Hybrid Clinical-Radiomics Model for Precisely Predicting the Invasiveness of Lung Adenocarcinoma Manifesting as Pure Ground-Glass Nodule.
- 作者列表："Song L","Xing T","Zhu Z","Han W","Fan G","Li J","Du H","Song W","Jin Z","Zhang G
RATIONALE AND OBJECTIVES:To identify whether the radiomics features of computed tomography (CT) allowed for the preoperative discrimination of the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs) and further to develop and compare different predictive models. MATERIALS AND METHODS:We retrospectively included 187 lung adenocarcinomas presenting as pGGNs (66 preinvasive lesions and 121 invasive lesions), which were randomly divided into the training and test sets (8:2). Radiomics features were extracted from non-enhanced CT images. Clinical features, including patient's demographic characteristics, smoking status, and conventional CT features that reflect tumor's morphology and surrounding information were also collected. Intraclass correlation coefficient and ℓ2.1-norm minimization were used to identify influential feature subset which was then used to build three predictive models (clinical, radiomics, and clinical-radiomics models) with the gradient boosting regression tree classifier. The performances of the predictive models were evaluated using the area under the curve (AUC). RESULTS:Of the 1409 radiomics features and 27 clinical feature subtypes, 102 features were selected to construct the hybrid clinical-radiomics model, which achieved the best discriminative power (AUC = 0.934 and 0.929 in training and test set). The radiomics model showed comparable predictive performance (AUC = 0.911 and 0.901 in training and test set) compared to the clinical model (AUC = 0.911 and 0.894 in training and test set). CONCLUSION:The radiomics model showed good predictive performance in discriminating invasive lesions from preinvasive lesions for lung adenocarcinomas presenting as pGGNs. Its performance can be further improved by adding clinical features.
原理和目的: 确定计算机断层扫描 (CT) 的放射组学特征是否允许术前区分表现为纯磨玻璃结节 (pGGNs) 的肺腺癌的侵袭性并进一步开发和比较不同的预测模型。 材料和方法: 我们回顾性纳入了 187 例表现为 pGGNs 的肺腺癌 (66 个浸润前病变和 121 个浸润病灶)，随机分为训练集和测试集 (8:2)。从非增强 CT 图像中提取影像组学特征。还收集了临床特征，包括患者的人口统计学特征、吸烟状况和反映肿瘤形态和周围信息的常规 CT 特征。使用组内相关系数和 2.1-范数最小化来识别有影响的特征子集，然后用于构建三个预测模型 (临床、放射组学和临床-放射组学模型) 使用梯度提升回归树分类器。使用曲线下面积 (AUC) 评价预测模型的性能。 结果: 在 1409 个影像组学特征和 27 个临床特征亚型中，选取 102 个特征构建临床-影像组学混合模型,取得了最好的判别力 (auc = 0.934 和 0.929)。与临床模型 (训练和测试集 auc = 0.911 和 0.901) 相比，radiomics 模型显示出相当的预测性能 (训练和测试集 auc = 0.911 和 0.894)。 结论: 对于表现为 pGGNs 的肺腺癌，radiomics 模型在区分侵袭性病变和浸润前病变方面显示出良好的预测性能。它的性能可以通过增加临床特征进一步提高。
METHODS:BACKGROUND:The objectives of this study are to assess the chest drainage volumes of patients undergoing anatomic resection of non-small cell lung carcinoma and to determine the safety and effectiveness of administering enoxaparin for thromboprophylaxis. METHODS:A total of 77 patients were included in the study. A study was conducted on the first group of 42 patients in which enoxaparin prophylaxis (enoxaparin, 40 mg) was subcutaneously injected once a day for a period of three days after the patients underwent anatomic pulmonary resection between March 2016 and March 2018. An enoxaparin-free group was identified and included 35 patients who received no enoxaparin prophylaxis after undergoing anatomic pulmonary resection between February 2013 and February 2016. We compared the changes in hemoglobin (Hb) levels, postoperative 3-day drainage volume, transfusion volume, pulmonary complications and length of stay between the two groups. RESULTS:No differences in postoperative Hb levels, chest drainage volume, transfusion volume, postoperative complications, and length of stay were observed between the two groups. Deep-vein thrombosis was noted in a patient in the enoxaparin-free group. No major bleeding was noted in either group. CONCLUSION:We found that for patients undergoing anatomic resection of primary lung cancer, the blood transfusion and chest drainage volumes did not differ, regardless of whether the patients were given enoxaparin. To the best of our knowledge, the impact of low-molecular-weight heparin on chest tube drainage volume for patients undergoing anatomic resection of non-small cell lung carcinoma has not been investigated before.
METHODS::The aim of the present study was to compare the safety and efficacy of cryoablation (CA) and microwave ablation (MWA) as treatments for non-small cell lung cancer (NSCLC). Patients with stage IIIB or IV NSCLC treated with CA (n=45) or MWA (n=56) were enrolled in the present study. The primary endpoint was progression-free survival (PFS); the secondary endpoints included overall survival (OS) time and adverse events (AEs). The median PFS times between the two groups were not significantly different (P=0.36): CA, 10 months [95% confidence interval (CI), 7.5-12.4] vs. MWA, 11 months (95% CI, 9.5-12.4). The OS times between the two groups were also not significantly different (P=0.07): CA, 27.5 months (95% CI, 22.8-31.2 months) vs. MWA, 18 months (95% CI, 12.5-23.5). For larger tumors (>3 cm), patients treated with MWA had significantly longer median PFS (P=0.04; MWA, 10.5 months vs. CA, 7.0 months) and OS times (P=0.04; MWA, 24.5 months vs. CA, 14.5 months) compared patients treated with CA. However, for smaller tumors (≤3 cm), median PFS (P=0.79; MWA, 11.0 months vs. CA, 13.0 months) and OS times (P=0.39; MWA, 30.0 months vs. CA, 26.5 months) between the two groups did not differ significantly. The incidence rates of AEs were similar in the two groups (P>0.05). The number of applicators, tumor size and length of the lung traversed by applicators were associated with a higher risk of pneumothorax and intra-pulmonary hemorrhage in the two groups. Treatment with CA resulted in significantly less intraprocedural pain compared with treatment with MWA (P=0.001). Overall, the present study demonstrated that CA and MWA were comparably safe and effective procedures for the treatment of small tumors. However, treatment with MWA was superior compared with CA for the treatment of large tumors.
METHODS:BACKGROUND:BRAF mutations occurring in 1%-5% of patients with non-small-cell lung cancer (NSCLC) are therapeutic targets for these cancers but the impact of the exact mutation on clinical activity is unclear. The French National Cancer Institute (INCA) launched the AcSé vemurafenib trial to assess the efficacy and safety of vemurafenib in cancers with various BRAF mutations. We herein report the results of the NSCLC cohort. PATIENTS AND METHODS:Tumour samples were screened for BRAF mutations in INCA-certified molecular genetic centres. Patients with BRAF-mutated tumours progressing after ≥1 line of treatment were proposed vemurafenib 960 mg twice daily. Between October 2014 and July 2018, 118 patients were enrolled in the NSCLC cohort. The primary outcome was the objective response rate (ORR) assessed every 8 weeks (RECIST v1.1). A sequential Bayesian approach was planned with an inefficacy bound of 10% for ORR. If no early stopping occurred, the treatment was of interest if the estimated ORR was ≥30% with a 90% probability. Secondary outcomes were tolerance, response duration, progression-free survival (PFS), and overall survival (OS). RESULTS:Of the 118 patients enrolled, 101 presented with a BRAFV600 mutation and 17 with BRAFnonV600 mutations; the median follow-up was 23.9 months. In the BRAFnonV600 cohort, no objective response was observed and this cohort was stopped. In the BRAFV600 cohort, 43/96 patients had objective responses. The mean Bayesian estimated success rate was 44.9% [95% confidence intervals (CI) 35.2%-54.8%]. The ORR had a 99.9% probability of being ≥30%. Median response duration was 6.4 months, median PFS was 5.2 months (95% CI 3.8-6.8), and OS was 10 months (95% CI 6.8-15.7). The vemurafenib safety profile was consistent with previous publications. CONCLUSION:Routine biomarker screening of NSCLC should include BRAFV600 mutations. Vemurafenib monotherapy is effective for treating patients with BRAFV600-mutated NSCLC but not those with BRAFnonV600 mutations. TRIAL REGISTRATION:ClinicalTrials.gov identifier: NCT02304809.