Prognostic significance of the International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society classification of stage I lung adenocarcinoma: A retrospective study based on analysis of 110 Chinese patients

Establishment of artificial intelligence model for precise histological subtyping of lung adenocarcinoma and its application to quantitative and spatial analysis

BACKGROUND

The histological subtype of lung adenocarcinoma is a major prognostic factor. We developed a new artificial intelligence model to classify lung adenocarcinoma images into seven histological subtypes and adopted the model for whole-slide images to investigate the relationship between the distribution of histological subtypes and clinicopathological factors.

METHODS

Using histological subtype images, which are typical for pathologists, we trained and validated an artificial intelligence model. Then, the model was applied to whole-slide images of resected lung adenocarcinoma specimens from 147 cases.

RESULT

The model achieved an accuracy of 99.7% in training sets and 90.4% in validation sets consisting of typical tiles of histological subtyping for pathologists. When the model was applied to whole-slide images, the predominant subtype according to the artificial intelligence model classification matched that determined by pathologists in 75.5% of cases. The predominant subtype and tumor grade (using the WHO fourth and fifth classifications) determined by the artificial intelligence model resulted in similar recurrence-free survival curves to those determined by pathologists. Furthermore, we stratified the recurrence-free survival curves for patients with different proportions of high-grade components (solid, micropapillary and cribriform) according to the physical distribution of the high-grade component. The results suggested that tumors with centrally located high-grade components had a higher malignant potential (P < 0.001 for 5-20% high-grade component).

CONCLUSION

The new artificial intelligence model for histological subtyping of lung adenocarcinoma achieved high accuracy, and subtype quantification and subtype distribution analyses could be achieved. Artificial intelligence model therefore has potential for clinical application for both quantification and spatial analysis.

Overcoming the Interobserver Variability in Lung Adenocarcinoma Subtyping: A Clustering Approach to Establish a Ground Truth for Downstream Applications

CONTEXT.—

The accurate identification of different lung adenocarcinoma histologic subtypes is important for determining prognosis but can be challenging because of overlaps in the diagnostic features, leading to considerable interobserver variability.

OBJECTIVE.—

To provide an overview of the diagnostic agreement for lung adenocarcinoma subtypes among pathologists and to create a ground truth using the clustering approach for downstream computational applications.

DESIGN.—

Three sets of lung adenocarcinoma histologic images with different evaluation levels (small patches, areas with relatively uniform histology, and whole slide images) were reviewed by 17 international expert lung pathologists and 1 pathologist in training. Each image was classified into one or several lung adenocarcinoma subtypes.

RESULTS.—

Among the 4702 patches of the first set, 1742 (37%) had an overall consensus among all pathologists. The overall Fleiss κ score for the agreement of all subtypes was 0.58. Using cluster analysis, pathologists were hierarchically grouped into 2 clusters, with κ scores of 0.588 and 0.563 in clusters 1 and 2, respectively. Similar results were obtained for the second and third sets, with fair-to-moderate agreements. Patches from the first 2 sets that obtained the consensus of the 18 pathologists were retrieved to form consensus patches and were regarded as the ground truth of lung adenocarcinoma subtypes.

CONCLUSIONS.—

Our observations highlight discrepancies among experts when assessing lung adenocarcinoma subtypes. However, a subsequent number of consensus patches could be retrieved from each cluster, which can be used as ground truth for the downstream computational pathology applications, with minimal influence from interobserver variability.

Comparison of outcomes following lobectomy, segmentectomy, and wedge resection based on pathological subtyping in patients with pN0 invasive lung adenocarcinoma ≤1 cm

PURPOSE

We sought to analyze the prognostic significance of lung adenocarcinoma classification for patients with pathological N0 (pN0) lung invasive adenocarcinomas ≤1 cm who underwent surgical resection and investigate the optimal surgical procedure according to lung adenocarcinoma classification.

METHODS

A total of 1409 consecutive patients with resected pN0 invasive lung adenocarcinoma ≤1 cm were retrospectively reviewed. Comprehensive histologic subtyping was determined according to IASLC/ATS/ERS lung adenocarcinoma classification. Recurrence-free survival (RFS) and overall survival (OS) were compared between patients receiving lobectomy, segmentectomy, and wedge resection.

RESULTS

RFS and OS favored lobectomy and segmentectomy compared with wedge resection in the entire cohort. Five-year RFS rates were 100%, 98.2%, 97.3%, 77.8%, and 82.8% (p < 0.001) for lepidic, acinar, papillary, micropapillary, and solid predominant subtypes, while 5-year OS rates were 100%, 98.4%, 98.1%, 88.9%, and 96.5% (p < 0.001), respectively. Multivariate analysis showed that adenocarcinoma predominant pathological subtype and CT appearance were independent prognostic factors for RFS, and surgical procedure was independent factor for both RFS and OS. Specifically, wedge resection showed worse survival compared with anatomical resection in patients with papillary, micropapillary, or solid predominant subtypes, whereas in patients with lepidic predominant and acinar predominant subtypes, wedge resection showed comparable RFS with anatomical resection.

CONCLUSIONS

Anatomical resection showed better survival for patients with pN0 invasive lung adenocarcinoma ≤1 cm. For patients with invasive adenocarcinoma ≤1 cm in whom anatomical resection is not feasible, wedge resection could provide similar oncological effect when tumor is lepidic predominant or acinar predominant.

Risk of development of brain metastases according to the IASLC/ATS/ERS lung adenocarcinoma classification in locally advanced and metastatic disease

INTRODUCTION

Brain metastases (BM) are frequent among lung cancer patients, affecting prognosis and quality of life. The International Association for the Study of Lung Cancer (IASLC), American Thoracic Society (ATS) and European Respiratory Society (ERS) lung adenocarcinoma (LADC) classification (IASLC/ATS/ERS) has prognostic impact in early-stage disease; however, its role in the advanced setting is not precise. This study aims to determine the correlation between the predominant histological subtype and the risk of developing brain metastases (BM) in locally advanced and metastatic (stages IIIB-IV) LADC.

METHODS

A total of 710 patients with LADC were treated at our institution from January 2010 to December 2017. After excluding patients with brain metastases at diagnoses (n = 151), they were categorized according to the IASLC/ATS/ERS LADC classification to estimate the risk of developing brain metastases. A competing risk analysis was employed, considering death a competing risk event.

RESULTS

From 559 patients, the mean age was 59 ± 13.2 years, women (52.4 %), and clinical-stage IV (79.2 %). LADC subtypes distribution was lepidic (11.6 %), acinar (37.9 %), papillary (10.2 %), micropapillary (6.8 %), and solid (33.5 %). A total of 27.0 % of patients developed BM, 32.9 % died without brain affection, and 40.0 % did not progress. The predominantly solid subtype showed the greatest probability of all subtypes for developing BM [HR 4.0; 95 % CI (1.80-8.91), p = 0.0006], followed by micropapillary [HR1.11; 95 % CI (0.36-3.39), p = 0.85). The solid subtype, moderately differentiated tumors, age, and ECOG PS (>2) were associated with increased hazards in the multivariate analysis.

CONCLUSION

According to the IASLC/ATS/ERS classification, the predominantly solid pattern was significantly associated with an increased risk of developing BM in patients with locally advanced and metastatic LADC. Its prognostic value might help explore novel clinical approaches, modify monitoring for earlier detection, prevent complications, and reduce morbidity.

Micropapillary pattern of stage IIIA-N2 lung adenocarcinoma is a prognostic factor after adjuvant chemoradiotherapy

Aim: This study aims to investigate the significance of a micropapillary pattern in stage IIIA-N₂ lung adenocarcinoma after adjuvant chemoradiotherapy. Patients & methods: A total of 257 patients with stage IIIA-N₂ lung adenocarcinoma were enrolled in this study. Patients were classified into three groups based on the proportion of micropapillary components: micropapillary negative, micropapillary minor component and micropapillary predominant component. Results: The micropapillary predominant group had the shortest median disease-free survival and overall survival times compared with the micropapillary minor component and micropapillary negative groups (median overall survival time: 54 months vs 64 months vs not reached; p = 0.004). Furthermore, the micropapillary pattern was an independent prognostic factor for disease-free survival and overall survival (p < 0.05). Conclusion: The micropapillary pattern of IIIA-N₂ lung adenocarcinoma is related to worse prognosis.

Both the presence of a micropapillary component and the micropapillary predominant subtype predict poor prognosis after lung adenocarcinoma resection: a meta-analysis

Objective

It has been confirmed that the micropapillary (MP) pattern is a poor prognostic factor after resection of lung adenocarcinoma (ADC), but the proportion of the MP component as a prognostic criterion is still controversial. Hence, a meta-analysis was performed to evaluate whether the presence of an MP component has equal prognostic power as the MP predominant subtype.

Methods

Literature retrieval was performed in the MEDLINE, EMBASE, and Cochrane databases until December 23, 2019. Eligible studies were selected based on the inclusion and exclusion criteria. The included studies were divided into two subgroups, the MP component subgroup and the MP predominant subgroup, according to the proportion of the MP pattern to analyse the effect of this pattern on disease-free survival (DFS) and overall survival (OS). The hazard ratio (HR) and 95% confidence interval (CI) were extracted from each study. Review Manager 5.3 was used for statistical analyses.

Results

Finally, 10 studies, including a total of 4934 lung ADC patients, were included in this meta-analysis. Our results indicated a significantly worse pooled DFS (HR 1.62, 95% CI 1.20–2.21) and OS (HR 1.53, 95% CI 1.19–1.96) in the subgroup of MP predominant subtype patients. The pooled DFS (HR 1.80, 95% CI 1.45–2.85) and OS (HR 2.26, 95% CI 1.46–3.52) were also poor in the subgroup of patients with the presence of an MP component.

Conclusions

Both the presence of an MP component and the MP predominant subtype are related to poor DFS and OS after lung ADC resection and represent adverse prognostic factor for lung ADC patients. However, there are some limitations in this meta-analysis, and quantitative stratification based on the proportion of the MP component is needed to explore its effect on prognosis of lung ADC patients in the future.

The Correlation between EGFR Mutation Status and DNA Content of Lung Adenocarcinoma Cells in Pleural Effusion

Objectives: Lung adenocarcinomas with or without epidermal growth factor receptor (EGFR) mutations have shown different drug effects against EGFR inhibitors. But it is not very clear if EGFR mutation status affects the biological behavior of lung adenocarcinoma, because tumor gene regulation is very complicated and can be affected by many factors. We aimed to explore if EGFR mutation status is related with tumor malignant degree by investigating the relevance of EGFR mutation status with DNA content and aneuploid peaks of lung adenocarcinoma cells in pleural fluids without using EGFR-TKIs.

Materials and Methods: 591 cases of lung adenocarcinoma patients in Hebei Tumor Hospital who had undergone EGFR gene detection and DNA quantitative analysis were collected from January 2012 to August 2018.They were divided into two groups: EGFR mutant group and non-mutant group. EGFR mutations were detected by Amplification Refractory Mutation System (ARMS) and ABI 7500 Fluorescence quantitative PCR with pleural effusions. DNA content and aneuploid peaks were detected by LD DNA image cytometry (DNA-ICM). Rank-sum test of SPSS 16 was used for statistical analysis.

Results: The maximum DI, the mean DI of the first 20 cells greater than 5C, the percentage of cells greater than 5C and the number of cells greater than 9C of the first 20 cells in the mutant group were all higher than those in the non-mutant group, having statistical significance (p<0.001); the peaks of aneuploid cells in the mutant group occurred more often than those in the non-mutant group, having statistical significance (p<0.001).

Conclusions: Our study has shown that advanced lung adenocarcinomas with EGFR-mutations had higher DI values, more aneuploid cells and more frequent aneuploid peaks compared with those without EGFR-mutations, suggesting that advanced lung adenocarcinomas with EGFR mutations are more aggressive than those without EGFR mutations.

Expansion of the Concept of Micropapillary Adenocarcinoma to Include a Newly Recognized Filigree Pattern as Well as the Classical Pattern Based on 1468 Stage I Lung Adenocarcinomas

INTRODUCTION

The classical micropapillary (MIP) pattern is defined in the 2015 WHO classification as tumor cells growing in papillary tufts forming florets that lack fibrovascular cores, and it is associated with poor prognosis. We observed a novel pattern that we termed a filigree MIP pattern and investigated its relationship with the classical MIP pattern.

METHODS

Filigree pattern was defined as tumor cells growing in delicate, lace-like, narrow stacks of cells without fibrovascular cores. We required at least three piled-up nuclei from the alveolar wall basal layer, with a breadth of up to three cells across. To assess the relationship of the filigree pattern with the classical MIP pattern, we documented their frequencies in the context of the clinical and pathologic characteristics of 1468 stage I invasive adenocarcinomas, including survival analysis using cumulative incidence of recurrence by competing risks.

RESULTS

We observed the filigree MIP pattern in 35% of cases. By including the filigree pattern as an MIP pattern, we identified 57 more MIP predominant cases in addition to the previously diagnosed 87 MIP predominant adenocarcinomas. These 57 cases were reclassified from papillary (n = 37), acinar (n = 16), and solid (n = 4) predominant adenocarcinoma, respectively. Of the 144 MIP predominant adenocarcinomas, the filigree predominant MIP pattern (n = 78) showed a poor prognosis like the classical predominant MIP pattern (n = 66) (p = 0.464). In addition, like the classical MIP pattern (p = 0.010), even a small amount (≥5%) of filigree MIP pattern was significantly associated with worse cumulative incidence of recurrence (p = 0.001) in multivariable analysis.

CONCLUSION

The frequent association with the classical MIP pattern and the similar poor prognosis supports inclusion of the filigree pattern in the MIP pattern subtype.

Value of adjuvant chemotherapy in patients with resected stage IB solid predominant and solid non-predominant lung adenocarcinoma

BACKGROUND

The use of adjuvant chemotherapy (ACT) for stage IB lung adenocarcinoma remains controversial. We examined the benefits of ACT in stage IB patients with tumors composed of solid material.

METHODS

The records of 309 patients with stage IB lung adenocarcinoma who had undergone complete resection between 2006 and 2015 were reviewed. All pathological slides were evaluated for the composition of solid material.

RESULTS

Our data showed that although disease-free survival (DFS) and overall survival (OS) were not significantly different (P = 0.306 and P = 0.061, respectively) between patients displaying a solid pattern of tumor growth and treated with or without ACT, patients with a solid predominant pattern of tumor growth treated with ACT had longer DFS (hazard ratio 0.359; P = 0.033) and OS (hazard ratio 0.205; P = 0.003). In patients with solid non-predominant patterns, treatment with ACT had no effect on DFS (P = 0.326) or OS (P = 0.508).

CONCLUSIONS

Postoperative patients with the solid predominant pattern of stage IB lung adenocarcinoma may benefit from ACT, while those with the solid non-predominant pattern will not.