Automated thorax disease diagnosis using multi-branch residual attention network.

Chest X-ray (CXR) is an extensively utilized radiological modality for supporting the diagnosis of chest diseases. However, existing research approaches suffer from limitations in effectively integrating multi-scale CXR image features and are also hindered by imbalanced datasets. Therefore, there is a pressing need for further advancement in computer-aided diagnosis (CAD) of thoracic diseases. To tackle these challenges, we propose a multi-branch residual attention network (MBRANet) for thoracic disease diagnosis. MBRANet comprises three components. Firstly, to address the issue of inadequate extraction of spatial and positional information by the convolutional layer, a novel residual structure incorporating a coordinate attention (CA) module is proposed to extract features at multiple scales. Next, based on the concept of a Feature Pyramid Network (FPN), we perform multi-scale feature fusion in the following manner. Thirdly, we propose a novel Multi-Branch Feature Classifier (MFC) approach, which leverages the class-specific residual attention (CSRA) module for classification instead of relying solely on the fully connected layer. In addition, the designed BCEWithLabelSmoothing loss function improves the generalization ability and mitigates the problem of class imbalance by introducing a smoothing factor. We evaluated MBRANet on the ChestX-Ray14, CheXpert, MIMIC-CXR, and IU X-Ray datasets and achieved average AUCs of 0.841, 0.895, 0.805, and 0.745, respectively. Our method outperformed state-of-the-art baselines on these benchmark datasets.

Osteo-cartilaginous pain syndromes at the chest wall: results of costal cartilage excision.

Background: Various pathologies of the lower ribs may lead to potentially severe pain in a heterogenous group of patients. Costal cartilage excision (CCE) has been shown to result in durable pain relief in some patients. Even though literature is scarce, we reviewed our experience with surgically treated osteo-cartilaginous pain syndromes (OCPSs) of the chest wall. Methods: We performed a retrospective case series from two institutions including patients operated for OCPS from 2014 to 2022. Results: Our case series consists of 11 patients (72.7% female) with OCPS that were treated by CCE. The median age was 43.5±17.1 years. Body mass index (BMI) was 23.6±3.4 kg/m2 (range, 18.5-29.6). The interval between first symptoms and diagnosis was 2.6 years (range, 3-127). In 5 patients, symptoms started after preceding chest wall trauma. All but one case were unilateral with no significant predominance regarding the side (6 left/4 right/1 bilateral). Postoperative length of hospital stay was 2.3±0.6 days. There was no patient morbidity or mortality. At follow-up, OCPS related pain had ceased in 7 of 9 patients (78%). Two patients stated to have significantly less pain and two patients didn't have a follow-up. Conclusions: Our analysis indicates that CCE in OCPS is safe and has good long-term results.

[Surgery of old people-Thoracic surgery]. / Chirurgie des alten Menschen ­ Thoraxchirurgie.

Background: The incidence of a large number of diseases relevant to thoracic surgery increases with age; however, old age is still frequently considered a contraindication per se for curative interventions and extensive surgical procedures. Objective: Overview of the current relevant literature, derivation of recommendations for patient selection as well as preoperative, perioperative and postoperative optimization. Material and methods: Analysis of the current study situation. Results: Recent data show that for most thoracic diseases, age alone is not a reason to withhold surgical treatment. Much more important for the selection are comorbidities, frailty, malnutrition and cognitive impairment. A lobectomy or segmentectomy for stage I non-small cell lung cancer (NSCLC) in carefully selected octogenarians can provide acceptable to even comparably good short-term and long-term results as in younger patients. Selected > 75-year-old patients with stages II-IIIA NSCLC even benefit from adjuvant chemotherapy. With appropriate selection high-risk interventions, such as pneumonectomy in > 70-year-old patients and pulmonary endarterectomy in > 80-year-old patients can be performed without an increase in mortality rates. Even lung transplantation can lead to good long-term results in carefully selected > 70-year-old patients. Minimally invasive surgical techniques and nonintubated anesthesia contribute to risk reduction in marginal patients. Discussion: In thoracic surgery the biological age rather than the chronological age is decisive. In view of the increasingly older population, further studies are urgently needed to optimize patient selection, type of intervention, preoperative planning and postoperative treatment as well as the quality of life.

Value of peripheral blood circulating tumor cell detection in the diagnosis of thoracic diseases and the prediction of severity.

Circulating tumor cell (CTC) detection, as a noninvasive liquid biopsy method, has been used in the diagnosis, prognostic indication, and monitoring of a variety of cancers. In this study, we aimed to investigate whether CTC detection could be used in the early diagnosis and prediction of severity of thoracic diseases. We enrolled 168 thoracic disease patients, all of whom underwent pathological biopsy. Carcinoembryonic antigen (CEA) and neuron-specific enolase (NSE) measurement was also performed in 146 patients. There were 131 cases of malignant thoracic diseases and 37 cases of benign lesions. We detected CTCs in a 5 ml peripheral blood sample with the CTCBiopsy® system and analyzed the value of CTC count for predicting disease severity. Of 131 patients with a diagnosis of thoracic malignancy, CTCs were found in blood samples from 122 patients. However, only 2 out of 37 patients with benign thoracic disease had no detectable CTCs. There was no significant correlation between CTC count and benign and malignant lesions (P = 0.986). However, among 131 patients who had been diagnosed with malignant lesions, 33 had lymph node metastasis or distant metastasis. The presence of CTCs was significantly correlated with metastasis (P = 0.016 OR = 1.14). The area under the receiver operating characteristic (ROC) curve was 0.625 (95% confidence interval (CI), 0.519 to 0.730 P = 0.032). In addition, with stage IA1 as the cutoff, all patients were further divided into an early-stage group and a late-stage group. CTC count was significantly correlated with disease progression (P = 0.031 OR = 1.11), with an area under the curve (AUC) of 0.599 (95% CI, 0.506-0.692 P = 0.47). The sensitivity and specificity of CTC detection for the diagnosis of disease stage were 72.3% and 45.5%, respectively. In addition, the cutoff of 2.5 CTCs was the same when predicting disease metastasis and staging. Furthermore, the combination of CTC count, demographic characteristics and tumor markers had better predictive significance for disease staging. CTC count can effectively indicate the stages and metastasis of thoracic diseases, but it cannot differentiate benign and malignant diseases.

[Surgery of old people-Thoracic surgery]. / Chirurgie des alten Menschen ­ Thoraxchirurgie.

BACKGROUND: The incidence of a large number of diseases relevant to thoracic surgery increases with age; however, old age is still frequently considered a contraindication per se for curative interventions and extensive surgical procedures. OBJECTIVE: Overview of the current relevant literature, derivation of recommendations for patient selection as well as preoperative, perioperative and postoperative optimization. MATERIAL AND METHODS: Analysis of the current study situation. RESULTS: Recent data show that for most thoracic diseases, age alone is not a reason to withhold surgical treatment. Much more important for the selection are comorbidities, frailty, malnutrition and cognitive impairment. A lobectomy or segmentectomy for stage I non-small cell lung cancer (NSCLC) in carefully selected octogenarians can provide acceptable to even comparably good short-term and long-term results as in younger patients. Selected > 75-year-old patients with stages II-IIIA NSCLC even benefit from adjuvant chemotherapy. With appropriate selection high-risk interventions, such as pneumonectomy in > 70-year-old patients and pulmonary endarterectomy in > 80-year-old patients can be performed without an increase in mortality rates. Even lung transplantation can lead to good long-term results in carefully selected > 70-year-old patients. Minimally invasive surgical techniques and nonintubated anesthesia contribute to risk reduction in marginal patients. DISCUSSION: In thoracic surgery the biological age rather than the chronological age is decisive. In view of the increasingly older population, further studies are urgently needed to optimize patient selection, type of intervention, preoperative planning and postoperative treatment as well as the quality of life.

Spontaneous pneumomediastinum in a young adult female.

Spontaneous pneumomediastinum is characterized by the accumulation of air in the mediastinum with no identified cause. It is a rare and self-limiting condition. We report the case of a 32-year-old female patient with controlled bronchial asthma, who presented with spontaneous pneumomediastinum, with no precipitating event. The evolution is generally benign and the treatment is conservative. Symptomatic medication may be instituted.

Prospective evaluation of thoracic diseases using a compact flat-panel detector spiral computed tomographic scanner.

Objective: To prospectively evaluate the image quality and diagnostic performance of a compact flat-panel detector (FD) scanner for thoracic diseases compared to a clinical CT scanner. Materials and methods: The institutional review board approved this single-center prospective study, and all participants provided informed consent. From December 2020 to May 2021, 30 patients (mean age, 67.1 ± 8.3 years) underwent two same-day low-dose chest CT scans using clinical state-of-art and compact FDCT scanners. Image quality was assessed visually and quantitatively. Two readers evaluated the diagnostic performance for nodules, parenchymal opacifications, bronchiectasis, linear opacities, and pleural abnormalities in 40 paired CT scans. The other 20 paired CT scans were used to examine the agreement of semi-quantitative CT scoring regarding bronchiectasis, bronchiolitis, nodules, airspace consolidations, and cavities. Results: FDCT images had significantly lower visual image quality than clinical CT images (all p < 0.001). The two CT image sets showed no significant differences in signal-to-noise and contrast-to-noise ratios (56.8 ± 12.5 vs. 57.3 ± 15.2; p = 0.985 and 62.9 ± 11.7 vs. 60.7 ± 16.9; p = 0.615). The pooled sensitivity was comparable for nodules, parenchymal opacifications, linear opacities, and pleural abnormalities (p = 0.065-0.625), whereas the sensitivity was significantly lower in FDCT images than in clinical CT images for micronodules (p = 0.007) and bronchiectasis (p = 0.004). The specificity was mostly 1.0. Semi-quantitative CT scores were similar between the CT image sets (p > 0.05), and intraclass correlation coefficients were around 0.950 or higher, except for bronchiectasis (0.869). Conclusion: Compact FDCT images provided lower image quality but comparable diagnostic performance to clinical CT images for nodules, parenchymal opacifications, linear opacities, and pleural abnormalities.

HealthyGAN: Learning from Unannotated Medical Images to Detect Anomalies Associated with Human Disease.

Automated anomaly detection from medical images, such as MRIs and X-rays, can significantly reduce human effort in disease diagnosis. Owing to the complexity of modeling anomalies and the high cost of manual annotation by domain experts (e.g., radiologists), a typical technique in the current medical imaging literature has focused on deriving diagnostic models from healthy subjects only, assuming the model will detect the images from patients as outliers. However, in many real-world scenarios, unannotated datasets with a mix of both healthy and diseased individuals are abundant. Therefore, this paper poses the research question of how to improve unsupervised anomaly detection by utilizing (1) an unannotated set of mixed images, in addition to (2) the set of healthy images as being used in the literature. To answer the question, we propose HealthyGAN, a novel one-directional image-to-image translation method, which learns to translate the images from the mixed dataset to only healthy images. Being one-directional, HealthyGAN relaxes the requirement of cycle-consistency of existing unpaired image-to-image translation methods, which is unattainable with mixed unannotated data. Once the translation is learned, we generate a difference map for any given image by subtracting its translated output. Regions of significant responses in the difference map correspond to potential anomalies (if any). Our HealthyGAN outperforms the conventional state-of-the-art methods by significant margins on two publicly available datasets: COVID-19 and NIH ChestX-ray14, and one institutional dataset collected from Mayo Clinic. The implementation is publicly available at https://github.com/mahfuzmohammad/HealthyGAN.

Clinical Features and Survival Outcome of Early-Stage Primary Pulmonary MALT Lymphoma After Surgical Treatment.

Background: We aimed to study the clinical features and survival outcomes of patients with early-stage primary pulmonary mucosa-associated lymphoid tissue (MALT) lymphoma who underwent surgery. Methods: This is a retrospective, single-center study including 32 patients with early-stage primary pulmonary MALT lymphoma. Univariate and multivariate Cox analyses were performed to select independent prognostic factors. The overall survival (OS) was analyzed by the Kaplan-Meier method and was compared with the log-rank test. Results: Among the 32 patients included, there were 16 men (50.0%) and 16 women (50.0%). The average age was 59.2 years old. Ten patients had non-specific clinical symptoms including cough, expectoration, and chest pain, and four patients had B symptoms. CT images are not specific and can be shown as peripheral, central, solid, and ground glass but more peripheral (93.8%) and solid (75.0%). In prognostic analysis, univariate analysis showed that tumor stage and size were associated with relapse-free survival (RFS) and OS [hazard ratio (HR) = 1.105, 95% CI: 1.021-1.197, P = 0.011; HR = 1.211, 95% CI: 1.158-1.968, P = 0.003, respectively]. It seems to indicate that higher stage and larger size indicate a worse prognosis, but we could not find statistically significant predictors in multivariate analysis. Sublobectomy was performed in 21 (65.6) cases, lobectomy was performed in the other 11 (34.4) cases, both of them can achieve good prognosis (5-year RFS and OS are both 100%), and there is no significant difference between them. Conclusions: The clinical manifestation of early-stage primary pulmonary MALT lymphoma is not significantly specific, and surgical resection is an effective treatment.

A novel augmented deep transfer learning for classification of COVID-19 and other thoracic diseases from X-rays.

Deep learning has provided numerous breakthroughs in natural imaging tasks. However, its successful application to medical images is severely handicapped with the limited amount of annotated training data. Transfer learning is commonly adopted for the medical imaging tasks. However, a large covariant shift between the source domain of natural images and target domain of medical images results in poor transfer learning. Moreover, scarcity of annotated data for the medical imaging tasks causes further problems for effective transfer learning. To address these problems, we develop an augmented ensemble transfer learning technique that leads to significant performance gain over the conventional transfer learning. Our technique uses an ensemble of deep learning models, where the architecture of each network is modified with extra layers to account for dimensionality change between the images of source and target data domains. Moreover, the model is hierarchically tuned to the target domain with augmented training data. Along with the network ensemble, we also utilize an ensemble of dictionaries that are based on features extracted from the augmented models. The dictionary ensemble provides an additional performance boost to our method. We first establish the effectiveness of our technique with the challenging ChestXray-14 radiography data set. Our experimental results show more than 50% reduction in the error rate with our method as compared to the baseline transfer learning technique. We then apply our technique to a recent COVID-19 data set for binary and multi-class classification tasks. Our technique achieves 99.49% accuracy for the binary classification, and 99.24% for multi-class classification.

Triple attention learning for classification of 14 thoracic diseases using chest radiography.

Chest X-ray is the most common radiology examinations for the diagnosis of thoracic diseases. However, due to the complexity of pathological abnormalities and lack of detailed annotation of those abnormalities, computer-aided diagnosis (CAD) of thoracic diseases remains challenging. In this paper, we propose the triple-attention learning (A 3 Net) model for this CAD task. This model uses the pre-trained DenseNet-121 as the backbone network for feature extraction, and integrates three attention modules in a unified framework for channel-wise, element-wise, and scale-wise attention learning. Specifically, the channel-wise attention prompts the deep model to emphasize the discriminative channels of feature maps; the element-wise attention enables the deep model to focus on the regions of pathological abnormalities; the scale-wise attention facilitates the deep model to recalibrate the feature maps at different scales. The proposed model has been evaluated on 112,120images in the ChestX-ray14 dataset with the official patient-level data split. Compared to state-of-the-art deep learning models, our model achieves the highest per-class AUC in classifying 13 out of 14 thoracic diseases and the highest average per-class AUC of 0.826 over 14 thoracic diseases.

Non-intubated video-assisted thoracoscopic surgery vs. intubated video-assisted thoracoscopic surgery for thoracic disease: a systematic review and meta-analysis of 1,684 cases.

BACKGROUND: Non-intubated video-assisted thoracoscopic surgery (NIVATS) has been increasingly used in lobectomy, bullectomy, wedge resection, lung volume reduction, sympathectomy and talc pleurodesis, which may reduce postoperative complications. However, the benefits of non-intubated and intubated methods of VATS remain controversial. METHODS: We comprehensively searched PubMed, Web of Science, Embase and the Cochrane Library, and performed a systematic review to assess the two techniques. Random and fixed-effects meta-analytical models were used based on the low between-study heterogeneity. Study quality, publication bias, and heterogeneity were assessed. RESULTS: Compared to intubated methods, NIVATS had a lower postoperative complications rate [odds ratio (OR): 0.63; 95% confidence interval (CI), 0.46-0.86; P<0.01], shorter global in-operating time [weighted mean difference (WMD): -35.96 min; 95% CI, -48.00 to -23.91; P<0.01], shorter hospital stay (WMD: -1.35 days; 95% CI, -1.72 to -0.98; P<0.01), shorter anesthesia time (WMD: -7.29 min; 95% CI, -13.30 to -1.29; P<0.01), shorter chest-tube placement time (WMD: -1.04 days; 95% CI, -1.75 to -0.33; P<0.01), less chest pain (WMD: -1.31; 95% CI, -2.45 to -0.17; P<0.05) and lower perioperative mortality rate (OR: 0.13; 95% CI, 0.02-0.99; P=0.05). CONCLUSIONS: NIVATS is a safe, efficient and feasible technique for thoracic surgery and may be a better alternative procedure owing to its advantage in reducing postoperative complications rate, hospital stay, and chest pain.

SDFN: Segmentation-based deep fusion network for thoracic disease classification in chest X-ray images.

This study aims to automatically diagnose thoracic diseases depicted on the chest x-ray (CXR) images using deep convolutional neural networks. The existing methods generally used the entire CXR images for training purposes, but this strategy may suffer from two drawbacks. First, potential misalignment or the existence of irrelevant objects in the entire CXR images may cause unnecessary noise and thus limit the network performance. Second, the relatively low image resolution caused by the resizing operation, which is a common pre-processing procedure for training neural networks, may lead to the loss of image details, making it difficult to detect pathologies with small lesion regions. To address these issues, we present a novel method termed as segmentation-based deep fusion network (SDFN), which leverages the domain knowledge and the higher-resolution information of local lung regions. Specifically, the local lung regions were identified and cropped by the Lung Region Generator (LRG). Two CNN-based classification models were then used as feature extractors to obtain the discriminative features of the entire CXR images and the cropped lung region images. Lastly, the obtained features were fused by the feature fusion module for disease classification. Evaluated by the NIH benchmark split on the Chest X-ray 14 Dataset, our experimental result demonstrated that the developed method achieved more accurate disease classification compared with the available approaches via the receiver operating characteristic (ROC) analyses. It was also found that the SDFN could localize the lesion regions more precisely as compared to the traditional method.

Diagnostic value and safety of color doppler ultrasound-guided transthoracic core needle biopsy of thoracic disease.

Objective: The aim of the present study was to explore the diagnostic value and safety of color Doppler ultrasound (US)-guided transthoracic core needle biopsy (CNB) of peripheral lung, chest wall and mediastinal lesions using automated biopsy guns.Materials and methods: We analyzed clinical and image data, histopathologic and microbiologic details and complications from 121 patients with peripheral lung, chest wall and mediastinal lesions who underwent color Doppler US-guided transthoracic CNB in Ningbo First Hospital between January 2015 and June 2018.Results: Color Doppler US-guided transthoracic CNB performed with a freehand technique using automated biopsy guns had a sensitivity of 93.94%, a specificity of 100%, a positive predictive value of 100%, a negative predictive value of 78.57%, and a diagnostic accuracy of 95.04%. Lesion size did not affect the diagnostic rate (P=0.40). No serious complications of the procedure were noted.Conclusion: Color Doppler US-guided transthoracic CNB of peripheral lung, chest wall and mediastinal lesions is a safe and inexpensive procedure. The diagnostic accuracy of color Doppler US-guided transthoracic CNB was higher than that of color Doppler US-guided transthoracic fine needle aspiration biopsy (FNAB).

Low Levels of PaO2 after Long-term Noninvasive Ventilation are a Poor Prognostic Factor in Patients with Restrictive Thoracic Disease.

Objective The effects of partial pressure of arterial oxygen (PaO2) after introducing long-term noninvasive ventilation (NIV) on the prognosis of patients with restrictive thoracic disease and chronic respiratory failure are not exactly known. Methods Data from 141 patients with restrictive thoracic disease under long-term nocturnal NIV were retrospectively examined. We divided the patients into 2 groups according to the daytime PaO2 value while breathing spontaneously with prescribed oxygen at 12 months after introducing NIV: PaO2≥80 Torr group (n=76) and PaO2<80 Torr group (n=65). Results During the 4-year follow-up, the mortality was significantly higher in the PaO2<80 Torr group than in the PaO2≥80 Torr group (50.8% vs. 32.9%, p=0.03). Independent factors associated with the 4-year mortality after introducing NIV determined by a multivariate logistic regression analysis were a low body mass index [odds ratio (OR) 0.87; 95% confidence interval (CI) 0.77 to 0.97; p=0.01], assisted mode with NIV (OR 4.11; 95% CI, 1.79 to 9.45; p=0.0009), hospitalization during the first year of introducing NIV (OR 1.72; 95% CI, 1.06 to 2.79; p=0.03), and daytime PaO2<80 Torr at 12 months after introducing NIV (OR 2.30; 95% CI, 1.03 to 5.10; p=0.04). Conclusion A low daytime PaO2 at 12 months after introducing NIV was an independent risk factor for mortality. Keeping the daytime PaO2≥80 Torr through the adjustment of the nocturnal NIV settings or increased diurnal supplemental oxygen may help improve the prognosis in patients with restrictive thoracic disease who are under NIV.

Thoracic Diseases With Musculoskeletal Manifestations and Vice Versa: A Review.

OBJECTIVE: The purpose of this article is to review several thoracic conditions that are associated with certain musculoskeletal radiological abnormalities using imaging of patients with concomitant chest and musculoskeletal manifestations as illustrative examples. CONCLUSION: Radiologic findings of many thoracic diseases are often nonspecific. When standing alone, their interpretation commonly results in long differential diagnosis. However, in certain instances, a reasonably accurate diagnosis can be made based on imaging findings alone.

[Thoracic endometriosis complicated with pneumopericard and iterative pneumothorax due to bullous dystrophy]. / Endométriose thoracique compliquée de pneumopéricarde et pneumothorax itératifs sur dystrophie bulleuse.

Thoracic endometriosis is a rare entity characterized by presence of endometrial tissue in pleura, lung parenchyma or airways. Most frequent manifestations are catamenial pneumothorax, hemothorax, hemoptysis and pulmonary nodules. We report here a rare case of a woman with thoracic endometriosis who developed iterative pneumothorax and pneumopericardium on bilateral bullous pulmonary dystrophy. She was a 37-year-old woman without any tobacco exposure and with previous history of pleural tuberculosis treated 5 years earlier. She was first referred to our centre for right pleuro-pneumothorax and hemorrhagic ascites. Pleural fluid examinations did not show any tuberculosis relapse, the evolution was favorable after thoracic drainage and there was no parenchymal lung abnormality on CT scan after surgery. Celioscopic peritoneal examination revealed stage IV peritoneal endometriosis. One year later, she was admitted for left catamenial pneumothorax. Thoracic CT scan showed apparition of large subpleural bulla. She underwent thoracotomy for bulla resection and left partial pleurectomy. Two years later, she was hospitalized for right pneumothorax and compressive pneumopericardium. Surgical lung biopsies confirmed pleuropulmonary endometriosis. Thoracotomy was performed for talcage pleurodesis and diaphragmatic leakages sutures. Lung bulla are rare in thoracic endometriosis, mechanism of their formation remains unknown. Pericardial involvement is rare in endometriosis; we report here a unique case of pneumopericardium.

Pulmonary Hypertension and Its Response to Treatment in a Patient with Kyphosis-related Alveolar Hypoventilation.

Pulmonary hypertension (PH) with kyphoscoliosis-related alveolar hypoventilation is uncommon, so little is known about the effectiveness of treatments for this condition. A 66-year-old man with kyphosis who had been treated with nocturnal noninvasive positive-pressure ventilation developed PH with a mean pulmonary arterial pressure (PAP) of 32 mmHg and a pulmonary vascular resistance (PVR) of 5.95 Wood units. After addition of oxygen therapy and tadalafil, his condition improved. One year later, his mean PAP and PVR were 25 mmHg and 3.62 Wood units, respectively. This case shows the therapeutic potential of vasoactive medications for alveolar hypoventilation-related PH.

Three-dimensional versus two-dimensional video-assisted thoracic surgery for thoracic disease: a meta-analysis.

OBJECTIVES: It remains unclear whether 3D systems are manoeuvrable in video-assisted thoracic surgery (VATS) for patients with thoracic diseases. The objective of this systematic review and meta-analysis was to evaluate the efficacy and safety of 3D VATS compared with 2D VATS. METHODS: A systemic research of the literature was performed using the PubMed, Embase, the Cochrane library, China National Knowledge Infrastructure, Wanfang and CQVIP databases through December 2016. Studies investigating the efficacy and safety of 3D VATS compared with 2D VATS were eligible for our meta-analysis. Odds ratios and mean differences or standard mean differences with 95% confidence intervals (95% CI) as well as a P-value were applied to compare continuous and dichotomous variables, respectively. RESULTS: Seven studies with 1080 patients (525 patients for 3D VATS and 555 patients for 2D VATS) were included. There were significant differences in the 3D group with regard to shorter operation times (standard mean difference = -0.66, 95% CI: -0.98 to - 0.34; P < 0.001), less blood loss (mean difference = -12.12, 95% CI: -19.07 to - 5.16; P < 0.001) and shorter postoperative drainage times (standard mean difference = -0.53, 95% CI: -0.92 to - 0.14; P = 0.008) compared with the 2D group. However, no statistical difference was found for postoperative hospital stay, total postoperative drainage volume, postoperative drainage volume in 24 h, number of lymph nodes dissected and postoperative complications. CONCLUSIONS: The results of this systematic review and meta-analysis suggest that 3D VATS might be an acceptable method for treating thoracic diseases in the future.

How to design a randomized clinical trial: tips and tricks for conduct a successful study in thoracic disease domain.

Randomized controlled trials (RCTs) are considered one of the highest level of evidence in clinical practice, due to their strong confidence and robustness in producing data. The "randomization" (e.g., allocating patients randomly in each group of the study) allows eliminating many pre-analytical differences that might bias the entire study. Nevertheless, RCTs aren't free of internal pitfalls that might make them not easy to be developed or utilized. Our objective is to explain RCT management difficulties and suggest certain tips useful for the design of a RCT in thoracic disease domain. In particular have a realistic timeline, define a clear objective and precise endpoints, balance the study with a correct randomization and focus on the right equilibrium between strict selection criteria and more heterogeneous parameters are key elements that help researchers assuring a strong scientific validity.