A problem with clinical T factor in the 8th TNM edition: Prognosis and EGFR mutation status of small sized lung cancers with difficulty to measure the diameter of solid component in part-solid tumor

Deep Learning Features and Metabolic Tumor Volume Based on PET/CT to Construct Risk Stratification in Non-small Cell Lung Cancer

RATIONALE AND OBJECTIVES

To build a risk stratification by incorporating PET/CT-based deep learning features and whole-body metabolic tumor volume (MTVwb), which was to make predictions about overall survival (OS) and progression-free survival (PFS) for those with non-small cell lung cancer (NSCLC) as a complement to the TNM staging.

MATERIALS AND METHODS

The study enrolled 590 patients with NSCLC (413 for training and 177 for testing). Features were extracted by employing a convolutional neural network. The combined risk stratification (CRS) was constructed by the selected features and MTVwb, which were contrasted and integrated with TNM staging. In the testing set, those were verified.

RESULTS

Multivariate analysis revealed that CRS was an independent predictor of OS and PFS. C-indexes of the CRS demonstrated statistically significant increases in comparison to TNM staging, excepting predicting OS in the testing set (for OS, C-index=0.71 vs. 0.691 in the training set and 0.73 vs. 0.736 in the testing set; for PFS, C-index=0.702 vs. 0.686 in the training set and 0.732 vs. 0.71 in the testing set). The nomogram that combined CRS with TNM staging demonstrated the most superior model performance in the training and testing sets (C-index=0.741 and 0.771).

CONCLUSION

The addition of CRS improves TNM staging's predictive power and shows potential as a useful tool to support physicians in making treatment decisions.

Oncological characteristics of epidermal growth factor receptor-mutated clinical stage IA lung adenocarcinoma with radiologically pure-solid appearance

OBJECTIVES

We evaluated the clinicopathological and oncological characteristics of epidermal growth factor receptor-mutated clinical stage IA radiological pure-solid lung adenocarcinoma and compared them with those of a ground-glass opacity component.

METHODS

Between 2008 and 2020, data from 1014 surgically resected clinical stage 0-IA epidermal growth factor receptor-mutated lung adenocarcinomas were evaluated. Oncological outcomes were assessed using multivariable analysis. Overall survival was estimated using Kaplan-Meier analysis and the log-rank test. The cumulative incidence of recurrence was estimated using the Gray's test.

RESULTS

Of these, 233 (23%) were radiologically pure-solid tumors, which demonstrated a higher proportion of nodal metastasis, micropapillary component, spread through alveolar space, and Ex19 subtype compared with those of tumors with ground-glass opacity (P < .001). Multivariable analysis revealed that the presence of ground-glass opacity was an independently significant factor for overall survival (P = .037) and cumulative incidence of recurrence (P < .001). In cases where the oncological outcomes were stratified by the presence of ground-glass opacity component, the 5-year overall survival was excellent at more than 90% in tumors with ground-glass opacity despite clinical-T categories (P = .2044); however, tumor size significantly affected survival only in pure-solid tumors (T1a, 100%; T1b, 77.7%; T1c, 68.5%; P = .0056). Furthermore, the cumulative incidence of recurrence was low in tumors with ground-glass opacity despite the clinical-T categories, whereas tumor size significantly affected the cumulative incidence of recurrence only in pure-solid tumors (5-year cumulative incidence of recurrence: T1a-b, 18.9%; T1c, 41.3%; P < .001).

CONCLUSIONS

Oncologic behavior and prognosis of radiologically pure-solid tumors were significantly poorer than those of tumors with ground-glass opacity among patients with epidermal growth factor receptor-mutated early-stage lung adenocarcinoma. These findings imply distinct tumorigenesis based on the presence of ground-glass opacity, even in tumors with epidermal growth factor receptor mutations.