The adenocarcinoma-specific stage shift in the Anti-lung Cancer Association project: Significance of repeated screening for lung cancer for more than 5 years with low-dose helical computed tomography in a high-risk cohort

Three-Dimensional Texture Feature Analysis of Pulmonary Nodules in CT Images: Lung Cancer Predictive Models Based on Support Vector Machine Classifier

To extract texture features of pulmonary nodules from three-dimensional views and to assess if predictive models of lung CT images from a three-dimensional texture feature could improve assessments conducted by radiologists. Clinical and CT imaging data for three dimensions (axial, coronal, and sagittal) in pulmonary nodules in 285 patients were collected from multiple centers and the Cancer Imaging Archive after ethics committee approval. Three-dimensional texture feature values (contourlets), and clinical and computed tomography (CT) imaging data were built into support vector machine (SVM) models to predict lung cancer, using four evaluation methods (disjunctive, conjunctive, voting, and synthetic); sensitivity, specificity, the Youden index, discriminant power (DP), and F value were calculated to assess model effectiveness. Additionally, diagnostic accuracy (three-dimensional model, axial model, and radiologist assessment) was assessed using the area under the curves for receiver operating characteristic (ROC) curves. Cross-sectional data from 285 patients (median age, 62 [range, 45-83] years; 115 males [40.4%]) were evaluated. Integrating three-dimensional assessments, the voting method had relatively high effectiveness based on both sensitivity (0.98) and specificity (0.79), which could improve radiologist diagnosis (maximum sensitivity, 0.75; maximum specificity, 0.51) for 23% and 28% respectively. Furthermore, the three-dimensional texture feature model of the voting method has the best diagnosis of precision rate (95.4%). Of all three-dimensional texture feature methods, the result of the voting method was the best, maintaining both high sensitivity and specificity scores. Additionally, the three-dimensional texture feature models were superior to two-dimensional models and radiologist-based assessments.

Estimation of malignancy of pulmonary nodules at CT scans: Effect of computer-aided diagnosis on diagnostic performance of radiologists

OBJECTIVES

To develop a computer-aided diagnosis (CAD) system for distinguishing malignant from benign pulmonary nodules on computed tomography (CT) scans, and to assess whether the diagnostic performance of radiologists with different experiences can be improved with the assistant of CAD.

MATERIALS AND METHODS

A total of 857 malignant nodules from 601 patients and 426 benign nodules from 278 patients were retrospectively collected from four hospitals. In this study, we exploited convolutional neural network in the framework of deep learning to classify whether a nodule was benign or malignant. A total of 745 malignant nodules and 370 benign nodules were used as the training data of our CAD system. The remaining 112 malignant nodules and 56 benign nodules were used as the test data. The participants were two senior chest radiologists, two secondary chest radiologists, and two junior radiology residents. The readers estimated the likelihood of malignancy of pulmonary nodules first without and then with CAD output. Receiver-operating characteristic (ROC) curve was used to evaluate readers' diagnostic performance.

RESULTS

When a threshold level of 58% was used to estimate the likelihood of malignancy, the sensitivity, specificity, and diagnostic accuracy values of our CAD scheme alone were 93.8%, 83.9%, and 90.5%, respectively. For all six readers, the mean area under the ROC curve (A_z ) values without and with CAD system were 0.913 and 0.938, respectively. For each reader, there is a large difference in A_z values that assessed without and with CAD system. With CAD output, the readers made correct changes an average of 15.7 times and incorrect changes an average of 2 times.

CONCLUSION

Our CAD system significantly improved the diagnostic performance of readers regardless of their experience levels for assessment of the likelihood of malignancy of pulmonary nodules.

Can CT Screening Give Rise to a Beneficial Stage Shift in Lung Cancer Patients? Systematic Review and Meta-Analysis

Objectives

To portray the stage characteristics of lung cancers detected in CT screenings, and explore whether there’s universal stage superiority over other methods for various pathological types using available data worldwide in a meta-analysis approach.

Materials and Methods

EMBASE and MEDLINE were searched for studies on lung cancer CT screening in natural populations through July 2015 without language or other filters. Twenty-four studies (8 trials and 16 cohorts) involving 1875 CT-detected lung cancer patients were enrolled and assessed by QUADAS-2. Pathology-confirmed stage information was carefully extracted by two reviewers. Stage I or limited stage proportions were pooled by random effect model with Freeman-Tukey double arcsine transformation.

Results

Pooled stage I cancer proportion in CT screenings was 73.2% (95% confidence interval: 68.6%, 77.5%), with a significant rising trend (P_trend<0.05) from baseline (64.7%) to ≥5 repeat rounds (87.1%). Relative to chest radiograph and usual care, the increased stage I proportions in CT were 12.2% (P>0.05), and 46.5% (P<0.05), respectively. Pathology-specifically, adenocarcinomas (66%) and squamous cell lung cancers (17%) composed the majority of CT-detected lung cancers, and had significantly higher stage I proportions relative to chest radiograph (bronchioloalveolar adenocarcinomas, 80.9% vs 51.4%; other adenocarcinomas, 58.8% vs 38.3%; squamous cell lung cancers, 52.3% vs 38.3%; all P<0.05). However, the percentage of small cell lung cancer was lower using CT than other detection routes, and no significant difference in limited stage proportion was observed (6.8% vs 10.8%, P>0.05).

Conclusion

CT screening can detect more early stage non-small cell lung cancers, but not all of them could be beneficial as there are a considerable number of indolent ones such as bronchioloalveolar adenocarcinomas. Still, current evidence is lacking regarding small cell lung cancers.

Comparative evaluation of support vector machines for computer aided diagnosis of lung cancer in CT based on a multi-dimensional data set

Lung cancer is one of the most common forms of cancer resulting in over a million deaths per year worldwide. In this paper, the usage of support vector machine (SVM) classification for lung cancer is investigated, presenting a systematic quantitative evaluation against Boosting, Decision trees, k-nearest neighbor, LASSO regressions, neural networks and random forests. A large database of 5984 regions of interest (ROIs) and 488 input features (including textural features, patient characteristics, and morphological features) were used to train the classifiers and evaluate for their performance. The evaluation for classifiers' performance was based on a tenfold cross validation framework, receiver operating characteristic curve (ROC), and Matthews correlation coefficient. Area under curve (AUC) of SVM, Boosting, Decision trees, k-nearest neighbor, LASSO, neural networks, random forests were 0.94, 0.86, 0.73, 0.72, 0.91, 0.92, and 0.85, respectively. It was proved that SVM classification offered significantly increased classification performance compared to the reference methods. This scheme may be used as an auxiliary tool to differentiate between benign and malignant SPNs of CT images in future.

Prognostic impact of serum albumin levels on the recurrence of stage I non-small cell lung cancer

OBJECTIVE

Patients with stage I non-small cell lung cancer who have undergone complete surgical resection harbor a 30% risk for tumor recurrence. Thus, the identification of factors that are predictive for tumor recurrence is urgently needed. The aim of this study was to test the prognostic value of serum albumin levels on tumor recurrence in patients with stage I non-small cell lung cancer.

METHODS

Stage I non-small cell lung cancer patients who underwent complete surgical resection of the primary tumor at Zhejiang Hospital were analyzed in this study. Serum albumin levels were measured before surgery and once again after surgery in 101 histologically diagnosed non-small cell lung cancer patients. Correlations between the pre- and post-operative serum albumin levels and various clinical demographics and recurrence-free survival rates were analyzed.

RESULTS

Patients with pre-operative hypoalbuminemia (<3.5 g/dl) had a significantly worse survival rate than patients with normal pre-operative serum albumin levels (≥3.5 g/dl) (p=0.008). Patients with post-operative hypoalbuminemia had a worse survival rate when compared with patients with normal post-operative serum albumin levels (p=0.001). Cox multivariate analysis identified pre-operative hypoalbuminemia, post-operative hypoalbuminemia and tumor size over 3 cm as independent negative prognostic factors for recurrence.

CONCLUSION

Serum albumin levels appear to be a significant independent prognostic factor for tumor recurrence in patients with stage I non-small cell lung cancer who have undergone complete resection. Patient pre-treatment and post-treatment serum albumin levels provide an easy and early means of discrimination between patients with a higher risk for recurrence and patients with a low risk of recurrence.

[Comparative values of different imaging methods in lung cancer screening]

Radiology is the primary lung cancer screening technique. Whether the mortality rate of lung cancer could be markedly reduce by radiological screening was still unknown to us. It was suggested that high-risk individuals should take regular radiological examinations to detect early lung cancers, followed by suitable treatment. In this review, we compared the values of different radiological methods in lung cancer screening.

Bronchioloalveolar Carcinoma and Minimally Invasive Adenocarcinoma

The most recent WHO classification of lung cancer defines bronchioloalveolar carcinoma (BAC) as a noninvasive carcinoma or adenocarcinoma in situ. However, the use of this terminology is not uniform and does not reflect standardized criteria. As a result, the diagnosis of BAC has been used in association with small, solitary, and well-differentiated adenocarcinoma as well as tumors with advanced clinical stage. At present, there is a growing consensus among specialists in thoracic oncology that BAC or adenocarcinoma in situ is a rare tumor, and the term should be restricted to adenocarcinomas that show a pure lepidic pattern of growth. The amount of invasive component present in a tumor with a predominant lepidic growth pattern has also been under intense scrutiny. The concept of minimally invasive adenocarcinoma is developing in order to differentiate a pure BAC from an invasive adenocarcinoma that still carries an excellent prognosis.