Role of the Thoracic Radiologist in the Evaluation and Management of Solid and Subsolid Lung Nodules

Identifying Solitary Granulomatous Nodules from Solid Lung Adenocarcinoma: Exploring Robust Image Features with Cross-Domain Transfer Learning

PURPOSE

This study aimed to find suitable source domain data in cross-domain transfer learning to extract robust image features. Then, a model was built to preoperatively distinguish lung granulomatous nodules (LGNs) from lung adenocarcinoma (LAC) in solitary pulmonary solid nodules (SPSNs).

METHODS

Data from 841 patients with SPSNs from five centres were collected retrospectively. First, adaptive cross-domain transfer learning was used to construct transfer learning signatures (TLS) under different source domain data and conduct a comparative analysis. The Wasserstein distance was used to assess the similarity between the source domain and target domain data in cross-domain transfer learning. Second, a cross-domain transfer learning radiomics model (TLRM) combining the best performing TLS, clinical factors and subjective CT findings was constructed. Finally, the performance of the model was validated through multicentre validation cohorts.

RESULTS

Relative to other source domain data, TLS based on lung whole slide images as source domain data (TLS-LW) had the best performance in all validation cohorts (AUC range: 0.8228-0.8984). Meanwhile, the Wasserstein distance of TLS-LW was 1.7108, which was minimal. Finally, TLS-LW, age, spiculated sign and lobulated shape were used to build the TLRM. In all validation cohorts, The AUC ranges were 0.9074-0.9442. Compared with other models, decision curve analysis and integrated discrimination improvement showed that TLRM had better performance.

CONCLUSIONS

The TLRM could assist physicians in preoperatively differentiating LGN from LAC in SPSNs. Furthermore, compared with other images, cross-domain transfer learning can extract robust image features when using lung whole slide images as source domain data and has a better effect.

Prognostic value of ground glass opacity on computed tomography in pathological stage I pulmonary adenocarcinoma: A meta-analysis

BACKGROUND

The clinical role of ground glass opacity (GGO) on computed tomography (CT) in stage I pulmonary adenocarcinoma patients currently remains unclear.

AIM

To explore the prognostic value of GGO on CT in lung adenocarcinoma patients who were pathologically diagnosed with tumor-node-metastasis stage I.

METHODS

A comprehensive and systematic search was conducted through the PubMed, EMBASE and Web of Science databases up to April 3, 2021. The hazard ratio (HR) and corresponding 95% confidence interval (CI) were combined to assess the association between the presence of GGO and prognosis, representing overall survival and disease-free survival. Subgroup analysis based on the ratio of GGO was also conducted. STATA 12.0 software was used for statistical analysis.

RESULTS

A total of 12 studies involving 4467 patients were included. The pooled results indicated that the GGO predicted favorable overall survival (HR = 0.44, 95%CI: 0.34-0.59, P < 0.001) and disease-free survival (HR = 0.35, 95%CI: 0.18-0.70, P = 0.003). Subgroup analysis based on the ratio of GGO further demonstrated that the proportion of GGO was a good prognostic indicator in pathological stage I pulmonary adenocarcinoma patients, and patients with a higher ratio of GGO showed better prognosis than patients with a lower GGO ratio did.

CONCLUSION

This meta-analysis manifested that the presence of GGO on CT predicted favorable prognosis in tumor-node-metastasis stage I lung adenocarcinoma. Patients with a higher GGO ratio were more likely to have a better prognosis than patients with a lower GGO ratio.