Validated Prognostic Scores to Predict Outcomes in ECLS-Bridged Patients to Lung Transplantation.

Selection of patients who may benefit from extracorporeal life support (ECLS) as a bridge to lung transplant (LTx) is crucial. The aim was to assess if validated prognostic scores could help in selecting patients who may benefit from ECLS-bridging predicting their outcomes. Clinical data of patients successfully ECLS-bridged to LTx from 2009 to 2021 were collected from two European centers. For each patient, we calculated Sequential Organ Failure Assessment (SOFA), Simplified Acute Physiology Score III (SAPS III), Acute Physiology and Chronic Health Evaluation II (APACHE II), before placing ECLS support, and then correlated with outcome. Median values of SOFA, SAPS III, and APACHE II were 5 (IQR 3-9), 57 (IQR 47.5-65), and 21 (IQR 15-26). In-hospital, 30 and 90 days mortality were 21%, 14%, and 22%. SOFA, SAPS III, and APACHE II were analyzed as predictors of in-hospital, 30 and 90 days mortality (SOFA C-Index: 0.67, 0.78, 0.72; SAPS III C-index: 0.48, 0.45, 0.51; APACHE II C-Index: 0.49, 0.45, 0.52). For SOFA, the score with the best performance, a value ≥9 was identified to be the optimal cut-off for the prediction of the outcomes of interest. SOFA may be considered an adequate predictor in these patients, helping clinical decision-making. More specific and simplified scores for this population are necessary.

[Surgical or bronchoscopic lung volume reduction for emphysema therapy]. / Chirurgische oder bronchoskopische Lungenvolumenreduktion zur Emphysemtherapie.

More than 20 years ago, surgical lung volume reduction (LVRS) was already established in patients with advanced emphysema as a palliative therapy option that reduces respiratory distress and improves lung function and quality of life. In addition, bronchoscopic procedures (BLVR) aimed at volume reduction have existed for just over 10 years. The advantages and disadvantages of LVRS and BLVR are discussed in this article.

Single-cell profiling of myasthenia gravis identifies a pathogenic T cell signature.

Myasthenia gravis (MG) is an autoimmune disease characterized by impaired neuromuscular signaling due to autoantibodies targeting the acetylcholine receptor. Although its auto-antigens and effector mechanisms are well defined, the cellular and molecular drivers underpinning MG remain elusive. Here, we employed high-dimensional single-cell mass and spectral cytometry of blood and thymus samples from MG patients in combination with supervised and unsupervised machine-learning tools to gain insight into the immune dysregulation underlying MG. By creating a comprehensive immune map, we identified two dysregulated subsets of inflammatory circulating memory T helper (Th) cells. These signature ThCD103 and ThGM cells populated the diseased thymus, were reduced in the blood of MG patients, and were inversely correlated with disease severity. Both signature Th subsets rebounded in the blood of MG patients after surgical thymus removal, indicative of their role as cellular markers of disease activity. Together, this in-depth analysis of the immune landscape of MG provides valuable insight into disease pathogenesis, suggests novel biomarkers and identifies new potential therapeutic targets for treatment.

Surgical Outcomes and Risk Analysis of Primary Pulmonary Sarcoma.

BACKGROUND: Primary pulmonary sarcoma (PPS) is a rare malignant lung neoplasm, and there is very little medical evidence about treatment of PPS. The aim of this study is to clarify the clinical characteristics and therapeutic outcome of patients who underwent surgical resection for PPS. METHODS: We retrospectively reviewed the records of patients who underwent surgical resection for PPS in our institution between 1995 and 2014. Cases who only underwent biopsy were excluded. RESULTS: A total of 24 patients (18 males, 6 females), with a median age of 60 (interquartile range: 44-67) years, were analyzed. The surgical procedures performed in these patients were pneumonectomy (n = 10), lobectomy (n = 11), and wedge resection (n = 3). Complete resection was achieved in 16 patients. The pathological stages (tumor, node, metastases lung cancer classification, 8th edition) of the patients were I (n = 4), II (n = 12), III (n = 2), and IV (n = 5), and there were four cases of lymph node metastasis. The 5-year overall survival rate of the patients was 50% (95% confidence interval [CI]: 29-72). Adverse prognostic factors for overall survival were incomplete resection (hazard ratio [HR]: 4.4, 95% CI: 2.1-42), advanced pathological stage (HR 14, 95% CI: 2.8-66), higher pathological grade (HR 4.5, 95% CI: 1.2-17), and tumor size ≥ 7 cm (HR 4.7, 95% CI: 1.1-21). CONCLUSIONS: Our series of PPS revealed that incomplete resection, advanced pathological stage, higher pathological grade, and tumor size were unfavorable factors for long-term survival.

Which Anesthesia Regimen Is Best to Reduce Morbidity and Mortality in Lung Surgery?: A Multicenter Randomized Controlled Trial.

BACKGROUND: One-lung ventilation during thoracic surgery is associated with hypoxia-reoxygenation injury in the deflated and subsequently reventilated lung. Numerous studies have reported volatile anesthesia-induced attenuation of inflammatory responses in such scenarios. If the effect also extends to clinical outcome is yet undetermined. We hypothesized that volatile anesthesia is superior to intravenous anesthesia regarding postoperative complications. METHODS: Five centers in Switzerland participated in the randomized controlled trial. Patients scheduled for lung surgery with one-lung ventilation were randomly assigned to one of two parallel arms to receive either propofol or desflurane as general anesthetic. Patients and surgeons were blinded to group allocation. Time to occurrence of the first major complication according to the Clavien-Dindo score was defined as primary (during hospitalization) or secondary (6-month follow-up) endpoint. Cox regression models were used with adjustment for prestratification variables and age. RESULTS: Of 767 screened patients, 460 were randomized and analyzed (n = 230 for each arm). Demographics, disease and intraoperative characteristics were comparable in both groups. Incidence of major complications during hospitalization was 16.5% in the propofol and 13.0% in the desflurane groups (hazard ratio for desflurane vs. propofol, 0.75; 95% CI, 0.46 to 1.22; P = 0.24). Incidence of major complications within 6 months from surgery was 40.4% in the propofol and 39.6% in the desflurane groups (hazard ratio for desflurane vs. propofol, 0.95; 95% CI, 0.71 to 1.28; P = 0.71). CONCLUSIONS: This is the first multicenter randomized controlled trial addressing the effect of volatile versus intravenous anesthetics on major complications after lung surgery. No difference between the two anesthesia regimens was evident.

Lung Volume Reduction Surgery and Improvement of Endothelial Function and Blood Pressure in Patients with Chronic Obstructive Pulmonary Disease. A Randomized Controlled Trial.

RATIONALE: Cardiovascular disease is a major cause of morbidity and mortality in patients with chronic obstructive pulmonary disease (COPD). Preliminary studies have shown that both airflow obstruction and systemic inflammation may contribute to endothelial dysfunction in COPD. Lung volume reduction surgery (LVRS) is a treatment option in selected patients with COPD with emphysema that improves breathing mechanics and lung function. OBJECTIVES: To determine the effect of LVRS on endothelial function and systemic inflammation. METHODS: We conducted a randomized controlled trial in 30 patients scheduled for LVRS. In the intervention group, immediate LVRS was performed after baseline evaluation followed by reassessment 3 months later. In the control group, reassessment followed 3 months after baseline evaluation, and thereafter LVRS was performed. MEASUREMENTS AND MAIN RESULTS: The primary outcome measures were the treatment effect on endothelial function and systemic inflammation. In the LVRS group 14 patients completed the trial and 13 in the control group. LVRS led to a relative reduction in mean (SD) residual volume/total lung capacity of -12% (12%) and an increase in FEV1 of 29% (27%). Flow-mediated dilatation of the brachial artery increased in the intervention group as compared with the control group (+2.9%; 95% confidence interval, +2.1 to +3.6%; P < 0.001), whereas there was no significant change in systemic inflammation. A significant treatment effect on mean blood pressure was observed (-9.0 mm Hg; 95% confidence interval, -17.5 to -0.5; P = 0.039). CONCLUSIONS: Endothelial function and blood pressure are improved 3 months after LVRS in patients with severe COPD and emphysema. LVRS may therefore have beneficial effects on cardiovascular outcomes. Clinical trial registered with www.clinicaltrials.gov (NCT 01020344).

Determinants of outcome of solitary fibrous tumors of the pleura: an observational cohort study.

BACKGROUND: Solitary fibrous tumors of the pleura (SFTP) are rare and their long-term outcome is difficult to predict, as there are insufficient data which allow accurate characterization of the malignant variant. Thus the aim of this study was to describe the outcome and possible determinants of malignant behavior of SFTPs. METHODS: Data were collected retrospectively from medical records of patients treated at the University Hospital Zurich from 1992 to 2012. Kaplan-Meier and Cox regression analysis were performed to define disease-free survival time (defined as survival without tumor-recurrence or tumor-related death) using the classical histo-morphological criteria (tumor size, localization, pedunculation, tumor necrosis or hemorrhage, mitotic activity and nuclear pleomorphism) and immunohistochemical parameters. RESULTS: 42 patients (20 males) with SFTP (median (IQR) age 62 (56-71) years) could be identified. SFTP were associated with symptoms in 50% of all cases. Complete resection was achieved by video-assisted thoracic surgery or thoracotomy in 20 and 22 patients, respectively. Three SFTP-related deaths (7.1%) and four tumor recurrences (9.5%) were observed. Mean disease-free survival time was 136.2 (± 13.1) months, and 2-, 5- and 10-year disease-free survival was 91%, 84%, and 67%, respectively. Mean disease-free survival inversely correlated with the mean tumor diameter, number of mitotic figures and proliferation rate (Ki-67 expression). Other criteria (tumor necrosis, atypical localization, sessile tumor, and pleomorphism) were not statistically significant prognostic parameters. CONCLUSIONS: Patients with large SFTP with a high mitotic index and high proliferation rate should be followed-up closely and over a prolonged time period in order to recognize recurrence of the SFTP early and at a treatable stage. Future research on this topic should focus on the prognostic role of immunohistochemistry including Ki-67 expression and molecular parameters.

Risk factors influencing postoperative pleural empyema in patients with pleural mesothelioma: a retrospective single-centre analysis.

OBJECTIVES: Postoperative empyema is a severe, potentially lethal complication also present, but poorly studied in patients undergoing surgery for pleural mesothelioma. We aimed to analyse which perioperative characteristics might be associated with an increased risk for postoperative empyema. METHODS: From September 1999 to February 2023 a retrospective analysis of consecutive patients undergoing surgery for pleural mesothelioma at the University Hospital of Zurich was performed. Uni- and multivariable logistic regression was used to identify associated risk factors of postoperative empyema after surgery. RESULTS: A total of 400 PM patients were included in the analysis, of which n = 50 patients developed empyema after surgery (12.5%). Baseline demographics were comparable between patients with (Eyes) and without empyema (Eno). 39% (n = 156) patients underwent extrapleural pneumonectomy (EPP), of whom 22% (n = 35) developed postoperative pleural empyema; 6% (n = 15) of the remaining 244 patients undergoing pleurectomy and decortication (n = 46), extended pleurectomy and decortication (n = 114), partial pleurectomy (n = 54) or explorative thoracotomy (n = 30) resulted in postoperative empyema. In multivariable logistic regression analysis, EPP (odds ratio 2.8, 95% confidence interval 1.5-5.4, P = 0.002) emerged as the only risk factor associated with postoperative empyema when controlled for smoking status. Median overall survival was significantly worse for Eyes (16 months, interquartile range 5-27 months) than for Eno (18 months, interquartile range 8-35 months). CONCLUSIONS: Patients undergoing EPP had a significantly higher risk of developing postoperative pleural empyema compared to patients undergoing other surgery types. Survival of patients with empyema was significantly shorter.

Relevance of pleural adhesions for short- and long-term outcomes after lung volume reduction surgery.

Objective: Pleural adhesions (PLAs) have been shown to be a possible risk factor for air leak after lung volume reduction surgery (LVRS), but the relevance of PLA for lung function outcome remains unclear. We analyzed our LVRS cohort for the influence of PLA on short-term (ie, prolonged air leak) and long-term outcomes. Methods: Retrospective observational cohort study with 187 consecutive patients who underwent LVRS from January 2016 to December 2019. PLA were defined as relevant if they were distributed extensively at the dorsal pleura; were present in at least at 2 areas, including the dorsal pleura; or present extensively at the mediastinal pleura. In patients with bilateral emphysema, bilateral LVRS was performed preferentially. The objectives were to quantify the association of PLA and rate of prolonged air leak (chest tube >7 days), and the association of PLA with postoperative exacerbations and with forced expiratory volume in 1 second 3 months postoperatively. The associations were quantified with odds ratios for binary outcomes, and with between-group differences for continuous outcomes. To account for missing observations, 100-fold multiple imputation was used. Results: PLAs were found in 46 of 187 patients (24.6%). There was a 32.6% rate of prolonged air leak (n = 61), mean chest tube time was 7.84 days. A total of 94 (50.3%) LVRSs were unilateral and 93 were bilateral. There was evidence for an association between PLA and the rate of prolonged air leak (odds ratio, 2.83; 95% CI, 1.36 to 5.89; P = .006). There was no evidence for an association between PLA and postoperative exacerbations (odds ratio, 1.11; 95% CI, 0.5 to 2.45; P = .79). There was no evidence for an association between PLA and forced expiratory volume in 1 second (estimate -1.52; 95% CI -5.67 to 2.63; P = .47). Both unilateral and bilateral LVRS showed significant postoperative improvements in forced expiratory volume in 1 second by 27% (8.43 units; 95% CI, 3.66-13.12; P = .0006) and by 28% (7.87 units; 95% CI, 4.68-11.06; P < .0001) and a reduction in residual volume of 15% (-33.9 units; 95% CI, -56.37 to -11.42; P = .003) and 15% (-34.9 units; 95% CI, -52.57 to -17.22; P = .0001), respectively. Conclusions: Patients should be aware of potential prolongation of hospitalization due to PLA. However, there might be no relevant influence of PLA on lung function outcomes.

Outcome Analysis of Treatment Modalities for Thoracic Sarcomas.

BACKGROUND: Primary chest wall sarcomas are a rare and heterogeneous group of chest wall tumors that require multimodal oncologic and surgical therapy. The aim of this study was to review our experience regarding the surgical treatment of chest wall sarcomas, evaluating the short- and long-term results. METHODS: In this retrospective single-center study, patients who underwent surgery for soft tissue and bone sarcoma of the chest wall between 1999 and 2018 were included. We analyzed the oncologic and surgical outcomes of chest wall resections and reconstructions, assessing overall and recurrence-free survival and the associated clinical factors. RESULTS: In total, 44 patients underwent chest wall resection for primary chest wall sarcoma, of which 18 (41%) received surgery only, 10 (23%) received additional chemoradiotherapy, 7% (3) received surgery with chemotherapy, and 30% (13) received radiotherapy in addition to surgery. No perioperative mortality occurred. Five-year overall survival was 51.5% (CI 95%: 36.1-73.4%), and median overall survival was 1973 days (CI 95% 1461; -). As determined in the univariate analysis, the presence of metastasis upon admission and tumor grade were significantly associated with shorter survival (p = 0.037 and p < 0.01, respectively). Five-year recurrence-free survival was 71.5% (95% CI 57.6%; 88.7%). Tumor resection margins and metastatic disease upon diagnosis were significantly associated with recurrence-free survival (p < 0.01 and p < 0.01, respectively). CONCLUSION: Surgical therapy is the cornerstone of the treatment of chest wall sarcomas and can be performed safely. Metastasis and high tumor grade have a negative influence on overall survival, while tumor margins and metastasis have a negative influence on local recurrence.

[Lung Cancer Surgery for Severe COPD with Emphysema: Tumor Resection with Improvement of Lung Function]. / Lungenkrebschirurgie bei schwerer COPD mit Emphysem: Tumorresektion mit Verbesserung der Lungenfunktion.

Lung Cancer Surgery for Severe COPD with Emphysema: Tumor Resection with Improvement of Lung Function Abstract. The golden standard for the therapy of early stage non-small cell lung cancer consists of surgical resection, usually performed as lobectomy or segmentectomy. These procedures demand a certain operability, including certain lung functional reserves. Patients with COPD and emphysema usually have lung function values far below that. Nevertheless, these patients can be offered treatmentif at the same time they qualify for concomitant lung volume reduction surgery (LVRS). LVRS with simultaneous tumor resection can consolidate the diagnosis, provide definite histology, correct staging, and thorough tumor resection might even improve the postoperative lung function. As with all patients with a (possible) diagnosis of cancer, the indication must be discussed in an interdiscplinary tumor board.

Surgical management of lung cancer during the COVID-19 pandemic - a narrative review and single-centre report.

The coronavirus disease 2019 (COVID-19) pandemic has had a severe impact on oncological and thoracic surgical practice worldwide. In many hospitals, the care of COVID-19 patients required a reduction of elective surgery, to avoid viral transmission within the hospital, and to save and preserve personnel and material resources. Cancer patients are more susceptible to severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection and are at an increased risk of a severe course of disease. In many patients with lung cancer, this risk is further increased owing to comorbidities, older age and a pre-existing lung disease. Surgical resection is an important part of the treatment in patients with early stage or locally advanced non-small cell lung cancer, but the treatment of these patients during the COVID-19 pandemic becomes a challenging balance between the risk of patient exposure to SARS-CoV-2 and the need to provide timely and adequate cancer treatment despite limited hospital capacities. This manuscript aims to provide an overview of the surgical treatment of lung cancer patients during the COVID-19 pandemic including the triage and prioritisation as well as the surgical approach, and our own experience with cancer surgery during the first pandemic wave. We furthermore aim to highlight the risk and potential consequences of delayed lung cancer treatment due to the deferral of surgery, screening appointments and follow-up visits. With much attention being diverted to COVID-19, it is important to retain awareness of cancer patients, maintain oncological surgery and avoid treatment delay during the pandemic.

The Swiss Approach - feasibility of a national low-dose CT lung cancer screening program.

BACKGROUND: Lung cancer is the leading cause of cancer-related deaths in Switzerland. Despite this, there is no lung cancer screening program in the country. In the United States, low-dose computed tomography (LDCT) lung cancer screening is partially established and endorsed by guidelines. Moreover, evidence is growing that screening reduces lung cancer-related mortality and this was recently shown in a large European randomized controlled trial. Implementation of a lung cancer screening program, however, is challenging and depends on many country-specific factors. The goal of this article is to outline a potential Swiss lung cancer screening program. FRAMEWORK: An exhaustive literature review on international screening models as well as interviews and site visits with international experts were initiated. Furthermore, workshops and interviews with national experts and stakeholders were conducted to share experiences and to establish the basis for a national Swiss lung cancer screening program. SCREENING APPROACH: General practitioners, pulmonologists and the media should be part of the recruitment process. Decentralisation of the screening might lead to a higher adherence rate. To reduce stigmatisation, the screening should be integrated in a "lung health check". Standardisation and a common quality level are mandatory. The PLCOm2012 risk calculation model with a threshold of 1.5% risk for developing cancer in the next six years should be used in addition to established inclusion criteria. Biennial screening is preferred. LUNG RADS and NELSON+ are applied as classification models for lung nodules. CONCLUSION: Based on data from recent studies, literature research, a health technology assessment, the information gained from this project and a pilot study the Swiss Interest Group for lung cancer screening (CH-LSIG) recommends the timely introduction of a systematic lung cancer screening program in Switzerland. The final decision is for the Swiss Cancer Screening Committee to make.

Lung Volume Reduction Surgery in Patients with Homogeneous Emphysema.

Randomized controlled trials have demonstrated that lung volume reduction surgery (LVRS) improves exercise capacity, lung function, and quality of life in patients with heterogenous emphysema on computed tomographic and perfusion scan. However, most patients have a nonheterogenous type of destruction. These patients, summarized under "homogeneous emphysema," may also benefit from LVRS as long they are severely hyperinflated, and adequate function is remaining with a diffusing capacity of the lungs for carbon monoxide greater than 20% and no pulmonary hypertension. Surgical mortality is low when patients are well selected.

Long-Term Outcomes of Cadaveric Lobar Lung Transplantation: An Important Surgical Option.

BACKGROUND: Cadaveric lobar lung transplantation (L-LTx) is developed to overcome donor-recipient size mismatch. Controversial short- and long-term outcomes following L-LTx have been reported compared to full-sized lung transplantation (F-LTx). This study reports long-term outcomes after L-LTx. METHODS: We reviewed patients undergoing lung transplantation (LTx) between 2000 and 2016. The decision to perform L-LTx was made based mainly on donor-recipient height discrepancy and visual assessment of donor lungs. Predicted donor-recipient total lung capacity (TLC) ratio was calculated more recently. Primary outcome was overall survival. RESULTS: In all, 370 bilateral LTx were performed during the study period, among those 250 (67%) underwent F-LTx and 120 (32%) underwent L-LTx, respectively. One- and 5-year survival rates were 85% vs. 90% and 53% vs. 63% for L-LTx and F-LTx, respectively (p = 0.16). Chronic lung allograft dysfunction (CLAD)-free survival at 5 years was 48% in L-LTx vs. 51% in F-LTx recipients (p = 0.89), respectively. Age, intraoperative extracorporeal membrane oxygenation (ECMO) use, intensive care unit (ICU) stay, and postoperative renal replacement therapy (RRT) were significant prognostic factors for survival using multivariate analysis. CONCLUSIONS: Overall survival and CLAD-free survival following L-LTx were comparable to F-LTx. Given the ongoing donor organ shortage, cadaveric L-LTx remains as an important resource in LTx.

Lymphovascular invasion is an independent prognostic factor for survival in pathologically proven N2 non-small cell lung cancer.

BACKGROUND: We aimed to analyse the nodal spread of our non-small cell lung cancer pN2 cohort according to tumour location, the possible implications of an unusual spreading pattern, and other factors influencing postoperative survival after anatomical lung resection. METHODS: In this retrospective observational study, clinical data was collected for 124 consecutive non-small cell lung cancer (NSCLC) patients with a pathological N2 (stage IIIA or B) undergoing anatomical lung resection at our institution between 2001 and 2010. Cox regression was used to analyse independent predictors of 5-year overall survival and recurrence-free survival. RESULTS: A total of 105 patients were included in the final analysis. Tumour location in the right upper lobe and middle lobe  was significantly more often associated with involvement of lymph node stations 2 and 4 than NSCLC in the right lower lobe (station 2: right upper vs right lower lobe, p = 0.001 and middle vs right lower lobe, p = 0.038; station 4: right upper vs right lower lobe, p<0.001 and middle vs right lower lobe, p = 0.056), while tumours in the right upper lobe showed significantly less involvement of stations 7 and 8 compared with right lower lobe tumours (station 7 p <0.001, station 8 p = 0.004). Left sided tumours in the upper lobe had significantly more involvement of station 5 compared to lower lobe tumours (p = 0.009). However, atypical lymphatic nodal zone involvement did not emerge as a significant predictor of survival. Lymphovascular invasion was the only independent prognostic factor for 5-year overall survival (hazard ratio [HR] 2.10, p = 0.015) and recurrence-free survival (HR 1.68, p = 0.049) when controlled for adjuvant therapy. CONCLUSION: Lymphovascular invasion was identified as the only independent prognostic factor for 5-year overall survival and recurrence-free survival in our pathologically proven N2 NSCLC cohort when controlled for adjuvant therapy. This study extends the current evidence of an adverse prognostic effect of lymphovascular invasion on a stage III population, confirms the adverse prognostic effect of lymphovascular invasion detected by immunohistochemistry, and thereby reveals another subgroup within the pN2 population with worse prognosis regarding 5-year overall survival and recurrence-free survival.  .

Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis.

OBJECTIVES: To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG). METHODS: Patients with histologically confirmed TET in the years 2000-2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance. RESULTS: 105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22-82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3-94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9-93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8-79.5). CONCLUSIONS: CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.