Dataset Information

Novel Endoscopic Criteria for Predicting Tumor Invasion Depth in Superficial Esophageal Squamous Carcinoma.

ABSTRACT: BACKGROUND:Accurate prediction of tumor invasion depth in superficial esophageal squamous carcinoma (SESC) is essential for deciding the appropriate treatment strategy. We proposed novel endoscopic criteria to differentiate between mucosal and submucosal esophageal cancers and to evaluate the diagnostic accuracy and usefulness of the criteria. METHODS:A total of 352 patients who underwent endoscopic or surgical resection for SESC between 1991 and 2010 were included. First, the novel endoscopic criteria were created based on the endoscopic features of 60 randomly selected patients as follows: for T1m cancers, I. flat or slightly elevated or depressed lesion with smooth/even surface of any size, II. slightly elevated lesion of ? 1 cm with granular or uneven surface, III. hyperemic flat lesion of ? 3 cm with granular or uneven surface, IV. slightly depressed lesion of ? 2 cm with uneven surface and for T1sm cancers, I. irregularly (unevenly) nodular or protruded lesion of any size, II. slightly elevated lesion of > 1 cm with granular or uneven surface, III. hyperemic flat lesion of > 3 cm with granular or uneven surface, IV. irregularly (unevenly) depressed lesion of > 2 cm, and V. ulcerative lesion of any size. Next, the endoscopic findings of the remaining 292 patients were reviewed according to the criteria. RESULTS:The accuracy of novel endoscopic criteria was 79.5% (232/292). The sensitivity and specificity of mucosal cancers were 78.4% and 81.0%, respectively, whereas those for submucosal cancers were 81.0% and 78.4%, respectively. The accuracy for mucosal cancers was high (97.3%, 72/74) when the lesions were flat or slightly elevated/depressed with smooth/even surface regardless of size, whereas that for submucosal cancers was high (85.7%, 18/21) when the lesions were irregular/nodular protrusions regardless of size. In multivariate analysis, macroscopic type IIb lesion was identified as an independent factor affecting accuracy (P < 0.05). The difference in recurrence-free survival rates between endoscopically mucosal and submucosal cancers was significant (P = 0.026). CONCLUSION:The novel endoscopic criteria appear to be accurate and useful in predicting invasion depth in SESC. Our criteria might help not only to decide the treatment strategy between surgery and endoscopic resection but also to predict the outcomes of SESC.

SUBMITTER: Choi JY

PROVIDER: S-EPMC7590655 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Novel Endoscopic Criteria for Predicting Tumor Invasion Depth in Superficial Esophageal Squamous Carcinoma.

Choi Ji Young JY Bae Suh Eun SE Ahn Ji Yong JY Lee Jeong Hoon JH Park Young Soo YS Kim Do Hoon DH Choi Kee Don KD Chang Hye Sook HS Song Ho June HJ Lee Gin Hyug GH Choe Jaewon J Jang Se Jin SJ Jung Hwoon Yong HY

Journal of Korean medical science 20201026 41

<h4>Background</h4>Accurate prediction of tumor invasion depth in superficial esophageal squamous carcinoma (SESC) is essential for deciding the appropriate treatment strategy. We proposed novel endoscopic criteria to differentiate between mucosal and submucosal esophageal cancers and to evaluate the diagnostic accuracy and usefulness of the criteria.<h4>Methods</h4>A total of 352 patients who underwent endoscopic or surgical resection for SESC between 1991 and 2010 were included. First, the nov ...[more]

PMID: 33107226

Similar Datasets

Project description:The lymphovascular invasion (LVI) status facilitates the determination of the optimal therapeutic strategy for superficial esophageal squamous cell carcinoma (SESCC), but in clinical practice, LVI must be confirmed by postoperative pathology. However, studies of the risk factors for LVI in SESCC are limited. Consequently, this study aimed to identify the risk factors for LVI and use these factors to establish a prediction model. The data of 516 patients who underwent radical esophagectomy between January 2007 and September 2019 were retrospectively collected (training set, n=361, January 2007 to May 2015; validation set, n=155, June 2015 to September 2019). In the training set, least absolute shrinkage and selection operator (LASSO) regression and multivariate analyses were utilized to identify predictive factors for LVI in patients with SESCC. A nomogram was then developed using these predictors. The area under the curve (AUC), calibration curve, and decision curve were used to evaluate the efficiency, accuracy, and clinical utility of the model. LASSO regression indicated that the tumor size, depth of invasion, tumor differentiation, lymph node metastasis (LNM), sex, circumferential extension, the presence of multiple lesions, and the resection margin were correlated with LVI. However, multivariate analysis revealed that only the tumor size, depth of invasion, tumor differentiation, and LNM were independent risk factors for LVI. Incorporating these four variables, model 1 achieved an AUC of 0.817 in predicting LVI. Adding circumferential extension to model 1 did not appreciably change the AUC and integrated discrimination improvement, but led to a significant increase in the net reclassification improvement (p=0.011). A final nomogram was constructed by incorporating tumor size, depth of invasion, tumor differentiation, LNM, and circumferential extension and showed good discrimination (training set, AUC=0.833; validation set, AUC=0.819) and good calibration in the training and validation sets. Decision curve analysis demonstrated that the nomogram was clinically useful in both sets. Thus, it is possible to predict the status of LVI using this nomogram scoring system, which can aid the selection of an appropriate treatment plan.

Project description:ImportanceDistinguishing between mucosal and submucosal cancers is important for selecting the optimal treatment for patients with esophageal squamous cell carcinoma (ESCC); however, standard procedures for diagnosing cancer invasion depth have not yet been determined.ObjectiveTo evaluate the diagnostic performance of endoscopic ultrasonography (EUS) after conventional endoscopy for the evaluation of ESCC invasion depth.Design, setting, and participantsThis prospective single-arm confirmatory diagnostic study comprising 372 patients with T1 esophageal cancer was conducted at 41 secondary or tertiary hospitals in Japan. Enrollment began on July 20, 2017; patients were enrolled in 2 steps, with the first registration occurring from August 4, 2017, to December 11, 2019, and the second from August 9, 2017, to December 11, 2019. After the completion of all first and second registration examinations, patients received treatment and were followed up for 30 days, with follow-up ending on February 14, 2020. Patients were eligible for inclusion if they had pathologically or endoscopically diagnosed esophageal cancer with T1 clinical depth of invasion.InterventionsIn the first registration, nonmagnifying endoscopy (non-ME) and magnifying endoscopy (ME) were used to diagnose cancer invasion depth. In the second registration, patients from the first registration who had cancers invading the muscularis mucosa or submucosa were enrolled and received EUS. After completion of the protocol examinations, patients received treatment with endoscopic resection or esophagectomy. The pathological results of the resected specimens were used as the reference standard for evaluating cancer invasion depth.Main outcomes and measuresThe primary end point was the proportion of overdiagnosis of submucosal cancer (defined as invasion depth >200 μm) after receipt of non-ME and ME, with or without the addition of EUS. The secondary end points were underdiagnosis, sensitivity, and specificity.ResultsAmong 372 patients enrolled in the first registration, 371 received non-ME and ME. Of those, 300 patients were enrolled in the second registration, and 293 patients received EUS. A total of 269 patients (217 men [80.7%]; median age, 69 years; interquartile range, 62-75 years) were included in the final analysis. The addition of EUS was associated with a 6.6% increase in the proportion of overdiagnosis (from 16 of 74 patients [21.6%; 95% CI, 12.9%-32.7%] after non-ME and ME to 29 of 103 patients [28.2%; 95% CI, 19.7%-37.9%] after the addition of EUS; 1-sided P = .93). All subgroup analyses found similar increases in overdiagnosis of submucosal cancer. The addition of EUS was associated with a 4.5% reduction in the proportion of underdiagnosis (from 57 of 195 patients [29.2%; 95% CI, 23.0%-36.2%] after non-ME and ME to 41 of 166 patients [24.7%; 95% CI, 18.3%-32.0%] after the addition of EUS). After non-ME and ME, diagnostic sensitivity was 50.4% (95% CI, 41.0%-59.9%), specificity was 89.6% (95% CI, 83.7%-93.9%), and accuracy was 72.9% (95% CI, 67.1%-78.1%). After the addition of EUS, diagnostic sensitivity was 64.3% (95% CI, 54.9%-73.1%), specificity was 81.2% (95% CI, 74.1%-87.0%), and accuracy was 74.0% (95% CI, 68.3%-79.1%).Conclusions and relevanceThis study found that the addition of EUS was not associated with improvements in the diagnostic accuracy of cancer invasion depth. These findings do not support the routine use of EUS after conventional endoscopy for evaluating the invasion depth among patients with T1 ESCC.

Project description:BackgroundThe use of artificial intelligence (AI) assisted white light imaging (WLI) detection systems for superficial esophageal squamous cell carcinoma (SESCC) is limited by training with images from one specific endoscopy platform.MethodsIn this study, we developed an AI system with a convolutional neural network (CNN) model using WLI images from Olympus and Fujifilm endoscopy platforms. The training dataset consisted of 5892 WLI images from 1283 patients, and the validation dataset included 4529 images from 1224 patients. We assessed the diagnostic performance of the AI system and compared it with that of endoscopists. We analyzed the system's ability to identify cancerous imaging characteristics and investigated the efficacy of the AI system as an assistant in diagnosis.ResultsIn the internal validation set, the AI system's per-image analysis had a sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of 96.64%, 95.35%, 91.75%, 90.91%, and 98.33%, respectively. In patient-based analysis, these values were 90.17%, 94.34%, 88.38%, 89.50%, and 94.72%, respectively. The diagnostic results in the external validation set were also favorable. The CNN model's diagnostic performance in recognizing cancerous imaging characteristics was comparable to that of expert endoscopists and significantly higher than that of mid-level and junior endoscopists. This model was competent in localizing SESCC lesions. Manual diagnostic performances were significantly improved with the assistance by AI system, especially in terms of accuracy (75.12% vs. 84.95%, p = 0.008), specificity (63.29% vs. 76.59%, p = 0.017) and PPV (64.95% vs. 75.23%, p = 0.006).ConclusionsThe results of this study demonstrate that the developed AI system is highly effective in automatically recognizing SESCC, displaying impressive diagnostic performance, and exhibiting strong generalizability. Furthermore, when used as an assistant in the diagnosis process, the system improved manual diagnostic performance.

Project description:ObjectivesTo develop a radiomics model based on contrast-enhanced CT (CECT) to predict the lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC) and provide decision-making support for clinicians.Patients and methodsThis retrospective study enrolled 334 patients with surgically resected and pathologically confirmed ESCC, including 96 patients with LVI and 238 patients without LVI. All enrolled patients were randomly divided into a training cohort and a testing cohort at a ratio of 7:3, with the training cohort containing 234 patients (68 patients with LVI and 166 without LVI) and the testing cohort containing 100 patients (28 patients with LVI and 72 without LVI). All patients underwent preoperative CECT scans within 2 weeks before operation. Quantitative radiomics features were extracted from CECT images, and the least absolute shrinkage and selection operator (LASSO) method was applied to select radiomics features. Logistic regression (Logistic), support vector machine (SVM), and decision tree (Tree) methods were separately used to establish radiomics models to predict the LVI status in ESCC, and the best model was selected to calculate Radscore, which combined with two clinical CT predictors to build a combined model. The clinical model was also developed by using logistic regression. The receiver characteristic curve (ROC) and decision curve (DCA) analysis were used to evaluate the model performance in predicting the LVI status in ESCC.ResultsIn the radiomics model, Sphericity and gray-level non-uniformity (GLNU) were the most significant radiomics features for predicting LVI. In the clinical model, the maximum tumor thickness based on CECT (cThick) in patients with LVI was significantly greater than that in patients without LVI (P<0.001). Patients with LVI had higher clinical N stage based on CECT (cN stage) than patients without LVI (P<0.001). The ROC analysis showed that both the radiomics model (AUC values were 0.847 and 0.826 in the training and testing cohort, respectively) and the combined model (0.876 and 0.867, respectively) performed better than the clinical model (0.775 and 0.798, respectively), with the combined model exhibiting the best performance.ConclusionsThe combined model incorporating radiomics features and clinical CT predictors may potentially predict the LVI status in ESCC and provide support for clinical treatment decisions.

Dataset Information

Novel Endoscopic Criteria for Predicting Tumor Invasion Depth in Superficial Esophageal Squamous Carcinoma.

Publications

Novel Endoscopic Criteria for Predicting Tumor Invasion Depth in Superficial Esophageal Squamous Carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets