Depth Of Cancer Invasion Research Articles

Role of Artificial Intelligence in Upper Gastrointestinal Diseases: Present and Future

There has been extensive research and progress in the medical application of Artificial Intelligence (AI) technology. Radiologic and endoscopic diagnosis based on image analysis has been one of the main areas of focus. In the field of Gastrointestinal (GI) endoscopy, AI has been applied to gastroscopy, capsule endoscopy, and colonoscopy. There are relatively fewer studies in which AI is applied to upper GI diseases, and analysis has mainly focused on the detection of esophageal or gastric neoplasms in upper GI endoscopy. AI is also used to assess the depth of cancer invasion, detect Helicobacter pylori (H. pylori) infection, and diagnose the characteristics of subepithelial lesions. In the near future, AI is expected to expand to the field of disease treatment.

Indications of esophageal cancer for endoscopic submucosal dissection, curability, and future perspectives

This review considers the preferred preoperative examinations, indications for endoscopic submucosal dissection (ESD), and curative ability of ESD in patients with esophageal squamous cell carcinoma (SCC). Endoscopic evaluation by non-magnifying endoscopy followed by magnifying endoscopy is a common procedure for diagnosing invasion depth of superficial esophageal SCCs in Japan. However, endoscopic ultrasonography may increase overdiagnosis of the depth of cancer invasion, and therefore should not be performed routinely. Image-enhanced magnifying endoscopy or iodine staining is recommended for diagnosing the lateral extent of esophageal SCC. The indications for ESD include clinical T1a-epithelial/lamina propria (EP/LPM) N0M0 non-circumferential lesions, clinical T1a EP/LPM N0M0 circumferential lesions ≤ 50 mm, and clinical T1a-muscularis mucosae/T1b-submucosa 1 cancer (invading submucosa by ≤ 200 µm) N0M0 non-circumferential lesions. Pathological T1a EP/LPM without vascular invasion is defined as curative resection, while pathological T1a MM without vascular invasion is considered as non-curative resection, with undetermined recommendations for additional treatment. Pathological T1b cancer invading the submucosa or pathological vascular invasion-positivity is considered as non-curative resection, and additional treatment is recommended. An accurate preoperative diagnosis, appropriate indication, and adequate curability assessment based on the pathological diagnosis of resected specimens are important for effective ESD.

Measurement variations of MRI and CT in the assessment of tumor depth of invasion in oral cancer: A retrospective study

PurposeIn oral squamous cell carcinoma (OSCC), depth of invasion (DOI) is an important predictive, prognostic, and staging parameter. While it is known that DOI can be estimated from preoperative imaging, an analysis of measurements variations according to imaging modality and to depth of tumor itself is lacking. The aim of the study was to assess the accuracy of imaging-based estimation of DOI in relation with the tumor histological DOI. MethodsWe retrospectively reviewed 121 patients with OSCC treated at University Hospital Zurich. The radiologic DOI of CT, T1-weighted, and T2-weighted MRI were compared with histological DOI. Frequency of relevant imaging artifacts was assessed as well. ResultsA total of 110 CT (90.9 %) and 90 MRI (74 %) were analyzed. Both modalities were available for 79 patients (65.3 %). The median histological depth of invasion was 9 mm (IQR 4.5–14). The median depth of invasion was 14 mm (IQR 10–20) on CT, 13 mm (IQR 8.25–18) on T1-weighted MRI, and 13 mm (IQR 9–18.75) on T2-weighted MRI. All diagnostic modalities tended towards an overestimation of the histopathologic DOI from about 5–15 %. This trend was most pronounced for thin tumors, for which both CT and MRI lead to upstaging in over 50 % of the cases. For 25 (22.7 %) patients, dental scattering on CT rendered DOI not estimable. For MRI, 18 patients (20 %) had artifacts (blooming, motion artifacts) rendering DOI not estimable. ConclusionCT and MRI measurements of DOI in OSCC lead to an overestimation of histological DOI, especially in tumors with DOI<5 mm, with upstaging by imaging in over 50 % of the cases. Artifacts were present in more than 20 % of performed images.

Endoscopic Recognition and Management Strategies for Malignant Colorectal Polyps: Recommendations of the US Multi-Society Task Force on Colorectal Cancer.

Endoscopic Recognition and Management Strategies for Malignant Colorectal Polyps: Recommendations of the US Multi-Society Task Force on Colorectal Cancer.

Clinical practice guideline for endoscopic resection of early gastrointestinal cancer.

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Prognostic and clinicopathological significance of pretreatment mean platelet volume in cancer: a meta-analysis

ObjectiveOur study aimed to evaluate the prognostic and clinicopathological significance of pretreatment mean platelet volume (MPV) on cancer by using meta-analysis of published studies.DesignMeta-analysis.Data sourcesRelevant studies available before 22 December...

Using deep learning with convolutional neural network approach to identify the invasion depth of endometrial cancer in myometrium using MR images: A pilot study

Objective: Artificial intelligence (AI) is a rising technology with the power to improve the way we analyze diagnosis through medical imaging data. The discrepancy between preoperative magnetic resonance imaging (MRI) staging and postoperative pathologic staging of endometrial cancer remains unmet. This study aimed to validate the accuracy of AI to detect the depth of uterine myometrial invasion using deep learning techniques with convolutional neural networks (CNN) on MRI.

Circ_0072088 Promotes Proliferation, Migration, and Invasion of Esophageal Squamous Cell Cancer by Absorbing miR-377.

Circular RNA (circRNA) is an endogenous noncoding RNA. Accumulative investigations have confirmed that circRNAs play a vital role in carcinogenesis and tumor progression. Herein, we examined the expression and mechanism of circ_0072088 in esophageal squamous cell carcinoma (ESCC). As a result, circ_0072088 was significantly overexpressed in ESCC tissues and cells, which was closely associated with tumor size, invasion depth, clinical stage, and lymph node metastasis of esophageal cancer. Nuclear and cytoplasmic separation as well as FISH assays showed that circ_0072088 was mainly localized in the cytoplasm of ESCC cells. RNase R treatment assay revealed that circ_0072088 was steadier than linear ZFR mRNA. circ_0072088 promoted ESCC cell proliferation, migration and invasion in vitro, and cell proliferation in vivo. Mechanistically, circ_0072088 upregulated VEGF gene expression by acting as the sponge of miRNA-377. In conclusion, circ_0072088 might be used as a diagnostic biomarker and therapeutic target for ESCC.

PGC-1α and ERRα in patients with endometrial cancer: a translational study for predicting myometrial invasion.

Background: PGC-1α and ERRα are closely related to tumor formation and progression. However, the mechanism underlying the involvement of PGC-1α/ERRα in regulating invasion and migration in endometrial cancer remains to be explored.Results: Elevated levels of PGC-1α and ERRα were associated with advanced myometrial invasion, and PGC-1α and Vimentin expression was related to the depth of myometrial invasion in premenopausal endometrial cancer. Silencing of PGC-1α reduced ERRα activation and inhibited epithelial-mesenchymal-transition phenotypes, resulting in significant inhibition of invasion and migration. Overexpression of ERRα led to enhanced PGC-1α expression and increased activity of TFEB, promoting epithelial-mesenchymal-transition in endometrial cancer cells.Conclusions: PGC-1α and ERRα induce the epithelial-mesenchymal-transition therefore invasion and migration in endometrial cancer, and may be novel biomarkers to predict the risk of advanced myometrial invasion.Methods: PGC-1α, ERRα, and vimentin expression was analyzed in tissue microarrays using immunohistochemistry. PGC-1α and ERRα expression in endometrial cancer cell lines was investigated using quantitative PCR and western blotting analyses after infection with lentivirus-mediated small interfering RNA (siRNA) targeting PGC-1α (siRNA-PGC-1α) or overexpressing ERRα. E-cadherin and vimentin levels were determined using western blotting and cell immunouorescence analyses. Cell migration and invasiveness were evaluated using scratch and trans-well chamber assays.

Real-time assessment of video images for esophageal squamous cell carcinoma invasion depth using artificial intelligence.

Although optimal treatment of superficial esophageal squamous cell carcinoma (SCC) requires accurate evaluation of cancer invasion depth, the current process is rather subjective and may vary by observer. We, therefore, aimed to develop an AI system to calculate cancer invasion depth. We gathered and selected 23,977 images (6857 WLI and 17,120 NBI/BLI images) of pathologically proven superficial esophageal SCC from endoscopic videos and still images of superficial esophageal SCC taken in our facility, to use as a learning dataset. We annotated the images with information [such as magnified endoscopy (ME) or non-ME, pEP-LPM, pMM, pSM1, and pSM2-3 cancers] based on pathologic diagnosis of the resected specimens. We created a model using a convolutional neural network. Performance of the AI system was compared with that of invited experts who used the same validation video set, independent of the learning dataset. Accuracy, sensitivity, and specificity with non-magnified endoscopy (ME) were 87%, 50%, and 99% for the AI system and 85%, 45%, 97% for the experts. Accuracy, sensitivity, and specificity with ME were 89%, 71%, and 95% for the AI system and 84%, 42%, 97% for the experts. Most diagnostic parameters were higher when done by the AI system than by the experts. These results suggest that our AI system could potentially provide useful support during endoscopies.

Anatomical classification of upper gastrointestinal organs under various image capture conditions using AlexNet

BackgroundMachine learning has led to several endoscopic studies about the automated localization of digestive lesions and prediction of cancer invasion depth. Training and validation dataset collection are required for a disease in each digestive organ under a similar image capture condition; this is the first step in system development. This data cleansing task in data collection causes a great burden among experienced endoscopists. Thus, this study classified upper gastrointestinal (GI) organ images obtained via routine esophagogastroduodenoscopy (EGD) into precise anatomical categories using AlexNet. MethodIn total, 85,246 raw upper GI endoscopic images from 441 patients with gastric cancer were collected retrospectively. The images were manually classified into 14 categories: 0) white-light (WL) stomach with indigo carmine (IC); 1) WL esophagus with iodine; 2) narrow-band (NB) esophagus; 3) NB stomach with IC; 4) NB stomach; 5) WL duodenum; 6) WL esophagus; 7) WL stomach; 8) NB oral–pharynx–larynx; 9) WL oral–pharynx–larynx; 10) WL scaling paper; 11) specimens; 12) WL muscle fibers during endoscopic submucosal dissection (ESD); and 13) others. AlexNet is a deep learning framework and was trained using 49,174 datasets and validated using 36,072 independent datasets. ResultsThe accuracy rates of the training and validation dataset were 0.993 and 0.965, respectively. ConclusionsA simple anatomical organ classifier using AlexNet was developed and found to be effective in data cleansing task for collection of EGD images. Moreover, it could be useful to both expert and non-expert endoscopists as well as engineers in retrospectively assessing upper GI images.

Using Deep Learning with Convolutional Neural Network Approach to Identify the Invasion Depth of Endometrial Cancer in Myometrium Using MR Images: A Pilot Study.

Myometrial invasion affects the prognosis of endometrial cancer. However, discrepancies exist between pre-operative magnetic resonance imaging staging and post-operative pathological staging. This study aims to validate the accuracy of artificial intelligence (AI) for detecting the depth of myometrial invasion using a deep learning technique on magnetic resonance images. We obtained 4896 contrast-enhanced T1-weighted images (T1w) and T2-weighted images (T2w) from 72 patients who were diagnosed with surgico-pathological stage I endometrial carcinoma. We used the images from 24 patients (33.3%) to train the AI. The images from the remaining 48 patients (66.7%) were used to evaluate the accuracy of the model. The AI then interpreted each of the cases and sorted them into stage IA or IB. Compared with the accuracy rate of radiologists’ diagnoses (77.8%), the accuracy rate of AI interpretation in contrast-enhanced T1w was higher (79.2%), whereas that in T2w was lower (70.8%). The diagnostic accuracy was not significantly different between radiologists and AI for both T1w and T2w. However, AI was more likely to provide incorrect interpretations in patients with coexisting benign leiomyomas or polypoid tumors. Currently, the ability of this AI technology to make an accurate diagnosis has limitations. However, in hospitals with limited resources, AI may be able to assist in reading magnetic resonance images. We believe that AI has the potential to assist radiologists or serve as a reasonable alternative for pre-operative evaluation of the myometrial invasion depth of stage I endometrial cancers.

Highly accurate artificial intelligence systems to predict the invasion depth of gastric cancer: efficacy of conventional white-light imaging, nonmagnifying narrow-band imaging, and indigo-carmine dye contrast imaging

Diagnosing the invasion depth of gastric cancer (GC) is necessary to determine the optimal method of treatment. Although the efficacy of evaluating macroscopic features and EUS has been reported, there is a need for more accurate and objective methods. The primary aim of this study was to test the efficacy of novel artificial intelligence (AI) systems in predicting the invasion depth of GC. A total of 16,557 images from 1084 cases of GC for which endoscopic resection or surgery was performed between January 2013 and June 2019 were extracted. Cases were randomly assigned to training and test datasets at a ratio of 4:1. Through transfer learning leveraging a convolutional neural network architecture, ResNet50, 3 independent AI systems were developed. Each system was trained to predict the invasion depth of GC using conventional white-light imaging (WLI), nonmagnifying narrow-band imaging (NBI), and indigo-carmine dye contrast imaging (Indigo). The area under the curve of the WLI AI system was .9590. The lesion-based sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the WLI AI system were 84.4%, 99.4%, 94.5%, 98.5%, and 92.9%, respectively. The lesion-based accuracies of the WLI, NBI, and Indigo AI systems were 94.5%, 94.3%, and 95.5%, respectively, with no significant difference. These new AI systems trained with multiple images from different angles and distances could predict the invasion depth of GC with high accuracy. The lesion-based accuracy of the WLI, NBI, and Indigo AI systems was not significantly different.

Roles of Fascin mRNA expression in colorectal cancer: Meta-analysis and bioinformatics analysis.

Fascin (encoded by FSCN1) is a globular actin cross-linking protein that is required for the formation of actin-based cell surface processes, which are critical for cell migration and cell-matrix adhesion. In the present study, a systematic meta-analysis and bioinformatics analysis was used to identify clinicopathological or prognostic parameters in patients with colorectal cancer. A total of 17 articles were included in the present study obtained from PubMed, Web of Science, Wanfang data, SinoMed and CNKI databases. Odd ratios (ORs) and the corresponding 95% confidence intervals (CIs) were used to estimate the prognostic significance of Fascin expression in patients with colorectal cancer, and the association between Fascin expression and clinicopathological factors. There was a significant correlation between high Fascin expression and poor overall survival rates in patients with colorectal cancer (OR=0.48; 95% CI, 0.38-0.60; P<0.000001). The meta-analysis showed that the expression of Fascin was significantly higher in colorectal cancer tissue compared with the normal mucosa (OR=0.13; 95% CI, 0.10-0.16; P<0.000001) and adenoma (OR=0.23; 95% CI, 0.15-0.34; P<0.000001). Fascin expression was also associated with depth of invasion (OR=0.31; 95% CI, 0.19-0.50; P<0.000001), lymph node metastasis (OR=3.07; 95% CI, 1.72-5.46; P=0.0001), Dukes stage (OR=0.14; 95% CI, 0.04-0.46; P=0.001), Tumor-Node-Metastasis stage (OR=0.38; 95% CI, 0.21-0.71; P=0.003) and dedifferentiation (OR=0.42; 95% CI, 0.19-0.94; P=0.04). According to the bioinformatics analyses, FSCN1 mRNA expression levels were higher in colorectal cancer and adenoma tissues compared with the normal tissues (P<0.05). According to TCGA, FSCN1 mRNA expression was associated with a less favorable prognosis in patients with colorectal cancer as an independent factor (P<0.05), and positively correlated with depth of invasion, microsatellite instability and low serum carcinoembryonic antigen levels in colorectal cancer. Taken together, the results of the present study suggested that Fascin expression is a potential marker of tumorigenesis, aggressiveness and poor prognosis in patients with colorectal cancer.

Clinical Practice Guideline for Endoscopic Resection of Early Gastrointestinal Cancer

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Clinical Practice Guideline for Endoscopic Resection of Early Gastrointestinal Cancer

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Prognostic impact of resection margin involvement in surgically managed HPV-positive tonsil cancer.

To find out the role of resection margin involvement in surgically managed HPV-positive tonsil cancer. The study included 94 subjects with HPV-positive tonsil cancer undergoing surgical treatment. We evaluated the relationships between the resection margin status, clinicopathological factors, and oncological outcome. The rate of resection margin involvement was 22.3% (21/94) after ablative surgery. Margin involvement, lymphatic invasion, and extracapsular spread were associated with the 5-year disease-free survival (DFS) and disease-specific survival (DSS) rate in univariate analysis. Multivariate Cox regression analysis confirmed a significant association between the margin involvement and 5-year DFS rate (HR=4.602; 95% CI=1.202-17.620; p=0.026) and 5-year DSS rate (HR=12.826; 95% CI=1.399-117.593; p=0.024). The incidence of resection margin involvement was significantly higher in patients with larger tumors (35.19±15.07mm vs. 25.53±10.32mm, p=0.011) and more invasive tumors (17.84±7.90mm vs. 13.46±6.88mm, p=0.037). The cutoff value of tumor size and depth of invasion for resection margin involvement was 29.5mm (74% sensitivity and 63% specificity) and 14.5mm (74% sensitivity and 61% specificity), respectively. Resection margin involvement was significantly correlated with tumor size and the depth of invasion in HPV-positive tonsil cancer. Furthermore, resection margin involvement was associated with adverse outcomes.

The association between hyperfibrinogenemia and clinicopathological factors, and the survival analysis of gastric cancer.

e16547 Background: It is reported that hyperfibrinogenemia is commonly seen in gastric cancer. This study aim to discuss the association between fibrinogen level and preoperative clinicopathological factors and to evaluate the value as a predictor of prognosis. Methods: Retrospectively reviewed the medical records and follow-up data of patients with gastric cancer who underwent curative resection from January 2011 to December 2014 at Surgery Department of the Fourth Hospital of Hebei Medical University. Fibrinogen was measured a week before the surgery. Results: A total of 248 cases were enrolled. The means±SD of fibrinogen was 3.28±1.06g/L. Fibrinogen level was higher in older adults(≥60y), advanced tumor, poorly differentiated, deep invasion, lymph node metastasis, large tumor size and in those with high CEA, platelet count, albumin, NLR and PLR,( P&lt; 0.05). All the people were divided by the TNM staging system and found that the plasma fibrinogen was higher in stageⅡand Ⅲ (stageⅠvs. stageⅡ: 2.84±0.72g/L vs. 3.36±1.18g/L, P= 0.009;stageⅠvs. stage Ⅲ: 2.84±0.72g/L vs. 3.43±1.07g/L, P&lt; 0.001), however, there was no difference between stageⅡand Ⅲ( P= 0.662)(our study did not enrolled stage IV patients).When patients were classified into 4 groups according to the T classification, the plasma fibrinogen level gradually increased with increasing depth of cancer invasion (one way ANOVA; P= 0.002). Yet, when the patients who have lymph nodes metastasis classified according to the N classification, the differences among them did not have statistically significance ( P= 0.333). Multivariate analysis revealed that hyperfibrinogenemia had an independent association with advanced cancer (odds ratio,2.686(1.012-7.125); P= 0.047), lymph node metastasis (odds ratio,2.012 (1.012-3.125); P= 0.035) and tumor size(odds ratio,1.949 (1.099-3.454); P= 0.022). Our study aslo suggested that the patients with hyperfibrinogenemia before surgery showed a significantly lower survival rate (Log-Rank test; P&lt; 0.001), hyperfibrinogenemia was a independent predictor on the overall survival, which could predict worse clinical outcome. Conclusions: Hyperfibrinogenemia may be considered a useful biomarker to predict advanced tumor, lymph node metastasis and large tumor size and can be a good predictor of worse clinical outcome.

Risk factors and pathological characteristics for intraductal tumor spread of submucosal gland in early esophageal squamous cell neoplasia

The esophageal gland duct may serve as a pathway for the spread of early esophageal squamous cell neoplasia (ESCN) to a deeper layer. Deep intraductal tumor spreading cannot be completely eradicated by ablation therapy. However, the risk factors of ductal involvement (DI) in patients with ESCNs have yet to be investigated. We consecutively enrolled 160 early ESCNs, which were treated with endoscopic submucosal dissection. The resected specimens were reviewed for the number, morphology, resected margin, distribution and extension level of DI, which were then correlated to clinical factors. A total of 317 DIs (median:3, range 1–40 per-lesion) in 61 lesions (38.1%) were identified. Of these lesions, 14 have DIs maximally extended to the level of lamina propria mucosa, 17 to muscularis mucosae, and 30 to the submucosa. Multivariate logistic regression analysis showed that tumors located in the upper esophagus (OR = 2.93, 95% CI, 1.02–8.42), large tumor circumferential extension (OR = 5.39, 95% CI, 1.06–27.47), deep tumor invasion depth (OR = 4.12, 95% CI, 1.81–9.33) and numerous Lugol-voiding lesions in background esophageal mucosa (OR = 2.65, 95% CI, 1.10–6.37) were risk factors for DI. The maximally extended level of ducts involved were significantly correlated with the cancer invasion depth (P < 0.05). Notably, 245 (77%) of the involved ducts were located at the central-trisection of the lesions, and 52% of them (165/317) revealed dilatation of esophageal glandular ducts. Five (1.6%) of the involved ducts revealed cancer cell invasion through the glandular structures. In conclusion, DI is not uncommon in early ESCN and may be a major limitation of endoscopic ablation therapy.

Clinical Practice Guideline for Endoscopic Resection of Early Gastrointestinal Cancer.

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by <i>en bloc</i> fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.