Incidental Lung Nodules on Cross-sectional Imaging: Current Reporting and Management

Early comparison robotic bronchoscopy versus electromagnetic navigational bronchoscopy for biopsy of pulmonary nodules in a thoracic surgery practice

Pulmonary nodules are frequently encountered in high-risk patients. Often these require biopsy which can be challenging. We relate our experience comparing use of electromagnetic navigational bronchoscopy (ENB) to a robotic bronchoscopy system (RB). A retrospective review of patients undergoing bronchoscopic biopsy from 2015 to 2021. The timeframe overlapped with transition from ENB using Veran SPiN system to RB using Ion system by Intuitive. Patient and nodule characteristics were collected. Primary end point was overall diagnostic yield which was defined by pathologic confirmation of malignancy or benign finding. Secondary outcomes included diagnostic yield based on overall size of nodules and need for further work up and testing. 116 patients underwent ENB or RB of 134 nodules. No perioperative complications occurred. Diagnostic yield of ENB was 49.5% (41/91 nodules) versus 86.1% (37/43 nodules) for RB. Average nodule size for ENB was 2.55 cm versus 1.96 cm for RB. When divided based on size, ENB had a 30% diagnostic yield for nodules 1-2 cm (11/37 nodules, mean size 1.46 cm) and 64% yield for nodules 2-3 cm (14/22 nodules, mean size 2.38 cm). RB had an 81% yield for nodules 1-2 cm (mean size 1.41 cm) and 100% yield for nodules 2-3 cm (mean 2.3 cm). RB showed superiority over ENB in early implementation trials for biopsy of suspicious pulmonary nodules. It is a safe technology allowing for increased access to all lung fields and utilization in the thoracic surgical practice will be paramount to advancing the field.

Cell-Free DNA Fragmentomes in the Diagnostic Evaluation of Patients With Symptoms Suggestive of Lung Cancer

BACKGROUND

The diagnostic workup of individuals suspected of having lung cancer can be complex and protracted because conventional symptoms of lung cancer have low specificity and sensitivity.

RESEARCH QUESTION

Among individuals with symptoms of lung cancer, can a blood-based approach to analyze cell-free DNA (cfDNA) fragmentation (the DNA evaluation of fragments for early interception [DELFI] score) enhance evaluation for the possible presence of lung cancer?

STUDY DESIGN AND METHODS

Adults were referred to Bispebjerg Hospital (Copenhagen, Denmark) for diagnostic evaluation of initial imaging anomalies and symptoms consistent with lung cancer. Numbers and types of symptoms were extracted from medical records. cfDNA from plasma samples obtained at the prediagnostic visit was isolated, sequenced, and analyzed for genome-wide cfDNA fragmentation patterns. The relationships among clinical presentation, cancer status, and DELFI score were examined.

RESULTS

A total of 296 individuals were analyzed. Median DELFI scores were higher for those with lung cancer (n = 98) than those without cancer (n = 198; 0.94 vs 0.19; P < .001). In a multivariate model adjusted for age, smoking history, and presenting symptoms, the addition of the DELFI score improved the prediction of lung cancer for those who demonstrated symptoms (area under the receiver operating characteristic curve, 0.74-0.94).

INTERPRETATION

The DELFI score distinguishes individuals with lung cancer from those without cancer better than suspicious symptoms do. These results represent proof-of-concept support that fragmentation-based biomarker approaches may facilitate diagnostic resolution for patients with concerning symptoms of lung cancer.

A comprehensive nomogram combining CT-based radiomics with clinical features for differentiation of benign and malignant lung subcentimeter solid nodules

Objective

To establish a nomogram based on non-enhanced computed tomography(CT) imaging radiomics and clinical features for use in predicting the malignancy of sub-centimeter solid nodules (SCSNs).

Materials and methods

Retrospective analysis was performed of records for 198 patients with SCSNs that were surgically resected and examined pathologically at two medical institutions between January 2020 and June 2021. Patients from Center 1 were included in the training cohort (n = 147), and patients from Center 2 were included in the external validation cohort (n = 52). Radiomic features were extracted from chest CT images. The least absolute shrinkage and selection operator (LASSO) regression model was used for radiomic feature extraction and computation of radiomic scores. Clinical features, subjective CT findings, and radiomic scores were used to build multiple predictive models. Model performance was examined by evaluating the area under the receiver operating characteristic curve (AUC). The best model was selected for efficacy evaluation in a validation cohort, and column line plots were created.

Results

Pulmonary malignant nodules were significantly associated with vascular alterations in both the training (p &lt; 0.001) and external validation (p &lt; 0.001) cohorts. Eleven radiomic features were selected after a dimensionality reduction to calculate the radiomic scores. Based on these findings, three prediction models were constructed: subjective model (Model 1), radiomic score model (Model 2), and comprehensive model (Model 3), with AUCs of 0.672, 0.888, and 0.930, respectively. The optimal model with an AUC of 0.905 was applied to the validation cohort, and decision curve analysis indicated that the comprehensive model column line plot was clinically useful.

Conclusion

Predictive models constructed based on CT-based radiomics with clinical features can help clinicians diagnose pulmonary nodules and guide clinical decision making.

Pulmonary Histoplasmosis: A Clinical Update

Histoplasma capsulatum, the etiological agent for histoplasmosis, is a dimorphic fungus that grows as a mold in the environment and as a yeast in human tissues. The areas of highest endemicity lie within the Mississippi and Ohio River Valleys of North America and parts of Central and South America. The most common clinical presentations include pulmonary histoplasmosis, which can resemble community-acquired pneumonia, tuberculosis, sarcoidosis, or malignancy; however, certain patients can develop mediastinal involvement or progression to disseminated disease. Understanding the epidemiology, pathology, clinical presentation, and diagnostic testing performance is pivotal for a successful diagnosis. While most immunocompetent patients with mild acute or subacute pulmonary histoplasmosis should receive therapy, all immunocompromised patients and those with chronic pulmonary disease or progressive disseminated disease should also receive therapy. Liposomal amphotericin B is the agent of choice for severe or disseminated disease, and itraconazole is recommended in milder cases or as "step-down" therapy after initial improvement with amphotericin B. In this review, we discuss the current epidemiology, pathology, diagnosis, clinical presentations, and management of pulmonary histoplasmosis.

Identifying Solitary Granulomatous Nodules from Solid Lung Adenocarcinoma: Exploring Robust Image Features with Cross-Domain Transfer Learning

PURPOSE

This study aimed to find suitable source domain data in cross-domain transfer learning to extract robust image features. Then, a model was built to preoperatively distinguish lung granulomatous nodules (LGNs) from lung adenocarcinoma (LAC) in solitary pulmonary solid nodules (SPSNs).

METHODS

Data from 841 patients with SPSNs from five centres were collected retrospectively. First, adaptive cross-domain transfer learning was used to construct transfer learning signatures (TLS) under different source domain data and conduct a comparative analysis. The Wasserstein distance was used to assess the similarity between the source domain and target domain data in cross-domain transfer learning. Second, a cross-domain transfer learning radiomics model (TLRM) combining the best performing TLS, clinical factors and subjective CT findings was constructed. Finally, the performance of the model was validated through multicentre validation cohorts.

RESULTS

Relative to other source domain data, TLS based on lung whole slide images as source domain data (TLS-LW) had the best performance in all validation cohorts (AUC range: 0.8228-0.8984). Meanwhile, the Wasserstein distance of TLS-LW was 1.7108, which was minimal. Finally, TLS-LW, age, spiculated sign and lobulated shape were used to build the TLRM. In all validation cohorts, The AUC ranges were 0.9074-0.9442. Compared with other models, decision curve analysis and integrated discrimination improvement showed that TLRM had better performance.

CONCLUSIONS

The TLRM could assist physicians in preoperatively differentiating LGN from LAC in SPSNs. Furthermore, compared with other images, cross-domain transfer learning can extract robust image features when using lung whole slide images as source domain data and has a better effect.