Multi-kernel driven 3D convolutional neural network for automated detection of lung nodules in chest CT scans.

The accurate position detection of lung nodules is crucial in early chest computed tomography (CT)-based lung cancer screening, which helps to improve the survival rate of patients. Deep learning methodologies have shown impressive feature extraction ability in the CT image analysis task, but it is still a challenge to develop a robust nodule detection model due to the salient morphological heterogeneity of nodules and complex surrounding environment. In this study, a multi-kernel driven 3D convolutional neural network (MK-3DCNN) is proposed for computerized nodule detection in CT scans. In the MK-3DCNN, a residual learning-based encoder-decoder architecture is introduced to employ the multi-layer features of the deep model. Considering the various nodule sizes and shapes, a multi-kernel joint learning block is developed to capture 3D multi-scale spatial information of nodule CT images, and this is conducive to improving nodule detection performance. Furthermore, a multi-mode mixed pooling strategy is designed to replace the conventional single-mode pooling manner, and it reasonably integrates the max pooling, average pooling, and center cropping pooling operations to obtain more comprehensive nodule descriptions from complicated CT images. Experimental results on the public dataset LUNA16 illustrate that the proposed MK-3DCNN method achieves more competitive nodule detection performance compared to some state-of-the-art algorithms. The results on our constructed clinical dataset CQUCH-LND indicate that the MK-3DCNN has a good prospect in clinical practice.

Increased adipose tissue is associated with improved overall survival, independent of skeletal muscle mass in non-small cell lung cancer.

BACKGROUND: The prognostic significance of non-cancer-related prognostic factors, such as body composition, has gained extensive attention in oncological research. Compared with sarcopenia, the prognostic significance of adipose tissue for overall survival in non-small cell lung cancer remains unclear. We investigated the prognostic value of skeletal muscle and adipose tissue in patients with non-small cell lung cancer. METHODS: This retrospective study included 4434 patients diagnosed with non-small cell lung cancer between January 2014 and December 2016. Cross-sectional areas of skeletal muscle and subcutaneous fat were measured, and the pericardial fat volume was automatically calculated. The skeletal muscle index and subcutaneous fat index were calculated as skeletal muscle area and subcutaneous fat area divided by height squared, respectively, and the pericardial fat index was calculated as pericardial fat volume divided by body surface area. The association between body composition and outcomes was evaluated using Cox proportional hazards model. RESULTS: A total of 750 patients (501 males [66.8%] and 249 females [33.2%]; mean age, 60.9 ± 9.8 years) were included. Sarcopenia (60.8% vs. 52.7%; P < 0.001), decreased subcutaneous fat index (51.4% vs. 25.2%; P < 0.001) and decreased pericardial fat index (55.4% vs. 16.5%; P < 0.001) were more commonly found in the deceased group than survived group. In multivariable Cox regression analysis, after adjusting for clinical variables, increased subcutaneous fat index (hazard ratio [HR] = 0.56, 95% confidence interval [CI]: 0.47-0.66, P < 0.001) and increased pericardial fat index (HR = 0.47, 95% CI: 0.40-0.56, P < 0.001) were associated with longer overall survival. For stage I-III patients, increased subcutaneous fat index (HR = 0.62, 95% CI: 0.48-0.76, P < 0.001) and increased pericardial fat index (HR = 0.43, 95% CI: 0.34-0.54, P < 0.001) were associated with better 5-year overall survival rate. Similar results were recorded in stage IV patients. For patients with surgery, the prognostic value of increased subcutaneous fat index (HR = 0.60, 95% CI: 0.44-0.80, P = 0.001) and increased pericardial fat index (HR = 0.51, 95% CI: 0.38-0.68, P < 0.001) remained and predicted favourable overall survival. Non-surgical patients showed similar results as surgical patients. No association was noted between sarcopenia and overall survival (P > 0.05). CONCLUSIONS: Increased subcutaneous fat index and pericardial fat index were associated with a higher 5-year overall survival rate, independent of sarcopenia, in non-small cell lung cancer and may indicate a reduced risk of non-cancer-related death.

3D convolutional neural network model from contrast-enhanced CT to predict spread through air spaces in non-small cell lung cancer.

PURPOSE: The purpose of this study was to compare the efficacy of five non-invasive models, including three-dimensional (3D) convolutional neural network (CNN) model, to predict the spread through air spaces (STAS) status of non-small cell lung cancer (NSCLC), and to obtain the best prediction model to provide a basis for clinical surgery planning. MATERIALS AND METHODS: A total of 203 patients (112 men, 91 women; mean age, 60 years; age range 22-80 years) with NSCLC were retrospectively included. Of these, 153 were used for training cohort and 50 for validation cohort. According to the image biomarker standardization initiative reference manual, the image processing and feature extraction were standardized using PyRadiomics. The logistic regression classifier was used to build the model. Five models (clinicopathological/CT model, conventional radiomics model, computer vision (CV) model, 3D CNN model and combined model) were constructed to predict STAS by NSCLC. Area under the receiver operating characteristic curves (AUC) were used to validate the capability of the five models to predict STAS. RESULTS: For predicting STAS, the 3D CNN model was superior to the clinicopathological/CT model, conventional radiomics model, CV model and combined model and achieved satisfactory discrimination performance, with an AUC of 0.93 (95% CI: 0.70-0.82) in the training cohort and 0.80 (95% CI: 0.65-0.86) in the validation cohort. Decision curve analysis indicated that, when the probability of the threshold was over 10%, the 3D CNN model was beneficial for predicting STAS status compared to either treating all or treating none of the patients within certain ranges of risk threshold CONCLUSION: The 3D CNN model can be used for the preoperative prediction of STAS in patients with NSCLC, and was superior to the other four models in predicting patients' risk of developing STAS.

Development and Validation of a CT-Based Signature for the Prediction of Distant Metastasis Before Treatment of Non-Small Cell Lung Cancer.

RATIONALE AND OBJECTIVES: To develop and validate a radiomics model, a clinical-semantic model and a combined model by using standard methods for the pretreatment prediction of distant metastasis (DM) in patients with non-small-cell lung cancer (NSCLC) and to explore whether the combined model provides added value compared to the individual models. MATERIALS AND METHODS: This retrospective study involved 356 patients with NSCLC. According to the image biomarker standardization initiative reference manual, we standardized the image processing and feature extraction using in-house software. Finally, 6692 radiomics features were extracted from each lesion based on contrast-enhanced chest CT images. The least absolute shrinkage selection operator and the recursive feature elimination algorithm were used to select features. The logistic regression classifier was used to build the model. Three models (radiomics model, clinical-semantic model and combined model) were constructed to predict DM in NSCLC. Area under the receiver operating characteristic curves were used to validate the ability of the three models to predict DM. A visual nomogram based on the combined model was developed for DM risk assessment in each patient. RESULTS: The receiver operating characteristic curve showed predictive performance for DM of the radiomics model (area under the curve [AUC] values for training and validation were 0.76 [95% CI, 0.704 - 0.820] and 0.76 [95% CI, 0.653 - 0.858], respectively). The combined model had AUCs of 0.78 (95% CI, 0.723 - 0.835) and 0.77 (95% CI, 0.673 - 0.870) in the training and validation cohorts, respectively. Both the radiomics model and combined model performed better than the clinical-semantic model (0.70 [95% CI, 0.634 - 0.760] and 0.67 [95% CI, 0.554 - 0.787] in the training and validation cohorts, respectively). CONCLUSION: The radiomics model and combined model may be useful for the prediction of DM in patients with NSCLC.

An Image Study on Local Anesthetic Spread in Healthy Volunteers Receiving Subcostal Exterior Semilunaris Transversus Abdominis Plane (SE-TAP) Block.

BACKGROUND: Despite the popularity of the ultrasound-guided transversus abdominis plane (TAP) block and the diversity of advancing approaches, the extent of injectate spread limits its clinical benefits. This study used three-dimensional computed tomography (3D-CT) imaging and a cold stimulus to evaluate the spread of a local anesthetic injected through the subcostal exterior semilunaris to transversus abdominis plane (SE-TAP) block in healthy volunteers. METHODS: Eight healthy volunteers received a right-side ultrasound-guided SE-TAP block with 25 mL of 0.3% ropivacaine. The sensory block was assessed by a cold stimulus at 30 min, 2 h, 4 h, and 8 h following the SE-TAP block according to the 18-zone division method. A CT scan and 3D imaging were performed after the first sensory assessment. RESULTS: The injectate spread into the transversus abdominis space in all eight volunteers. 3D imaging confirmed that the injectate spread extensively along the costal margin in the plane of the transverse abdominis muscle and that it surpassed the semilunaris. Regarding the assessment using cold stimulus, five of six anterior zones and three of six lateral zones obtained successful rates of cutaneous sensory block higher than 75% 30 min after SE-TAP. Sensory block was achieved in the ventral dermatomes of all volunteers. CONCLUSION: Our study showed that the SE-TAP injectate, which was administered using simple anatomical landmarks to provide reliable analgesia for abdominal surgery, consistently spread along the costal margin and extensively blocked cutaneous sensitivity in the anterior and lateral abdominal walls.

FOXO1 and hsa-microRNA-204-5p affect the biologic behavior of MDA-MB-231 breast cancer cells.

RNA molecules and targeting microRNA (miRNA) have been reported as novel focuses in recent research on breast cancer. This study aimed to probe the expression of FOXO1 in the MDA-MB-231 cell line and to explore the target effects of FOXO1 with hsa-microRNA-204-5p (miR-204) on the biologic behavior of MDA-MB-231 cells. The expression of FOXO1 mRNA and protein in MDA-MB-231 cells were derived and verified from the public databases, literature, and experimental assays, then the downregulation of FOXO1 was confirmed in the MDA-MB-231 cell line. The target binding of FOXO1 and miR-204 was predicted by miRWalk and confirmed by luciferase reporter assays. MiR-204 targeted the 3' untranslated region of FOXO1 and reduced FOXO1 expression in miR-204-transfected cells, resulting in cell growth amplification but inhibition of cell migration and apoptosis, which were assessed using the MTT method, wound healing assays, and flow cytometry, respectively. The protein levels of serine-threonine kinase (AKT), c-jun N-terminal kinase (JNK), extracellular regulatory protein kinase (ERK), and the phosphorylated protein kinases (P-AKT, P-JNK, and P-ERK) were measured by western blot. It was found that AKT, JNK, and ERK remained constant, but P-AKT, P-JNK, and P-ERK were upregulated after miR-204 transfection. In summary, the expression of FOXO1 was downregulated in MDA-MB-231 cells; and the target binding of miR-204 and FOXO1 affected phosphatidylinositol 3-kinase (PI3K)/AKT and mitogen-activated protein kinase (MAPK) signal pathways, leading to different alterations of cellular activity in MDA-MB-231 cells.

Downregulation of hsa-microRNA-204-5p and identification of its potential regulatory network in non-small cell lung cancer: RT-qPCR, bioinformatic- and meta-analyses.

BACKGROUND: Pulmonary malignant neoplasms have a high worldwide morbidity and mortality, so the study of these malignancies using microRNAs (miRNAs) has attracted great interest and enthusiasm. The aim of this study was to determine the clinical effect of hsa-microRNA-204-5p (miR-204-5p) and its underlying molecular mechanisms in non-small cell lung cancer (NSCLC). METHODS: Expression of miR-204-5p was investigated by real-time quantitative PCR (RT-qPCR). After data mining from public online repositories, several integrative assessment methods, including receiver operating characteristic (ROC) curves, hazard ratios (HR) with 95% confidence intervals (95% CI), and comprehensive meta-analyses, were conducted to explore the expression and clinical utility of miR-204-5p. The potential objects regulated and controlled by miR-204-5p in the course of NSCLC were identified by estimated target prediction and analysis. The regulatory network of miR-204-5p, with its target genes and transcription factors (TFs), was structured from database evidence and literature references. RESULTS: The expression of miR-204-5p was downregulated in NSCLC, and the downtrend was related to gender, histological type, vascular invasion, tumor size, clinicopathologic grade and lymph node metastasis (P<0.05). MiR-204-5p was useful in prognosis, but was deemed unsuitable at present as an auxiliary diagnostic or prognostic risk factor for NSCLC due to the lack of statistical significance in meta-analyses and absence of large-scale investigations. Gene enrichment and annotation analyses identified miR-204-5p candidate targets that took part in various genetic activities and biological functions. The predicted TFs, like MAX, MYC, and RUNX1, interfered in regulatory networks involving miR-204-5p and its predicted hub genes, though a modulatory loop or axis of the miRNA-TF-gene that was out of range with shortage in database prediction, experimental proof and literature confirmation. CONCLUSIONS: The frequently observed decrease in miR-204-5p was helpful for NSCLC diagnosis. The estimated target genes and TFs contributed to the anti-oncogene effects of miR-204-5p.