Endoscopic assessment of tumor regression after preoperative chemoradiotherapy as a prognostic marker in locally advanced rectal cancer

Endoscopic resection of residual rectal neoplasia after definitive chemoradiotherapy for rectal cancer

The conventional approach to treating locally advanced rectal cancer, commonly defined as cT3 or cT4 primary tumors or with nodal metastases, involves chemoradiation (CRT) followed by surgical resection. There is a growing recognition of the potential for nonsurgical management following CRT or total neoadjuvant therapy (TNT), which allows for organ preservation. "Watch and wait" strategy may be considered if complete clinical response is achieved. In cases when adenoma or superficial cancer is present, a novel approach known as "salvage endoscopic resection of the residual disease" is emerging as a viable nonsurgical option for carefully selected patients. This review discusses available evidence and future potential for endoscopic management of residual neoplasia after oncological treatment of rectal cancer.

Deep learning of endoscopic features for the assessment of neoadjuvant therapy response in locally advanced rectal cancer

BACKGROUND

For locally advanced rectal cancer (LARC), accurate response evaluation is necessary to select complete responders after neoadjuvant therapy (NAT) for a watch-and-wait (W&W) strategy. Algorithms based on deep learning have shown great value in medical image analyses. Here we used deep learning algorithms of endoscopic images for the assessment of NAT response in LARC.

METHOD

214 LARC patients were retrospectively included in the study. After NAT, these patients underwent total mesorectal excision (TME) surgery. Among them, 51 (23.8%) of the patients achieved a pathological complete response (pCR). 160 patients from Shanghai Changzheng Hospital were regarded as primary dataset, and the other 54 patients from Zhejiang Cancer Hospital were regarded as validation dataset. ResNet-18 and DenseNet-121 were applied to train the models based on endoscopic images after NAT. Deep learning models were valid in the validation dataset and compared to manual method.

RESULTS

The performances were comparable in AUC between deep learning models and manual method. For mean metrics, sensitivity (0.750 vs. 0.417) and AUC (0.716 vs. 0.601) in ResNet-18 deep learning model were higher than those in the manual method. The deep learning models were able to identify the endoscopic features associated with NAT response by the heatmaps. A diagnostic flow diagram which integrated the deep learning model to assist the clinicians in making decisions for W&W strategy was constructed.

CONCLUSIONS

We created deep learning models using endoscopic features for assessment of NAT in LARC. The deep learning models achieved modest accuracies and performed comparably to manual method.

Clinical significance of evaluating endoscopic response to neoadjuvant chemotherapy in esophageal squamous cell carcinoma

BACKGROUND AND AIM

Clinical significance of endoscopic response (ER) after neoadjuvant chemotherapy (NAC) for esophageal cancer has not been fully understood. Thus, the present study aimed to investigate the association between ER to NAC and its clinicopathological outcomes in patients with esophageal squamous cell carcinoma (ESCC).

METHODS

In total, 141 patients who underwent NAC and subsequent esophagectomy for ESCC were included. ER to NAC was retrospectively evaluated based on macroscopic findings of the primary tumor, which was classified into three categories: endoscopic no response (eNR), endoscopic partial response (ePR), and endoscopic good response (eGR). An endoscopic responder was defined as patients with eGR/ePR.

RESULTS

Approximately 89.4% of patients had cStage II-III disease, and 7.1% had pathological complete response. Upon ER evaluation, eNR, ePR, and eGR were observed in 46 (32.6%), 54 (38.3%), and 41 (29.1%) patients, respectively. Pathological responders significantly increased as the ER grade became better. Among preoperative clinical factors, only ER significantly correlated with pathological response in univariate and multivariate analysis. Endoscopic responders showed a significantly better prognosis than did eNR patients (P < 0.001), although the overall survival (OS) of the patients with eGR and ePR was equivalent. Endoscopic responder, ypT, ypN, and pathological responder were significant predictors of OS in the univariate analysis, and endoscopic responder, ypN, and pathological responder were independent predictors in the multivariate analysis.

CONCLUSION

This study suggests that ER can be a simple and important tool to predict the pathological response and survival of patients who undergo NAC for ESCC.

The clinical significance of simple endoscopic scoring of patients with rectal cancer after concurrent chemoradiotherapy

BACKGROUND

Neoadjuvant concurrent chemoradiotherapy (CCRT) is an effective treatment option for patients with rectal cancer. In this study, we investigated the clinical efficacy of simple endoscopic scoring of patients with rectal cancer after CCRT.

METHODS

Between July 2008 and October 2015, medical records including endoscopic imaging from 41 patients with rectal cancer who received CCRT were retrospectively reviewed. Two expert gastroenterologists reviewed the endoscopic images and assigned scores from 0-3 according to post-CCRT findings. The scoring criteria were as follows: 0= scar without marginal elevation; 1= clean-based ulcer without marginal elevation; 2= clean-based ulcer with marginal elevation; 3= non-clean-based ulcer. We evaluated image scores to predict long-term outcomes using Kaplan-Meier curves and Cox regression models.

RESULTS

The median follow-up duration was 55 months (interquartile range: 35-76 months). Patients with a low score (≤2) had a 17.2% recurrence rate, whereas patients with a high score [3] had a 50.0% recurrence rate. Patients with a low score had longer disease-free survival (DFS) than those with a high score in log-rank test (P=0.026). In multivariate Cox regression analysis, a high score was a significant predictor of poor DFS in patients with rectal cancer after CCRT treatment (hazard ratio =4.89, 95% confidence interval: 1.11-21.50, P=0.036).

CONCLUSIONS

This simple endoscopic scoring approach is helpful for predicting prognosis of patients with rectal cancer after treatment with CCRT.

Creation of a rectal cancer registry in Italy by the Advanced International Mini-Invasive Surgery (AIMS) academy clinical research network

Background: The management of rectal cancer is multimodal and involves a multidisciplinary team of cancer specialists with expertise in medical oncology, surgical oncology, radiation oncology and radiology. It is crucial for highly specialized centers to collaborate via networks that aim to maintain uniformity in every aspect of treatment and rigorously gather patients’ data, from the first clinical evaluation to the last follow-up visit.

The Advanced International Mini-Invasive Surgery (AIMS) academy clinical research network aims to create a rectal cancer registry. This will prospectively collect the data of patients operated on for non-metastatic rectal cancer in high volume colorectal surgical units through a well design pre-fashioned database for non-metastatic rectal cancer, in order to take all multidisciplinary aspects into consideration.

Methods/Design: The protocol describes a multicenter prospective observational cohort study, investigating demographics, frailty, cancer-related features, surgical and radiological parameters, and oncological outcomes among patients with non-metastatic rectal cancer who are candidates for surgery with curative intent. Patients enrolled in the present registry will be followed up for 5 years after surgery.

Discussion: Standardization and centralization of data collection for neoplastic diseases is a virtuous process for patient care. The creation of a register will allow the control of the quality of treatments provided and permit prospective and retrospective studies to be carried out on complete and reliable high quality data. Establishing data collection in a prospective and systematic fashion is the only possibility to preserve the enormous resource that each patient represents.