Quantitative Computed Tomography Classification of Lung Nodules: Initial Comparison of 2- and 3-Dimensional Analysis

Vascular Biomarkers for Pulmonary Nodule Malignancy: Arteries vs. Veins

OBJECTIVE

This study aims to investigate the association between the arteries and veins surrounding a pulmonary nodule and its malignancy.

METHODS

A dataset of 146 subjects from a LDCT lung cancer screening program was used in this study. AI algorithms were used to automatically segment and quantify nodules and their surrounding macro-vasculature. The macro-vasculature was differentiated into arteries and veins. Vessel branch count, volume, and tortuosity were quantified for arteries and veins at different distances from the nodule surface. Univariate and multivariate logistic regression (LR) analyses were performed, with a special emphasis on the nodules with diameters ranging from 8 to 20 mm. ROC-AUC was used to assess the performance based on the k-fold cross-validation method. Average feature importance was evaluated in several machine learning models.

RESULTS

The LR models using macro-vasculature features achieved an AUC of 0.78 (95% CI: 0.71-0.86) for all nodules and an AUC of 0.67 (95% CI: 0.54-0.80) for nodules between 8-20 mm. Models including macro-vasculature features, demographics, and CT-derived nodule features yielded an AUC of 0.91 (95% CI: 0.87-0.96) for all nodules and an AUC of 0.82 (95% CI: 0.71-0.92) for nodules between 8-20 mm. In terms of feature importance, arteries within 5.0 mm from the nodule surface were the highest-ranked among macro-vasculature features and retained their significance even with the inclusion of demographics and CT-derived nodule features.

CONCLUSIONS

Arteries within 5.0 mm from the nodule surface emerged as a potential biomarker for effectively discriminating between malignant and benign nodules.

Thyroid Nodule Classification for Physician Decision Support Using Machine Learning-Evaluated Geometric and Morphological Features

The classification of thyroid nodules using ultrasound (US) imaging is done using the Thyroid Imaging Reporting and Data System (TIRADS) guidelines that classify nodules based on visual and textural characteristics. These are composition, shape, size, echogenicity, calcifications, margins, and vascularity. This work aims to reduce subjectivity in the current diagnostic process by using geometric and morphological (G-M) features that represent the visual characteristics of thyroid nodules to provide physicians with decision support. A total of 27 G-M features were extracted from images obtained from an open-access US thyroid nodule image database. 11 significant features in accordance with TIRADS were selected from this global feature set. Each feature was labeled (0 = benign and 1 = malignant) and the performance of the selected features was evaluated using machine learning (ML). G-M features together with ML resulted in the classification of thyroid nodules with a high accuracy, sensitivity and specificity. The results obtained here were compared against state-of the-art methods and perform significantly well in comparison. Furthermore, this method can act as a computer aided diagnostic (CAD) system for physicians by providing them with a validation of the TIRADS visual characteristics used for the classification of thyroid nodules in US images.

Low-Dose CT Screening for Lung Cancer: Evidence from 2 Decades of Study

Lung cancer remains the overwhelmingly greatest cause of cancer death in the United States, accounting for more annual deaths than breast, prostate, and colon cancer combined. Accumulated evidence since the mid to late 1990s, however, indicates that low-dose CT screening of high-risk patients enables detection of lung cancer at an early stage and can reduce the risk of dying from lung cancer. CT screening is now a recommended clinical service in the United States, subject to guidelines and reimbursement requirements intended to standardize practice and optimize the balance of benefits and risks. In this review, the evidence on the effectiveness of CT screening will be summarized and the current guidelines and standards will be described in the context of knowledge gained from lung cancer screening studies. In addition, an overview of the potential advances that may improve CT screening will be presented, and the need to better understand the performance in clinical practice outside of the research trial setting will be discussed. © RSNA, 2020.

Computerized identification of the vasculature surrounding a pulmonary nodule

OBJECTIVES

The idea of inferring the prognosis of lung tumor via its surrounding vasculature is novel, but not supported by available technology. In this study, we described and validated a computerized method to identify the vasculature surrounding a pulmonary nodule depicted on low-dose computed tomography (LDCT).

MATERIALS AND METHODS

The proposed computerized scheme identified the vessels surrounding a lung nodule by using novel computational geometric solutions and quantified them by decomposing the vessels into independent vessel branches. We validated this scheme by testing it on a dataset consisting of 100 chest CT examinations, with 50-paired benign and malignant nodules. Two experienced pulmonologists were asked to measure the vessel branches associated with a nodule under the aid of a visualization tool. We used the Bland-Altman plots and the concordance correlation coefficient (CCC) to assess the agreement between the results of the computer algorithm and two experienced pulmonologists.

RESULTS

Bland-Altman different analysis demonstrated a mean bias of 0.61 ± 4.17 in terms of vessel branches between the computer results and the human experts, while the inter-rater mean bias was -0.61 ± 1.60. The CCC-based agreements between the computer and the two raters were 0.90 / 0.86, 0.79 / 0.83 for benign and malignant nodules, respectively.

CONCLUSION

The small width of the limits of agreement between the computer algorithm and the human experts suggests that the results from the computer and the pulmonologist experts were relatively consistent, namely the computerized scheme is capable of reliably identifying the vasculature surrounding a nodule.

Computer-Aided Detection of Pulmonary Nodules in Computed Tomography Using ClearReadCT

This study evaluates the accuracy of a computer-aided detection (CAD) application for pulmonary nodular lesions (PNL) in computed tomography (CT) scans, the ClearReadCT (Riverain Technologies). The study was retrospective for 106 biopsied PNLs from 100 patients. Seventy-five scans were Contrast-Enhanced (CECT) and 25 received no enhancer (NECT). Axial reconstructions in soft-tissue and lung kernel were applied at three different slice thicknesses, 0.75 mm (CECT/NECT n = 25/6), 1.5 mm (n = 18/9) and 3.0 mm (n = 43/18). We questioned the effect of (1) enhancer, (2) kernel and (3) slice thickness on the CAD performance. Our main findings are: (1) Vessel suppression is effective and specific in both NECT and CECT. (2) Contrast enhancement significantly increased the CAD sensitivity from 60% in NECT to 80% in CECT, P = 0.025 Fischer's exact test. (3) The CAD sensitivity was 84% in 3 mm slices compared to 68% in 0.75 mm slices, P > 0.2 Fischer's exact test. (4) Small lesions of low attenuation were detected with higher sensitivity. (5) Lung kernel reconstructions increased the false positive rate without affecting the sensitivity (P > 0.05 McNemar's test). In conclusion, ClearReadCT showed an optimized sensitivity of 84% and a positive predictive value of 67% in enhanced lung scans with thick, soft kernel reconstructions. NECT, thin slices and lung kernel reconstruction were associated with inferior performance.

An Appraisal of Lung Nodules Automatic Classification Algorithms for CT Images

Lung cancer is one of the most deadly diseases around the world representing about 26% of all cancers in 2017. The five-year cure rate is only 18% despite great progress in recent diagnosis and treatment. Before diagnosis, lung nodule classification is a key step, especially since automatic classification can help clinicians by providing a valuable opinion. Modern computer vision and machine learning technologies allow very fast and reliable CT image classification. This research area has become very hot for its high efficiency and labor saving. The paper aims to draw a systematic review of the state of the art of automatic classification of lung nodules. This research paper covers published works selected from the Web of Science, IEEEXplore, and DBLP databases up to June 2018. Each paper is critically reviewed based on objective, methodology, research dataset, and performance evaluation. Mainstream algorithms are conveyed and generic structures are summarized. Our work reveals that lung nodule classification based on deep learning becomes dominant for its excellent performance. It is concluded that the consistency of the research objective and integration of data deserves more attention. Moreover, collaborative works among developers, clinicians, and other parties should be strengthened.

Highly accurate model for prediction of lung nodule malignancy with CT scans

Computed tomography (CT) examinations are commonly used to predict lung nodule malignancy in patients, which are shown to improve noninvasive early diagnosis of lung cancer. It remains challenging for computational approaches to achieve performance comparable to experienced radiologists. Here we present NoduleX, a systematic approach to predict lung nodule malignancy from CT data, based on deep learning convolutional neural networks (CNN). For training and validation, we analyze >1000 lung nodules in images from the LIDC/IDRI cohort. All nodules were identified and classified by four experienced thoracic radiologists who participated in the LIDC project. NoduleX achieves high accuracy for nodule malignancy classification, with an AUC of ~0.99. This is commensurate with the analysis of the dataset by experienced radiologists. Our approach, NoduleX, provides an effective framework for highly accurate nodule malignancy prediction with the model trained on a large patient population. Our results are replicable with software available at http://bioinformatics.astate.edu/NoduleX .

Quality assurance and quantitative imaging biomarkers in low-dose CT lung cancer screening

After years of assessment through controlled clinical trials, low-dose CT screening for lung cancer is becoming part of clinical practice. As with any cancer screening test, those undergoing lung cancer screening are not being evaluated for concerning signs or symptoms, but are generally in good health and proactively trying to prevent premature death. Given the resultant obligation to achieve the screening aim of early diagnosis while also minimizing the potential for morbidity from workup of indeterminate but ultimately benign screening abnormalities, careful implementation of screening with conformance to currently recognized best practices and a focus on quality assurance is essential. In this review, we address the importance of each component of the screening process to optimize the effectiveness of CT screening, discussing options for quality assurance at each step. We also discuss the potential added advantages, quality assurance requirements and current status of quantitative imaging biomarkers related to lung cancer screening. Finally, we highlight suggestions for improvements and needs for further evidence in evaluating the performance of CT screening as it transitions from the research trial setting into daily clinical practice.