Verification of T descriptor with consolidation size for sub-centimeter non-small cell lung cancer

Successful Application of Artificial Intelligence-Assisted Analysis of Invasive Pulmonary Adenocarcinoma Less Than 6 mm in Size: A Case Report and Literature Review

INTRODUCTION

Screening of lung nodules helps on early diagnosis of lung cancer, especially invasive pulmonary adenocarcinoma. Artificial intelligence (AI) has been applied in diagnosis of cancers. We used the AI-assisted lung nodule diagnostic system in the screening of lung nodules and lung cancer.

CASE PRESENTATION

A 66-year-old male complained of coughs and nodules in the right lung of 3-year duration. A ground-glass opacity was found in the right upper lung by routine computed tomography (CT). He had no family history of cancer, genetic diseases, or infectious diseases. AI-assisted analysis found four nodules, of which one was with the risk of malignancy of 88% (LungRads3), one was with the risk of malignancy of 15% (LungRads2), and the other two were smaller in size and considered benign. The patient underwent a thoracoscopic wedge resection of the right upper lung. The intraoperative frozen section pathology report confirmed invasive pulmonary adenocarcinoma, grade II, and primarily of alveolar and adherent types without metastasis.

CONCLUSION

In summary, AI-assisted lung nodule diagnostic system is effective in the screening of lung nodules and the differentiation between benign and malignant.

Outcome of Resected Lung Cancers with Subcentimeter Solid Component on Computed Tomography

Background Although the opportunity to treat subcentimeter lung cancers has increased, the optimal surgical methods remain unclear. We performed a retrospective study to examine the clinical outcome of subcentimeter lung cancers.

Patients and Methods In total, 118 patients who underwent curative resection for subcentimeter lung cancer from January 2005 to December 2013 were analyzed. Multivariate Cox proportional hazards models were used to calculate the hazard ratio to identify independent predictors of recurrence-free survival (RFS) and overall survival (OS).

Results Anatomical resections were performed for 64 patients (59 lobectomies and 5 segmentectomies) and wedge resections for 54 patients. Recurrence developed in six patients who had consolidation-predominant tumors (consolidation/tumor [C/T] ratio of >0.5) and underwent wedge resections. The first recurrence patterns were regional recurrences in three patients, both regional and distant in one, and distant in two. Seventeen patients died of other causes. The multivariate analysis revealed that the C/T ratio was the independent predictor of RFS (p = 0.008) and OS (p = 0.011).

Conclusion Patients with subcentimeter lung cancer rarely developed recurrence. The C/T ratio was the independent prognostic factor, and all relapsed patients received wedge resections. Even for subcentimeter lung cancers, we should select the extent of pulmonary resection after thoroughly considering whether wedge resection (less invasiveness) is a reasonable alternative to anatomical resection (superior oncologic efficacy) considering the C/T ratio of the lesion.

Narrative review of optimal prognostic radiological tools using computed tomography for T1N0-staged non-small cell lung cancer

Various radiological tools can predict the prognosis of non-small cell lung cancer (NSCLC). In this study, we evaluated the prognostic effect of different radiological tools such as whole tumor size (WTS), consolidation size (CS), consolidation tumor ratio (CTR), tumor disappearance ratio (TDR), mediastinal diameter (MD), and ground glass opacity (GGO) using high-resolution computed tomography (HRCT). We reviewed recent retrospective studies on the predictive effect of these radiological tools on disease-free survival (DFS) and overall survival (OS) in patients with T1N0-staged NSCLC. We searched PubMed and the British Library databases for the English literature published from January 2010 to December 2020 and generated a total of 32 publications (NSCLC, n=16; adenocarcinoma, n=16). The TNM classification version 7 was used in 18 studies, and version 8 in 14 studies. The evaluated radiological parameters were WTS, CS including T category, CTR, TDR, MD, presence of GGO, GGO ratio, and pure GGO. This review suggested that CS, MD, and the presence of GGO are optimal prognostic radiological tools for cT1N0-Staged NSCLC. CTR or TDR for part solid nodules (PSNs) is not a well-accepted prognostic factor. Further investigations are required to differentiate between benign scars and malignant components on HRCT and evaluate the prognosis of PSNs (1< CS ≤2 cm) with large WTS in the future.