The revised American Joint Committee on Cancer staging system (7th edition) improves prognostic stratification after minimally invasive esophagectomy for esophagogastric adenocarcinoma

Comparison of the prognostic difference between ypTNM and equivalent pTNM stages in esophageal squamous cell carcinoma based on the 8th edition of AJCC classification

Objective: With the separate ypTNM stage groupings established in the 8th edition of AJCC staging system for esophageal squamous cell cancer (ESCC), we aimed to evaluate the prognostic difference between ypTNM stage and equivalent pTNM stage.

Methods: ESCC patients with surgery alone (cohort 1) and patients with neoadjuvant therapy plus surgery (cohort 2) were enrolled in the study.

Results: In p0, pIb, pIIa, pIIb, pIIIa, pIIIb and pIVa stages of cohort 1, the 5-year DFS and OS rates were 100/100%, 80.5/86.2%, 58.9/57.8%, 51.1/52.7%, 36.3/35.8%, 21.5/22.6% and 11.9/18.0%. In ypI, ypII, ypIII and ypIVa stages of cohort 2, the 5-year DFS and OS rates were 60.9/67.0%, 44.3/52.1%, 48.4/43.2% and 0. Patients in ypI stage had a tendency of poorer survival compared with those in pI stage (P=0.024 for DFS, P=0.067 for OS). There was no significant difference in terms of DFS (P=0.335) or OS (P=0.903) between ypII and pII. Patients in ypIII stage had a tendency of better survival compared with those in pIII stage (P=0.015 for DFS, P=0.059 for OS). Patients in ypIVa stage exhibited a significantly poorer OS compared with those in pIVa stage (P=0.038).

Conclusions: With down-staged tumor after neoadjuvant therapy, survival of ypI was closed but not reached to the prognosis of equivalent pI, prognosis of ypII was similar to equivalent pII, and survival of ypIII tended to be better compared with equivalent pIII. However, without down-staged ypIVa tumor, the prognosis was worse compared with equivalent pIVa, indicating those patients were primary resistant to prescribed neoadjuvant therapy.

Automated AJCC (7th edition) staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN)

Purpose

A large chunk of lung cancers are of the type non-small cell lung cancer (NSCLC). Both the treatment planning and patients' prognosis depend greatly on factors like AJCC staging which is an abstraction over TNM staging. Many significant efforts have so far been made towards automated staging of NSCLC, but the groundbreaking application of a deep neural networks (DNNs) is yet to be observed in this domain of study. DNN is capable of achieving higher level of accuracy than the traditional artificial neural networks (ANNs) as it uses deeper layers of convolutional neural network (CNN). The objective of the present study is to propose a simple yet fast CNN model combined with recurrent neural network (RNN) for automated AJCC staging of NSCLC and to compare the outcome with a few standard machine learning algorithms along with a few similar studies.

Methods

The NSCLC radiogenomics collection from the cancer imaging archive (TCIA) dataset was considered for the study. The tumor images were refined and filtered by resizing, enhancing, de-noising, etc. The initial image processing phase was followed by texture based image segmentation. The segmented images were fed into a hybrid feature detection and extraction model which was comprised of two sequential phases: maximally stable extremal regions (MSER) and the speeded up robust features (SURF). After a prolonged experiment, the desired CNN-RNN model was derived and the extracted features were fed into the model.

Results

The proposed CNN-RNN model almost outperformed the other machine learning algorithms under consideration. The accuracy remained steadily higher than the other contemporary studies.

Conclusion

The proposed CNN-RNN model performed commendably during the study. Further studies may be carried out to refine the model and develop an improved auxiliary decision support system for oncologists and radiologists.

Visualized Evaluation of Blood Flow to the Gastric Conduit and Complications in Esophageal Reconstruction

BACKGROUND

Evaluation of the blood supply to gastric conduits is critically important to avoid complications after esophagectomy. We began visual evaluation of blood flow using indocyanine green (ICG) fluorescent imaging in July 2015, to reduce reconstructive complications. In this study, we aimed to statistically verify the efficacy of blood flow evaluation using our simplified ICG method.

STUDY DESIGN

A total of 285 consecutive patients who underwent esophagectomy and gastric conduit reconstruction were reviewed and divided into 2 groups: before and after introduction of ICG evaluation. The entire cohort and 68 patient pairs after propensity score matching (PS-M) were evaluated for clinical outcomes and the effect of visualized evaluation on reducing the risk of complication.

RESULTS

The leakage rate in the ICG group was significantly lower than in the non-ICG group for each severity grade, both in the entire cohort (285 subjects) and after PS-M; the rates of other major complications, including recurrent laryngeal nerve palsy and pneumonia, were not different. The duration of postoperative ICU stay was approximately 1 day shorter in the ICG group than in the non-ICG group in the entire cohort, and approximately 2 days shorter after PS-M. Visualized evaluation of blood flow with ICG methods significantly reduced the rate of anastomotic complications of all Clavien-Dindo (CD) grades. Odds ratios for ICG evaluation decreased with CD grade (0.3419 for CD ≥ 1; 0.241 for CD ≥ 2; and 0.2153 for CD ≥ 3).

CONCLUSIONS

Objective evaluation of blood supply to the reconstructed conduit using ICG fluorescent imaging reduces the risk and degree of anastomotic complication.

Validation of the Eighth Edition of the TNM Staging System for Lung Cancer in 2043 Surgically Treated Patients With Non-small-cell Lung Cancer

PURPOSE

The International Association for the Study of Lung Cancer has proposed a revision of the Tumor, Node, Metastasis (TNM) classification for lung cancer. The purpose of this study is to evaluate the prognostic value of the eighth edition of the TNM staging system in surgically treated patients with non-small-cell lung cancer.

METHODS

Data from 2043 consecutive patients with non-small-cell lung cancer who underwent surgical treatment in our single center between January 2006 and September 2015 were collected and analyzed retrospectively. Cox proportional hazard models were used to assess the prognostic significance of the T and N descriptors.

RESULTS

The reversed overall survival curves of stage IIA and stage IIB in the seventh edition were corrected in the eighth edition. Better prognostic value in predicting overall survival, including a higher log rank test of trend χ² statistic (433.6 vs. 414.2), a smaller Akaike Information Criterion value (4759.6 vs. 4768.2), a higher Harrell C-index (0.776 vs. 0.769), and a lower integrated Brier score (0.092 vs. 0.093), was observed for the eighth edition relative to the seventh edition. Recurrence-free survival analysis of subsets of patients stratified by T and N descriptors showed a stepwise deterioration. Significant differences were found between patients of subdivided stage IA (IAI vs. IA2; P = .003 and IA2 vs. IA3; P = .004).

CONCLUSION

The eighth edition of the TNM staging system for lung cancer has prognostic value superior to that of the seventh edition. It was able to predict recurrence-free survival well.

Recommendations for pathologic staging (pTNM) of cancer of the esophagus and esophagogastric junction for the 8th edition AJCC/UICC staging manuals

We report analytic and consensus processes that produced recommendations for pathologic stage groups (pTNM) of esophageal and esophagogastric junction cancer for the AJCC/UICC cancer staging manuals, 8th edition. The Worldwide Esophageal Cancer Collaboration provided data for 22,654 patients with epithelial esophageal cancers; 13,300 without preoperative therapy had pathologic assessment after esophagectomy or endoscopic treatment. Risk-adjusted survival for each patient was developed using random survival forest analysis to identify data-driven pathologic stage groups wherein survival decreased monotonically with increasing group, was distinctive between groups, and homogeneous within groups. The AJCC Upper GI Task Force, by smoothing, simplifying, expanding, and assessing clinical applicability, produced consensus pathologic stage groups. For pT1-3N0M0 squamous cell carcinoma (SCC) and pT1-2N0M0 adenocarcinoma, pT was inadequate for grouping; subcategorizing pT1 and adding histologic grade enhanced staging; cancer location improved SCC staging. Consensus eliminated location for pT2N0M0 and pT3N0M0G1 SCC groups, and despite similar survival, restricted stage 0 to pTis, excluding pT1aN0M0G1. Metastases markedly reduced survival; pT, pN, and pM sufficiently grouped advanced cancers. Stage IIA and IIB had different compositions for SCC and adenocarcinoma, but similar survival. Consensus stage IV subgrouping acknowledged pT4N+ and pN3 cancers had poor survival, similar to pM1. Anatomic pathologic stage grouping, based on pTNM only, produced identical consensus stage groups for SCC and adenocarcinoma at the cost of homogeneity in early groups. Pathologic staging can neither direct pre-treatment decisions nor aid in prognostication for treatment other than esophagectomy or endoscopic therapy. However, it provides a clean, single therapy reference point for esophageal cancer.