Vessel suppressed chest Computed Tomography for semi-automated volumetric measurements of solid pulmonary nodules

Software with artificial intelligence-derived algorithms for detecting and analysing lung nodules in CT scans: systematic review and economic evaluation

Background

Lung cancer is one of the most common types of cancer and the leading cause of cancer death in the United Kingdom. Artificial intelligence-based software has been developed to reduce the number of missed or misdiagnosed lung nodules on computed tomography images.

Objective

 To assess the accuracy, clinical effectiveness and cost-effectiveness of using  software with artificial intelligence-derived algorithms to assist in the detection and analysis of lung nodules in computed tomography scans of the chest compared with unassisted reading.

Design

Systematic review and de novo cost-effectiveness analysis.

Methods

Searches were undertaken from 2012 to January 2022. Company submissions were accepted until 31 August 2022. Study quality was assessed using the revised tool for the quality assessment of diagnostic accuracy studies (QUADAS-2), the extension to QUADAS-2 for assessing risk of bias in comparative accuracy studies (QUADAS-C) and the COnsensus-based Standards for the selection of health status Measurement INstruments (COSMIN) checklist. Outcomes were synthesised narratively. Two decision trees were used for cost-effectiveness: (1) a simple decision tree for the detection of actionable nodules and (2) a decision tree reflecting the full clinical pathways for people undergoing chest computed tomography scans. Models estimated incremental cost-effectiveness ratios, cost per correct detection of an actionable nodule, and cost per cancer detected and treated. We undertook scenario and sensitivity analyses.

Results

Twenty-seven studies were included. All were rated as being at high risk of bias. Twenty-four of the included studies used retrospective data sets. Seventeen compared readers with and without artificial intelligence software. One reported prospective screening experiences before and after artificial intelligence software implementation. The remaining studies either evaluated stand-alone artificial intelligence or provided only non-comparative evidence. (1) Artificial intelligence assistance generally improved the detection of any nodules compared with unaided reading (three studies; average per-person sensitivity 0.43-0.68 for unaided and 0.79-0.99 for artificial intelligence-assisted reading), with similar or lower specificity (three studies; 0.77-1.00 for unaided and 0.81-0.97 for artificial intelligence-assisted reading). Nodule diameters were similar or significantly larger with semiautomatic measurements than with manual measurements. Intra-reader and inter-reader agreement in nodule size measurement and in risk classification generally improved with artificial intelligence assistance or were comparable to those with unaided reading. However, the effect on measurement accuracy is unclear. (2) Radiologist reading time generally decreased with artificial intelligence assistance in research settings. (3) Artificial intelligence assistance tended to increase allocated risk categories as defined by clinical guidelines. (4) No relevant clinical effectiveness and cost-effectiveness studies were identified. (5) The de novo cost-effectiveness analysis suggested that for symptomatic and incidental populations, artificial intelligence-assisted computed tomography image analysis dominated the unaided radiologist in cost per correct detection of an actionable nodule. However, when relevant costs and quality-adjusted life-years from the full clinical pathway were included, artificial intelligence-assisted computed tomography reading was dominated by the unaided reader. For screening, artificial intelligence-assisted computed tomography image analysis was cost-effective in the base case and all sensitivity and scenario analyses.

Limitations

Due to the heterogeneity, sparseness, low quality and low applicability of the clinical effectiveness evidence and the major challenges in linking test accuracy evidence to clinical and economic outcomes, the findings presented here are highly uncertain and provide indicators/frameworks for future assessment.

Conclusions

Artificial intelligence-assisted analysis of computed tomography scan images may reduce variability of and improve consistency in the measurement and clinical management of lung nodules. Artificial intelligence may increase nodule and cancer detection but may also increase the number of patients undergoing computed tomography surveillance unnecessarily. No direct comparative evidence was found, and nor was any direct evidence found on clinical outcomes and cost-effectiveness. Artificial intelligence-assisted image analysis may be cost-effective in screening for lung cancer but not for symptomatic populations. However, reliable estimates of cost-effectiveness cannot be obtained with current evidence.

Study registration

This study is registered as PROSPERO CRD42021298449.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR135325) and is published in full in Health Technology Assessment; Vol. 29, No. 14. See the NIHR Funding and Awards website for further award information.

Impact of artificial intelligence assistance on pulmonary nodule detection and localization in chest CT: a comparative study among radiologists of varying experience levels

The study aimed to evaluate the impact of AI assistance on pulmonary nodule detection rates among radiology residents and senior radiologists, along with assessing the effectiveness of two different commercialy available AI software systems in improving detection rates and LungRADS classification in chest CT. The study cohort included 198 participants with 221 pulmonary nodules. Residents' mean detection rate increased significantly from 64 to 77% with AI assist, while seniors' detection rate remained largely unchanged (85% vs. 86%). Residents showed significant improvement in segmental nodule localization with AI assistance, seniors did not. Software 2 slightly outperformed software 1 in increasing detection rates (67-77% vs. 80-86%), but neither significantly affected LungRADS classification. The study suggests that clinical experience mitigates the need for additional AI software, with the combination of CAD with residents being the most beneficial approach. Both software systems performed similarly, with software 2 showing a slightly higher but non-significant increase in detection rates.

ACR Appropriateness Criteria® Incidentally Detected Indeterminate Pulmonary Nodule

Incidental pulmonary nodules are common. Although the majority are benign, most are indeterminate for malignancy when first encountered making their management challenging. CT remains the primary imaging modality to first characterize and follow-up incidental lung nodules. This document reviews available literature on various imaging modalities and summarizes management of indeterminate pulmonary nodules detected incidentally. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Factors influencing the outcome of volumetry tools for pulmonary nodule analysis: a systematic review and attempted meta-analysis

Health systems worldwide are implementing lung cancer screening programmes to identify early-stage lung cancer and maximise patient survival. Volumetry is recommended for follow-up of pulmonary nodules and outperforms other measurement methods. However, volumetry is known to be influenced by multiple factors. The objectives of this systematic review (PROSPERO CRD42022370233) are to summarise the current knowledge regarding factors that influence volumetry tools used in the analysis of pulmonary nodules, assess for significant clinical impact, identify gaps in current knowledge and suggest future research. Five databases (Medline, Scopus, Journals@Ovid, Embase and Emcare) were searched on the 21st of September, 2022, and 137 original research studies were included, explicitly testing the potential impact of influencing factors on the outcome of volumetry tools. The summary of these studies is tabulated, and a narrative review is provided. A subset of studies (n = 16) reporting clinical significance were selected, and their results were combined, if appropriate, using meta-analysis. Factors with clinical significance include the segmentation algorithm, quality of the segmentation, slice thickness, the level of inspiration for solid nodules, and the reconstruction algorithm and kernel in subsolid nodules. Although there is a large body of evidence in this field, it is unclear how to apply the results from these studies in clinical practice as most studies do not test for clinical relevance. The meta-analysis did not improve our understanding due to the small number and heterogeneity of studies testing for clinical significance. CRITICAL RELEVANCE STATEMENT: Many studies have investigated the influencing factors of pulmonary nodule volumetry, but only 11% of these questioned their clinical relevance in their management. The heterogeneity among these studies presents a challenge in consolidating results and clinical application of the evidence. KEY POINTS: • Factors influencing the volumetry of pulmonary nodules have been extensively investigated. • Just 11% of studies test clinical significance (wrongly diagnosing growth). • Nodule size interacts with most other influencing factors (especially for smaller nodules). • Heterogeneity among studies makes comparison and consolidation of results challenging. • Future research should focus on clinical applicability, screening, and updated technology.

Comparability of Pulmonary Nodule Size Measurements among Different Scanners and Protocols: Should Diameter Be Favorized over Volume?

BACKGROUND

To assess the impact of the lung cancer screening protocol recommended by the European Society of Thoracic Imaging (ESTI) on nodule diameter, volume, and density throughout different computed tomography (CT) scanners.

METHODS

An anthropomorphic chest phantom containing fourteen different-sized (range 3-12 mm) and CT-attenuated (100 HU, -630 HU and -800 HU, termed as solid, GG1 and GG2) pulmonary nodules was imaged on five CT scanners with institute-specific standard protocols (P_S) and the lung cancer screening protocol recommended by ESTI (ESTI protocol, P_E). Images were reconstructed with filtered back projection (FBP) and iterative reconstruction (REC). Image noise, nodule density and size (diameter/volume) were measured. Absolute percentage errors (APEs) of measurements were calculated.

RESULTS

Using P_E, dosage variance between different scanners tended to decrease compared to P_S, and the mean differences were statistically insignificant (p = 0.48). P_S and P_E(REC) showed significantly less image noise than P_E(FBP) (p < 0.001). The smallest size measurement errors were noted with volumetric measurements in P_E(REC) and highest with diametric measurements in P_E(FBP). Volume performed better than diameter measurements in solid and GG1 nodules (p < 0.001). However, in GG2 nodules, this could not be observed (p = 0.20). Regarding nodule density, REC values were more consistent throughout different scanners and protocols.

CONCLUSION

Considering radiation dose, image noise, nodule size, and density measurements, we fully endorse the ESTI screening protocol including the use of REC. For size measurements, volume should be preferred over diameter.

European lung cancer screening: valuable trial evidence for optimal practice implementation

Lung cancer screening (LCS) by low-dose computed tomography is a strategy for secondary prevention of lung cancer. In the last two decades, LCS trials showed several options to practice secondary prevention in association with primary prevention, however, the translation from trial to practice is everything but simple. In 2020, the European Society of Radiology and European Respiratory Society published their joint statement paper on LCS. This commentary aims to provide the readership with detailed description about hurdles and potential solutions that could be encountered in the practice of LCS.

Volumetric Measurements in Lung Cancer Screening Reduces Unnecessary Low-Dose Computed Tomography Scans: Results from a Single-Center Prospective Trial on 4119 Subjects

This study aims to compare the low-dose computed tomography (LDCT) outcome and volume-doubling time (VDT) derived from the measured volume (MV) and estimated volume (EV) of pulmonary nodules (PNs) detected in a single-center lung cancer screening trial. MV, EV and VDT were obtained for prevalent pulmonary nodules detected at the baseline round of the bioMILD trial. The LDCT outcome (based on bioMILD thresholds) and VDT categories were simulated on PN- and screenee-based analyses. A weighted Cohen’s kappa test was used to assess the agreement between diagnostic categories as per MV and EV, and 1583 screenees displayed 2715 pulmonary nodules. In the PN-based analysis, 40.1% PNs were included in different LDCT categories when measured by MV or EV. The agreements between MV and EV were moderate (κ = 0.49) and fair (κ = 0.37) for the LDCT outcome and VDT categories, respectively. In the screenee-based analysis, 46% pulmonary nodules were included in different LDCT categories when measured by MV or EV. The agreements between MV and EV were moderate (κ = 0.52) and fair (κ = 0.34) for the LDCT outcome and VDT categories, respectively. Within a simulated lung cancer screening based on a recommendation by estimated volumetry, the number of LDCTs performed for the evaluation of pulmonary nodules was higher compared with in prospective volumetric management.

Impact of Vessel Suppressed-CT on Diagnostic Accuracy in Detection of Pulmonary Metastasis and Reading Time

RATIONALE AND OBJECTIVES

To assess if vessel suppression (VS) improves nodule detection rate, interreader agreement, and reduces reading time in oncologic chest computed tomography (CT).

MATERIAL AND METHODS

One-hundred consecutive oncologic patients (65 male; median age 60y) who underwent contrast-enhanced chest CT were retrospectively included. For all exams, additional VS series (ClearRead CT, Riverrain Technologies, Miamisburg) were reconstructed. Two groups of three radiologists each with matched experience were defined. Each group evaluated the SD-CT as well as VS-CT. Each reader marked the presence, size, and position of pulmonary nodules and documented reading time. In addition, for the VS-CT the presence of false positive nodules had to be stated. Cohen's Kappa (k) was used to calculate the interreader-agreement between groups. Reading time was compared using paired t test.

RESULTS

Nodule detection rate was significantly higher in VS-CT compared to the SD-CT (+21%; p <0.001). Interreader-agreement was higher in the VS-CT (k = 0.431, moderate agreement) compared to SD-CT (k = 0.209, fair agreement). Almost all VS-CT series had false positive findings (97-99 out of 100). Average reading time was significantly shorter in the VS-CT compared to the SD-CT (154 ± 134vs. 194 ± 126; 21%, p<0.001).

CONCLUSIONS

Vessel suppression increases nodule detection rate, improves interreader agreement, and reduces reading time in chest CT of oncologic patients. Due to false positive results a consensus reading with the SD-CT is essential.

Lung Nodules in Melanoma Patients: Morphologic Criteria to Differentiate Non-Metastatic and Metastatic Lesions

Lung nodules are frequent findings in chest computed tomography (CT) in patients with metastatic melanoma. In this study, we assessed the frequency and compared morphologic differences of metastases and benign nodules. We retrospectively evaluated 85 patients with melanoma (AJCC stage III or IV). Inclusion criteria were ≤20 lung nodules and follow-up using CT ≥183 days after baseline. Lung nodules were evaluated for size and morphology. Nodules with significant growth, nodule regression in line with RECIST assessment or histologic confirmation were judged to be metastases. A total of 438 lung nodules were evaluated, of which 68% were metastases. At least one metastasis was found in 78% of patients. A 10 mm diameter cut-off (used for RECIST) showed a specificity of 95% and a sensitivity of 20% for diagnosing metastases. Central location (n = 122) was more common in metastatic nodules (p = 0.009). Subsolid morphology (n = 53) was more frequent (p < 0.001), and calcifications (n = 13) were solely found in non-metastatic lung nodules (p < 0.001). Our data show that lung nodules are prevalent in about two-thirds of melanoma patients (AJCC stage III/IV) and the majority are metastases. Even though we found a few morphologic indicators for metastatic or non-metastatic lung nodules, morphology has limited value to predict the presence of lung metastases.

Screen-detected solid nodules: from detection of nodule to structured reporting

Lung cancer screening (LCS) is gaining some interest worldwide after positive results from International trials. Unlike other screening practices, LCS is performed by an extremely sensitive test, namely low-dose computed tomography (LDCT) that can detect the smallest nodules in lung parenchyma. Up-to-date detection approaches, such as computer aided detection systems, have been increasingly employed for lung nodule automatic identification and are largely used in most LCS programs as a complementary tool to visual reading. Solid nodules of any size are represented in the vast majority of subjects undergoing LDCT. However, less than 1% of solid nodules will be diagnosed lung cancer. This fact calls for specific characterization of nodules to avoid false positives, overinvestigation, and reduce the risks associated with nodule work up. Recent research has been exploring the potential of artificial intelligence, including deep learning techniques, to enhance the accuracy of both detection and characterisation of lung nodule. Computer aided detection and diagnosis algorithms based on artificial intelligence approaches have demonstrated the ability to accurately detect and characterize parenchymal nodules, reducing the number of false positives, and to outperform some of the currently used risk models for prediction of lung cancer risk, potentially reducing the proportion of surveillance CT scans. These forthcoming approaches will eventually integrate a new reasoning for development of future guidelines, which are expected to evolve into precision and personalized stratification of lung cancer risk stratification by continuous fashion, as opposed to the current format with a limited number of risk classes within fixed thresholds of nodule size. This review aims to detail the standard of reference for optimal management of solid nodules by low-dose computed and its projection into the fine selection of candidates for work up.

Hessian-MRLoG: Hessian information and multi-scale reverse LoG filter for pulmonary nodule detection

Computer-aided detection (CADe) of pulmonary nodules is an effective approach for early detection of lung cancer. However, due to the low contrast of lung computed tomography (CT) images, the interference of blood vessels and classifications, CADe has the problems of low detection rate and high false-positive rate (FPR). To solve these problems, a novel method using Hessian information and multi-scale reverse Laplacian of Gaussian (LoG) (Hessian-MRLoG) is proposed and developed in this work. Also, since the intensity distribution of the LoG operator and the lung nodule in CT images are inconsistent, and their shapes are mismatched, a multi-scale reverse Laplacian of Gaussian (MRLoG) is constructed. In addition, in order to enhance the effectiveness of target detection, the second-order partial derivatives of MRLoG are partially adjusted by introducing an adjustment factor. On this basis, the Hessian-MRLoG model is developed, and a novel elliptic filter is designed. Ultimately, in this study, the method of Hessian-MRLoG filtering is proposed and developed for pulmonary nodule detection. To verify its effectiveness and accuracy, the proposed method was used to analyze the LUNA16 dataset. The experimental results revealed that the proposed method had an accuracy of 93.6% and produced 1.0 false positives per scan (FPs/scan), indicating that the proposed method can improve the detection rate and significantly reduce the FPR. Therefore, the proposed method has the potential for application in the detection, localization and labeling of other lesion areas.

Solitary Pulmonary nodule segmentation based on pyramid and improved grab cut

BACKGROUND AND OBJECTIVE

Accurate segmentation of solitary pulmonary nodule of digital radiography image is essential for lesion appearance measurement and medical follow-up. However, the imaging characteristics of digital radiography, the inhomogeneity and fuzzy contours of nodules often lead to poor performances. This work aims to develop a segmentation framework that satisfies the requirements of accurate segmentation.

METHODS

In this work, an interactive segmentation method which combined the enhanced total-variance pyramid and improved Grab cut was proposed to improve the performance of nodule segmentation. The edge-preserving multi-resolution pyramid structure did the rough segmentation on low resolution images, which provided contour nearby curves to initial the following accuracy segmentation and shortened the time of energy decreasing. With the multiscale information being incorporated to optimize the edge term and improve the appearance model, a novel Gibbs energy functional was constructed to extract the nodule in a proper scale. By introducing the multiscale processing and optimizing the energy terms, the proposed method could overcome the inhomogeneity and fuzzy contours.

RESULTS

For evaluation of the nodule segmentation, quantitative metrics such as precision, intersection over union, and dice similarity coefficient were introduced and compared in the experimental part. The proposed solitary pulmonary nodule segmentation method produced the results with mean values of precision 0.957, dice similarity coefficient 0.933, and intersection over union 0.891, respectively. And the corresponding standard deviation values were 0.041, 0.047, and 0.045.

CONCLUSIONS

From the quantitative assessment and comparison in the experiments, the proposed method achieved a competitive performance in accuracy and stability, even in the cases with low contrast and fuzzy contours.

The Use of Artificial Intelligence in the Differentiation of Malignant and Benign Lung Nodules on Computed Tomograms Proven by Surgical Pathology

The purpose of this work was to evaluate the performance of an existing commercially available artificial intelligence (AI) software system in differentiating malignant and benign lung nodules. The AI tool consisted of a vessel-suppression function and a deep-learning-based computer-aided-detection (VS-CAD) analyzer. Fifty patients (32 females, mean age 52 years) with 75 lung nodules (47 malignant and 28 benign) underwent low-dose computed tomography (LDCT) followed by surgical excision and the pathological analysis of their 75 nodules within a 3 month time frame. All 50 cases were then processed by the AI software to generate corresponding VS images and CAD outcomes. All 75 pathologically proven lung nodules were well delineated by vessel-suppressed images. Three (6.4%) of the 47 lung cancer cases, and 11 (39.3%) of the 28 benign nodules were ignored and not detected by the AI without showing a CAD analysis summary. The AI system/radiologists produced a sensitivity and specificity (shown in %) of 93.6/89.4 and 39.3/82.1 in distinguishing malignant from benign nodules, respectively. AI sensitivity was higher than that of radiologists, though not statistically significant (p = 0.712). Specificity obtained by the radiologists was significantly higher than that of the VS-CAD AI (p = 0.003). There was no significant difference between the malignant and benign lesions with respect to age, gender, pure ground-glass pattern, the diameter and location of the nodules, or nodules <6 vs. ≥6 mm. However, more part-solid nodules were proven to be malignant than benign (90.9% vs. 9.1%), and more solid nodules were proven to be benign than malignant (86.7% vs. 13.3%) with statistical significance (p = 0.001 and <0.001, respectively). A larger cohort and prospective study are required to validate the AI performance.

Quantification of MRI T2-weighted High Signal Volume in Cystic Fibrosis: A Pilot Study

Background In patients with cystic fibrosis (CF), pulmonary structures with high MRI T2 signal intensity relate to inflammatory changes in the lung and bronchi. These areas of pathologic abnormalities can serve as imaging biomarkers. The feasibility of automated quantification is unknown. Purpose To quantify the MRI T2 high-signal-intensity lung volume and T2-weighted volume-intensity product (VIP) by using a black-blood T2-weighted radial fast spin-echo sequence in participants with CF. Materials and Methods Healthy individuals and study participants with CF were prospectively enrolled between January 2017 and November 2017. All participants underwent a lung MRI protocol including T2-weighted radial fast spin-echo sequence. Participants with CF also underwent pulmonary function tests the same day. Participants with CF exacerbation underwent repeat MRI after their treatment with antibiotics. Two observers supervised automated quantification of T2-weighted high-signal-intensity volume (HSV) and T2-weighted VIP independently, and the average score was chosen as consensus. Statistical analysis used the Mann-Whitney test for comparison of medians, correlations used the Spearman test, comparison of paired medians used the Wilcoxon signed rank test, and reproducibility was evaluated by using intraclass correlation coefficient. Results In 10 healthy study participants (median age, 21 years [age range, 18-27 years]; six men) and 12 participants with CF (median age, 18 years [age range, 9-40 years]; eight men), T2-weighted HSV was equal to 0% and 4.1% (range, 0.1%-17%), respectively, and T2-weighted VIP was equal to 0 msec and 303 msec (range, 39-1012 msec), respectively (P < .001). In participants with CF, T2-weighted HSV or T2-weighted VIP were associated with forced expiratory volume in 1 second percentage predicted (ρ = -0.88 and ρ = -0.94, respectively; P < .001). In six participants with CF exacerbation and follow-up after treatment, a decrease in both T2-weighted HSV and T2-weighted VIP was observed (P = .03). The intra- and interobserver reproducibility of MRI were good (intraclass correlation coefficients, >0.99 and >0.99, respectively). Conclusion In patients with cystic fibrosis (CF), automated quantification of lung MRI high-signal-intensity volume was reproducible and correlated with pulmonary function testing severity, and it improved after treatment for CF exacerbation. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Revel and Chassagnon in this issue.

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.