Objective To investigate the clinical and pathological characteristics, prognosis and treatment strategies of adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA). Methods We retrospectively analyzed the clinical data of 489 patients with AIS and MIA in our hospital from January 2007 to August 2015. There were 122 males and 367 females with an average age of 26–78 (51±9) years. According to the pathological types, they were divided into the AIS group (246 patients) and the MIA group (243 patients). In the AIS group, there were 60 males and 186 females with an average age of 50±7 years. In the MIA group, there were 62 males and 181 females with an average age of 54±5 years. The clinicopathological features, surgical methods and prognosis of the two groups were compared. Results There were significant differences in age, value of carcino-embryonic antigen (CEA), nodule shape and nodule size between the AIS and MIA groups (P<0.05). AIS patients were mostly under the age of 60 years with the value of CEA in the normal range which often appeared as pure ground-glass opacity lung nodules <1 cm in diameter on the CT scan. MIA often appeared as mixed ground-glass nodules <1.5 cm in diameter, accompanied by bronchiectasis and pleural indentation. The 5-year disease-free survival rate of the AIS and MIA groups reached 100%, and there was no statistical difference in the prognosis between the two groups after subtotal lobectomy (pulmonary resection and wedge resection) and lobectomy, systematic lymph node dissection and mediastinal lymph node sampling. Conclusion The analysis of preoperative clinical and imaging features can predict the AIS and MIA and provide individualized surgery and postoperative treatment program.
Objective To analyze the expression of H2A histone family, member X (H2AFX) gene in lung adenocarcinoma and its influence on prognosis. Methods We analyzed the expression level of H2AFX gene in the tumor tissues (497 cases) and normal adjacent tissues (54 cases) of lung adenocarcinoma patients via The Cancer Genome Atlas. The patients were divided into high expression group and low expression group according to the expression level of H2AFX gene in lung adenocarcinoma samples. The relationship between H2AFX and clinicopathological features of patients was analyzed through logistic regression. Kaplan-Meier survival curve and log-rank test were used to study the correlation between H2AFX expression and the prognosis of lung adenocarcinoma patients. Univariate and multiple Cox regression analyses were performed to determine the prognostic significance of H2AFX expression in lung adenocarcinoma patients. The research also covered H2AFX-related pathways of genes in the development of lung adenocarcinoma with gene set enrichment analysis (GSEA). Results The H2AFX expression was higher in lung adenocarcinoma tissues than that in normal adjacent tissues (P<0.001). Besides, it was significantly correlated with age (P<0.001), T staging (P=0.007), and N staging (P=0.010), but had little to do with M staging or gender (P>0.05). Kaplan-Meier survival curve and log-rank test showed that the survival rate of patients with high H2AFX expression was vastly lower than that of patients with low H2AFX expression (P<0.001). Multiple Cox regression analysis demonstrated that H2AFX could be an independent prognostic factor for lung adenocarcinoma [hazard ratio=1.41, 95% confidence interval (1.11, 1.78), P=0.004]. The results of GSEA displayed that H2AFX was involved in cell cycle, homologous recombination, DNA replication, base excision and repair, spliceosome, mismatch repair, p53 signaling pathway, nucleotide excision and repair, RNA degradation, RNA polymerase, and other pathways. Conclusions The expression of H2AFX gene is high in lung adenocarcinoma, and closely connected to the prognosis, occurrence, and evolution of lung adenocarcinoma. This gene can be one of the new molecular markers and therapeutic targets for lung adenocarcinoma.
Lung cancer is one of the malignant tumors with the greatest threat to human health, and studies have shown that some genes play an important regulatory role in the occurrence and development of lung cancer. In this paper, a LightGBM ensemble learning method is proposed to construct a prognostic model based on immune relate gene (IRG) profile data and clinical data to predict the prognostic survival rate of lung adenocarcinoma patients. First, this method used the Limma package for differential gene expression, used CoxPH regression analysis to screen the IRG to prognosis, and then used XGBoost algorithm to score the importance of the IRG features. Finally, the LASSO regression analysis was used to select IRG that could be used to construct a prognostic model, and a total of 17 IRG features were obtained that could be used to construct model. LightGBM was trained according to the IRG screened. The K-means algorithm was used to divide the patients into three groups, and the area under curve (AUC) of receiver operating characteristic (ROC) of the model output showed that the accuracy of the model in predicting the survival rates of the three groups of patients was 96%, 98% and 96%, respectively. The experimental results show that the model proposed in this paper can divide patients with lung adenocarcinoma into three groups [5-year survival rate higher than 65% (group 1), lower than 65% but higher than 30% (group 2) and lower than 30% (group 3)] and can accurately predict the 5-year survival rate of lung adenocarcinoma patients.
ObjectiveTo compare the recent efficiency and toxicity reactions of pemetrexed plus cisplatin and paclitaxel plus cisplatin for advanced lung adenocarcinoma. MethodsOne hundred and twenty-four patients with advanced lung adenocarcinoma treated in our hospital between January 2009 and December 2012 were divided into pemetrexed plus cisplatin group (group PP, n=63) and paclitaxel plus cisplatin group (group TP, n=61). The effect was evaluated after two courses of treatment, and the toxicity reactions were evaluated every course. ResultsThe objective response rate, disease control rate and progression-free survival in group PP and TP were respectively 58.7% vs 37.7%, 74.6% vs 52.5%, and 6.1 months vs 4.5 months, with significant differences (P<0.05). The incidence of nausea and vomiting, and white blood cell decrease (neutropenia) in group PP were significantly lower than that in group TP (χ2=16.164, P<0.001; χ2=9.469, P=0.002). There were no significant differences in incidence of thrombocytopenia, anemia and hepatic function damage (χ2=0.098, P=0.755; χ2=0.267, P=0.606; χ2=0.006, P=0.973). ConclusionPemetrexed plus cisplatin shows obviously superior effects and fewer side effects on advanced lung adenocarcinoma compared with paclitaxel plus cisplatin regime.
Lung adenocarcinoma has become the most common type of lung cancer. According to the 2015 World Health Organization histological classification of lung cancer, invasive lung adenocarcinoma can be divided into 5 subtypes: lepidic, acinar, papillary, solid, and micropapillary. Relevant studies have shown that the local lobectomy or sublobectomy is sufficient for early lepidic predominant adenocarcinoma, while lobectomy should be recommended for tumors containing micropapillary and solid ingredients (≥5%). Currently, the percentage of micropapillary and solid components diagnosed by frozen pathological examination is 65.7%, and the accuracy of diagnosis is limited. Therefore, to improve the accuracy of diagnosis, it is necessary to seek new methods and techniques. This paper summarized the characteristics and rapid diagnosis tools of early lung adenocarcinoma subtypes.
ObjectiveTo explore the accuracy of machine learning algorithms based on SHOX2 and RASSF1A methylation levels in predicting early-stage lung adenocarcinoma pathological types. MethodsA retrospective analysis was conducted on formalin-fixed paraffin-embedded (FFPE) specimens from patients who underwent lung tumor resection surgery at Affiliated Hospital of Nantong University from January 2021 to January 2023. Based on the pathological classification of the tumors, patients were divided into three groups: a benign tumor/adenocarcinoma in situ (BT/AIS) group, a minimally invasive adenocarcinoma (MIA) group, and an invasive adenocarcinoma (IA) group. The methylation levels of SHOX2 and RASSF1A in FFPE specimens were measured using the LungMe kit through methylation-specific PCR (MS-PCR). Using the methylation levels of SHOX2 and RASSF1A as predictive variables, various machine learning algorithms (including logistic regression, XGBoost, random forest, and naive Bayes) were employed to predict different lung adenocarcinoma pathological types. ResultsA total of 272 patients were included. The average ages of patients in the BT/AIS, MIA, and IA groups were 57.97, 61.31, and 63.84 years, respectively. The proportions of female patients were 55.38%, 61.11%, and 61.36%, respectively. In the early-stage lung adenocarcinoma prediction model established based on SHOX2 and RASSF1A methylation levels, the random forest and XGBoost models performed well in predicting each pathological type. The C-statistics of the random forest model for the BT/AIS, MIA, and IA groups were 0.71, 0.72, and 0.78, respectively. The C-statistics of the XGBoost model for the BT/AIS, MIA, and IA groups were 0.70, 0.75, and 0.77, respectively. The naive Bayes model only showed robust performance in the IA group, with a C-statistic of 0.73, indicating some predictive ability. The logistic regression model performed the worst among all groups, showing no predictive ability for any group. Through decision curve analysis, the random forest model demonstrated higher net benefit in predicting BT/AIS and MIA pathological types, indicating its potential value in clinical application. ConclusionMachine learning algorithms based on SHOX2 and RASSF1A methylation levels have high accuracy in predicting early-stage lung adenocarcinoma pathological types.
Lung adenocarcinoma is a prevalent histological subtype of non-small cell lung cancer with different morphologic and molecular features that are critical for prognosis and treatment planning. In recent years, with the development of artificial intelligence technology, its application in the study of pathological subtypes and gene expression of lung adenocarcinoma has gained widespread attention. This paper reviews the research progress of machine learning and deep learning in pathological subtypes classification and gene expression analysis of lung adenocarcinoma, and some problems and challenges at the present stage are summarized and the future directions of artificial intelligence in lung adenocarcinoma research are foreseen.
ObjectiveTo investigate the correlation between histological subtypes of invasive lung adenocarcinoma and epithelial growth factor receptor (EGFR) gene mutation, and to provide a reference for clinical prediction of EGFR gene mutation status.MethodsFrom October 2017 to May 2019, 102 patients with invasive lung adenocarcinoma were collected, including 58 males and 44 females aged 62 (31-84) years. Invasive lung adenocarcinoma was classified into different histological subtypes. Scorpion probe amplification block mutation system (ARMS) real-time PCR was used to detect the mutation of EGFR gene in adenocarcinoma specimens, and the relationship between invasive lung adenocarcinoma subtypes and EGFR mutation status was analyzed.ResultsIn 102 patients with invasive lung adenocarcinoma, EGFR gene mutations were detected in 68 patients, and the mutation rate was 66.7% (68/102). The mutation sites were mainly concentrated in the exons 19 and 21; the mutation rate was higher in female patients (34/44, 77.3%) and non-smokers (34/58, 58.6%). EGFR mutation was mostly caused by acinar-like invasive lung adenocarcinoma, and was rare in solid-type lung adenocarcinoma. The EGFR gene mutation rates in different subtypes of adenocarcinoma were statistically different (P<0.05).ConclusionThe EGFR mutation status is related to gender, smoking status and histological subtype of invasive lung adenocarcinoma. EGFR mutation rates are higher in female, non-smoking and acinar-like invasive lung adenocarcinoma patients, and are lower in patients with solid type lung adenocarcinoma.
Lung ground glass opacity (GGO), which is associated with the pathology of the lung adenocarcinoma, is drawing more and more attention with the increased detection rate. However, it is still in the research stage for the imaging interpretation of GGO lesions. In this paper, we reviewed and analyzed the new classification of lung adenocarcinoma corresponding to the interpretation of GGO imaging feature, which emphasizes on how to determine the GGO lesions comprehensively and quantitative determination of the invasive extent of GGO.
ObjectiveTo investigate the CT signs and clinicopathological features of peripheral cavitary lung adenocarcinoma with the largest diameter less than or equal to 3 cm.Methods From January 2015 to December 2017, the CT signs and clinicopathological fertures of 51 patients with ≤3 cm peripheral cavitary lung adenocarcinoma diagnosed by chest CT and surgical pathology were retrospectively analyzed. Furthermore, CT signs and clinicopathological features of thick-walled cavitary lung adenocarcinoma and thin-walled cavitary lung adenocarcinoma were compared. There were 29 males and 22 females at age of 62 (56, 67) years.ResultsThere were 27 thick-walled cavitary lung adenocarcinoma and 24 thin-walled cavitary lung adenocarcinoma. Thick-walled cavitary adenocarcinoma had greater SUVmax [6.5 (3.7, 9.7) vs. 2.2 (1.4, 3.8), P=0.019], larger cavity wall thickness (11.8±4.6 mm vs. 7.6±3.7 mm, P=0.001), larger tumor tissue size [2.1 (1.7, 2.8) cm vs. 1.6 (1.2, 2.0) cm, P=0.006], and more solid nodules (17 patients vs. 8 patients, P=0.035). Thin-walled cavitary adenocarcinoma had more smoking history (12 patients vs. 6 patients, P=0.038), larger cavity size [12.3 (9.2, 16.6) mm vs. 4.4 (2.8, 7.1) mm, P=0.000], and larger proportion of cavities [0.30 (0.19, 0.37) vs. 0.03 (0.01, 0.09), P=0.000]. On CT signs, there were more features of irregular inner wall (19 patients vs. 6 patients, P=0.000), intra-cystic separation (16 patients vs. 6 patients, P=0.001) and vessels through the cystic cavity (10 patients vs. 1 patient, P=0.001) in thin-walled caviraty lung adenocarcinoma.ConclusionPeripheral cavitary lung adenocarcinoma of ≤3 cm on chest CT has characteristic manifestations in clinical, imaging and pathology, and there is a statistical difference between thick-walled cavitary lung adenocarcinoma and thin-walled cavitary lung adenocarcinoma.