Effect of histologic differences between biopsy and final resection on treatment outcomes in early gastric cancer

An artificial intelligence system for comprehensive pathologic outcome prediction in early gastric cancer through endoscopic image analysis (with video)

BACKGROUND

Accurate prediction of pathologic results for early gastric cancer (EGC) based on endoscopic findings is essential in deciding between endoscopic and surgical resection. This study aimed to develop an artificial intelligence (AI) model to assess comprehensive pathologic characteristics of EGC using white-light endoscopic images and videos.

METHODS

To train the model, we retrospectively collected 4,336 images and prospectively included 153 videos from patients with EGC who underwent endoscopic or surgical resection. The performance of the model was tested and compared to that of 16 endoscopists (nine experts and seven novices) using a mutually exclusive set of 260 images and 10 videos. Finally, we conducted external validation using 436 images and 89 videos from another institution.

RESULTS

After training, the model achieved predictive accuracies of 89.7% for undifferentiated histology, 88.0% for submucosal invasion, 87.9% for lymphovascular invasion (LVI), and 92.7% for lymph node metastasis (LNM), using endoscopic videos. The area under the curve values of the model were 0.992 for undifferentiated histology, 0.902 for submucosal invasion, 0.706 for LVI, and 0.680 for LNM in the test. In addition, the model showed significantly higher accuracy than the experts in predicting undifferentiated histology (92.7% vs. 71.6%), submucosal invasion (87.3% vs. 72.6%), and LNM (87.7% vs. 72.3%). The external validation showed accuracies of 75.6% and 71.9% for undifferentiated histology and submucosal invasion, respectively.

CONCLUSIONS

AI may assist endoscopists with high predictive performance for differentiation status and invasion depth of EGC. Further research is needed to improve the detection of LVI and LNM.

Nomogram for pre-procedural prediction of non-curative endoscopic resection in patients with early gastric cancer

BACKGROUND

Non-curative resection (non-CR) after endoscopic submucosal dissection (ESD) requires additional surgery due to the possibility of lymph node metastasis (LNM). Therefore, it is important to accurately predict the risk of non-CR to avoid unnecessary preoperative procedures. Thus, we aimed to develop and verify a nomogram to predict the risk of non-CR prior to ESD.

METHODS

Patients who underwent ESD for early gastric cancer (EGC) were divided into CR and non-CR groups based on the present ESD criteria. The pre-procedural factors, such as endoscopic features, radiologic findings, and pathology of the lesion, were compared between the groups to identify the risk factors associated with non-CR. A nomogram was developed using multivariate analysis, and its predictive value was assessed using an external validation group.

RESULTS

Among 824 patients, 682 were curative (82.7%) and 142 were non-curative (17.3%). By comparing two groups, endoscopic features including redness, whitish mucosal change, fold convergence, and large lesion size; histologic features such as moderately or poorly differentiated or signet ring cell carcinoma; and abnormal CT findings including non-specific lymph node enlargement and fold thickening were identified as significant predictors of non-CR. The nomogram was developed based on these predictors and showed good predictive performance in the external validation, with an area under the curve of 0.87.

CONCLUSIONS

We developed a nomogram to predict the risk of non-CR prior to ESD. These predictive factors in addition to the existing ESD criteria can help provide the best treatment option for patients with EGC.

A Prediction Model Based on the Risk Factors Associated with Pathological Upgrading in Patients with Early-Stage Gastric Neoplasms Diagnosed by Endoscopic Forceps Biopsy

Background/Aims

The discrepancies between the diagnosis of preoperative endoscopic forceps biopsy (EFB) and endoscopic submucosal dissection (ESD) in patients with early gastric neoplasm (EGN) exist objectively. Among them, pathological upgrading directly influences the accuracy and appropriateness of clinical decisions. The aims of this study were to investigate the risk factors for the discrepancies, with a particular focus on pathological upgrading and to establish a prediction model for estimating the risk of pathological upgrading after EFB.

Methods

We retrospectively collected the records of 978 patients who underwent ESD from December 1, 2017 to July 31, 2021 and who had a final histopathology determination of EGN. A nomogram to predict the risk of pathological upgrading was constructed after analyzing subgroup differences among the 901 lesions enrolled.

Results

The ratio of pathological upgrading was 510 of 953 (53.5%). Clinical, laboratorial and endoscopic characteristics were analyzed using univariable and binary multivariable logistic regression analyses. A nomogram was constructed by including age, history of chronic atrophic gastritis, symptoms of digestive system, blood high density lipoprotein concentration, macroscopic type, pathological diagnosis of EFB, uneven surface, remarkable redness, and lesion size. The C-statistics were 0.804 (95% confidence interval, 0.774 to 0.834) and 0.748 (95% confidence interval, 0.664 to 0.832) in the training and validation set, respectively. We also built an online webserver based on the proposed nomogram for convenient clinical use.

Conclusions

The clinical value of identifying the preoperative diagnosis of EGN lesions is limited when using EFB separately. We have developed a nomogram that can predict the probability of pathological upgrading with good calibration and discrimination value.

The added value of radiomics from dual-energy spectral CT derived iodine-based material decomposition images in predicting histological grade of gastric cancer

BACKGROUND

The histological differentiation grades of gastric cancer (GC) are closely related to treatment choices and prognostic evaluation. Radiomics from dual-energy spectral CT (DESCT) derived iodine-based material decomposition (IMD) images may have the potential to reflect histological grades.

METHODS

A total of 103 patients with pathologically proven GC (low-grade in 40 patients and high-grade in 63 patients) who underwent preoperative DESCT were enrolled in our study. Radiomic features were extracted from conventional polychromatic (CP) images and IMD images, respectively. Three radiomic predictive models (model-CP, model-IMD, and model-CP-IMD) based on solely CP selected features, IMD selected features and CP coupled with IMD selected features were constructed. The clinicopathological data of the enrolled patients were analyzed. Then, we built a combined model (model-Combine) developed with CP-IMD and clinical features. The performance of these models was evaluated and compared.

RESULTS

Model-CP-IMD achieved better AUC results than both model-CP and model-IMD in both cohorts. Model-Combine, which combined CP-IMD radiomic features, pT stage, and pN stage, yielded the highest AUC values of 0.910 and 0.912 in the training and testing cohorts, respectively. Model-CP-IMD and model-Combine outperformed model-CP according to decision curve analysis.

CONCLUSION

DESCT-based radiomics models showed reliable diagnostic performance in predicting GC histologic differentiation grade. The radiomic features extracted from IMD images showed great promise in terms of enhancing diagnostic performance.

Endoscopic diagnosis of early gastric cancer

Background: Among the types of gastric cancer, the proportion of early gastric cancer has shown a steady increase because the national screening programs have been conducted in Korea. Accordingly, the paradigm shift of the treatment procedure from surgical gastrectomy to endoscopic resection for selected early gastric cancer has accelerated recently. For successful treatment of early gastric cancer, early detection is essential to accurately predict the histological type, depth of invasion, and horizontal margins of the tumor.Current Concepts: The diagnosis of early gastric cancer and selection of treatment procedures comprises the following steps: (1) presence diagnosis, (2) qualitative diagnosis, and (3) quantitative diagnosis. Presently, early gastric cancer diagnosis is based on the endoscopic detection of a demarcated lesion and irregularity of the mucosal surface or color pattern. If a lesion is diagnosed as early gastric cancer, qualitative and quantitative diagnostic processes should be conducted. Qualitative diagnosis predicts the histological type (differentiated vs. undifferentiated), whereas quantitative diagnosis predicts the invasion depth and horizontal margins of the lesion. The diagnostic processes are based on the macroscopic morphology and color of the lesion, while sometimes using chromoendoscopy, image-enhanced endoscopy, and magnifying endoscopy.Discussion and Conclusion: If gastric cancer is detected at an early stage, most cases can be treated only by endoscopic resection. Therefore, endoscopists should have systematic knowledge regarding the findings of early gastric cancer for timely detection and appropriate selection of the treatment procedure.

Systematic Endoscopic Approach to Early Gastric Cancer in Clinical Practice

Early gastric cancers (EGCs) are defined as gastric cancers confined to the mucosa or submucosa, regardless of regional lymph node metastasis. The proportion of EGCs has been increasing due to the increase in screening endoscopy for gastric cancers; therefore, the paradigm shift from surgical resection to endoscopic resection as a treatment modality for selected EGCs is accelerating. For successful endoscopic resection of EGCs, it is important to detect EGCs at an early stage and to accurately predict the histological type, depth of invasion, and horizontal margins of the tumor. The diagnostic process of EGCs can be divided into three steps: presence diagnosis, qualitative diagnosis, and quantitative diagnosis. The presence diagnosis of EGCs is mainly based on two endoscopic findings: a well-demarcated lesion and irregularity in the color/surface pattern. Qualitative diagnosis refers to the prediction of histological type, which is mainly possible based on the macroscopic shape and color of the lesion. Quantitative diagnosis of EGCs consists of predicting the depth of invasion by detailed examination of the macroscopic morphology and determining horizontal margins using chromoendoscopy. Although advanced diagnostic modalities, such as endosonography or magnifying endoscopy, are helpful for the qualitative and quantitative diagnosis of EGCs, these modalities are not available in most hospitals. Therefore, it is still very important to evaluate EGCs systematically during conventional endoscopy for successful endoscopic treatment.

Mixed histology poses a greater risk for noncurative endoscopic resection in early gastric cancers regardless of the predominant histologic types

OBJECTIVES

Clinicopathologic characteristics and treatment outcomes of mixed-histological-type (MT) early gastric cancers (EGCs) treated with endoscopic submucosal dissection (ESD) have not been sufficiently elucidated. We aimed to clarify them in comparison with pure-histological-type EGCs.

METHODS

We used 3022 consecutive EGCs in 2281 patients treated with ESD from our prospectively maintained database. Cases were stratified into four groups according to the final diagnosis of the resected specimen are as follows: 2780 pure differentiated-type (DT), 127 DT-predominant MT (D-MT), 87 pure undifferentiated-type (UDT), and 28 UDT-predominant MT (U-MT). Clinicopathologic characteristics and treatment outcome were compared between pure DT and D-MT, and between pure UDT and U-MT separately. Risk factors for deep submucosal invasion, lymphovascular invasion, and a final diagnosis of MT were identified using multivariate analysis.

RESULTS

Both D-MT (41.7 vs. 92.0%; P < 0.0001) and U-MT (35.7 vs. 75.9%; P = 0.0002) showed a significantly lower curative resection rate than their pure histologic counterparts. Multivariate analysis revealed that MT was an independent risk factor for deep submucosal (OR 6.55; 95% CI, 4.18-10.14) and lymphovascular (OR 4.74; 95% CI, 2.72-8.29) invasion. Preoperative biopsy results that did not show well-differentiated tubular adenocarcinoma (OR 28.2; 95% CI, 18.9-42.9) were an independent risk factor for a final diagnosis of MT.

CONCLUSIONS

MT poses a greater risk for noncurative resection regardless of the predominant histologic types, reflecting more aggressive malignant potential. Although a biopsy examination rarely shows MT, clinicians should consider the possibility of MT when a biopsy examination does not show well-differentiated tubular adenocarcinoma.

Predictive Factors and Long-Term Outcomes of Early Gastric Carcinomas in Patients with Non-Curative Resection by Endoscopic Submucosal Dissection

Purpose

Non-curative resection (NCR) remains problematic in some cases of early gastric carcinomas (EGCs) treated by endoscopic submucosal dissection (ESD). The aim of this study was to identify predictors of NCR, especially of eCura C1 and eCura C2 resections, before ESD and study long-term outcomes of EGC patients with NCR.

Patients and Methods

A retrospective review of medical records was conducted over an 8-year period for EGCs undergoing ESD. Clinicopathologic and endoscopic characteristics and patients’ survival were analyzed. Risk factors for NCR and eCura C1 and C2 resections were assessed by logistic analyses. Survival of patients was estimated with the Kaplan–Meier method with a Log rank test.

Results

A total of 463 patients with 472 lesions were qualified. By univariate and multivariate analyses, the predictors for NCR and eCura C2 resections were tumor size >20 mm, tumors located in cardia-fundus, uneven surface, margin elevation, and mixed and undifferentiated types, and those for eCura C1 resection were tumors located in cardia-fundus, negative lifting sign, and mixed and undifferentiated types. The 5-year cancer-specific and cancer-free survival rates were 100.0% and 94.2%, and 95.3% and 83.4% in the curative resection (CR) and NCR groups, respectively. The 5-year cancer-specific and cancer-free survival rates were significantly greater in the CR group than that in the NCR group (P <0.0001).

Conclusion

In this cohort, we identified various endoscopic and pathologic features of EGCs to predict NCR, especially eCura C1 and eCura C2 resections before ESD. These clinically valuable factors would be very informative to endoscopists and surgeons who perform ESD to resect EGCs.