Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models.

Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.

Predictive value of CT and 18F-FDG PET/CT features on spread through air space in lung adenocarcinoma.

BACKGROUND: Lung adenocarcinoma, a leading cause of cancer-related mortality, demands precise prognostic indicators for effective management. The presence of spread through air space (STAS) indicates adverse tumor behavior. However, comparative differences between 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography(PET)/computed tomography(CT) and CT in predicting STAS in lung adenocarcinoma remain inadequately explored. This retrospective study analyzes preoperative CT and 18F-FDG PET/CT features to predict STAS, aiming to identify key predictive factors and enhance clinical decision-making. METHODS: Between February 2022 and April 2023, 100 patients (108 lesions) who underwent surgery for clinical lung adenocarcinoma were enrolled. All these patients underwent 18F-FDG PET/CT, thin-section chest CT scan, and pathological biopsy. Univariate and multivariate logistic regression was used to analyze CT and 18F-FDG PET/CT image characteristics. Receiver operating characteristic curve analysis was performed to identify a cut-off value. RESULTS: Sixty lesions were positive for STAS, and 48 lesions were negative for STAS. The STAS-positive was frequently observed in acinar predominant. However, STAS-negative was frequently observed in minimally invasive adenocarcinoma. Univariable analysis results revealed that CT features (including nodule type, maximum tumor diameter, maximum solid component diameter, consolidation tumor ratio, pleural indentation, lobulation, spiculation) and all 18F-FDG PET/CT characteristics were statistically significant difference in STAS-positive and STAS-negative lesions. And multivariate logistic regression results showed that the maximum tumor diameter and SUVmax were the independent influencing factors of CT and 18F-FDG PET/CT in STAS, respectively. The area under the curve of maximum tumor diameter and SUVmax was 0.68 vs. 0.82. The cut-off value for maximum tumor diameter and SUVmax was 2.35 vs. 5.05 with a sensitivity of 50.0% vs. 68.3% and specificity of 81.2% vs. 87.5%, which showed that SUVmax was superior to the maximum tumor diameter. CONCLUSION: The radiological features of SUVmax is the best model for predicting STAS in lung adenocarcinoma. These radiological features could predict STAS with excellent specificity but inferior sensitivity.

The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung.

OBJECTIVE: To explore the value of six machine learning models based on PET/CT radiomics combined with EGFR in predicting brain metastases of lung adenocarcinoma. METHODS: Retrospectively collected 204 patients with lung adenocarcinoma who underwent PET/CT examination and EGFR gene detection before treatment from Cancer Hospital Affiliated to Shandong First Medical University in 2020. Using univariate analysis and multivariate logistic regression analysis to find the independent risk factors for brain metastasis. Based on PET/CT imaging combined with EGFR and PET metabolic indexes, established six machine learning models to predict brain metastases of lung adenocarcinoma. Finally, using ten-fold cross-validation to evaluate the predictive effectiveness. RESULTS: In univariate analysis, patients with N2-3, EGFR mutation-positive, LYM%≤20, and elevated tumor markers(P<0.05) were more likely to develop brain metastases. In multivariate Logistic regression analysis, PET metabolic indices revealed that SUVmax, SUVpeak, Volume, and TLG were risk factors for lung adenocarcinoma brain metastasis(P<0.05). The SVM model was the most efficient predictor of brain metastasis with an AUC of 0.82 (PET/CT group),0.70 (CT group),0.76 (PET group). CONCLUSIONS: Radiomics combined with EGFR machine learning model as a new method have higher accuracy than EGFR mutation alone. SVM model is the most effective method for predicting brain metastases of lung adenocarcinoma, and the prediction efficiency of PET/CT group is better than PET group and CT group.

A nomogram based on the quantitative and qualitative features of CT imaging for the prediction of the invasiveness of ground glass nodules in lung adenocarcinoma.

PURPOSE: Based on the quantitative and qualitative features of CT imaging, a model for predicting the invasiveness of ground-glass nodules (GGNs) was constructed, which could provide a reference value for preoperative planning of GGN patients. MATERIALS AND METHODS: Altogether, 702 patients with GGNs (including 748 GGNs) were included in this study. The GGNs operated between September 2020 and July 2022 were classified into the training group (n = 555), and those operated between August 2022 and November 2022 were classified into the validation group (n = 193). Clinical data and the quantitative and qualitative features of CT imaging were harvested from these patients. In the training group, the quantitative and qualitative characteristics in CT imaging of GGNs were analyzed by using performing univariate and multivariate logistic regression analyses, followed by constructing a nomogram prediction model. The differentiation, calibration, and clinical practicability in both the training and validation groups were assessed by the nomogram models. RESULTS: In the training group, multivariate logistic regression analysis disclosed that the maximum diameter (OR = 4.707, 95%CI: 2.06-10.758), consolidation/tumor ratio (CTR) (OR = 1.027, 95%CI: 1.011-1.043), maximum CT value (OR = 1.025, 95%CI: 1.004-1.047), mean CT value (OR = 1.035, 95%CI: 1.008-1.063; P = 0.012), spiculation sign (OR = 2.055, 95%CI: 1.148-3.679), and vascular convergence sign (OR = 2.508, 95%CI: 1.345-4.676) were independent risk parameters for invasive adenocarcinoma. Based on these findings, we established a nomogram model for predicting the invasiveness of GGN, and the AUC was 0.910 (95%CI: 0.885-0.934) and 0.902 (95%CI: 0.859-0.944) in the training group and the validation group, respectively. The internal validation of the Bootstrap method showed an AUC value of 0.905, indicating a good differentiation of the model. Hosmer-Lemeshow goodness of fit test for the training and validation groups indicated that the model had a good fitting effect (P > 0.05). Furthermore, the calibration curve and decision analysis curve of the training and validation groups reflected that the model had a good calibration degree and clinical practicability. CONCLUSION: Combined with the quantitative and qualitative features of CT imaging, a nomogram prediction model can be created to forecast the invasiveness of GGNs. This model has good prediction efficacy for the invasiveness of GGNs and can provide help for the clinical management and decision-making of GGNs.

Mean computed tomography value to predict spread through air spaces in clinical N0 lung adenocarcinoma.

BACKGROUND: The aim of this study was to assess the ability of radiologic factors such as mean computed tomography (mCT) value, consolidation/tumor ratio (C/T ratio), solid tumor size, and the maximum standardized uptake (SUVmax) value by F-18 fluorodeoxyglucose positron emission tomography to predict the presence of spread through air spaces (STAS) of lung adenocarcinoma. METHODS: A retrospective study was conducted on 118 patients those diagnosed with clinically without lymph node metastasis and having a pathological diagnosis of adenocarcinoma after undergoing surgery. Receiver operating characteristics (ROC) analysis was used to assess the ability to use mCT value, C/T ratio, tumor size, and SUVmax value to predict STAS. Univariate and multiple logistic regression analyses were performed to determine the independent variables for the prediction of STAS. RESULTS: Forty-one lesions (34.7%) were positive for STAS and 77 lesions were negative for STAS. The STAS positive group was strongly associated with a high mCT value, high C/T ratio, large solid tumor size, large tumor size and high SUVmax value. The mCT values were - 324.9 ± 19.3 HU for STAS negative group and - 173.0 ± 26.3 HU for STAS positive group (p < 0.0001). The ROC area under the curve of the mCT value was the highest (0.738), followed by SUVmax value (0.720), C/T ratio (0.665), solid tumor size (0.649). Multiple logistic regression analyses using the preoperatively determined variables revealed that mCT value (p = 0.015) was independent predictive factors of predicting STAS. The maximum sensitivity and specificity were obtained at a cutoff value of - 251.8 HU. CONCLUSIONS: The evaluation of mCT value has a possibility to predict STAS and may potentially contribute to the selection of suitable treatment strategies.

The radiological characteristics, tertiary lymphoid structures, and survival status associated with EGFR mutation in patients with subsolid nodules like stage I-II LUAD.

BACKGROUND: Epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) recommended for the patients with subsolid nodule in early lung cancer stage is not routinely. The clinical value and impact in patients with EGFR mutation on survival outcomes is further needed to be elucidated to decide whether the application of EGFR-TKIs was appropriate in early lung adenocarcinoma (LUAD) stage appearing as subsolid nodules. MATERIALS AND METHODS: The inclusion of patients exhibiting clinical staging of IA-IIB subsolid nodules. Clinical information, computed tomography (CT) features before surgical resection and pathological characteristics including tertiary lymphoid structures of the tumors were recorded for further exploration of correlation with EGFR mutation and prognosis. RESULTS: Finally, 325 patients were enrolled into this study, with an average age of 56.8 ± 9.8 years. There are 173 patients (53.2%) harboring EGFR mutation. Logistic regression model analysis showed that female (OR = 1.944, p = 0.015), mix ground glass nodule (OR = 2.071, p = 0.003, bubble-like lucency (OR = 1.991, p = 0.003) were significant risk factors of EGFR mutations. Additionally, EGFR mutations were negatively correlated with TLS presence and density. Prognosis analysis showed that the presence of TLS was associated with better recurrence-free survival (RFS)(p = 0.03) while EGFR mutations were associated with worse RFS(p = 0.01). The RFS in patients with TLS was considerably excel those without TLS within EGFR wild type group(p = 0.018). Multivariate analyses confirmed that EGFR mutation was an independent prognostic predictor for RFS (HR = 3.205, p = 0.037). CONCLUSIONS: In early-phase LUADs, subsolid nodules with EGFR mutation had specific clinical and radiological signatures. EGFR mutation was associated with worse survival outcomes and negatively correlated with TLS, which might weaken the positive impact of TLS on prognosis. Highly attention should be paid to the use of EGFR-TKI for further treatment as agents in early LUAD patients who carrying EGFR mutation.

Radiological and clinical features of large consolidative-type pulmonary invasive mucinous adenocarcinoma.

BACKGROUND: This study aimed to investigate the radiological, pathological, and prognostic characteristics of large consolidative-type pulmonary invasive mucinous adenocarcinomas (IMA). METHODS: We retrospectively reviewed 738 patients who confirmed IMA between January 2010 and August 2022, and two radiologists reviewed imaging data to determine subtypes. We included 41 patients with pathologically large consolidative-type IMA. We analyzed their radiological, pathological, and prognostic characteristics. The recurrence-free survival (RFS) and overall survival (OS) were determined using the Kaplan-Meier method. RESULTS: Most lesions were located in the lower lobe, with 46.3% patients showing multiple lesions. Halo, angiogram, vacuole, air bronchogram, and dead branch sign were observed in 97.6%, 73.2%, 63.4%, 61.0%, and 61.0% of the cases, respectively. Unevenly low enhancement was observed in 88.89% of patients. T3 and T4 pathological stages were observed in 50.0% and 30.6% of patients, respectively. Lymph node metastasis was observed in 16.7% patients, with no distant metastasis. Spread-through air spaces and intrapulmonary dissemination were observed in 27.8% and 19.4% patients, respectively. Moreover, Kirsten rat sarcoma viral oncogene mutations were found in 68.6% of cases, and no epidermal growth factor receptor mutations were seen. Among all mutation sites, G12V mutation is the most common, accounting for 40%. The average RFS and OS were 19.4 and 66.4 months, respectively, with 3-year RFS and OS rates of 30.0% and 75.0%, respectively. Pleural invasion and lymph node metastasis were independent risk factors for diagnosis. CONCLUSION: Halo, vacuole, angiogram, and dead branch signs were frequently observed in consolidative-type IMA. Kirsten rat sarcoma viral oncogene mutations are common in consolidative-type IMA, especially site G12V, whereas epidermal growth factor receptor mutations were rare; therefore, gene immunotherapy was more difficult. Most patients were in stage T3-T4; however, lymph node metastasis was rare.

TDASD: Generating medically significant fine-grained lung adenocarcinoma nodule CT images based on stable diffusion models with limited sample size.

BACKGROUND AND OBJECTIVES: Spread through air spaces (STAS) is an emerging lung cancer infiltration pattern. Predicting its spread through CT scans is crucial. However, limited STAS data makes this prediction task highly challenging. Stable diffusion is capable of generating more diverse and higher-quality images compared to traditional GAN models, surpassing the dominating GAN family models in image synthesis over the past few years. To alleviate the issue of limited STAS data, we propose a method TDASD based on stable diffusion, which is able to generate high-resolution CT images of pulmonary nodules corresponding to specific nodular signs according to the medical professionals. METHODS: First, we apply the stable diffusion method for fine-tuning training on publicly available lung datasets. Subsequently, we extract nodules from our hospital's lung adenocarcinoma data and apply slight rotations to the original nodule CT slices within a reasonable range before undergoing another round of fine-tuning through stable diffusion. Finally, employing DDIM and Ksample sampling methods, we generate lung adenocarcinoma nodule CT images with signs based on prompts provided by doctors. The method we propose not only safeguards patient privacy but also enhances the diversity of medical images under limited data conditions. Furthermore, our approach to generating medical images incorporates medical knowledge, resulting in images that exhibit pertinent medical features, thus holding significant value in tumor discrimination diagnostics. RESULTS: Our TDASD method has the capability to generate medically meaningful images by optimizing input prompts based on medical descriptions provided by experts. The images generated by our method can improve the model's classification accuracy. Furthermore, Utilizing solely the data generated by our method for model training, the test results on the original real dataset reveal an accuracy rate that closely aligns with the testing accuracy achieved through training on real data. CONCLUSIONS: The method we propose not only safeguards patient privacy but also enhances the diversity of medical images under limited data conditions. Furthermore, our approach to generating medical images incorporates medical knowledge, resulting in images that exhibit pertinent medical features, thus holding significant value in tumor discrimination diagnostics.

Clinical characteristics and MRI based radiomics nomograms can predict iPFS and short-term efficacy of third-generation EGFR-TKI in EGFR-mutated lung adenocarcinoma with brain metastases.

BACKGROUND: Predicting short-term efficacy and intracranial progression-free survival (iPFS) in epidermal growth factor receptor gene mutated (EGFR-mutated) lung adenocarcinoma patients with brain metastases who receive third-generation epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) therapy was of great significance for individualized treatment. We aimed to construct and validate nomograms based on clinical characteristics and magnetic resonance imaging (MRI) radiomics for predicting short-term efficacy and intracranial progression free survival (iPFS) of third-generation EGFR-TKI in EGFR-mutated lung adenocarcinoma patients with brain metastases. METHODS: One hundred ninety-four EGFR-mutated lung adenocarcinoma patients with brain metastases who received third-generation EGFR-TKI treatment were included in this study from January 1, 2017 to March 1, 2023. Patients were randomly divided into training cohort and validation cohort in a ratio of 5:3. Radiomics features extracted from brain MRI were screened by least absolute shrinkage and selection operator (LASSO) regression. Logistic regression analysis and Cox proportional hazards regression analysis were used to screen clinical risk factors. Single clinical (C), single radiomics (R), and combined (C + R) nomograms were constructed in short-term efficacy predicting model and iPFS predicting model, respectively. Prediction effectiveness of nomograms were evaluated by calibration curves, Harrell's concordance index (C-index), receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Kaplan-Meier analysis was used to compare the iPFS of high and low iPFS rad-score patients in the predictive iPFS R model and to compare the iPFS of high-risk and low-risk patients in the predictive iPFS C + R model. RESULTS: Overall response rate (ORR) was 71.1%, disease control rate (DCR) was 91.8% and median iPFS was 12.67 months (7.88-20.26, interquartile range [IQR]). There were significant differences in iPFS between patients with high and low iPFS rad-scores, as well as between high-risk and low-risk patients. In short-term efficacy model, the C-indexes of C + R nomograms in training cohort and validation cohort were 0.867 (0.835-0.900, 95%CI) and 0.803 (0.753-0.854, 95%CI), while in iPFS model, the C-indexes were 0.901 (0.874-0.929, 95%CI) and 0.753 (0.713-0.793, 95%CI). CONCLUSIONS: The third-generation EGFR-TKI showed significant efficacy in EGFR-mutated lung adenocarcinoma patients with brain metastases, and the combined line plot of C + R can be utilized to predict short-term efficacy and iPFS.

Transfer learning-based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma.

BACKGROUND: To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC). METHODS: Retrospective data from 516 LADC patients, encompassing preoperative PET/CT images, clinical information, and EGFR mutation status, were divided into training (n = 404) and test sets (n = 112). Several deep learning models were developed utilizing transfer learning, involving CT-only and PET-only models. A dual-stream model fusing PET and CT and a three-stream transfer learning model (TS_TL) integrating clinical data were also developed. Image preprocessing includes semi-automatic segmentation, resampling, and image cropping. Considering the impact of class imbalance, the performance of the model was evaluated using ROC curves and AUC values. RESULTS: TS_TL model demonstrated promising performance in predicting the EGFR mutation status, with an AUC of 0.883 (95%CI = 0.849-0.917) in the training set and 0.730 (95%CI = 0.629-0.830) in the independent test set. Particularly in advanced LADC, the model achieved an AUC of 0.871 (95%CI = 0.823-0.919) in the training set and 0.760 (95%CI = 0.638-0.881) in the test set. The model identified distinct activation areas in solid or subsolid lesions associated with wild and mutant types. Additionally, the patterns captured by the model were significantly altered by effective tyrosine kinase inhibitors treatment, leading to notable changes in predicted mutation probabilities. CONCLUSION: PET/CT deep learning model can act as a tool for predicting EGFR mutation in LADC. Additionally, it offers clinicians insights for treatment decisions through evaluations both before and after treatment.

Mismatch Between Brain MRIs and 18 F-DOPA PET/CT : Impact on the Management of a Long Survivor With EGFR-Mutated Lung Adenocarcinoma.

ABSTRACT: After receiving erlotinib for 4 years, a man with advanced lung adenocarcinoma was treated with stereotactic radiotherapy for a left cerebellar brain metastasis. Local relapse of the metastasis was suspected 14 months after and confirmed on 18 F-DOPA PET. Three additional uptakes were described with no unequivocal MRI pathological signal. A second radiotherapy course was delivered. One year later, isolated local recurrence was suspected on a 3 T MRI, with a suspicious 18 F-DOPA uptake. Five additional 18 F-DOPA uptakes were described among which one increased between the 2 PETs. Because of these MRI/PET mismatches, a switch from erlotinib to osimertinib was preferred over surgery.

Primary Pulmonary Enteric Adenocarcinoma: Rare Imaging Findings.

INTRODUCTION: Pulmonary enteric adenocarcinoma (PEAC) is an extremely rare variant of lung adenocarcinoma characterized by pathological features similar to those of colorectal adenocarcinoma. It is mostly observed on computed tomography (CT) and positron emission tomography (PET)/CT as solitary or multiple nodules/masses in the lung. It tends to grow rapidly and is difficult to distinguish from lung metastatic colorectal cancer. Herein, we have presented a case of PEAC with special imaging findings. CASE PRESENTATION: A chest CT scan of a 72-year-old man with suspected chronic pneumonia revealed a well-defined consolidation in the upper lobe of the left lung. The lesion was slightly enlarged at the 9-month follow-up, and low FDG accumulation was subsequently observed using 18F-fluorodeoxyglucose (18F-FDG) PET/CT scans. The patient was later diagnosed with PEAC through percutaneous lung biopsy. CONCLUSION: Our case has demonstrated specific imaging findings of PEAC.

Development and validation of a clinic-radiological model to predict tumor spread through air spaces in stage I lung adenocarcinoma.

OBJECTIVES: Tumor spread through air spaces (STAS) is associated with poor prognosis and impacts surgical options. We aimed to develop a user-friendly model based on 2-[18F] FDG PET/CT to predict STAS in stage I lung adenocarcinoma (LAC). MATERIALS AND METHODS: A total of 466 stage I LAC patients who underwent 2-[18F] FDG PET/CT examination and resection surgery were retrospectively enrolled. They were split into a training cohort (n = 232, 20.3% STAS-positive), a validation cohort (n = 122, 27.0% STAS-positive), and a test cohort (n = 112, 29.5% STAS-positive) according to chronological order. Some commonly used clinical data, visualized CT features, and SUVmax were analyzed to identify independent predictors of STAS. A prediction model was built using the independent predictors and validated using the three chronologically separated cohorts. Model performance was assessed using ROC curves and calculations of AUC. RESULTS: The differences in age (P = 0.009), lesion density subtype (P < 0.001), spiculation sign (P < 0.001), bronchus truncation sign (P = 0.001), and SUVmax (P < 0.001) between the positive and negative groups were statistically significant. Age ≥ 56 years [OR(95%CI):3.310(1.150-9.530), P = 0.027], lesion density subtype (P = 0.004) and SUVmax ≥ 2.5 g/ml [OR(95%CI):3.268(1.021-1.356), P = 0.005] were the independent factors predicting STAS. Logistic regression was used to build the A-D-S (Age-Density-SUVmax) prediction model, and the AUCs were 0.808, 0.786 and 0.806 in the training, validation, and test cohorts, respectively. CONCLUSIONS: STAS was more likely to occur in older patients, in solid lesions and higher SUVmax in stage I LAC. The PET/CT-based A-D-S prediction model is easy to use and has a high level of reliability in diagnosing.

Computed Tomography Radiomics for Preoperative Prediction of Spread Through Air Spaces in the Early Stage of Surgically Resected Lung Adenocarcinomas.

PURPOSE: To assess the added value of radiomics models from preoperative chest CT in predicting the presence of spread through air spaces (STAS) in the early stage of surgically resected lung adenocarcinomas using multiple validation datasets. MATERIALS AND METHODS: This retrospective study included 550 early-stage surgically resected lung adenocarcinomas in 521 patients, classified into training, test, internal validation, and temporal validation sets (n=211, 90, 91, and 158, respectively). Radiomics features were extracted from the segmented tumors on preoperative chest CT, and a radiomics score (Rad-score) was calculated to predict the presence of STAS. Diagnostic performance of the conventional model and the combined model, based on a combination of conventional and radiomics features, for the diagnosis of the presence of STAS were compared using the area under the curve (AUC) of the receiver operating characteristic curve. RESULTS: Rad-score was significantly higher in the STAS-positive group compared to the STAS-negative group in the training, test, internal, and temporal validation sets. The performance of the combined model was significantly higher than that of the conventional model in the training set {AUC: 0.784 [95% confidence interval (CI): 0.722-0.846] vs. AUC: 0.815 (95% CI: 0.759-0.872), p=0.042}. In the temporal validation set, the combined model showed a significantly higher AUC than that of the conventional model (p=0.001). The combined model showed a higher AUC than the conventional model in the test and internal validation sets, albeit with no statistical significance. CONCLUSION: A quantitative CT radiomics model can assist in the non-invasive prediction of the presence of STAS in the early stage of lung adenocarcinomas.

18 F-FDG PET/CT characteristics of IASLC grade 3 invasive adenocarcinoma and the value of 18 F-FDG PET/CT for preoperative prediction: a new prognostication model.

OBJECTIVE: This study is performed to investigate the imaging characteristics of the International Association for the Study of Lung Cancer grade 3 invasive adenocarcinoma (IAC) on PET/CT and the value of PET/CT for preoperative predicting this tumor. MATERIALS AND METHODS: We retrospectively enrolled patients with IAC from August 2015 to September 2022. The clinical characteristics, serum tumor markers, and PET/CT features were analyzed. T test, Mann-Whitney U test, χ 2 test, Logistic regression analysis, and receiver operating characteristic analysis were used to predict grade 3 tumor and evaluate the prediction effectiveness. RESULTS: Grade 3 tumors had a significantly higher maximum standardized uptake value (SUV max ) and consolidation-tumor-ratio (CTR) ( P  < 0.001), while Grade 1 - 2 tumors were prone to present with air bronchogram sign or vacuole sign ( P  < 0.001). A stepwise logistic regression analysis revealed that smoking history, CEA, SUV max , air bronchogram sign or vacuole sign and CTR were useful predictors for Grade 3 tumors. The established prediction model based on the above 5 parameters generated a high AUC (0.869) and negative predictive value (0.919), respectively. CONCLUSION: Our study demonstrates that grade 3 IAC has a unique PET/CT imaging feature. The prognostication model established with smoking history, CEA, SUV max , air bronchogram sign or vacuole sign and CTR can effectively predict grade 3 tumors before the operation.

Predicting occult lymph node metastasis in solid-predominantly invasive lung adenocarcinoma across multiple centers using radiomics-deep learning fusion model.

BACKGROUND: In solid-predominantly invasive lung adenocarcinoma (SPILAC), occult lymph node metastasis (OLNM) is pivotal for determining treatment strategies. This study seeks to develop and validate a fusion model combining radiomics and deep learning to predict OLNM preoperatively in SPILAC patients across multiple centers. METHODS: In this study, 1325 cT1a-bN0M0 SPILAC patients from six hospitals were retrospectively analyzed and divided into pathological nodal positive (pN+) and negative (pN-) groups. Three predictive models for OLNM were developed: a radiomics model employing decision trees and support vector machines; a deep learning model using ResNet-18, ResNet-34, ResNet-50, DenseNet-121, and Swin Transformer, initialized randomly or pre-trained on large-scale medical data; and a fusion model integrating both approaches using addition and concatenation techniques. The model performance was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). RESULTS: All patients were assigned to four groups: training set (n = 470), internal validation set (n = 202), and independent test set 1 (n = 227) and 2 (n = 426). Among the 1325 patients, 478 (36%) had OLNM (pN+). The fusion model, combining radiomics with pre-trained ResNet-18 features via concatenation, outperformed others with an average AUC (aAUC) of 0.754 across validation and test sets, compared to aAUCs of 0.715 for the radiomics model and 0.676 for the deep learning model. CONCLUSION: The radiomics-deep learning fusion model showed promising ability to generalize in predicting OLNM from CT scans, potentially aiding personalized treatment for SPILAC patients across multiple centers.

"All in one" nanoprobe Au-TTF-1 for target FL/CT bioimaging, machine learning technology and imaging-guided photothermal therapy against lung adenocarcinoma.

The accurate preoperative diagnosis and tracking of lung adenocarcinoma is hindered by non-targeting and diffusion of dyes used for marking tumors. Hence, there is an urgent need to develop a practical nanoprobe for tracing lung adenocarcinoma precisely even treating them noninvasively. Herein, Gold nanoclusters (AuNCs) conjugate with thyroid transcription factor-1 (TTF-1) antibody, then multifunctional nanoprobe Au-TTF-1 is designed and synthesized, which underscores the paramount importance of advancing the machine learning diagnosis and bioimaging-guided treatment of lung adenocarcinoma. Bright fluorescence (FL) and strong CT signal of Au-TTF-1 set the stage for tracking. Furthermore, the high specificity of TTF-1 antibody facilitates selective targeting of lung adenocarcinoma cells as compared to common lung epithelial cells, so machine learning software Lung adenocarcinoma auxiliary detection system was designed, which combined with Au-TTF-1 to assist the intelligent recognition of lung adenocarcinoma jointly. Besides, Au-TTF-1 not only contributes to intuitive and targeted visualization, but also guides the following noninvasive photothermal treatment. The boundaries of tumor are light up by Au-TTF-1 for navigation, it penetrates into tumor and implements noninvasive photothermal treatment, resulting in ablating tumors in vivo locally. Above all, Au-TTF-1 serves as a key platform for target bio-imaging navigation, machine learning diagnosis and synergistic PTT as a single nanoprobe, which demonstrates attractive performance on lung adenocarcinoma.

The value of CT shape quantification in predicting pathological classification of lung adenocarcinoma.

OBJECTIVE: To evaluate whether quantification of lung GGN shape is useful in predicting pathological categorization of lung adenocarcinoma and guiding the clinic. METHODS: 98 patients with primary lung adenocarcinoma were pathologically confirmed and CT was performed preoperatively, and all lesions were pathologically ≤ 30 mm in size. On CT images, we measured the maximum area of the lesion's cross-section (MA). The longest diameter of the tumor (LD) was marked with points A and B, and the perpendicular diameter (PD) was marked with points C and D, which was the longest diameter perpendicular to AB. and D, which was the longest diameter perpendicular to AB. We took angles A and B as big angle A (BiA) and small angle A (SmA). We measured the MA, LD, and PD, and for analysis we derived the LD/PD ratio and the BiA/SmA ratio. The data were analysed using the chi-square test, t-test, ROC analysis, and binary logistic regression analysis. RESULTS: Precursor glandular lesions (PGL) and microinvasive adenocarcinoma (MIA) were distinguished from invasive adenocarcinoma (IAC) by the BiA/SmA ratio and LD, two independent factors (p = 0.007, p = 0.018). Lung adenocarcinoma pathological categorization was indicated by the BiA/SmA ratio of 1.35 and the LD of 11.56 mm with sensitivity of 81.36% and 71.79%, respectively; specificity of 71.79% and 74.36%, respectively; and AUC of 0.8357 (95% CI: 0.7558-0.9157, p < 0.001), 0.8666 (95% CI: 0.7866-0.9465, p < 0.001), respectively. In predicting the pathological categorization of lung adenocarcinoma, the area under the ROC curve of the BiA/SmA ratio combined with LD was 0.9231 (95% CI: 0.8700-0.9762, p < 0.001), with a sensitivity of 81.36% and a specificity of 89.74%. CONCLUSIONS: Quantification of lung GGN morphology by the BiA/SmA ratio combined with LD could be helpful in predicting pathological classification of lung adenocarcinoma.