The probability of malignancy in solitary pulmonary nodules. Application to small radiologically indeterminate nodules

Incidental pulmonary nodules - current guidelines and management

BACKGROUND

 Due to the greater use of high-resolution cross-sectional imaging, the number of incidental pulmonary nodules detected each year is increasing. Although the vast majority of incidental pulmonary nodules are benign, many early lung carcinomas could be diagnosed with consistent follow-up. However, for a variety of reasons, the existing recommendations are often not implemented correctly. Therefore, potential for improvement with respect to competence, communication, structure, and process is described.

METHODS

 This article presents the recommendations for incidental pulmonary nodules from the current S3 guideline for lung cancer (July 2023). The internationally established recommendations (BTS guidelines and Fleischner criteria) are compared and further studies on optimized management were included after a systematic literature search in PubMed.

RESULTS AND CONCLUSION

 In particular, AI-based software solutions are promising, as they can be used in a support capacity on several levels at once and can lead to simpler and more automated management. However, to be applicable in routine clinical practice, software must fit well into the radiology workflow and be integrated. In addition, "Lung Nodule Management" programs or clinics that follow a high-quality procedure for patients with incidental lung nodules or nodules detected by screening have been established in the USA. Similar structures might also be implemented in Germany in a future screening program in which patients with incidental pulmonary nodules could be included.

KEY POINTS

  · Incidental pulmonary nodules are common but are often not adequately managed. · The updated S3 guideline for lung cancer now includes recommendations for incidental pulmonary nodules. · Competence, communication, structure, and process levels offer significant potential for improvement.

CITATION FORMAT

· Glandorf J, Vogel-Claussen J, . Incidental pulmonary nodules - current guidelines and management. Fortschr Röntgenstr 2024; 196: 582 - 590.

Imaging of Solid Pulmonary Nodules

Early detection with accurate classification of solid pulmonary nodules is critical in reducing lung cancer morbidity and mortality. Computed tomography (CT) remains the most widely used imaging examination for pulmonary nodule evaluation; however, other imaging modalities, such as PET/CT and MRI, are increasingly used for nodule characterization. Current advances in solid nodule imaging are largely due to developments in machine learning, including automated nodule segmentation and computer-aided detection. This review explores current multi-modality solid pulmonary nodule detection and characterization with discussion of radiomics and risk prediction models.

Radiomics and Clinical Data for the Diagnosis of Incidental Pulmonary Nodules and Lung Cancer Screening: Radiolung Integrative Predictive Model

INTRODUCTION

Early diagnosis of lung cancer (LC) is crucial to improve survival rates. Radiomics models hold promise for enhancing LC diagnosis. This study assesses the impact of integrating a clinical and a radiomic model based on deep learning to predict the malignancy of pulmonary nodules (PN).

METHODOLOGY

Prospective cross-sectional study of 97 PNs from 93 patients. Clinical data included epidemiological risk factors and pulmonary function tests. The region of interest of each chest CT containing the PN was analysed. The radiomic model employed a pre-trained convolutional network to extract visual features. From these features, 500 with a positive standard deviation were chosen as inputs for an optimised neural network. The clinical model was estimated by a logistic regression model using clinical data. The malignancy probability from the clinical model was used as the best estimate of the pre-test probability of disease to update the malignancy probability of the radiomic model using a nomogram for Bayes' theorem.

RESULTS

The radiomic model had a positive predictive value (PPV) of 86%, an accuracy of 79% and an AUC of 0.67. The clinical model identified DLCO, obstruction index and smoking status as the most consistent clinical predictors associated with outcome. Integrating the clinical features into the deep-learning radiomic model achieves a PPV of 94%, an accuracy of 76% and an AUC of 0.80.

CONCLUSIONS

Incorporating clinical data into a deep-learning radiomic model improved PN malignancy assessment, boosting predictive performance. This study supports the potential of combined image-based and clinical features to improve LC diagnosis.

Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis

BACKGROUND

There has been growing interest in using artificial intelligence/deep learning (DL) to help diagnose prevalent diseases earlier. In this study we sought to survey the landscape of externally validated DL-based computer-aided diagnostic (CADx) models, and assess their diagnostic performance for predicting the risk of malignancy in computed tomography (CT)-detected pulmonary nodules.

METHODS

An electronic search was performed in four databases (from inception to 10 August 2023). Studies were eligible if they were peer-reviewed experimental or observational articles comparing the diagnostic performance of externally validated DL-based CADx models with models widely used in clinical practice to predict the risk of malignancy. A bivariate random-effect approach for the meta-analysis on the included studies was used.

RESULTS

Seventeen studies were included, comprising 8553 participants and 9884 nodules. Pooled analyses showed DL-based CADx models were 11.6% more sensitive than physician judgement alone, and 14.5% more than clinical risk models alone. They had a similar pooled specificity to physician judgement alone [0.77 (95% CI 0.68-0.84) v 0.81 (95% CI 0.71-0.88)], and were 7.4% more specific than clinical risk models alone. They had superior pooled areas under the receiver operating curve (AUC), with relative pooled AUCs of 1.03 (95% CI 1.00-1.07) and 1.10 (95% CI 1.07-1.13) versus physician judgement and clinical risk models alone, respectively.

CONCLUSION

DL-based models are already used in clinical practice in certain settings for nodule management. Our results show their diagnostic performance potentially justifies wider, more routine deployment alongside experienced physician readers to help inform multidisciplinary team decision-making.

A Real-World Assessment of Stage I Lung Cancer Through Electronic Nose Technology

INTRODUCTION

Electronic nose (E-nose) technology has reported excellent sensitivity and specificity in the setting of lung cancer screening. However, the performance of E-nose specifically for early-stage tumors remains unclear. Therefore, the aim of our study was to assess the diagnostic performance of E-nose technology in clinical stage I lung cancer.

METHODS

This phase IIc trial (NCT04734145) included patients diagnosed with a single greater than or equal to 50% solid stage I nodule. Exhalates were prospectively collected from January 2020 to August 2023. Blinded bioengineers analyzed the exhalates, using E-nose technology to determine the probability of malignancy. Patients were stratified into three risk groups (low-risk, [<0.2]; moderate-risk, [≥0.2-0.7]; high-risk, [≥0.7]). The primary outcome was the diagnostic performance of E-nose versus histopathology (accuracy and F1 score). The secondary outcome was the clinical performance of the E-nose versus clinicoradiological prediction models.

RESULTS

Based on the predefined cutoff (<0.20), E-nose agreed with histopathologic results in 86% of cases, achieving an F1 score of 92.5%, based on 86 true positives, two false negatives, and 12 false positives (n = 100). E-nose would refer fewer patients with malignant nodules to observation (low-risk: 2 versus 9 and 11, respectively; p = 0.028 and p = 0.011) than would the Swensen and Brock models and more patients with malignant nodules to treatment without biopsy (high-risk: 27 versus 19 and 6, respectively; p = 0.057 and p < 0.001).

CONCLUSIONS

In the setting of clinical stage I lung cancer, E-nose agrees well with histopathology. Accordingly, E-nose technology can be used in addition to imaging or as part of a "multiomics" platform.

Establishment and validation of multiclassification prediction models for pulmonary nodules based on machine learning

BACKGROUND

Lung cancer is the leading cause of cancer-related death worldwide. This study aimed to establish novel multiclassification prediction models based on machine learning (ML) to predict the probability of malignancy in pulmonary nodules (PNs) and to compare with three published models.

METHODS

Nine hundred fourteen patients with PNs were collected from four medical institutions (A, B, C and D), which were organized into tables containing clinical features, radiologic features and laboratory test features. Patients were divided into benign lesion (BL), precursor lesion (PL) and malignant lesion (ML) groups according to pathological diagnosis. Approximately 80% of patients in A (total/male: 632/269, age: 57.73 ± 11.06) were randomly selected as a training set; the remaining 20% were used as an internal test set; and the patients in B (total/male: 94/53, age: 60.04 ± 11.22), C (total/male: 94/47, age: 59.30 ± 9.86) and D (total/male: 94/61, age: 62.0 ± 11.09) were used as an external validation set. Logical regression (LR), decision tree (DT), random forest (RF) and support vector machine (SVM) were used to establish prediction models. Finally, the Mayo model, Peking University People's Hospital (PKUPH) model and Brock model were externally validated in our patients.

RESULTS

The AUC values of RF model for MLs, PLs and BLs were 0.80 (95% CI: 0.73-0.88), 0.90 (95% CI: 0.82-0.99) and 0.75 (95% CI: 0.67-0.88), respectively. The weighted average AUC value of the RF model for the external validation set was 0.71 (95% CI: 0.67-0.73), and its AUC values for MLs, PLs and BLs were 0.71 (95% CI: 0.68-0.79), 0.98 (95% CI: 0.88-1.07) and 0.68 (95% CI: 0.61-0.74), respectively. The AUC values of the Mayo model, PKUPH model and Brock model were 0.68 (95% CI: 0.62-0.74), 0.64 (95% CI: 0.58-0.70) and 0.57 (95% CI: 0.49-0.65), respectively.

CONCLUSIONS

The RF model performed best, and its predictive performance was better than that of the three published models, which may provide a new noninvasive method for the risk assessment of PNs.

Influence of CT dose reduction on AI-driven malignancy estimation of incidental pulmonary nodules

OBJECTIVES

The purpose of this study was to determine the influence of dose reduction on a commercially available lung cancer prediction convolutional neuronal network (LCP-CNN).

METHODS

CT scans from a cohort provided by the local lung cancer center (n = 218) with confirmed pulmonary malignancies and their corresponding reduced dose simulations (25% and 5% dose) were subjected to the LCP-CNN. The resulting LCP scores (scale 1-10, increasing malignancy risk) and the proportion of correctly classified nodules were compared. The cohort was divided into a low-, medium-, and high-risk group based on the respective LCP scores; shifts between the groups were studied to evaluate the potential impact on nodule management. Two different malignancy risk score thresholds were analyzed: a higher threshold of ≥ 9 ("rule-in" approach) and a lower threshold of > 4 ("rule-out" approach).

RESULTS

In total, 169 patients with 196 nodules could be included (mean age ± SD, 64.5 ± 9.2 year; 49% females). Mean LCP scores for original, 25% and 5% dose levels were 8.5 ± 1.7, 8.4 ± 1.7 (p > 0.05 vs. original dose) and 8.2 ± 1.9 (p < 0.05 vs. original dose), respectively. The proportion of correctly classified nodules with the "rule-in" approach decreased with simulated dose reduction from 58.2 to 56.1% (p = 0.34) and to 52.0% for the respective dose levels (p = 0.01). For the "rule-out" approach the respective values were 95.9%, 96.4%, and 94.4% (p = 0.12). When reducing the original dose to 25%/5%, eight/twenty-two nodules shifted to a lower, five/seven nodules to a higher malignancy risk group.

CONCLUSION

CT dose reduction may affect the analyzed LCP-CNN regarding the classification of pulmonary malignancies and potentially alter pulmonary nodule management.

CLINICAL RELEVANCE STATEMENT

Utilization of a "rule-out" approach with a lower malignancy risk threshold prevents underestimation of the nodule malignancy risk for the analyzed software, especially in high-risk cohorts.

KEY POINTS

• LCP-CNN may be affected by CT image parameters such as noise resulting from low-dose CT acquisitions. • CT dose reduction can alter pulmonary nodule management recommendations by affecting the outcome of the LCP-CNN. • Utilization of a lower malignancy risk threshold prevents underestimation of pulmonary malignancies in high-risk cohorts.

A Nasal Swab Classifier to Evaluate the Probability of Lung Cancer in Patients With Pulmonary Nodules

BACKGROUND

Accurate assessment of the probability of lung cancer (pCA) is critical in patients with pulmonary nodules (PNs) to help guide decision-making. We sought to validate a clinical-genomic classifier developed using whole-transcriptome sequencing of nasal epithelial cells from patients with a PN ≤ 30 mm who smoke or have previously smoked.

RESEARCH QUESTION

Can the pCA in individuals with a PN and a history of smoking be predicted by a classifier that uses clinical factors and genomic data from nasal epithelial cells obtained by cytologic brushing?

STUDY DESIGN AND METHODS

Machine learning was used to train a classifier using genomic and clinical features on 1,120 patients with PNs labeled as benign or malignant established by a final diagnosis or a minimum of 12 months of radiographic surveillance. The classifier was designed to yield low-, intermediate-, and high-risk categories. The classifier was validated in an independent set of 312 patients, including 63 patients with a prior history of cancer (other than lung cancer), comparing the classifier prediction with the known clinical outcome.

RESULTS

In the primary validation set, sensitivity and specificity for low-risk classification were 96% and 42%, whereas sensitivity and specificity for high-risk classification was 58% and 90%, respectively. Sensitivity was similar across stages of non-small cell lung cancer, independent of subtype. Performance compared favorably with clinical-only risk models. Analysis of 63 patients with prior cancer showed similar performance as did subanalyses of patients with light vs heavy smoking burden and those eligible for lung cancer screening vs those who were not.

INTERPRETATION

The nasal classifier provides an accurate assessment of pCA in individuals with a PN ≤ 30 mm who smoke or have previously smoked. Classifier-guided decision-making could lead to fewer diagnostic procedures in patients without cancer and more timely treatment in patients with lung cancer.

Tumor microenvironment(TME) and single-source dual-energy CT(ssDECT) on assessment of inconformity between RECIST1.1 and pathological remission in neoadjuvant immunotherapy of NSCLC

BACKGROUND

The inconformity (IC) between pathological and imaging remissions after neoadjuvant immunotherapy in patients with NSCLC can affect the evaluation of curative effect of neoadjuvant therapy and the decision regarding the chance of surgery.

MATERIALS AND METHODS

Patients who achieved disease control(CR/PR/SD) after neoadjuvant chemoimmunotherapy from a clinical trial (NCT04326153) and after neoadjuvant chemotherapy during the same period were enrolled in this study. All patients underwent radical resection and systematic mediastinal lymphadenectomy after neoadjuvant treatments. The pathological remission, immunohistochemistry (CD4, CD8, CD20, CD56, FoxP3, CD68, CD163, CD11b tumor-infiltrating lymphocytes, or macrophages), and single-source dual-energy computed tomography (ssDECT) scans were assessed. The IC between imaging remission by CT and pathological remission was investigated. The underlying cause of IC, the correlation between IC and DFS, and prognostic biomarkers were explored.

RESULTS

After neoadjuvant immunotherapy, enhanced immune killing and reduced immunosuppressive performance were observed. 70 % of neoadjuvant chemoimmunotherapy patients were in high/medium IC level. Massive necrosis and repair around and inside the cancer nest were the main pathological changes observed 30-45 days post-treatment with PD1/PD-L1 antibody and were the main causes of IC between the pathology and imaging responses after neoadjuvant immunotherapy. High IC and preoperative CD8 expression (H score ≥ 3) indicate a high pathological response rate and prolonged DFS. Iodine material density ssDECT images showed that the iodine content in the lesion causes hyperattenuation in post-neoadjuvant lesion in PCR patient.

CONCLUSIONS

Compared to chemotherapy and targeted therapy, the efficacy of neoadjuvant immunotherapy was underestimated based on the RECIST criteria due to the unique antitumor therapeutic mechanism. Preoperative CD8+ expression and ssDECT predict this IC and evaluate the residual tumor cells. This is of great significance for screening immune beneficiaries and making more accurate judgments about the timing of surgery.

Association of patient and health care organization factors with incidental nodule guidelines adherence: A multi-system observational study

BACKGROUND

Health care organizations are increasingly developing systems to ensure patients with pulmonary nodules receive guideline-adherent care. Our goal was to determine patient and organization factors that are associated with radiologist adherence as well as clinician and patient concordance to 2005 Fleischner Society guidelines for incidental pulmonary nodule follow-up.

MATERIALS

Trained researchers abstracted data from the electronic health record from two Veterans Affairs health care systems for patients with incidental pulmonary nodules as identified by interpreting radiologists from 2008 to 2016.

METHODS

We classified radiology reports and patient follow-up into two categories. Radiologist-Fleischner Adherence was the agreement between the radiologist's recommendation in the computed tomography report and the 2005 Fleischner Society guidelines. Clinician/Patient-Fleischner Concordance was agreement between patient follow-up and the guidelines. We calculated multivariable-adjusted predicted probabilities for factors associated with Radiologist-Fleischner Adherence and Clinician/Patient-Fleischner Concordance.

RESULTS

Among 3150 patients, 69% of radiologist recommendations were adherent to 2005 Fleischner guidelines, 4% were more aggressive, and 27% recommended less aggressive follow-up. Overall, only 48% of patients underwent follow-up concordant with 2005 Fleischner Society guidelines, 37% had less aggressive follow-up, and 15% had more aggressive follow-up. Radiologist-Fleischner Adherence was associated with Clinician/Patient-Fleischner Concordance with evidence for effect modification by health care system.

CONCLUSION

Clinicians and patients seem to follow radiologists' recommendations but often do not obtain concordant follow-up, likely due to downstream differential processes in each health care system. Health care organizations need to develop comprehensive and rigorous tools to ensure high levels of appropriate follow-up for patients with pulmonary nodules.

Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis

BACKGROUND

The exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies based on deep learning, particularly the advent of convolutional neural networks (CNNs), AI presents an expanded horizon of applications in lung cancer screening, including lung segmentation, nodule detection, false-positive reduction, nodule classification, and prognosis.

METHODOLOGY

This review initially analyzes the current status of AI technologies. It then explores the applications of AI in lung cancer screening, including lung segmentation, nodule detection, and classification, and assesses the potential of AI in enhancing the sensitivity of nodule detection and reducing false-positive rates. Finally, it addresses the challenges and future directions of AI in lung cancer screening.

RESULTS

AI holds substantial prospects in lung cancer screening. It demonstrates significant potential in improving nodule detection sensitivity, reducing false-positive rates, and classifying nodules, while also showing value in predicting nodule growth and pathological/genetic typing.

CONCLUSIONS

AI offers a promising supportive approach to lung cancer screening, presenting considerable potential in enhancing nodule detection sensitivity, reducing false-positive rates, and classifying nodules. However, the universality and interpretability of AI results need further enhancement. Future research should focus on the large-scale validation of new deep learning-based algorithms and multi-center studies to improve the efficacy of AI in lung cancer screening.

A metabolomics study on carcinogenesis of ground-glass nodules

Objective

This study aimed to identify differential metabolites and key metabolic pathways between lung adenocarcinoma (LUAD) tissues and normal lung (NL) tissues using metabolomics techniques, to discover potential biomarkers for the early diagnosis of lung cancer.

Material and Methods

Forty-five patients with primary ground-glass nodules (GGN) identified on computed tomography imaging and who were willing to undergo surgery at Shanghai General Hospital from December 2021 to December 2022 were recruited to the study. All participants underwent video thoracoscopy surgery with segmental or wedge resection of the lung. Tissue samples for pathological examination were collected from the site of ground-glass nodules (GGN) lesion and 3 cm away from the lesion (NL). The pathology results were 35 lung adenocarcinoma (LUAD) cases (13 invasive adenocarcinoma, 14 minimally invasive adenocarcinoma, and eight adenocarcinoma in situ), 10 benign samples, and 45 NL tissues. For the untargeted metabolomics technique, 25 LUAD samples were assigned as the case group and 30 NL tissues as the control group. For the targeted metabolomics technique, ten LUAD samples were assigned as the case group and 15 NL tissues as the control group. Samples were analyzed by untargeted and targeted metabolomics, with liquid chromatography-tandem mass spectrometry detection used as part of the experimental procedure.

Results

Untargeted metabolomics revealed 164 differential metabolites between the case and control groups, comprising 110 up regulations and 54 down regulations. The main metabolic differences found by the untargeted method were organic acids and their derivatives. Targeted metabolomics revealed 77 differential metabolites between the case and control groups, comprising 69 up regulations and eight down regulations. The main metabolic changes found by the targeted method were fatty acids, amino acids, and organic acids. The levels of organic acids such as lactic acid, fumaric acid, and malic acid were significantly increased in LUAD tissue compared to NL. Specifically, an increased level of L-lactic acid was found by both untargeted (variable importance in projection [VIP] = 1.332, fold-change [FC] = 1.678, q = 0.000) and targeted metabolomics (VIP = 1.240, FC = 1.451, q = 0.043). Targeted metabolomics also revealed increased levels of fumaric acid (VIP = 1.481, FC = 1.764, q = 0.106) and L-malic acid (VIP = 1.376, FC = 1.562, q = 0.012). Most of the 20 differential fatty acids identified were downregulated, including dodecanoic acid (VIP = 1.416, FC = 0.378, q = 0.043) and tridecane acid (VIP = 0.880, FC = 0.780, q = 0.106). Furthermore, increased levels of differential amino acids were found in LUAD samples.

Conclusion

Lung cancer is a complex and heterogeneous disease with diverse genetic alterations. The study of metabolic profiles is a promising research field in this cancer type. Targeted and untargeted metabolomics revealed significant differences in metabolites between LUAD and NL tissues, including elevated levels of organic acids, decreased levels of fatty acids, and increased levels of amino acids. These metabolic features provide valuable insights into LUAD pathogenesis and can potentially serve as biomarkers for prognosis and therapy response.

Predicting subsolid pulmonary nodules before percutaneous needle biopsy: a comparison of artificial neural network and biopsy results

AIM

To establish an artificial neural network (ANN) model to predict subsolid nodules (SSNs) before percutaneous core-needle biopsy (PCNB). The results of the two methods were compared to provide guidance on the treatment of SSNs.

MATERIALS AND METHODS

This was a single-centre retrospective study using data from 1,459 SSNs between 2013 and 2021. The ANN was developed using data from patients who underwent surgery following computed tomography (CT) (SFC) and validated using data from patients who underwent surgery following biopsy (SFB). The prediction results of the ANN for the PCNB group and the histopathological results obtained after biopsy were compared with the histopathological results of lung nodules in the same group after surgery. Additionally, the choice of predictors for PCNB was analysed using multivariate analysis.

RESULTS

There was no significant difference between the accuracies of the ANN and PCNB in the SFB group (p=0.086). The sensitivity of PCNB was lower than that of the ANN (p=0.000), but the specificity was higher (p=0.001). PCNB had better diagnostic ability than the ANN. The incidence of precursor lesions and non-neoplastic lesions in the SFB group was lower than that in the SFC group (p=0.000). A history of malignant tumours, size (2-3 cm), volume (>400 cm3) and mean CT value (≥-450 HU) are important factors for selecting PCNB.

CONCLUSIONS

Both ANN and PCNB have comparable accuracy in diagnosing SSNs; however, PCNB has a slightly higher diagnostic ability than ANN. Selecting appropriate patients for PCNB is important for maximising the benefit to SSN patients.

The Lung Cancer Prediction Model "Stress Test": Assessment of Models' Performance in a High-Risk Prospective Pulmonary Nodule Cohort

BACKGROUND

Pulmonary nodules represent a growing health care burden because of delayed diagnosis of malignant lesions and overtesting for benign processes. Clinical prediction models were developed to inform physician assessment of pretest probability of nodule malignancy but have not been validated in a high-risk cohort of nodules for which biopsy was ultimately performed.

RESEARCH QUESTION

Do guideline-recommended prediction models sufficiently discriminate between benign and malignant nodules when applied to cases referred for biopsy by navigational bronchoscopy?

STUDY DESIGN AND METHODS

We assembled a prospective cohort of 322 indeterminate pulmonary nodules in 282 patients referred to a tertiary medical center for diagnostic navigational bronchoscopy between 2017 and 2019. We calculated the probability of malignancy for each nodule using the Brock model, Mayo Clinic model, and Veterans Affairs (VA) model. On a subset of 168 patients who also had PET-CT scans before biopsy, we also calculated the probability of malignancy using the Herder model. The performance of the models was evaluated by calculating the area under the receiver operating characteristic curves (AUCs) for each model.

RESULTS

The study cohort contained 185 malignant and 137 benign nodules (57% prevalence of malignancy). The malignant and benign cohorts were similar in terms of size, with a median longest diameter for benign and malignant nodules of 15 and 16 mm, respectively. The Brock model, Mayo Clinic model, and VA model showed similar performance in the entire cohort (Brock AUC, 0.70; 95% CI, 0.64-0.76; Mayo Clinic AUC, 0.70; 95% CI, 0.64-0.76; VA AUC, 0.67; 95% CI, 0.62-0.74). For 168 nodules with available PET-CT scans, the Herder model had an AUC of 0.77 (95% CI, 0.68-0.85).

INTERPRETATION

Currently available clinical models provide insufficient discrimination between benign and malignant nodules in the common clinical scenario in which a patient is being referred for biopsy, especially when PET-CT scan information is not available.

A clinical-radiological predictive model for solitary pulmonary nodules and the relationship between radiological features and pathological subtype

AIM

To develop a clinical-radiological model to predict the malignancy of solitary pulmonary nodules (SPNs) and to evaluate the accuracy of chest computed tomography imaging characteristics of SPN in diagnosing pathological type.

MATERIALS AND METHODS

The predictive model was developed using a retrospective cohort of 601 SPN patients (Group A) between July 2015 and July 2020. The established model was tested using a second retrospective cohort of 124 patients between August 2020 and August 2021 (Group B). The radiological characteristics of all adenocarcinomas in two groups were analysed to determine the correlation between radiological and pathological characteristics.

RESULTS

Malignant nodules were found in 78.87% of cases and benign in 21.13%. Two clinical characteristics (age and gender) and four radiological characteristics (calcification, vascular convergence, pleural retraction sign, and density) were identified as independent predictors of malignancy in patients with SPN using logistic regression analysis. The area under the receiver operating characteristic curve (0.748) of the present model was greater than the other two reported models. Diameter, spiculation, lobulation, vascular convergence, and pleural retraction signs differed significantly among pre-invasive lesions, minimally invasive adenocarcinoma, and invasive adenocarcinoma. Only diameter and density were significantly different among invasive adenocarcinoma subtypes.

CONCLUSIONS

Older age, male gender, no calcification, vascular convergence, pleural contraction sign, and lower density were independent malignancy predictors of SPNs. Furthermore, the pathological classification can be clarified based on the radiological characteristics of SPN, providing a new option for the prevention and treatment of early lung cancer.

Construction and validation of a predictive model of invasive adenocarcinoma in pure ground-glass nodules less than 2 cm in diameter

OBJECTIVES

In this study, we aimed to develop a multiparameter prediction model to improve the diagnostic accuracy of invasive adenocarcinoma in pulmonary pure glass nodules.

METHOD

We included patients with pulmonary pure glass nodules who underwent lung resection and had a clear pathology between January 2020 and January 2022 at the Qilu Hospital of Shandong University. We collected data on the clinical characteristics of the patients as well as their preoperative biomarker results and computed tomography features. Thereafter, we performed univariate and multivariate logistic regression analyses to identify independent risk factors, which were then used to develop a prediction model and nomogram. We then evaluated the recognition ability of the model via receiver operating characteristic (ROC) curve analysis and assessed its calibration ability using the Hosmer-Lemeshow test and calibration curves. Further, to assess the clinical utility of the nomogram, we performed decision curve analysis.

RESULT

We included 563 patients, comprising 174 and 389 cases of invasive and non-invasive adenocarcinoma, respectively, and identified seven independent risk factors, namely, maximum tumor diameter, age, serum amyloid level, pleural effusion sign, bronchial sign, tumor location, and lobulation. The area under the ROC curve was 0.839 (95% CI: 0.798-0.879) for the training cohort and 0.782 (95% CI: 0.706-0.858) for the validation cohort, indicating a relatively high predictive accuracy for the nomogram. Calibration curves for the prediction model also showed good calibration for both cohorts, and decision curve analysis showed that the clinical prediction model has clinical utility.

CONCLUSION

The novel nomogram thus constructed for identifying invasive adenocarcinoma in patients with isolated pulmonary pure glass nodules exhibited excellent discriminatory power, calibration capacity, and clinical utility.

LIONS PREY: A New Logistic Scoring System for the Prediction of Malignant Pulmonary Nodules

OBJECTIVES

Classifying radiologic pulmonary lesions as malignant is challenging. Scoring systems like the Mayo model lack precision in predicting the probability of malignancy. We developed the logistic scoring system 'LIONS PREY' (Lung lesION Score PREdicts malignancY), which is superior to existing models in its precision in determining the likelihood of malignancy.

METHODS

We evaluated all patients that were presented to our multidisciplinary team between January 2013 and December 2020. Availability of pathological results after resection or CT-/EBUS-guided sampling was mandatory for study inclusion. Two groups were formed: Group A (malignant nodule; n = 238) and Group B (benign nodule; n = 148). Initially, 22 potential score parameters were derived from the patients' medical histories.

RESULTS

After uni- and multivariate analysis, we identified the following eight parameters that were integrated into a scoring system: (1) age (Group A: 64.5 ± 10.2 years vs. Group B: 61.6 ± 13.8 years; multivariate p-value: 0.054); (2) nodule size (21.8 ± 7.5 mm vs. 18.3 ± 7.9 mm; p = 0.051); (3) spiculation (73.1% vs. 41.9%; p = 0.024); (4) solidity (84.9% vs. 62.8%; p = 0.004); (5) size dynamics (6.4 ± 7.7 mm/3 months vs. 0.2 ± 0.9 mm/3 months; p < 0.0001); (6) smoking history (92.0% vs. 43.9%; p < 0.0001); (7) pack years (35.1 ± 19.1 vs. 21.3 ± 18.8; p = 0.079); and (8) cancer history (34.9% vs. 24.3%; p = 0.052). Our model demonstrated superior precision to that of the Mayo score (p = 0.013) with an overall correct classification of 96.0%, a calibration (observed/expected-ratio) of 1.1, and a discrimination (ROC analysis) of AUC (95% CI) 0.94 (0.92-0.97).

CONCLUSIONS

Focusing on essential parameters, LIONS PREY can be easily and reproducibly applied based on computed tomography (CT) scans. Multidisciplinary team members could use it to facilitate decision making. Patients may find it easier to consent to surgery knowing the likelihood of pulmonary malignancy. The LIONS PREY app is available for free on Android and iOS devices.

Radiomics and artificial intelligence for risk stratification of pulmonary nodules: Ready for primetime?

Pulmonary nodules are ubiquitously found on computed tomography (CT) imaging either incidentally or via lung cancer screening and require careful diagnostic evaluation and management to both diagnose malignancy when present and avoid unnecessary biopsy of benign lesions. To engage in this complex decision-making, clinicians must first risk stratify pulmonary nodules to determine what the best course of action should be. Recent developments in imaging technology, computer processing power, and artificial intelligence algorithms have yielded radiomics-based computer-aided diagnosis tools that use CT imaging data including features invisible to the naked human eye to predict pulmonary nodule malignancy risk and are designed to be used as a supplement to routine clinical risk assessment. These tools vary widely in their algorithm construction, internal and external validation populations, intended-use populations, and commercial availability. While several clinical validation studies have been published, robust clinical utility and clinical effectiveness data are not yet currently available. However, there is reason for optimism as ongoing and future studies aim to target this knowledge gap, in the hopes of improving the diagnostic process for patients with pulmonary nodules.

Diagnostic yield using electromagnetic navigation bronchoscopy for peripheral pulmonary nodules <2 cm

BACKGROUND

Although electromagnetic navigation bronchoscopy (ENB) is highly sensitive in the diagnosis of peripheral pulmonary nodules (PPNs), its diagnostic yield for subgroups of smaller PPNs is under evaluation.

OBJECTIVES

Diagnostic yield evaluation of biopsy using ENB for PPNs <2 cm.

DESIGN

The diagnostic yield, sensitivity, specificity, positive predictive value, and negative predictive value of the ENB-mediated biopsy for PPNs were evaluated.

METHODS

Patients who had PPNs with diameters <2 cm and underwent ENB-mediated biopsy between May 2015 and February 2020 were consecutively enrolled. The final diagnosis was made via pathological examination after surgery.

RESULTS

A total of 82 lesions from 65 patients were analyzed. The median tumor size was 11 mm. All lesions were subjected to ENB-mediated biopsy, of which 29 and 53 were classified as malignant and benign, respectively. Subsequent segmentectomy, lobectomy, or wedge resection, following pathological examinations were performed on 64 nodules from 57 patients. The overall sensitivity, specificity, positive predictive value, and negative predictive value for nodules <2 cm were 53.3%, 91.7%, 92.3%, and 51.2%, respectively. The receiver operating curve showed an area under the curve of 0.721 (p < 0.001). Additionally, the sensitivity, specificity, positive predictive value, and negative predictive value were 62.5%, 100%, 100%, and 42.9%, respectively, for nodules with diameters equal to or larger than 1 cm; and 30.8%, 86.7%, 66.7%, and 59.1%, respectively, for nodules less than 1 cm. In the subgroup analysis, neither the lobar location nor the distance of the PPNs to the pleura affected the accuracy of the ENB diagnosis. However, the spiculated sign had a negative impact on the accuracy of the ENB biopsy (p = 0.010).

CONCLUSION

ENB has good specificity and positive predictive value for diagnosing PPNs <2 cm; however, the spiculated sign may negatively affect ENB diagnostic accuracy. In addition, the diagnostic reliability may only be limited to PPNs equal to or larger than 1 cm.

Deep learning for malignancy risk estimation of incidental sub-centimeter pulmonary nodules on CT images

OBJECTIVES

To establish deep learning models for malignancy risk estimation of sub-centimeter pulmonary nodules incidentally detected by chest CT and managed in clinical settings.

MATERIALS AND METHODS

Four deep learning models were trained using CT images of sub-centimeter pulmonary nodules from West China Hospital, internally tested, and externally validated on three cohorts. The four models respectively learned 3D deep features from the baseline whole lung region, baseline image patch where the nodule located, baseline nodule box, and baseline plus follow-up nodule boxes. All regions of interest were automatically segmented except that the nodule boxes were additionally manually checked. The performance of models was compared with each other and that of three respiratory clinicians.

RESULTS

There were 1822 nodules (981 malignant) in the training set, 806 (416 malignant) in the testing set, and 357 (253 malignant) totally in the external sets. The area under the curve (AUC) in the testing set was 0.754, 0.855, 0.928, and 0.942, respectively, for models derived from baseline whole lung, image patch, nodule box, and the baseline plus follow-up nodule boxes. When baseline models externally validated (follow-up images not available), the nodule-box model outperformed the other two with AUC being 0.808, 0.848, and 0.939 respectively in the three external datasets. The resident, junior, and senior clinicians achieved an accuracy of 67.0%, 82.5%, and 90.0%, respectively, in the testing set. The follow-up model performed comparably to the senior clinician.

CONCLUSION

The deep learning algorithms solely mining nodule information can efficiently predict malignancy of incidental sub-centimeter pulmonary nodules.

CLINICAL RELEVANCE STATEMENT

The established models may be valuable for supporting clinicians in routine clinical practice, potentially reducing the number of unnecessary examinations and also delays in diagnosis.

KEY POINTS

• According to different regions of interest, four deep learning models were developed and compared to evaluate the malignancy of sub-centimeter pulmonary nodules by CT images. • The models derived from baseline nodule box or baseline plus follow-up nodule boxes demonstrated sufficient diagnostic accuracy (86.4% and 90.4% in the testing set), outperforming the respiratory resident (67.0%) and junior clinician (82.5%). • The proposed deep learning methods may aid clinicians in optimizing follow-up recommendations for sub-centimeter pulmonary nodules and may lead to fewer unnecessary diagnostic interventions.

Noninvasive diagnosis of pulmonary nodules using a circulating tsRNA-based nomogram

Evaluating the accuracy of pulmonary nodule diagnosis avoids repeated low-dose computed tomography (LDCT)/CT scans or invasive examination, yet remains a main clinical challenge. Screening for new diagnostic tools is urgent. Herein, we established a nomogram based on the diagnostic signature of five circulating tsRNAs and CT information to predict malignant pulmonary nodules. In total, 249 blood samples of patients with pulmonary nodules were selected from three different lung cancer centers. Five tsRNAs were identified in the discovery and training cohorts and the diagnostic signature was established by the randomForest algorithm (tRF-Ser-TGA-003, tRF-Val-CAC-005, tRF-Ala-AGC-060, tRF-Val-CAC-024, and tiRNA-Gln-TTG-001). A nomogram was developed by combining tsRNA signature and CT information. The high level of accuracy was identified in an internal validation cohort (n = 83, area under the receiver operating characteristic curve [AUC] = 0.930, sensitivity 100.0%, specificity 73.8%) and external validation cohort (n = 66, AUC = 0.943, sensitivity 100.0%, specificity 86.8%). Furthermore, the diagnostic ability of our model discriminating invasive malignant ones from noninvasive lesions was assessed. A robust performance was achieved in the diagnosis of invasive malignant lesions in both training and validation cohorts (discovery cohort: AUC = 0.850, sensitivity 86.0%, specificity 81.4%; internal validation cohort: AUC = 0.784, sensitivity 78.8%, specificity 78.1%; and external validation cohort: AUC = 0.837, sensitivity 85.7%, specificity 84.0%). This novel circulating tsRNA-based diagnostic model has potential significance in predicting malignant pulmonary nodules. Application of the model could improve the accuracy of pulmonary nodule diagnosis and optimize surgical plans.

Factors associated with overdiagnosis of benign pulmonary nodules as malignancy: a retrospective cohort study

OBJECTIVE

To establish a preoperative model for the differential diagnosis of benign and malignant pulmonary nodules (PNs), and to evaluate the related factors of overdiagnosis of benign PNs at the time of imaging assessments.

MATERIALS AND METHODS

In this retrospective study, 357 patients (median age, 52 years; interquartile range, 46-59 years) with 407 PNs were included, who underwent surgical histopathologic evaluation between January 2020 and December 2020. Patients were divided into a training set (n = 285) and a validation set (n = 122) to develop a preoperative model to identify benign PNs. CT scan features were reviewed by two chest radiologists, and imaging findings were categorized. The overdiagnosis rate of benign PNs was calculated, and bivariate and multivariable logistic regression analyses were used to evaluate factors associated with benign PNs that were over-diagnosed as malignant PNs.

RESULTS

The preoperative model identified features such as the absence of part-solid and non-solid nodules, absence of spiculation, absence of vascular convergence, larger lesion size, and CYFRA21-1 positivity as features for identifying benign PNs on imaging, with a high area under the receiver operating characteristic curve of 0.88 in the validation set. The overdiagnosis rate of benign PNs was found to be 50%. Independent risk factors for overdiagnosis included diagnosis as non-solid nodules, pleural retraction, vascular convergence, and larger lesion size at imaging.

CONCLUSION

We developed a preoperative model for identifying benign and malignant PNs and evaluating factors that led to the overdiagnosis of benign PNs. This preoperative model and result may help clinicians and imaging physicians reduce unnecessary surgery.

Clinical Adjuncts to Lung Cancer Screening: A Narrative Review

The updated US Preventive Services Task Force guidelines on lung cancer screening have significantly expanded the population of screening eligible adults, among whom the balance of benefits and harms associated with lung cancer screening vary considerably. Clinical adjuncts are additional information and tools that can guide decision-making to optimally screen individuals who are most likely to benefit. Proposed adjuncts include integration of clinical history, risk prediction models, shared-decision-making tools, and biomarker tests at key steps in the screening process. Although evidence regarding their clinical utility and implementation is still evolving, they carry significant promise in optimizing screening effectiveness and efficiency for lung cancer.

The Thoracic Research Evaluation and Treatment 2.0 Model: A Lung Cancer Prediction Model for Indeterminate Nodules Referred for Specialist Evaluation

BACKGROUND

Appropriate risk stratification of indeterminate pulmonary nodules (IPNs) is necessary to direct diagnostic evaluation. Currently available models were developed in populations with lower cancer prevalence than that seen in thoracic surgery and pulmonology clinics and usually do not allow for missing data. We updated and expanded the Thoracic Research Evaluation and Treatment (TREAT) model into a more generalized, robust approach for lung cancer prediction in patients referred for specialty evaluation.

RESEARCH QUESTION

Can clinic-level differences in nodule evaluation be incorporated to improve lung cancer prediction accuracy in patients seeking immediate specialty evaluation compared with currently available models?

STUDY DESIGN AND METHODS

Clinical and radiographic data on patients with IPNs from six sites (N = 1,401) were collected retrospectively and divided into groups by clinical setting: pulmonary nodule clinic (n = 374; cancer prevalence, 42%), outpatient thoracic surgery clinic (n = 553; cancer prevalence, 73%), or inpatient surgical resection (n = 474; cancer prevalence, 90%). A new prediction model was developed using a missing data-driven pattern submodel approach. Discrimination and calibration were estimated with cross-validation and were compared with the original TREAT, Mayo Clinic, Herder, and Brock models. Reclassification was assessed with bias-corrected clinical net reclassification index and reclassification plots.

RESULTS

Two-thirds of patients had missing data; nodule growth and fluorodeoxyglucose-PET scan avidity were missing most frequently. The TREAT version 2.0 mean area under the receiver operating characteristic curve across missingness patterns was 0.85 compared with that of the original TREAT (0.80), Herder (0.73), Mayo Clinic (0.72), and Brock (0.68) models with improved calibration. The bias-corrected clinical net reclassification index was 0.23.

INTERPRETATION

The TREAT 2.0 model is more accurate and better calibrated for predicting lung cancer in high-risk IPNs than the Mayo, Herder, or Brock models. Nodule calculators such as TREAT 2.0 that account for varied lung cancer prevalence and that consider missing data may provide more accurate risk stratification for patients seeking evaluation at specialty nodule evaluation clinics.

Assessing the clinical utility of biomarkers using the intervention probability curve (IPC)

BACKGROUND

Assessing the clinical utility of biomarkers is a critical step before clinical implementation. The reclassification of patients across clinically relevant subgroups is considered one of the best methods to estimate clinical utility. However, there are important limitations with this methodology. We recently proposed the intervention probability curve (IPC) which models the likelihood that a provider will choose an intervention as a continuous function of the probability, or risk, of disease.

OBJECTIVE

To assess the potential impact of a new biomarker for lung cancer using the IPC.

METHODS

The IPC derived from the National Lung Screening Trial was used to assess the potential clinical utility of a biomarker for suspected lung cancer. The summary statistics of the change in likelihood of intervention over the population can be interpreted as the expected clinical impact of the added biomarker.

RESULTS

The IPC analysis of the novel biomarker estimated that 8% of the benign nodules could avoid an invasive procedure while the cancer nodules would largely remain unchanged (0.1%). We showed the benefits of this approach compared to traditional reclassification methods based on thresholds.

CONCLUSIONS

The IPC methodology can be a valuable tool for assessing biomarkers prior to clinical implementation.

A Multicenter, Single-Arm, Prospective Trial Assessing the Diagnostic Yield of Electromagnetic Bronchoscopic and Transthoracic Navigation for Peripheral Pulmonary Nodules

Rationale: Strict adherence to procedural protocols and diagnostic definitions is critical to understand the efficacy of new technologies. Electromagnetic navigational bronchoscopy (ENB) for lung nodule biopsy has been used for decades without a solid understanding of its efficacy, but offers the opportunity for simultaneous tissue acquisition via electromagnetic navigational transthoracic biopsy (EMN-TTNA) and staging via endobronchial ultrasound (EBUS). Objective: To evaluate the diagnostic yield of EBUS, ENB, and EMN-TTNA during a single procedure using a strict a priori definition of diagnostic yield with central pathology adjudication. Methods: A prospective, single-arm trial was conducted at eight centers enrolling participants with pulmonary nodules (<3 cm; without computed tomography [CT]- and/or positron emission tomography-positive mediastinal lymph nodes) who underwent a staged procedure with same-day CT, EBUS, ENB, and EMN-TTNA. The procedure was staged such that, when a diagnosis had been achieved via rapid on-site pathologic evaluation, the procedure was ended and subsequent biopsy modalities were not attempted. A study finding was diagnostic if an independent pathology core laboratory confirmed malignancy or a definitive benign finding. The primary endpoint was the diagnostic yield of the combination of CT, EBUS, ENB, and EMN-TTNA. Measurements and Main Results: A total of 160 participants at 8 centers with a mean nodule size of 18 ± 6 mm were enrolled. The diagnostic yield of the combined procedure was 59% (94 of 160; 95% confidence interval [CI], 51-66%). Nodule regression was found on same-day CT in 2.5% of cases (4 of 160; 95% CI, 0.69-6.3%), and EBUS confirmed malignancy in 7.1% of cases (11 of 156; 95% CI, 3.6-12%). The yield of ENB alone was 49% (74 of 150; 95% CI, 41-58%), that of EMN-TTNA alone was 27% (8 of 30; 95% CI, 12-46%), and that of ENB plus EMN-TTNA was 53% (79 of 150; 95% CI, 44-61%). Complications included a pneumothorax rate of 10% and a 2% bleeding rate. When EMN-TTNA was performed, the pneumothorax rate was 30%. Conclusions: The diagnostic yield for ENB is 49%, which increases to 59% with the addition of same-day CT, EBUS, and EMN-TTNA, lower than in prior reports in the literature. The high complication rate and low diagnostic yield of EMN-TTNA does not support its routine use. Clinical trial registered with www.clinicaltrials.gov (NCT03338049).

[Prevention, Diagnosis, Therapy, and Follow-up of Lung Cancer - Interdisciplinary Guideline of the German Respiratory Society and the German Cancer Society - Abridged Version]

The current S3 Lung Cancer Guidelines are edited with fundamental changes to the previous edition based on the dynamic influx of information to this field:The recommendations include de novo a mandatory case presentation for all patients with lung cancer in a multidisciplinary tumor board before initiation of treatment, furthermore CT-Screening for asymptomatic patients at risk (after federal approval), recommendations for incidental lung nodule management , molecular testing of all NSCLC independent of subtypes, EGFR-mutations in resectable early stage lung cancer in relapsed or recurrent disease, adjuvant TKI-therapy in the presence of common EGFR-mutations, adjuvant consolidation treatment with checkpoint inhibitors in resected lung cancer with PD-L1 ≥ 50%, obligatory evaluation of PD-L1-status, consolidation treatment with checkpoint inhibition after radiochemotherapy in patients with PD-L1-pos. tumor, adjuvant consolidation treatment with checkpoint inhibition in patients withPD-L1 ≥ 50% stage IIIA and treatment options in PD-L1 ≥ 50% tumors independent of PD-L1status and targeted therapy and treatment option immune chemotherapy in first line SCLC patients.Based on the current dynamic status of information in this field and the turnaround time required to implement new options, a transformation to a "living guideline" was proposed.

Expanding Role of Advanced Image Analysis in CT-detected Indeterminate Pulmonary Nodules and Early Lung Cancer Characterization

The implementation of low-dose chest CT for lung screening presents a crucial opportunity to advance lung cancer care through early detection and interception. In addition, millions of pulmonary nodules are incidentally detected annually in the United States, increasing the opportunity for early lung cancer diagnosis. Yet, realization of the full potential of these opportunities is dependent on the ability to accurately analyze image data for purposes of nodule classification and early lung cancer characterization. This review presents an overview of traditional image analysis approaches in chest CT using semantic characterization as well as more recent advances in the technology and application of machine learning models using CT-derived radiomic features and deep learning architectures to characterize lung nodules and early cancers. Methodological challenges currently faced in translating these decision aids to clinical practice, as well as the technical obstacles of heterogeneous imaging parameters, optimal feature selection, choice of model, and the need for well-annotated image data sets for the purposes of training and validation, will be reviewed, with a view toward the ultimate incorporation of these potentially powerful decision aids into routine clinical practice.

Nomogram combining clinical and radiological characteristics for predicting the malignant probability of solitary pulmonary nodules measuring ≤ 2 cm

Background

At present, how to identify the benign or malignant nature of small (≤ 2 cm) solitary pulmonary nodules (SPN) are an urgent clinical challenge. This retrospective study aimed to develop a clinical prediction model combining clinical and radiological characteristics for assessing the probability of malignancy in SPNs measuring ≤ 2 cm.

Method

In this study, we included patients with SPNs measuring ≤ 2 cm who underwent pulmonary resection with definite pathology at Qilu Hospital of Shandong University from January 2020 to December 2021. Clinical features, preoperative biomarker results, and computed tomography characteristics were collected. The enrolled patients were randomized at a ratio of 7:3 into a training cohort of 775 and a validation cohort of 331. The training cohort was used to construct the predictive model, while the validation cohort was used to test the model independently. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors. The prediction model and nomogram were established based on the independent risk factors. The receiver operating characteristic (ROC) curve was used to evaluate the identification ability of the model. The calibration power was evaluated using the Hosmer-Lemeshow test and calibration curve. The clinical utility of the nomogram was also assessed by decision curve analysis (DCA).

Result

A total of 1,106 patients were included in this study. Among them, the malignancy rate of SPNs was 85.08% (941/1,106). We finally identified the following six independent risk factors by logistic regression: age, carcinoembryonic antigen, nodule shape, calcification, maximum diameter, and consolidation-to-tumor ratio. The area under the ROC curve (AUC) for the training cohort was 0.764 (95% confidence interval [CI]: 0.714-0.814), and the AUC for the validation cohort was 0.729 (95% CI: 0.647-0.811), indicating that the prediction accuracy of nomogram was relatively good. The calibration curve of the predictive model also demonstrated a good calibration in both cohorts. DCA proved that the clinical prediction model was useful in clinical practice.

Conclusion

We developed and validated a predictive model and nomogram for estimating the probability of malignancy in SPNs measuring ≤ 2 cm. With the application of predictive models, thoracic surgeons can make more rational clinical decisions while avoiding overtreatment and wasting medical resources.

A machine learning-based PET/CT model for automatic diagnosis of early-stage lung cancer

Objective

The aim of this study was to develop a machine learning-based automatic analysis method for the diagnosis of early-stage lung cancer based on positron emission tomography/computed tomography (PET/CT) data.

Methods

A retrospective cohort study was conducted using PET/CT data from 187 cases of non-small cell lung cancer (NSCLC) and 190 benign pulmonary nodules. Twelve PET and CT features were used to train a diagnosis model. The performance of the machine learning-based PET/CT model was tested and validated in two separate cohorts comprising 462 and 229 cases, respectively.

Results

The standardized uptake value (SUV) was identified as an important biochemical factor for the early stage of lung cancer in this model. The PET/CT diagnosis model had a sensitivity and area under the curve (AUC) of 86.5% and 0.89, respectively. The testing group comprising 462 cases showed a sensitivity and AUC of 85.7% and 0.87, respectively, while the validation group comprising 229 cases showed a sensitivity and AUC of 88.4% and 0.91, respectively. Additionally, the proposed model improved the clinical discrimination ability for solid pulmonary nodules (SPNs) in the early stage significantly.

Conclusion

The feature data collected from PET/CT scans can be analyzed automatically using machine learning techniques. The results of this study demonstrated that the proposed model can significantly improve the accuracy and positive predictive value (PPV) of SPNs at the early stage. Furthermore, this algorithm can be optimized into a robotic and less biased PET/CT automatic diagnosis system.

Improving lung cancer diagnosis with cancer, fungal, and imaging biomarkers

OBJECTIVE

Indeterminate pulmonary nodules (IPNs) represent a significant diagnostic burden in health care. We aimed to compare a combination clinical prediction model (Mayo Clinic model), fungal (histoplasmosis serology), imaging (computed tomography [CT] radiomics), and cancer (high-sensitivity cytokeratin fraction 21; hsCYFRA 21-1) biomarker approach to a validated prediction model in diagnosing lung cancer.

METHODS

A prospective specimen collection, retrospective blinded evaluation study was performed in 3 independent cohorts with 6- to 30-mm IPNs (n = 281). Serum histoplasmosis immunoglobulin G and immunoglobulin M antibodies and hsCYFRA 21-1 levels were measured and a validated CT radiomic score was calculated. Multivariable logistic regression models were estimated with Mayo Clinic model variables, histoplasmosis antibody levels, CT radiomic score, and hsCYFRA 21-1. Diagnostic performance of the combination model was compared with that of the Mayo Clinic model. Bias-corrected clinical net reclassification index (cNRI) was used to estimate the clinical utility of a combination biomarker approach.

RESULTS

A total of 281 patients were included (111 from a histoplasmosis-endemic region). The combination biomarker model including the Mayo Clinic model score, histoplasmosis antibody levels, radiomics, and hsCYFRA 21-1 level showed improved diagnostic accuracy for IPNs compared with the Mayo Clinic model alone with an area under the receiver operating characteristics curve of 0.80 (95% CI, 0.76-0.84) versus 0.72 (95% CI, 0.66-0.78). Use of this combination model correctly reclassified intermediate risk IPNs into low- or high-risk category (cNRI benign = 0.11 and cNRI malignant = 0.16).

CONCLUSIONS

The addition of cancer, fungal, and imaging biomarkers improves the diagnostic accuracy for IPNs. Integrating a combination biomarker approach into the diagnostic algorithm of IPNs might decrease unnecessary invasive testing of benign nodules and reduce time to diagnosis for cancer.

Assessing a biomarker's ability to reduce invasive procedures in patients with benign lung nodules: Results from the ORACLE study

A blood-based integrated classifier (IC) has been clinically validated to improve accuracy in assessing probability of cancer risk (pCA) for pulmonary nodules (PN). This study evaluated the clinical utility of this biomarker for its ability to reduce invasive procedures in patients with pre-test pCA ≤ 50%. This was a propensity score matching (PSM) cohort study comparing patients in the ORACLE prospective, multicenter, observational registry to control patients treated with usual care. This study enrolled patients meeting the intended use criteria for IC testing: pCA ≤ 50%, age ≥40 years, nodule diameter 8-30 mm, and no history of lung cancer and/or active cancer (except for non-melanomatous skin cancer) within 5 years. The primary aim of this study was to evaluate invasive procedure use on benign PNs of registry patients as compared to control patients. A total of 280 IC tested, and 278 control patients met eligibility and analysis criteria and 197 were in each group after PSM (IC and control groups). Patients in the IC group were 74% less likely to undergo an invasive procedure as compared to the control group (absolute difference 14%, p <0.001) indicating that for every 7 patients tested, one unnecessary invasive procedure was avoided. Invasive procedure reduction corresponded to a reduction in risk classification, with 71 patients (36%) in the IC group classified as low risk (pCA < 5%). The proportion of IC group patients with malignant PNs sent to surveillance were not statistically different than the control group, 7.5% vs 3.5% for the IC vs. control groups, respectively (absolute difference 3.91%, p 0.075). The IC for patients with a newly discovered PN has demonstrated valuable clinical utility in a real-world setting. Use of this biomarker can change physicians' practice and reduce invasive procedures in patients with benign pulmonary nodules. Trial registration: Clinical trial registration: ClinicalTrials.gov NCT03766958.

Multi-Omic Biomarkers Improve Indeterminate Pulmonary Nodule Malignancy Risk Assessment

The clinical management of patients with indeterminate pulmonary nodules is associated with unintended harm to patients and better methods are required to more precisely quantify lung cancer risk in this group. Here, we combine multiple noninvasive approaches to more accurately identify lung cancer in indeterminate pulmonary nodules. We analyzed 94 quantitative radiomic imaging features and 41 qualitative semantic imaging variables with molecular biomarkers from blood derived from an antibody-based microarray platform that determines protein, cancer-specific glycan, and autoantibody-antigen complex content with high sensitivity. From these datasets, we created a PSR (plasma, semantic, radiomic) risk prediction model comprising nine blood-based and imaging biomarkers with an area under the receiver operating curve (AUROC) of 0.964 that when tested in a second, independent cohort yielded an AUROC of 0.846. Incorporating known clinical risk factors (age, gender, and smoking pack years) for lung cancer into the PSR model improved the AUROC to 0.897 in the second cohort and was more accurate than a well-characterized clinical risk prediction model (AUROC = 0.802). Our findings support the use of a multi-omics approach to guide the clinical management of indeterminate pulmonary nodules.

Incidental Pulmonary Nodules and Lung Cancer Screening

Incidental nodules and lung cancer screening nodules are causes of concern and anxiety for the patients. Both these require diligent follow up according to their respective guidelines.

High risk lung nodule: A multidisciplinary approach to diagnosis and management

Pulmonary nodules are often discovered incidentally during CT scans performed for other reasons. While the vast majority of nodules are benign, a small percentage may represent early-stage lung cancer with the potential for curative treatments. With the growing use of CT for both clinical purposes and lung cancer screening, the number of pulmonary nodules detected is expected to increase substantially. Despite well-established guidelines, many nodules do not receive proper evaluation due to a variety of factors, including inadequate coordination of care and financial and social barriers. To address this quality gap, novel approaches such as multidisciplinary nodule clinics and multidisciplinary boards may be necessary. As pulmonary nodules may indicate early-stage lung cancer, it is crucial to adopt a risk-stratified approach to identify potential lung cancers at an early stage, while minimizing the risk of harm and expense associated with over investigation of low-risk nodules. This article, authored by multiple specialists involved in nodule management, delves into the diagnostic approach to lung nodules. It covers the process of determining whether a patient requires tissue sampling or continued surveillance. Additionally, the article provides an in-depth examination of the various biopsy and therapeutic options available for malignant lung nodules. The article also emphasizes the significance of early detection in reducing lung cancer mortality, especially among high-risk populations. Furthermore, it addresses the creation of a comprehensive lung nodule program, which involves smoking cessation, lung cancer screening, and systematic evaluation and follow-up of both incidental and screen-detected nodules.

Diagnostic outcomes of robotic-assisted bronchoscopy for pulmonary lesions in a real-world multicenter community setting

BACKGROUND

Robot-assisted bronchoscopy (RAB) is among the newest bronchoscopic technologies, allowing improved visualization and access for small and hard-to-reach nodules. RAB studies have primarily been conducted at academic centers, limiting the generalizability of results to the broader real-world setting, while variability in diagnostic yield definitions has impaired the validity of cross-study comparisons. The objective of this study was to determine the diagnostic yield and sensitivity for malignancy of RAB in patients with pulmonary lesions in a community setting and explore the impact of different definitions on diagnostic yield estimates.

METHODS

Data were collected retrospectively from medical records of patients ≥ 21 years who underwent bronchoscopy with the Monarch® Platform (Auris Health, Inc., Redwood City, CA) for biopsy of pulmonary lesions at three US community hospitals between January 2019 and March 2020. Diagnostic yield was calculated at the index RAB and using 12-month follow-up data. At index, all malignant and benign (specific and non-specific) diagnoses were considered diagnostic. After 12 months, benign non-specific cases were considered diagnostic only when follow-up data corroborated the benign result. An alternative definition at index classified benign non-specific results as non-diagnostic, while an alternative 12-month definition categorized index non-diagnostic cases as diagnostic if no malignancy was diagnosed during follow-up.

RESULTS

The study included 264 patients. Median lesion size was 19.3 mm, 58.9% were peripherally located, and 30.1% had a bronchus sign. Samples were obtained via Monarch in 99.6% of patients. Pathology led to a malignant diagnosis in 115 patients (43.6%), a benign diagnosis in 110 (41.7%), and 39 (14.8%) non-diagnostic cases. Index diagnostic yield was 85.2% (95% CI: [80.9%, 89.5%]) and the 12-month diagnostic yield was 79.4% (95% CI: [74.4%, 84.3%]). Alternative definitions resulted in diagnostic yield estimates of 58.7% (95% CI: [52.8%, 64.7%]) at index and 89.0% (95% CI: [85.1%, 92.8%]) at 12 months. Sensitivity for malignancy was 79.3% (95% CI: [72.7%, 85.9%]) and cancer prevalence was 58.0% after 12 months.

CONCLUSIONS

RAB demonstrated a high diagnostic yield in the largest study to date, despite representing a real-world community population with a relatively low prevalence of cancer. Alternative definitions had a considerable impact on diagnostic yield estimates.

Multi-omics integrated circulating cell-free DNA genomic signatures enhanced the diagnostic performance of early-stage lung cancer and postoperative minimal residual disease

BACKGROUND

Liquid biopsy is a promising non-invasive alternative for cancer screening and minimal residual disease (MRD) detection, although there are some concerns regarding its clinical applications. We aimed to develop an accurate detection platform based on liquid biopsy for both cancer screening and MRD detection in patients with lung cancer (LC), which is also applicable to clinical use.

METHODS

We applied a modified whole-genome sequencing (WGS) -based High-performance Infrastructure For MultIomics (HIFI) method for LC screening and postoperative MRD detection by combining the hyper-co-methylated read approach and the circulating single-molecule amplification and resequencing technology (cSMART2.0).

FINDINGS

For early screening of LC, the LC score model was constructed using the support vector machine, which showed sensitivity (51.8%) at high specificity (96.3%) and achieved an AUC of 0.912 in the validation set prospectively enrolled from multiple centers. The screening model achieved detection efficiency with an AUC of 0.906 in patients with lung adenocarcinoma and outperformed other clinical models in solid nodule cohort. When applied the HIFI model to real social population, a negative predictive value (NPV) of 99.92% was achieved in Chinese population. Additionally, the MRD detection rate improved significantly by combining results from WGS and cSMART2.0, with sensitivity of 73.7% at specificity of 97.3%.

INTERPRETATION

In conclusion, the HIFI method is promising for diagnosis and postoperative monitoring of LC.

FUNDING

This study was supported by CAMS Innovation Fund for Medical Sciences, Chinese Academy of Medical Sciences, National Natural Science Foundation of China, Beijing Natural Science Foundation and Peking University People's Hospital.

Performance of radiomics models derived from different CT reconstruction parameters for lung cancer risk prediction

BACKGROUND

This study analysed the performance of radiomics features extracted from computed tomography (CT) images with different reconstruction parameters in differentiating malignant and benign pulmonary nodules.

METHODS

We evaluated routine chest CT images acquired from 148 participants with pulmonary nodules, which were pathologically diagnosed during surgery in West China Hospital, including a 5 mm unenhanced lung window, a 5 mm unenhanced mediastinal window, a 5 mm contrast-enhanced mediastinal window and a 1 mm unenhanced lung window. The pulmonary nodules were segmented, and 1409 radiomics features were extracted for each window. Then, we created 15 cohorts consisting of single windows or multiple windows. Univariate correlation analysis and principal component analysis were performed to select the features, and logistic regression analysis was performed to establish models for each cohort. The area under the curve (AUC) was applied to compare model performance.

RESULTS

There were 75 benign and 73 malignant pulmonary nodules, with mean diameters of 18.63 and 19.86 mm, respectively. For the single-window setting, the AUCs of the radiomics model from the 5 mm unenhanced lung window, 5 mm unenhanced mediastinal window, 5 mm contrast-enhanced mediastinal window and 1 mm unenhanced lung window were 0.771, 0.808, 0.750, and 0.771 in the training set and 0.711, 0.709, 0.684, and 0.674 in the test set, respectively. Regarding the multiple-window setting, the radiomics model based on all four windows showed an AUC of 0.825 in the training set and 0.743 in the test set. Statistically, the 15 models demonstrated comparable performances (P > 0.05).

CONCLUSION

A single chest CT window was acceptable in predicting the malignancy of pulmonary nodules, and additional windows did not statistically improve the performance of the radiomics models. In addition, slice thickness and contrast enhancement did not affect the diagnostic performance.

Development and Validation of a Risk Assessment Model for Pulmonary Nodules Using Plasma Proteins and Clinical Factors

BACKGROUND

Deficiencies in risk assessment for patients with pulmonary nodules (PNs) contribute to unnecessary invasive testing and delays in diagnosis.

RESEARCH QUESTION

What is the accuracy of a novel PN risk model that includes plasma proteins and clinical factors? How does the accuracy compare with that of an established risk model?

STUDY DESIGN AND METHODS

Based on technology using magnetic nanosensors, assays were developed with seven plasma proteins. In a training cohort (n = 429), machine learning approaches were used to identify an optimal algorithm that subsequently was evaluated in a validation cohort (n = 489), and its performance was compared with the Mayo Clinic model.

RESULTS

In the training set, we identified a support vector machine algorithm that included the seven plasma proteins and six clinical factors that demonstrated an area under the receiver operating characteristic curve of 0.87 and met other selection criteria. The resulting risk reclassification model (RRM) was used to recategorize patients with a pretest risk of between 10% and 84%, and its performance was assessed across five risk strata (low, ≤ 10%; moderate, 10%-34%; intermediate, 35%-70%; high, 71%-84%; very high, > 85%). Stratification by the RRM decreased the proportion of intermediate-risk patients from 26.7% to 10.8% (P < .001) and increased the low-risk and high-risk strata from 16.8% to 21.9% (P < .001) and from 3.7% to 12.1% (P < .001), respectively. Among patients classified as low risk by the RRM and Mayo Clinic model, the corresponding true-negative to false-negative ratios were 16.8 and 19.5, respectively. Among patients classified as very high risk by the RRM and Mayo Clinic model, the corresponding true-positive to false-positive ratios were 28.5 and 17.0, respectively. Compared with the Mayo Clinic model, the RRM provided higher specificity at the low-risk threshold and higher sensitivity at the very high-risk threshold.

INTERPRETATION

The RRM accurately reclassified some patients into low-risk and very high-risk categories, suggesting the potential to improve PN risk assessment.

Improving Lung Cancer Diagnosis with CT Radiomics and Serum Histoplasmosis Testing

BACKGROUND

Indeterminate pulmonary nodules (IPN) are a diagnostic challenge in regions where pulmonary fungal disease and smoking prevalence are high. We aimed to determine the impact of a combined fungal and imaging biomarker approach compared with a validated prediction model (Mayo) to rule out benign disease and diagnose lung cancer.

METHODS

Adults ages 40 to 90 years with 6-30 mm IPNs were included from four sites. Serum samples were tested for histoplasmosis IgG and IgM antibodies by enzyme immunoassay and a CT-based risk score was estimated from a validated radiomic model. Multivariable logistic regression models including Mayo score, radiomics score, and IgG and IgM histoplasmosis antibody levels were estimated. The areas under the ROC curves (AUC) of the models were compared among themselves and to Mayo. Bias-corrected clinical net reclassification index (cNRI) was estimated to assess clinical reclassification using a combined biomarker model.

RESULTS

We included 327 patients; 157 from histoplasmosis-endemic regions. The combined biomarker model including radiomics, histoplasmosis serology, and Mayo score demonstrated improved diagnostic accuracy when endemic histoplasmosis was accounted for [AUC, 0.84; 95% confidence interval (CI), 0.79-0.88; P < 0.0001 compared with 0.73; 95% CI, 0.67-0.78 for Mayo]. The combined model demonstrated improved reclassification with cNRI of 0.18 among malignant nodules.

CONCLUSIONS

Fungal and imaging biomarkers may improve diagnostic accuracy and meaningfully reclassify IPNs. The endemic prevalence of histoplasmosis and cancer impact model performance when using disease related biomarkers.

IMPACT

Integrating a combined biomarker approach into the diagnostic algorithm of IPNs could decrease time to diagnosis.

Differences in VA and non-VA pulmonary nodules: All evaluations are not created equal

BACKGROUND

Indeterminate pulmonary nodules present a common challenge for clinicians who must recommend surveillance or intervention based on an assessed risk of malignancy.

PATIENTS AND METHODS

In this cohort study, patients presenting for indeterminate pulmonary nodule evaluation were enrolled at sites participating in the Colorado SPORE in Lung Cancer. They were followed prospectively and included for analysis if they had a definitive malignant diagnosis, benign diagnosis, or radiographic resolution or stability of their nodule for > 2 years.

RESULTS

Patients evaluated at the Veterans Affairs (VA) and non-VA sites were equally as likely to have a malignant diagnosis (48%). The VA cohort represented a higher-risk group than the non-VA cohort regarding smoking history and chronic obstructive pulmonary disease (COPD). There were more squamous cell carcinoma diagnoses among VA malignant nodules (25% vs. 10%) and a later stage at diagnosis among VA patients. Discrimination and calibration of risk calculators produced estimates that were wide-ranging and different when comparing between risk score calculators as well as between VA/non-VA cohorts. Application of current American College of Chest Physicians guidelines to our groups could have resulted in inappropriate resection of 12% of benign nodules.

CONCLUSION

Comparison of VA with non-VA patients shows important differences in underlying risk, histology of malignant nodules, and stage at diagnosis. This study highlights the challenge in applying risk calculators to a clinical setting, as the model discrimination and calibration were variable between calculators and between our higher-risk VA and lower-risk non-VA groups.

MICROABSTRACT

Risk stratification and management of indeterminate pulmonary nodules (IPNs) is a common clinical problem. In this prospective cohort study of 282 patients with IPNs from Veterans Affairs (VA) and non-VA sites, we found differences in patient and nodule characteristics, histology and diagnostic stage, and risk calculator performance. Our findings highlight challenges and shortcomings of current IPN management guidelines and tools.

Patient and Nodule Characteristics Associated With a Lung Cancer Diagnosis Among Individuals With Incidentally Detected Lung Nodules

BACKGROUND

Pulmonary nodules are a common incidental finding on CT imaging. Few studies have described patient and nodule characteristics associated with a lung cancer diagnosis using a population-based cohort.

RESEARCH QUESTION

Does a relationship exist between patient and nodule characteristics and lung cancer among individuals with incidentally detected pulmonary nodules, and can this information be used to create exploratory lung cancer prediction models with reasonable performance characteristics?

STUDY DESIGN AND METHODS

We conducted a retrospective cohort study of adults older than 18 years with lung nodules of any size incidentally detected by chest CT imaging between 2005 and 2015. All patients had at least 2 years of complete follow-up. To evaluate the relationship between patient and nodule characteristics and lung cancer, we used binomial regression. We used logistic regression to create prediction models, and we internally validated model performance using bootstrap optimism correction.

RESULTS

Among 7,240 patients with a median age of 67 years, 56% of whom were women, with a median BMI of 28 kg/m2, 56% of whom were ever smokers, 31% of whom had prior nonlung malignancy, with a median nodule size 5.6 mm, 57% of whom had multiple nodules, and 40% of whom had an upper lobe nodule, 265 patients (3.7%; 95% CI, 3.2%-4.1%) had a diagnosis of lung cancer. In a multivariate analysis, age, sex, BMI, smoking history, and nodule size and location were associated with a lung cancer diagnosis, whereas prior malignancy and nodule number and laterality were not. We were able to construct two prediction models with an area under the curve value of 0.75 (95% CI, 0.72-0.80) and reasonable calibration.

INTERPRETATION

Lung cancer is uncommon among individuals with incidentally detected lung nodules. Some, but not all, previously identified factors associated with lung cancer also were associated with this outcome in this sample. These findings may have implications for clinical practice, future practice guidelines, and the development of novel lung cancer prediction models for individuals with incidentally detected lung nodules.

Diagnosing Non-Small Cell Lung Cancer by Exhaled Breath Profiling Using an Electronic Nose: A Multicenter Validation Study

BACKGROUND

Despite the potential of exhaled breath analysis of volatile organic compounds to diagnose lung cancer, clinical implementation has not been realized, partly due to the lack of validation studies.

RESEARCH QUESTION

This study addressed two questions. First, can we simultaneously train and validate a prediction model to distinguish patients with non-small cell lung cancer from non-lung cancer subjects based on exhaled breath patterns? Second, does addition of clinical variables to exhaled breath data improve the diagnosis of lung cancer?

STUDY DESIGN AND METHODS

In this multicenter study, subjects with non-small cell lung cancer and control subjects performed 5 min of tidal breathing through the aeoNose, a handheld electronic nose device. A training cohort was used for developing a prediction model based on breath data, and a blinded cohort was used for validation. Multivariable logistic regression analysis was performed, including breath data and clinical variables, in which the formula and cutoff value for the probability of lung cancer were applied to the validation data.

RESULTS

A total of 376 subjects formed the training set, and 199 subjects formed the validation set. The full training model (including exhaled breath data and clinical parameters from the training set) were combined in a multivariable logistic regression analysis, maintaining a cut off of 16% probability of lung cancer, resulting in a sensitivity of 95%, a specificity of 51%, and a negative predictive value of 94%; the area under the receiver-operating characteristic curve was 0.87. Performance of the prediction model on the validation cohort showed corresponding results with a sensitivity of 95%, a specificity of 49%, a negative predictive value of 94%, and an area under the receiver-operating characteristic curve of 0.86.

INTERPRETATION

Combining exhaled breath data and clinical variables in a multicenter, multi-device validation study can adequately distinguish patients with lung cancer from subjects without lung cancer in a noninvasive manner. This study paves the way to implement exhaled breath analysis in the daily practice of diagnosing lung cancer.

CLINICAL TRIAL REGISTRATION

The Netherlands Trial Register; No.: NL7025; URL: https://trialregister.nl/trial/7025.

Clinical Scores, Biomarkers and IT Tools in Lung Cancer Screening-Can an Integrated Approach Overcome Current Challenges?

As most lung cancer (LC) cases are still detected at advanced and incurable stages, there are increasing efforts to foster detection at earlier stages by low dose computed tomography (LDCT) based LC screening. In this scoping review, we describe current advances in candidate selection for screening (selection phase), technical aspects (screening), and probability evaluation of malignancy of CT-detected pulmonary nodules (PN management). Literature was non-systematically assessed and reviewed for suitability by the authors. For the selection phase, we describe current eligibility criteria for screening, along with their limitations and potential refinements through advanced clinical scores and biomarker assessments. For LC screening, we discuss how the accuracy of computerized tomography (CT) scan reading might be augmented by IT tools, helping radiologists to cope with increasing workloads. For PN management, we evaluate the precision of follow-up scans by semi-automatic volume measurements of CT-detected PN. Moreover, we present an integrative approach to evaluate the probability of PN malignancy to enable safe decisions on further management. As a clear limitation, additional validation studies are required for most innovative diagnostic approaches presented in this article, but the integration of clinical risk models, current imaging techniques, and advancing biomarker research has the potential to improve the LC screening performance generally.

Prediction of histologic types in solid lung lesions using preoperative contrast-enhanced CT

OBJECTIVES

This study aimed to develop and validate a predicting model for the histologic classification of solid lung lesions based on preoperative contrast-enhanced CT.

METHODS

A primary dataset of 1012 patients from Tianjin Medical University Cancer Institute and Hospital (TMUCIH) was randomly divided into a development cohort (708) and an internal validation cohort (304). Patients from the Second Hospital of Shanxi Medical University (SHSMU) were set as an external validation cohort (212). Two clinical factors (age, gender) and twenty-one characteristics on contrast-enhanced CT were used to construct a multinomial multivariable logistic regression model for the classification of seven common histologic types of solid lung lesions. The area under the receiver operating characteristic curve was used to assess the diagnostic performance of the model in the development and validation cohorts, separately.

RESULTS

Multivariable analysis showed that two clinical factors and twenty-one characteristics on contrast-enhanced CT were predictive in lung lesion histologic classification. The mean AUC of the proposed model for histologic classification was 0.95, 0.94, and 0.92 in the development, internal validation, and external validation cohort, respectively. When determining the malignancy of lung lesions based on histologic types, the mean AUC of the model was 0.88, 0.86, and 0.90 in three cohorts.

CONCLUSIONS

We demonstrated that by utilizing both clinical and CT characteristics on contrast-enhanced CT images, the proposed model could not only effectively stratify histologic types of solid lung lesions, but also enabled accurate assessment of lung lesion malignancy. Such a model has the potential to avoid unnecessary surgery for patients and to guide clinical decision-making for preoperative treatment.

KEY POINTS

• Clinical and CT characteristics on contrast-enhanced CT could be used to differentiate histologic types of solid lung lesions. • Predicting models using preoperative contrast-enhanced CT could accurately assessment of tumor malignancy based on predicted histologic types.

Incidentalomas in chest CT

Advances in imaging technology have dramatically increased the resolution of CT and improved detection of disease; these advances also have led to an increase in incidentalomas or incidental findings that often do not represent significant disease. Incidental findings on thoracic CT are common and can be problematic and expensive to evaluate. Thoracic imagers often are having to make recommendations for appropriate management which adds to the burden. Thoracic CT incidental findings are broad and include those of the lungs, heart, mediastinum, pleura, chest wall, thoracic soft tissues as well as the lower neck and upper abdomen. Of these, incidental pulmonary nodules have garnered the most interest over the years, but all incidentals may be proven to represent significant disease. In the USA, the American College of Radiology has generated white papers on incidentals that have proven useful. Currently, a number of investigations to utilize artificial intelligence for qualification and management of incidentals are ongoing. Likewise, the radiology/imaging community must support efforts to collaboratively address incidental findings and management concerns. As such, continued efforts to establish guidelines for appropriate identification, classification and management of incidentals is important to improve patient care and assure fiscally responsible assessment.

Diagnostic Accuracy of a Convolutional Neural Network Assessment of Solitary Pulmonary Nodules Compared With PET With CT Imaging and Dynamic Contrast-Enhanced CT Imaging Using Unenhanced and Contrast-Enhanced CT Imaging

BACKGROUND

Solitary pulmonary nodules (SPNs) measuring 8 to 30 mm in diameter require further workup to determine the likelihood of malignancy.

RESEARCH QUESTION

What is the diagnostic performance of a lung cancer prediction convolutional neural network (LCP-CNN) in SPNs using unenhanced and contrast-enhanced CT imaging compared with the current clinical workup?

STUDY DESIGN AND METHODS

This was a post hoc analysis of the Single Pulmonary Nodule Investigation: Accuracy and Cost-Effectiveness of Dynamic Contrast Enhanced Computed Tomography in the Characterisation of Solitary Pulmonary Nodules trial, a prospective multicenter study comparing the diagnostic accuracy of dynamic contrast-enhanced (DCE) CT imaging with PET imaging in SPNs. The LCP-CNN was designed and validated in an external cohort. LCP-CNN-generated risk scores were created from the noncontrast and contrast-enhanced CT scan images from the DCE CT imaging. The gold standard was histologic analysis or 2 years of follow-up. The area under the receiver operating characteristic curves (AUC) were calculated using LCP-CNN score, maximum standardized uptake value, and DCE CT scan maximum enhancement and were compared using the DeLong test.

RESULTS

Two hundred seventy participants (mean ± SD age, 68.3 ± 8.8 years; 49% women) underwent PET with CT scan imaging and DCE CT imaging with CT scan data available centrally for LCP-CNN analysis. The accuracy of the LCP-CNN on the noncontrast images (AUC, 0.83; 95% CI, 0.79-0.88) was superior to that of DCE CT imaging (AUC, 0.76; 95% CI, 0.69-0.82; P = .03) and equal to that of PET with CT scan imaging (AUC, 0.86; 95% CI, 0.81-0.90; P = .35). The presence of contrast resulted in a small reduction in diagnostic accuracy, with the AUC falling from 0.83 (95% CI, 0.79-0.88) on the noncontrast images to 0.80 to 0.83 after contrast (P < .05 for 240 s after contrast only).

INTERPRETATION

An LCP-CNN algorithm provides an AUC equivalent to PET with CT scan imaging in the diagnosis of solitary pulmonary nodules.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier; No.: NCT02013063.

Clinical Impact and Generalizability of a Computer-Assisted Diagnostic Tool to Risk-Stratify Lung Nodules With CT

OBJECTIVE

To evaluate whether an imaging classifier for radiology practice can improve lung nodule classification and follow-up.

METHODS

A machine learning classifier was developed and trained using imaging data from the National Lung Screening Trial (NSLT) to produce a malignancy risk score (malignancy Similarity Index [mSI]) for individual lung nodules. In addition to NLST cohorts, external cohorts were developed from a tertiary referral lung cancer screening program data set and an external nonscreening data set of all nodules detected on CT. Performance of the mSI combined with Lung-RADS was compared with Lung-RADS alone and the Mayo and Brock risk calculators.

RESULTS

We analyzed 963 subjects and 1,331 nodules across these cohorts. The mSI was comparable in accuracy (area under the curve = 0.89) to existing clinical risk models (area under the curve = 0.86-0.88) and independently predictive in the NLST cohort of 704 nodules. When compared with Lung-RADS, the mSI significantly increased sensitivity across all cohorts (25%-117%), with significant increases in specificity in the screening cohorts (17%-33%). When used in conjunction with Lung-RADS, use of mSI would result in earlier diagnoses and reduced follow-up across cohorts, including the potential for early diagnosis in 42% of malignant NLST nodules from prior-year CT scans.

CONCLUSION

A computer-assisted diagnosis software improved risk classification from chest CTs of screening and incidentally detected lung nodules compared with Lung-RADS. mSI added predictive value independent of existing radiological and clinical variables. These results suggest the generalizability and potential clinical impact of a tool that is straightforward to implement in practice.

Morphologic Severity of Atypia Is Predictive of Lung Cancer Diagnosis

In cytologic analysis of lung nodules, specimens classified as atypia cannot be definitively diagnosed as benign or malignant. Atypia patients are typically subject to additional procedures to obtain repeat samples, thus delaying diagnosis. We evaluate morphologic categories predictive of lung cancer in atypia patients. This retrospective study stratified patients evaluated for primary lung nodules based on cytologic diagnoses. Atypia patients were further stratified based on the most severe verbiage used to describe the atypical cytology. Logistic regressions and receiver operator characteristic curves were performed. Of 129 patients with cytologic atypia, 62.8% later had cytologically or histologically confirmed lung cancer and 37.2% had benign respiratory processes. Atypia severity significantly predicted final diagnosis even while controlling for pack years and modified Herder score (p = 0.012). Pack years, atypia severity, and modified Herder score predicted final diagnosis independently and while adjusting for covariates (all p < 0.001). This model generated a significantly improved area under the curve compared to pack years, atypia severity, and modified Herder score (all p < 0.001) alone. Patients with severe atypia may benefit from repeat sampling for cytologic confirmation within one month due to high likelihood of malignancy, while those with milder atypia may be followed clinically.

Correlation between lung cancer probability and number of pulmonary nodules in baseline computed tomography lung cancer screening: A retrospective study based on the Chinese population

Background

Screening for lung cancer with LDCT detects a large number of nodules. However, it is unclear whether nodule number influences lung cancer probability. This study aimed to acquire deeply insight into the distribution characteristics of nodule number in the Chinese population and to reveal the association between the nodule number and the probability of lung cancer (LC).

Methods

10,167 asymptomatic participants who underwent LDCT LC screening were collected. Noncalcified nodules larger than 4 mm were included. The nodule number per participant was determined. We defined five categories according to the number of nodules (based on nodule type and size): one, two, three, four, and more than four nodules. We stratified the nodules as groups A, B, and C and participants as Amax, Bmax, and Cmax groups, and explored the association between nodule number and the probability of LC on nodule and participant levels.

Results

97 participants were confirmed to have LC. The probabilities of LC were 49/1719, 22/689, 11/327, 6/166, and 9/175 in participants with one, two, three, four, and more than four nodules (p>0.05), respectively. In the Bmax group, the probability of LC was significantly higher in participants with one nodule than those with >4 nodules (p<0.05), and the probability of LC showed a negative linear trend with increasing nodule numbers (p<0.05). Based on the nodule-level analyses, in Group B, LC probability was significantly higher when participants had a solitary nodule than when they had >4 nodules (p<0.05).

Conclusion

LC probability does not significantly change with the number of nodules. However, when stratified by the nodule size, the effect of nodule number on LC probability was nodule-size dependent, and greater attention and active follow-up are required for solitary nodules especially SNs/solid component of PSNs measuring 6-15 mm or NSNs measuring 8-15 mm. Assessing the nodule number in conjunction with nodule size in baseline LDCT LC screening is considered beneficial.