Lung Metastases In Patients Research Articles

Value of 18F-FDG PET/CT-based radiomics features for differentiating primary lung cancer and solitary lung metastasis in patients with colorectal adenocarcinoma

Objective To investigate the value and applicability of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomics in differentiating primary lung cancer (PLC) from solitary lung metastasis (SLM) in patients with colorectal cancer (CRC). Materials and methods This retrospective study included 103 patients with CRC and solitary pulmonary nodules (SPNs). The least absolute shrinkage and selection operator (LASSO) was used to screen for optimal radiomics features and establish a PET/CT radiomics model. PET/CT Visual and complex models (combining radiomics with PET/CT visual features) were developed. The area under the receiver operating characteristic (ROC) curve (AUC) was used to determine the predictive value and diagnostic efficiency of the models. Results The AUC of the PET/CT radiomics model for differentiating PLC from SLM was 0.872 (95% CI: 0.806–0.939), which was not different from that of the visual (0.829 [95% CI: 0.749–0.908; p = .352]). However, the AUC of the complex model (0.936 [95% CI:0.892–0.981]) was significantly higher than that of the PET/CT radiomics (p = .005) and visual model (p = .001). The sensitivity (SEN), specificity (SPE), accuracy (ACC), positive predictive value (PPV), and negative predictive value (NPV) of PET/CT radiomics for differentiating PLC from SLM were 0.720, 0.887, 0.806, 0.857, and 0.770, respectively. Conclusion PET/CT radiomics can effectively distinguish PLC and SLM in patients with CRC and SPNs and guide the implementation of personalized treatment.

Establishment of a nomogram for potential prediction of lung metastasis in patients with primary limb bone tumors: a study based on the SEER database.

The prognosis of lung metastasis in primary limb bone tumors represents a pivotal yet challenging aspect of oncological management. Despite advancements in diagnostic modalities, the predictive accuracy for metastatic spread remains suboptimal. This study aims to bridge this gap by leveraging the Surveillance, Epidemiology, and End Results (SEER) database to construct a nomogram that forecasts the risk of lung metastasis, thereby enhancing clinical decision-making processes. A retrospective cohort, including 1,822 patients with primary limb bony tumors from 2010 to 2015 in the SEER database, was extracted. Using precise inclusion and exclusion criteria, variables essential for predicting lung metastasis were identified through univariate and multivariate analyses, along with least absolute shrinkage and selection operator (LASSO) regression. These variables provided a solid basis for creating the multivariable nomogram, of which the discriminating power and utility were verified using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis. The model incorporated seven key predicting variables, including age, histological type, surgery, radiation, chemotherapy, T stage, and N stage. The nomogram emerged as a cohesive whole with good discriminative power. The area under the curve (AUC) was 0.806 in the training cohort and 0.767 in the validation cohort. The calibration curves demonstrated the model's validity by showing a good match between the actual outcomes and the model-predicted probabilities of lung metastasis. This study showed for the first time the reliability of the predictive model in translating the hard-to-interpret demographic, clinical, and pathologic data into a very usable predictive model. Thus, it represents a significant step toward demystifying the risk of lung metastasis in primary limb bone tumors. It is an invitation for a paradigm shift of oncology, to evidence-based, person-based oncology that is taking a new metric for cancer prognosis.

1938P Nomogram for predicting lung metastases in patients with papillary thyroid cancer under 55 years old

1938P Nomogram for predicting lung metastases in patients with papillary thyroid cancer under 55 years old

NQO1 Triggers Neutrophil Recruitment and NET Formation to Drive Lung Metastasis of Invasive Breast Cancer.

Metastasis to the lungs is a leading cause of death for patients with breast cancer. Therefore, effective therapies are urgently needed to prevent and treat lung metastasis. In this study, we uncovered a mechanism by which NAD(P)H:quinone oxidoreductase 1 (NQO1) orchestrates lung metastasis. NQO1 stabilized and upregulated peptidyl-prolyl cis-trans isomerase A (PPIA), a chaperone that regulates protein conformation and activity, by preventing its oxidation at a critical cysteine residue C161. PPIA subsequently activated CD147, a membrane protein that facilitates cell invasion. Moreover, NQO1-induced secretion of PPIA modulated the immune landscape of both primary and lung metastatic sites. Secreted PPIA engaged CD147 on neutrophils and triggered the release of neutrophil extracellular traps (NET) and neutrophil elastase, which enhanced tumor progression, invasiveness, and lung colonization. Pharmacological targeting of PPIA effectively inhibited NQO1-mediated breast cancer lung metastasis. These findings reveal a previously unrecognized NQO1-PPIA-CD147-NET axis that drives breast cancer lung metastasis. Inhibiting this axis is a potential therapeutic strategy to limit lung metastasis in patients with breast cancer. Significance: NQO1 stabilizes and promotes the secretion of PPIA to activate CD147 in neutrophils and stimulate NET formation, promoting breast cancer lung metastasis and providing therapeutic targets for this fatal condition.

Development of a prediction model for lung metastasis by using postoperative circulating tumor DNA binding clinicopathological risk factors in patients with colorectal cancer.

e15035 Background: Lung metastasis is common in patients with colorectal cancer (CRC). However, diagnosing lung metastasis in CRC is challenging due to slow-growing pulmonary lesions. Circulating tumor DNA (ctDNA) testing provides a direct indication of the presence of minimal residual disease (MRD) which contributing to cancer recurrence. Yet, there are no reports on the potential indications of ctDNA for the site of metastasis. The objective of this study is to develop a predictive model for lung metastasis in CRC patients who have received adjuvant therapy by integrating ctDNA with clinicopathological factors. Methods: Two independent cohorts' series were evaluated including 299 patients from China as training cohort and 134 patients from Spain as validation cohort from 2012-2020. We specifically focused on the detection of ctDNA in these patients. We employed LASSO regression for optimal feature selection and built a predictive model by multivariable logistic regression. Results: In training cohort, 59/299(19.7%) patients have detectable ctDNA. In validation cohort, 24/134 (18.6%) patients have detectable ctDNA. Patients who tested ctDNA-positive had a significantly higher incidence of lung metastasis (33.9% vs. 11.2%, P<0.001) compared to ctDNA-negative patients. A predictive model for lung metastasis was developed by multivariable logistic regression analysis. The model incorporated factors such as ctDNA status, preoperative carcinoembryonic antigen (CEA) level, presence of cancerous nodes, and the mutation status of Phosphatidylinositol-4,5-Bisphosphate 3-Kinase Catalytic Subunit Alpha (PIK3CA) in plasma. The lung metastasis prediction nomogram demonstrated a favorable ability to distinguish with a concordance index of 0.775 (95% CI: 0.706-0.775) during internal validation. The Hosmer-Lemeshow test, with p-value of 0.967, indicated that prediction nomogram model had a good fit. In addition, the prediction model of validation cohort demonstrated a discriminative performance with a concordance index of 0.724(95% CI: 0.698-0.724). Furthermore, the DCA (Decision Curve Analysis) and CIC (Clinical Impact Curve) in both cohorts indicated that the lung metastasis nomogram exhibited a favorable clinical net benefit. Finally, through multi-model comparison, it was found that the predictive performance of the model, which includes ctDNA and blood PIK3CA mutation status, was significantly superior to all clinical prediction models. Conclusions: A lung metastasis prediction nomogram was developed by integrating postoperative ctDNA and clinicopathological risk factors. The purpose of this nomogram is to assist clinicians in predicting the probability of lung metastasis in patients who have undergone surgery for CRC, with the aim to facilitate prompt intervention.

Tumor cell-released autophagosomes (TRAPs) induce PD-L1-decorated NETs that suppress T-cell function to promote breast cancer pulmonary metastasis

BackgroundLung metastasis is the primary cause of breast cancer-related mortality. Neutrophil extracellular traps (NETs) are involved in the progression of breast cancer. However, the mechanism of NET formation is not...

The Evaluation and Management of Lung Metastases in Patients with Giant Cell Tumors of Bone in the Denosumab Era.

Giant cell tumor of bone (GCTB) is characterized by uncertain biological behavior due to its local aggressiveness and metastasizing potential. In this study, we conducted a meta-analysis of the contemporary literature to evaluate all management strategies for GCTB metastases. A combination of the terms "lung metastases", "giant cell tumor", "bone", "treatment", and "oncologic outcomes" returned 133 patients meeting our inclusion criteria: 64 males and 69 females, with a median age of 28 years (7-63), at the onset of primary GCTB. Lung metastases typically occur at a mean interval of 26 months (range: 0-143 months) after treatment of the primary site, commonly presenting as multiple and bilateral lesions. Various treatment approaches, including surgery, chemotherapy, radiotherapy, and drug administration, were employed, while 35 patients underwent routine monitoring only. Upon a mean follow-up of about 7 years (range: 1-32 years), 90% of patients were found to be alive, while 10% had died. Death occurred in 25% of patients who had chemotherapy, whereas 96% of those not treated or treated with Denosumab alone were alive at a mean follow-up of 6 years (range: 1-19 years). Given the typically favorable prognosis of lung metastases in patients with GCTB, additional interventions beyond a histological diagnosis confirmation may not be needed. Denosumab, by reducing the progression of the disease, can play a pivotal role in averting or delaying lung failure.

A prediction model for lung metastases in patients with indeterminate pulmonary nodules in newly diagnosed colorectal cancer

IntroductionMultidisciplinary teams treating patients with newly diagnosed Colorectal Cancer (CRC) often encounter the appearance of Indeterminate Pulmonary Nodules (IPNs) that warrants follow–up with repetitive medical imaging and anxiety for patients. We determined the incidence of IPNs in patients with newly diagnosed CRC and developed and validated a model for individualized risk prediction of IPNs being lung metastases. Material and methodsNewly diagnosed CRC who underwent surgery between November 2011 to June 2014 were included to create the risk model, developed using both clinical experience and statistical selection. Discrimination and calibration slopes of the risk score were evaluated in an independent temporal validation sample. A nomogram is presented to assist clinicians in estimating an individual risk score. ResultsOut of 2111 CRC patients staged with chest CT, 204 (9.6%) had IPNs and 54/204 (26%) had lung metastases. We identified 4 predictors: “location of primary tumour”, “pathological nodal stage”, “size of the largest nodule” and “extrapulmonary synchronous metastases at diagnosis”. Discrimination of the final model in the validation sample was demonstrated by the difference in mean predicted risk between progressed cases en non-progressed cases (49% versus 21%, p = <0.001). ConclusionA prediction model with 4 clinical risk factors can be used to assist multidisciplinary teams in the prediction of individualized risk of lung metastases and imaging strategy in patients with IPNs and newly diagnosed colorectal cancer. The model performed well in new patients not included in the model development.

RANK/RANKL axis promotes migration, invasion, and metastasis of osteosarcoma via activating NF-κB pathway

Osteosarcoma (OS) is one of the most prevalent primary bone tumors with a high degree of metastasis and poor prognosis. Epithelial-to-mesenchymal transition (EMT) is a cellular mechanism that contributes to the invasion and metastasis of cancer cells, and OS cells have been reported to exhibit EMT-like characteristics. Our previous studies have shown that the interaction between tumor necrosis factor superfamily member 11 (TNFRSF11A; also known as RANK) and its ligand TNFSF11 (also known as RANKL) promotes the EMT process in breast cancer cells. However, whether the interaction between RANK and RANKL enhances aggressive behavior by inducing EMT in OS cells has not yet been elucidated. In this study, we showed that the interaction between RANK and RANKL increased the migration, invasion, and metastasis of OS cells by promoting EMT. Importantly, we clarified that the RANK/RANKL axis induces EMT by activating the nuclear factor-kappa B (NF-κB) pathway. Furthermore, the NF-κB inhibitor dimethyl fumarate (DMF) suppressed migration, invasion, and EMT in OS cells. Our results suggest that the RANK/RANKL axis may serve as a potential tumor marker and promising therapeutic target for OS metastasis. Furthermore, DMF may have clinical applications in the treatment of lung metastasis in patients with OS.

Abstract A039: Metabolic evolution in breast cancer predicts organ-specific metastasis

Abstract The metastatic cascade is a critical component of cancer evolution. Understanding the rewired metabolism in organ-specific metastasis in breast cancer could help identify strategies to improve the treatment and prevention of metastatic disease. Here, we used a systems biology approach to assess the evolution of metabolic fluxes from parental breast cancer cells to their brain- and lung-homing metastatic derivatives. We found that divergent lineages had distinct, heritable metabolic fluxes. Lung-homing cells maintained adaptations for high glycolytic flux despite low levels of glycolytic intermediates, constitutively activating a pathway sink into lactate. This exacerbated Warburg effect –– stronger than the Warburg effect in the primary tumor –– was associated with a high ratio of lactate dehydrogenase (LDH) to pyruvate dehydrogenase (PDH) expression, a signature which correlated with lung metastasis in patients with breast cancer. While feature classification models trained on clinical characteristics alone were unable to predict tropism, the LDH/PDH ratio was a significant predictor of a patient's future metastasis to the lung but not to other organs, independent of other transcriptomic signatures. Lung- and brain-homing lineages had differential selection patterns in acidic metabolic microenvironments. High lactate efflux was also a trait in lung-homing metastatic pancreatic cancer cells, suggesting that lactate production may be a convergent phenotype in lung metastasis. Together, these analyses highlight the essential role that metabolic evolution plays in organ-specific cancer metastasis and identify a putative biomarker for predicting lung metastasis in breast cancer patients. Citation Format: Deepti Mathur, Chen Liao, Wendy Lin, Alessandro La Ferlita, Salvatore Alaimo, Samuel Taylor, Yi Zhong, Christine Iacobuzio-Donahue, Alfredo Ferro, Joao Xavier. Metabolic evolution in breast cancer predicts organ-specific metastasis [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Translating Cancer Evolution and Data Science: The Next Frontier; 2023 Dec 3-6; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(3 Suppl_2):Abstract nr A039.

Cellular origin and molecular mechanisms of lung metastases in patients with aggressive hepatoblastoma.

Lung metastases are the most threatening signs for patients with aggressive hepatoblastoma (HBL). Despite intensive studies, the cellular origin and molecular mechanisms of lung metastases in patients with aggressive HBL are not known. The aims of these studies were to identify metastasis-initiating cells in primary liver tumors and to determine if these cells are secreted in the blood, reach the lung, and form lung metastases. We have examined mechanisms of activation of key oncogenes in primary liver tumors and lung metastases and the role of these mechanisms in the appearance of metastasis-initiating cells in patients with aggressive HBL by RNA-Seq, immunostaining, chromatin immunoprecipitation, Real-Time Quantitative Reverse Transcription PCR and western blot approaches. Using a protocol that mimics the exit of metastasis-initiating cells from tumors, we generated 16 cell lines from liver tumors and 2 lines from lung metastases of patients with HBL. We found that primary HBL liver tumors have a dramatic elevation of neuron-like cells and cancer-associated fibroblasts and that these cells are released into the bloodstream of patients with HBL and found in lung metastases. In the primary liver tumors, the ph-S675-β-catenin pathway activates the expression of markers of cancer-associated fibroblasts; while the ZBTB3-SRCAP pathway activates the expression of markers of neurons via cancer-enhancing genomic regions/aggressive liver cancer domains leading to a dramatic increase of cancer-associated fibroblasts and neuron-like cells. Studies of generated metastasis-initiating cells showed that these cells proliferate rapidly, engage in intense cell-cell interactions, and form tumor clusters. The inhibition of β-catenin in HBL/lung metastases-released cells suppresses the formation of tumor clusters. The inhibition of the β-catenin-cancer-enhancing genomic regions/aggressive liver cancer domains axis could be considered as a therapeutic approach to treat/prevent lung metastases in patients with HBL.

Evaluation of the clinical efficacy of Ru'ai Shuhou recipe for the prevention of lung metastases from breast cancer: a retrospective study based on propensity score matching.

Breast cancer lung metastasis occurs at a high rate and at an early stage, and is the leading cause of death in breast cancer patients. The aim of this study was to investigate the effect of Ru'ai Shuhou Recipe (RSR) intervention on the occurrence of recurrent metastases, especially lung metastases, in postoperative patients with breast cancer. A retrospective cohort study was implemented at Shuguang Hospital of Shanghai University of Traditional Chinese Medicine in China between January 2014 to January 2019. Female patients were included according to the propensity score matching (PSM) method and balanced on the basis of general and clinical information such as age, body mass index, neo-adjuvant therapy, and surgical approach. Patients with pathological diagnosis of breast cancer were included in this study. Breast cancer patients were divided into exposed and non-exposed groups according to whether they took RSR-based botanical drugs after surgery. Kaplan-Meier survival analysis and Cox survival analysis to explore the relationship between RSR and 5-year disease-free survival and incidence of lung metastases in breast cancer patients after surgery. 360 female patients were assessed and 190 patients were included in the study after PSM (95 in each of the exposed and non-exposed groups). Of the 190 patients after PSM, 55.79% were over 50years of age. The mean follow-up time was 60.55 ± 14.82months in the exposed group and 57.12 ± 16.37months in the non-exposed group. There was no significant baseline characteristics difference between two groups. Kaplan-Meier analysis showed that the 5-year incidence of lung metastases was significantly lower in the exposed group, and the disease-free survival of patients was significantly longer. Cox univariate and multivariate analysis showed that neoadjuvant chemotherapy and lymph node metastasis were independent risk factors for the development of breast cancer lung metastasis, with risk ratios of 17.188 and 5.812, while RSR treatment was an independent protective factor against the development of breast cancer lung metastasis, with a risk ratio of 0.290. Standard biomedical treatment combined with RSR intervention can better prevent breast cancer recurrence and metastasis, reduce the incidence of lung metastasis in patients, and improve long-term prognosis.

Prediction of liver and lung metastases in patients with early-onset colorectal cancer by nomograms based on heterogeneous and homogenous risk factors.

Identifying the risk factors for distant metastasis in early-onset colorectal cancer (EOCRC) is crucial for elucidating its etiology and facilitating preventive treatment. This study aims to characterize the variability in EOCRC incidence and discern both heterogeneous and homogeneous risk factors associated with synchronous liver, lung, and hepato-lung metastases. This study included patients with EOCRC enrolled in the SEER database between 2010 and 2015 and divided patients into three groups by synchronous liver, lung, and hepato-lung metastases. Each group of patients with different metastasis types was randomly assigned to the development and validation cohort in a ratio of 7:3. Logistic regression was used to analyze the heterogeneous and homogenous risk factors for synchronous liver, lung, and hepato-lung metastases in the development cohort of patients. Nomograms were built to calculate the risk of metastasis, and the receiver operating characteristic (ROC) curve and calibration curve were used to quantitatively evaluate their performance. A total of 16,336 eligible patients with EOCRC were included in this study, of which 17.90% (2924/16,336) had distant metastases. The overall incidences of synchronous liver, lung, and hepato-lung metastases were 11.90% (1921/16,146), 2.42% (390/16,126), and 1.50% (241/16,108), respectively. Positive CEA values before treatment, increased lymphatic metastases, and deeper invasion of intestinal wall were positively correlated with three distant types of metastases. On the contrary, the correlation of age, ethnicity, location of primary tumor, and histologic grade among the three types was inconsistent. The ROC curve and calibration curve proved to have fine performance in predicting distant metastases of EOCRC. There are significant differences in the incidence of distant metastases in EOCRC, and related risk factors are heterogeneous and homogenous. Although limited risk factors were incorporated in this study, the established nomograms indicated good predictive performance.

Development and validation of an artificial intelligence prediction model and a survival risk stratification for lung metastasis in colorectal cancer from highly imbalanced data: A multicenter retrospective study

BackgroundTo assist clinicians with diagnosis and optimal treatment decision-making, we attempted to develop and validate an artificial intelligence prediction model for lung metastasis (LM) in colorectal cancer (CRC) patients. MethodsThe clinicopathological characteristics of 46037 CRC patients from the Surveillance, Epidemiology, and End Results (SEER) database and 2779 CRC patients from a multi-center external validation set were collected retrospectively. After feature selection by univariate and multivariate analyses, six machine learning (ML) models, including logistic regression, K-nearest neighbor, support vector machine, decision tree, random forest, and balanced random forest (BRF), were developed and validated for the LM prediction. In addition, stratified LM patients by risk score were utilized for survival analysis. ResultsExtremely low rates of LM with 2.59% and 4.50% were present in the development and validation set. As the imbalanced learning strategy, the BRF model with an Area under the receiver operating characteristic curve (AUC) of 0.874 and an average precision (AP) of 0.184 performed best compares with other models and clinical predictor. Patients with LM in the high-risk group had significantly poorer survival (P＜0.001) and failed to benefit from resection (P = 0.125). ConclusionsIn summary, we have utilized the BRF algorithm to develop an effective, non-invasive, and practical model for predicting LM in CRC patients based on highly imbalanced datasets. In addition, we have implemented a novel approach to stratify the survival risk of CRC patients with LM based the output of the model.

Routine perioperative blood tests predict survival of resectable lung cancer

There is growing evidence that inflammatory, immunologic, and metabolic status is associated with cancer patients survival. Here, we built a simple algorithm to predict lung cancer outcome. Perioperative routine blood tests (RBT) of a cohort of patients with resectable primary lung cancer (LC) were analysed. Inflammatory, immunologic, and metabolic profiles were used to create a single algorithm (RBT index) predicting LC survival. A concurrent cohort of patients with resectable lung metastases (LM) was used to validate the RBT index. Charts of 2088 consecutive LC and 1129 LM patients undergoing lung resection were evaluated. Among RBT parameters, C-reactive protein (CRP), lymphocytes, neutrophils, hemoglobin, albumin and glycemia independently correlated with survival, and were used to build the RBT index. Patients with a high RBT index had a higher 5-year mortality than low RBT patients (adjusted HR 1.93, 95% CI 1.62–2.31). High RBT patients also showed a fourfold higher risk of 30-day postoperative mortality (2.3% vs. 0.5%, p 0.0019). The LM analysis validated the results of the LC cohort. We developed a simple and easily available multifunctional tool predicting short-term and long-term survival of curatively resected LC and LM. Prospective external validation of RBT index is warranted.

Development and validation of a nomogram to predict lung metastasis in patients with testicular germ cell tumors

BackgroundLung metastatic tumor (LM) is one of testicular germ cell tumors' most common metastatic sites. Our study aimed to develop a nomogram for predicting the risk of LM among patients with testicular germ cell tumors (TGCTs). MethodsClinicopathological information of 4078 patients with TGCT between 2010 and 2015 was obtained from SEER. Univariate and multivariate logistic regression analyses were performed to identify risk factors for LM, and a nomogram was developed based on these factors. Calibration curves, area under the receiver operating curve (AUC), and decision curve analysis (DCA) were used to evaluate the accuracy and discrimination of the model. ResultsStudy participants included 4078 people with TGCTs, including 305 people with LM. They were randomly divided into two groups (training cohort = 2854 and validation cohort = 1224) at a ratio of 7:3. The following variables were incorporated in the nomogram: marital status, tumor histological type, T stage, brain metastasis, liver metastasis, lactate dehydrogenase (LDH), and chemotherapy. Besides, the AUC of it was 0.922 in the training cohort, while was 0.930 in the validation cohort. Training and validation cohort calibrations showed that the nomogram had excellent predictive abilities. DCA suggested it was more clinically relevant than the traditional TN staging. ConclusionWe have established a nomogram to predict the risk of LM in patients with TGCTs. Doctors and patients can use this nomogram to monitor and identify lung metastasis of tumors through active monitoring and follow-up.

Efficacy and Toxicity of Robotic Stereotactic Body Radiotherapy of Lung Metastases in Patients With Oligometastatic Disease.

Stereotactic body radiotherapy is a locally effective treatment for lung metastases in patients with oligometastatic disease, a modern variant of which is robotic (rSBRT). Since it is unclear which factors determine the success of rSBRT, we investigated a cohort of patients with lung metastases treated with rSBRT. In our retrospective single-center analysis, we included patients with oligometastatic disease of different cancer types who underwent SBRT of lung metastases using an Accuray Cyberknife® device between 2012 and 2019. We evaluated local control rate (LC), progression-free (PFS) and overall (OS) survival, and toxicity. Multivariate analysis was performed to identify independent factors associated with the efficacy and toxicity of rSBRT. A total of 70 lung metastases of 54 patients were evaluated. The 4-year Kaplan-Meier estimate for LC, PFS and OS were 72.0%, 12.4% and 49.7%, respectively. Cox regression showed that LC of metastases of colorectal carcinoma and metastases treated with a biological effective dose at an α/β-ratio of 10 (BED10) of <100 Gy was significantly worse than for other metastases. Patients suffered from grade I-II pneumonitis in 21.4% of cases treated with rSBRT (grade I: 20.0%; grade II: 1.4%). rSBRT is an effective and safe therapy for lung metastases. A BED10 of >100 Gy should be aimed for, especially for potentially radioresistant histologies such as colorectal carcinoma.

A proposed methodology for detecting the malignant potential of pulmonary nodules in sarcoma using computed tomographic imaging and artificial intelligence-based models.

The presence of lung metastases in patients with primary malignancies is an important criterion for treatment management and prognostication. Computed tomography (CT) of the chest is the preferred method to detect lung metastasis. However, CT has limited efficacy in differentiating metastatic nodules from benign nodules (e.g., granulomas due to tuberculosis) especially at early stages (<5mm). There is also a significant subjectivity associated in making this distinction, leading to frequent CT follow-ups and additional radiation exposure along with financial and emotional burden to the patients and family. Even 18F-fluoro-deoxyglucose positron emission technology-computed tomography (18F-FDG PET-CT) is not always confirmatory for this clinical problem. While pathological biopsy is the gold standard to demonstrate malignancy, invasive sampling of small lung nodules is often not clinically feasible. Currently, there is no non-invasive imaging technique that can reliably characterize lung metastases. The lung is one of the favored sites of metastasis in sarcomas. Hence, patients with sarcomas, especially from tuberculosis prevalent developing countries, can provide an ideal platform to develop a model to differentiate lung metastases from benign nodules. To overcome the lack of optimal specificity of CT scan in detecting pulmonary metastasis, a novel artificial intelligence (AI)-based protocol is proposed utilizing a combination of radiological and clinical biomarkers to identify lung nodules and characterize it as benign or metastasis. This protocol includes a retrospective cohort of nearly 2,000-2,250 sample nodules (from at least 450 patients) for training and testing and an ambispective cohort of nearly 500 nodules (from 100 patients; 50 patients each from the retrospective and prospective cohort) for validation. Ground-truth annotation of lung nodules will be performed using an in-house-built segmentation tool. Ground-truth labeling of lung nodules (metastatic/benign) will be performed based on histopathological results or baseline and/or follow-up radiological findings along with clinical outcome of the patient. Optimal methods for data handling and statistical analysis are included to develop a robust protocol for early detection and classification of pulmonary metastasis at baseline and at follow-up and identification of associated potential clinical and radiological markers.

Applying machine learning techniques to predict the risk of lung metastases from rectal cancer: a real-world retrospective study.

Metastasis in the lungs is common in patients with rectal cancer, and it can have severe consequences on their survival and quality of life. Therefore, it is essential to identify patients who may be at risk of developing lung metastasis from rectal cancer. In this study, we utilized eight machine-learning methods to create a model for predicting the risk of lung metastasis in patients with rectal cancer. Our cohort consisted of 27,180 rectal cancer patients selected from the Surveillance, Epidemiology and End Results (SEER) database between 2010 and 2017 for model development. Additionally, we validated our models using 1118 rectal cancer patients from a Chinese hospital to evaluate model performance and generalizability. We assessed our models' performance using various metrics, including the area under the curve (AUC), the area under the precision-recall curve (AUPR), the Matthews Correlation Coefficient (MCC), decision curve analysis (DCA), and calibration curves. Finally, we applied the best model to develop a web-based calculator for predicting the risk of lung metastasis in patients with rectal cancer. Our study employed tenfold cross-validation to assess the performance of eight machine-learning models for predicting the risk of lung metastasis in patients with rectal cancer. The AUC values ranged from 0.73 to 0.96 in the training set, with the extreme gradient boosting (XGB) model achieving the highest AUC value of 0.96. Moreover, the XGB model obtained the best AUPR and MCC in the training set, reaching 0.98 and 0.88, respectively. We found that the XGB model demonstrated the best predictive power, achieving an AUC of 0.87, an AUPR of 0.60, an accuracy of 0.92, and a sensitivity of 0.93 in the internal test set. Furthermore, the XGB model was evaluated in the external test set and achieved an AUC of 0.91, an AUPR of 0.63, an accuracy of 0.93, a sensitivity of 0.92, and a specificity of 0.93. The XGB model obtained the highest MCC in the internal test set and external validation set, with 0.61 and 0.68, respectively. Based on the DCA and calibration curve analysis, the XGB model had better clinical decision-making ability and predictive power than the other seven models. Lastly, we developed an online web calculator using the XGB model to assist doctors in making informed decisions and to facilitate the model's wider adoption (https://share.streamlit.io/woshiwz/rectal_cancer/main/lung.py). In this study, we developed an XGB model based on clinicopathological information to predict the risk of lung metastasis in patients with rectal cancer, which may help physicians make clinical decisions.

Staging Chest CT in Patients With Early-Stage Colon Cancer: Analysis of Impact on Survival Using Inverse Probability Weighting and Causal Diagram.

BACKGROUND. Staging chest CT has been shown to have negligible diagnostic yield for detecting lung metastases in patients with early-stage colon cancer. Nonetheless, staging chest CT may have potential survival benefits, including opportunistic screening of comorbidity and provision of a baseline examination for future comparisons. Evidence is lacking regarding the impact of staging chest CT on survival in patients with early-stage colon cancer. OBJECTIVE. The purpose of this study was to determine whether the performance of staging chest CT affects survival in patients with early-stage colon cancer. METHODS. This retrospective study included patients with early-stage colon cancer (defined as clinical stage 0 or I on staging abdominal CT) at a single tertiary hospital between January 2009 and December 2015. Patients were divided into two groups according to the presence of a staging chest CT examination. To ensure comparability between the two groups, inverse probability weighting was applied to adjust for the confounders derived from a causal diagram. The between-group differences in adjusted restricted mean survival time at 5 years were measured for overall survival, relapse-free survival, and thoracic metastasis-free survival. Sensitivity analyses were performed. RESULTS. A total of 991 patients (618 men and 373 women; median age, 64 years [IQR, 55-71 years]) were included: 606 patients (61.2%) had staging chest CT. For overall survival, the difference between groups in restricted mean survival time at 5 years was not significant (0.4 months [95% CI, -0.8 to 2.1 months]). The differences between groups in restricted mean survival at 5 years were also not significant for relapse-free survival (0.4 months [95% CI, -1.1 to 2.3 months]) and for thoracic metastasis-free survival (0.6 months [95% CI, -0.8 to 2.4 months]). Similar results were observed in sensitivity analyses that tested 3- and 10-year RMST differences, excluded patients who underwent FDG PET/CT during staging workup, and added treatment decision (surgery vs no surgery) to the causal diagram. CONCLUSION. The use of staging chest CT did not affect survival in patients with early-stage colon cancer. CLINICAL IMPACT. Staging chest CT may be omitted from the staging workup for patients with colon cancer of clinical stage 0 or I.