Identification of predictors for brain metastasis in newly diagnosed non-small cell lung cancer: a single-center cohort study

Comparison of 68Ga-FAP-2286 and 18F-FDG PET/CT in the diagnosis of advanced lung cancer

Purpose

The 68Ga/177Lu-FAP-2286 is a newly developed tumor imaging agent that shows potential for visualizing and treating tumor stroma. The objective of this research was to evaluate the effectiveness of 68Ga-FAP-2286 PET/CT and 18F-FDG PET/CT in diagnosing advanced lung cancer.

Methods

In this prospective study, patients with lung cancer who underwent 68Ga-FAP-2286 and 18F-FDG PET/CT examinations between September 2022 and June 2023 were analyzed. Lesion uptake was converted to SUVmax. A paired T-test was used to compare the SUVmax, and the number of positive lesions detected by the two methods was recorded.

Results

In total, 31 participants (median age: 56 years) were assessed. The uptake of 68Ga-FAP-2286 was significantly higher than that of 18F-FDG in primary lesions (9.90 ± 5.61 vs. 6.09 ± 2.84, respectively, P < 0.001), lymph nodes (7.95 ± 2.75 vs. 5.55 ± 1.59, respectively, P=0.01), and bone metastases (7.74 ± 3.72 vs. 5.66 ± 3.55, respectively, P=0.04). Furthermore, the detection sensitivity of lymph nodes using 68Ga-FAP-2286 PET/CT was superior to that with 18F-FDG PET/CT [100% (137/137) vs. 78.8% (108/137), respectively], as well as for bone metastases [100% (384/384) vs. 68.5% (263/384), respectively]. However, the detection sensitivity for primary tumors using both modalities was comparable [100% (13/13) for both].

Conclusion

Compared to 18F-FDG PET/CT, 68Ga-FAP-2286 PET/CT demonstrated better lesion detection capabilities for lung cancer, particularly in lymph nodes and bone metastases, providing compelling imaging evidence for the efficacy of 177Lu-FAP-2286 treatment.

Survival outcomes and predicting intracranial metastasis in stage III non-small cell lung cancer treated with definitive chemoradiation: Real-world data from a tertiary cancer center

PURPOSE/OBJECTIVE

Around 30% of patients with non-small cell lung cancers (NSCLC) are diagnosed with stage III disease at presentation, of which about 50% are treated with definitive chemoradiation (CRT). Around 65-80% of patients will eventually develop intracranial metastases (IM), though associated risk factors are not clearly described. We report survival outcomes and risk factors for development of IM in a cohort of patients with stage III NSCLC treated with CRT at a tertiary cancer center.

MATERIALS/METHODS

We identified 195 patients with stage III NSCLC treated with CRT from January 2010 to May 2021. Multivariable logistic regression was used to generate odds ratios for covariates associated with development of IM. Kaplan-Meier analysis with the Log Rank test was used for unadjusted time-to-event analyses. P-value for statistical significance was set at < 0.05 with a two-sided test.

RESULTS

Out of 195 patients, 108 (55.4%) had stage IIIA disease and 103 (52.8%) had adenocarcinoma histology. The median age and follow-up (in months) was 67 (IQR 60-74) and 21 (IQR 12-43), respectively. The dose of radiation was 60 Gy in 30 fractions for148 patients (75.9%). Of the 77 patients who received treatment since immunotherapy was available and standard at our cancer center, 45 (58.4%) received at least one cycle. During follow-up, 84 patients (43.1%) developed any metastasis, and 33 (16.9%) developed IM (either alone or with extracranial metastasis). 150 patients (76.9%) experienced a treatment delay (interval between diagnosis and treatment > 4 weeks). Factors associated with developing any metastasis included higher overall stage at diagnosis (p = 0.013) and higher prescribed dose (p = 0.022). Factors associated with developing IM included higher ratio of involved over sampled lymph nodes (p = 0.001) and receipt of pre-CRT systemic or radiotherapy for any reason (p = 0.034). On multivariate logistical regression, treatment delay (OR 3.9, p = 0.036) and overall stage at diagnosis (IIIA vs. IIIB/IIIC) (OR 2.8, p = 0.02) predicted development of IM. These findings were sustained on sensitivity analysis using different delay intervals. Median OS was not reached for the overall cohort, and was 43.1 months for patients with IM and 40.3 months in those with extracranial-only metastasis (p = 0.968). In patients with any metastasis, median OS was longer (p = 0.003) for those who experienced a treatment delay (48.4 months) compared to those that did not (12.2 months), likely due to expedited diagnosis and treatment in patients with a higher symptom burden secondary to more advanced disease.

CONCLUSIONS

In patients with stage III NSCLC treated with definitive CRT, the risk of IM appears to increase with overall stage at diagnosis and, importantly, may be associated with experiencing a treatment delay (> 4 weeks). Metastatic disease of any kind remains the primary life-limiting prognostic factor in these patients with advanced lung cancer. In patients with metastatic disease, treatment delay was associated with better survival. Patients who experience a treatment delay and those initially diagnosed at a more advanced overall stage may warrant more frequent surveillance for early diagnosis and treatment of IM. Healthcare system stakeholders should strive to mitigate treatment delay in patients with locally NSCLC to reduce the risk of IM. Further research is needed to better understand factors associated with survival, treatment delay, and the development of IM after CRT in the immunotherapy era.

Individual risk and prognostic value prediction by machine learning for distant metastasis in pulmonary sarcomatoid carcinoma: a large cohort study based on the SEER database and the Chinese population

Background

This study aimed to develop diagnostic and prognostic models for patients with pulmonary sarcomatoid carcinoma (PSC) and distant metastasis (DM).

Methods

Patients from the Surveillance, Epidemiology, and End Results (SEER) database were divided into a training set and internal test set at a ratio of 7 to 3, while those from the Chinese hospital were assigned to the external test set, to develop the diagnostic model for DM. Univariate logistic regression was employed in the training set to screen for DM-related risk factors, which were included into six machine learning (ML) models. Furthermore, patients from the SEER database were randomly divided into a training set and validation set at a ratio of 7 to 3 to develop the prognostic model which predicts survival of patients PSC with DM. Univariate and multivariate Cox regression analyses have also been performed in the training set to identify independent factors, and a prognostic nomogram for cancer-specific survival (CSS) for PSC patients with DM.

Results

For the diagnostic model for DM, 589 patients with PSC in the training set, 255 patients in the internal and 94 patients in the external test set were eventually enrolled. The extreme gradient boosting (XGB) algorithm performed best on the external test set with an area under the curve (AUC) of 0.821. For the prognostic model, 270 PSC patients with DM in the training and 117 patients in the test set were enrolled. The nomogram displayed precise accuracy with AUC of 0.803 for 3-month CSS and 0.869 for 6-month CSS in the test set.

Conclusion

The ML model accurately identified individuals at high risk for DM who needed more careful follow-up, including appropriate preventative therapeutic strategies. The prognostic nomogram accurately predicted CSS in PSC patients with DM.

Recurrence Patterns and Patient Outcomes in Resected Lung Adenocarcinoma Differ according to Ground-Glass Opacity at CT

Background Although lung adenocarcinoma with ground-glass opacity (GGO) is known to have distinct characteristics, limited data exist on whether the recurrence pattern and outcomes in patients with resected lung adenocarcinoma differ according to GGO presence at CT. Purpose To examine recurrence patterns and associations with outcomes in patients with resected lung adenocarcinoma according to GGO at CT. Materials and Methods Patients who underwent CT followed by lobectomy or pneumonectomy for lung adenocarcinoma between July 2010 and December 2017 were retrospectively included. Patients were divided into two groups based on the presence of GGO: GGO adenocarcinoma and solid adenocarcinoma. Recurrence patterns at follow-up CT examinations were investigated and compared between the two groups. The effects of patient grouping on time to recurrence, postrecurrence survival (PRS), and overall survival (OS) were evaluated using Cox regression. Results Of 1019 patients (mean age, 62 years ± 9 [SD]; 520 women), 487 had GGO adenocarcinoma and 532 had solid adenocarcinoma. Recurrences occurred more frequently in patients with solid adenocarcinoma (36.1% [192 of 532 patients]) than in those with GGO adenocarcinoma (16.2% [79 of 487 patients]). Distant metastasis was the most common mode of recurrence in the group with solid adenocarcinoma and all clinical stages. In clinical stage I GGO adenocarcinoma, all regional recurrences appeared as ipsilateral lung metastasis (39.2% [20 of 51]) without regional lymph node metastasis. Brain metastasis was more frequent in patients with clinical stage I solid adenocarcinoma (16.5% [16 of 97 patients]). The presence of GGO was associated with time to recurrence and OS (adjusted hazard ratio [HR], 0.6 [P < .001] for both). Recurrence pattern was an independent risk factor for PRS (adjusted HR, 2.1 for distant metastasis [P < .001] and 3.9 for brain metastasis [P < .001], with local-regional recurrence as the reference). Conclusion Recurrence patterns, time to recurrence, and overall survival differed between patients with and without ground-glass opacity at CT, and recurrence patterns were associated with postrecurrence survival. © RSNA, 2023 Supplemental material is available for this article.

Machine Learning for the Prediction of Synchronous Organ-Specific Metastasis in Patients With Lung Cancer

Background

This study aimed to develop an artificial neural network (ANN) model for predicting synchronous organ-specific metastasis in lung cancer (LC) patients.

Methods

A total of 62,151 patients who diagnosed as LC without data missing between 2010 and 2015 were identified from Surveillance, Epidemiology, and End Results (SEER) program. The ANN model was trained and tested on an 75/25 split of the dataset. The receiver operating characteristic (ROC) curves, area under the curve (AUC) and sensitivity were used to evaluate and compare the ANN model with the random forest model.

Results

For distant metastasis in the whole cohort, the ANN model had metrics AUC = 0.759, accuracy = 0.669, sensitivity = 0.906, and specificity = 0.613, which was better than the random forest model. For organ-specific metastasis in the cohort with distant metastasis, the sensitivity in bone metastasis, brain metastasis and liver metastasis were 0.913, 0.906 and 0.925, respectively. The most important variable was separate tumor nodules with 100% importance. The second important variable was visceral pleural invasion for distant metastasis, while histology for organ-specific metastasis.

Conclusions

Our study developed a “two-step” ANN model for predicting synchronous organ-specific metastasis in LC patients. This ANN model may provide clinicians with more personalized clinical decisions, contribute to rationalize metastasis screening, and reduce the burden on patients and the health care system.

Comparison of 68Ga-FAPI and 18F-FDG PET/CT in the Evaluation of Advanced Lung Cancer

Background Gallium 68 (⁶⁸Ga)-labeled fibroblast-activation protein inhibitor (FAPI) has recently been introduced as a promising tumor imaging agent. Purpose To compare ⁶⁸Ga-FAPI PET/CT with fluorine 18 (¹⁸F)-labeled fluorodeoxyglucose (FDG) PET/CT in evaluating lung cancer. Materials and Methods In this prospective study conducted from September 2020 to February 2021, images from participants with lung cancer who underwent both ⁶⁸Ga-FAPI and ¹⁸F-FDG PET/CT examinations were analyzed. The tracer uptakes, quantified by maximum standardized uptake value (SUV_max) and target-to-background ratio (TBR), were compared for paired positive lesions between both modalities using the paired t test or Wilcoxon signed-rank test. Results Thirty-four participants (median age, 64 years [interquartile range: 46-80 years]; 20 men) were evaluated. From visual evaluation, ⁶⁸Ga-FAPI PET/CT and ¹⁸F-FDG PET/CT showed similar performance in the delineation of primary tumors and detection of suspected metastases in the lungs, liver, and adrenal glands. The metabolic tumor volume in primary and recurrent lung tumors showed no difference between modalities (mean: 11.6 vs 10.8, respectively; P = .68). However, compared with ¹⁸F-FDG PET/CT, ⁶⁸Ga-FAPI PET/CT depicted more suspected metastases in lymph nodes (356 vs 320), brain (23 vs 10), bone (109 vs 91), and pleura (66 vs 35). From semiquantitative evaluation, the SUV_max and TBR of primary or recurrent tumors, positive lymph nodes, bone lesions, and pleural lesions at ⁶⁸Ga-FAPI PET/CT were all higher than those at ¹⁸F-FDG PET/CT (all P < .01). Although SUV_max of ⁶⁸Ga-FAPI and ¹⁸F-FDG in brain metastases were not different (mean SUV_max: 9.0 vs 7.4, P = .32), TBR was higher with ⁶⁸Ga-FAPI than with ¹⁸F-FDG (mean: 314.4 vs 1.0, P = .02). Conclusion Gallium 68-labeled fibroblast-activation protein inhibitor PET/CT may outperform fluorine 18-labeled fluorodeoxyglucose PET/CT in staging lung cancer, particularly in the detection of metastasis to the brain, lymph nodes, bone, and pleura. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Jacobson and Van den Abbeele in this issue.