal adenocarcinoma has modest reliability and accuracy for pT and pN stages prediction, with as much as 25% of patients having conflicting clinical and pathological staging, which heavily affects overall survival.…”

Section: Introductionmentioning

confidence: 99%

“…Endoscopic ultrasound scan shows poor accuracy in preoperative staging of the esophagogastric junction and esophageal adenocarcinoma. In fact, for node (N) staging, sensitivity is 77.3% and specificity 67.4%, with an accuracy of 77.9% 9 . Baseline SUV max of 18‐fluorine‐fluorodeoxyglucose positron emission tomography/computed tomography ( 18 F‐FDG PET/CT) exhibits a high predictive value of the preoperative CT stage, as it can predict a locally advanced tumor with high accuracy 10 .…”

Section: Introductionmentioning

confidence: 99%

Tumor immune microenvironment in therapy‐naive esophageal adenocarcinoma could predict the nodal status

et al. 2022

View full text Add to dashboard Cite

Background: Currently, preoperative staging of esophageal adenocarcinoma (EAC) has modest reliability and accuracy for pT and pN stages prediction, which heavily affects overall survival. The interplay among immune checkpoints, oncogenes, and intratumoral and peritumoral immune infiltrating cells could be used to predict loco-regional metastatic disease in early EAC. Methods:We prospectively evaluated immune markers expression and oncogenes status as well as intratumoral and peritumoral immune infiltrating cells populations in esophageal mucosa samples obtained from neoadjuvant therapynaïve patients who had esophagectomy for EAC.Results: Vascular invasion and high infiltration of lamina propria mononuclear cells resulted associated with nodal metastasis. Low infiltration of activated CD8 + CD28 + T cells was observed in both intratumoral and peritumoral mucosa of patients with nodal metastasis. Low levels of CD69, MYD88, and TLR4 transcripts were detected in the intratumoral specimen of patients with lymph node involvement. Receiver operating characteristic curve analysis showed good accuracy for detecting nodal metastasis for all the markers tested. Significant lower infiltration of CD8 T cells and M1 macrophages and a lower expression of CD8A, CD8B, and TBX21 were found also in Esophageal Adenocarcinoma TCGA pan-Cancer Atlas in the normal tissue of patients with nodal metastasis. Conclusions:Our data suggest that immune surveillance failure is the main driver of nodal metastasis onset. Moreover, nodal metastasis containment also involves the immune microenvironment of the peritumoral healthy tissue.

show abstract

Echoendoscopy in Preoperative Evaluation of Esophageal Adenocarcinoma and Gastroesophageal Junction: Systematic Review and Meta-analysis

Cited by 15 publications

References 59 publications

Efficacy of Digestive Endoscope Based on Artificial Intelligence System in Diagnosing Early Esophageal Carcinoma

Efficacy of Digestive Endoscope Based on Artificial Intelligence System in Diagnosing Early Esophageal Carcinoma

Role of Endoscopy in Esophageal Tuberculosis: A Narrative Review

Tumor immune microenvironment in therapy‐naive esophageal adenocarcinoma could predict the nodal status

Contact Info

Product

Resources

About