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.

A pre-treatment CT-based weighted radiomic approach combined with clinical characteristics to predict durable clinical benefits of immunotherapy in advanced lung cancer.

OBJECTIVES: To develop a pre-treatment CT-based predictive model to anticipate inoperable lung cancer patients' progression-free survival (PFS) to immunotherapy. METHODS: This single-center retrospective study developed and cross-validated a radiomic model in 185 patients and tested it in 48 patients. The binary endpoint is the durable clinical benefit (DCB, PFS ≥ 6 months) and non-DCB (NDCB, PFS < 6 months). Radiomic features were extracted from multiple intrapulmonary lesions and weighted by an attention-based multiple-instance learning model. Aggregated features were then selected through L2-regularized ridge regression. Five machine-learning classifiers were conducted to build predictive models using radiomic and clinical features alone and then together. Lastly, the predictive value of the model with the best performance was validated by Kaplan-Meier survival analysis. RESULTS: The predictive models based on the weighted radiomic approach showed superior performance across all classifiers (AUCs: 0.75-0.82) compared with the largest lesion approach (AUCs: 0.70-0.78) and the average sum approach (AUCs: 0.64-0.80). Among them, the logistic regression model yielded the most balanced performance (AUC = 0.87 [95%CI 0.84-0.89], 0.75 [0.68-0.82], 0.80 [0.68-0.92] in the training, validation, and test cohort respectively). The addition of five clinical characteristics significantly enhanced the performance of radiomic-only model (train: AUC 0.91 [0.89-0.93], p = .042; validation: AUC 0.86 [0.80-0.91], p = .011; test: AUC 0.86 [0.76-0.96], p = .026). Kaplan-Meier analysis of the radiomic-based predictive models showed a clear stratification between classifier-predicted DCB versus NDCB for PFS (HR = 2.40-2.95, p < 0.05). CONCLUSIONS: The adoption of weighted radiomic features from multiple intrapulmonary lesions has the potential to predict long-term PFS benefits for patients who are candidates for PD-1/PD-L1 immunotherapies. KEY POINTS: • Weighted radiomic-based model derived from multiple intrapulmonary lesions on pre-treatment CT images has the potential to predict durable clinical benefits of immunotherapy in lung cancer. • Early line immunotherapy is associated with longer progression-free survival in advanced lung cancer.

[CT-Based Weighted Radiomic Score Predicts Tumor Response to Immunotherapy in Non-Small Cell Lung Cancer].

Objective To develop a CT-based weighted radiomic model that predicts tumor response to programmed death-1(PD-1)/PD-ligand 1(PD-L1)immunotherapy in patients with non-small cell lung cancer.Methods The patients with non-small cell lung cancer treated by PD-1/PD-L1 immune checkpoint inhibitors in the Peking Union Medical College Hospital from June 2015 to February 2022 were retrospectively studied and classified as responders(partial or complete response)and non-responders(stable or progressive disease).Original radiomic features were extracted from multiple intrapulmonary lesions in the contrast-enhanced CT scans of the arterial phase,and then weighted and summed by an attention-based multiple instances learning algorithm.Logistic regression was employed to build a weighted radiomic scoring model and the radiomic score was then calculated.The area under the receiver operating characteristic curve(AUC)was used to compare the weighted radiomic scoring model,PD-L1 model,clinical model,weighted radiomic scoring + PD-L1 model,and comprehensive prediction model.Results A total of 237 patients were included in the study and randomized into a training set(n=165)and a test set(n=72),with the mean ages of(64±9)and(62±8)years,respectively.The AUC of the weighted radiomic scoring model reached 0.85 and 0.80 in the training set and test set,respectively,which was higher than that of the PD-L1-1 model(Z=37.30,P<0.001 and Z=5.69,P=0.017),PD-L1-50 model(Z=38.36,P<0.001 and Z=17.99,P<0.001),and clinical model(Z=11.40,P<0.001 and Z=5.76,P=0.016).The AUC of the weighted scoring model was not different from that of the weighted radiomic scoring + PD-L1 model and the comprehensive prediction model(both P>0.05).Conclusion The weighted radiomic scores based on pre-treatment enhanced CT images can predict tumor responses to immunotherapy in patients with non-small cell lung cancer.

Individualized nomogram for predicting ALK rearrangement status in lung adenocarcinoma patients.

OBJECTIVES: To develop a nomogram to identify anaplastic lymphoma kinase (ALK) mutations in lung adenocarcinoma patients using clinical, CT, PET/CT, and histopathological features. METHODS: This retrospective study included 399 lung adenocarcinoma patients (129 ALK-rearranged patients and 270 ALK-negative patients) that were randomly divided into a training cohort and an internal validation cohort (4:1 ratio). Clinical factors, radiologist-defined CT features, maximum standard uptake values (SUVmax), and histopathological features were used to construct predictive models with stepwise backward-selection multivariate logistic regression (MLR). The models were then evaluated using the AUC. The integrated model was compared to the clinico-radiological model using the DeLong test to evaluate the role of histopathological features. An associated individualized nomogram was established. RESULTS: The integrated model reached an AUC of 0.918 (95% CI, 0.886-0.950), sensitivity of 0.774, and specificity of 0.934 in the training cohort and an AUC of 0.857 (95% CI, 0.777-0.937), sensitivity of 0.739, and specificity of 0.810 in the validation cohort. The MLR analysis showed that younger age, never smoker, lymph node enlargement, the presence of cavity, high SUVmax, solid or micropapillary predominant histology subtype, and local invasiveness were strong and independent predictors of ALK rearrangements. The nomogram calculated the risk of harboring ALK mutation for lung adenocarcinoma patients and exhibited a good generalization ability. CONCLUSION: Our study demonstrates that histopathological features added value to the imaging characteristics-based model. The nomogram with clinical, imaging, and histopathological features can serve as a supplementary non-invasive tool to evaluate the probability of ALK rearrangement in lung adenocarcinoma. KEY POINTS: • The developed nomogram can accurately predict the probability of lung adenocarcinoma harboring ALK-fused gene. • Pathological analysis is important to predict ALK rearrangement in lung adenocarcinoma. • Lung adenocarcinoma with lepidic predominant growth pattern and TTF-1 negativity is unlikely to have ALK rearrangement.

Time-dependent CT score-based model for identifying severe/critical COVID-19 at a fever clinic after the emergence of Omicron variant.

Rationale and objectives: The computed tomography (CT) score has been used to evaluate the severity of COVID-19 during the pandemic; however, most studies have overlooked the impact of infection duration on the CT score. This study aimed to determine the optimal cutoff CT score value for identifying severe/critical COVID-19 during different stages of infection and to construct corresponding predictive models using radiological characteristics and clinical factors. Materials and methods: This retrospective study collected consecutive baseline chest CT images of confirmed COVID-19 patients from a fever clinic at a tertiary referral hospital from November 28, 2022, to January 8, 2023. Cohorts were divided into three subcohorts according to the time interval from symptom onset to CT examination at the hospital: early phase (0-3 days), intermediate phase (4-7 days), and late phase (8-14 days). The binary endpoints were mild/moderate and severe/critical infection. The CT scores and qualitative CT features were manually evaluated. A logistic regression analysis was performed on the CT score as determined by a visual assessment to predict severe/critical infection. Receiver operating characteristic analysis was performed and the area under the curve (AUC) was calculated. The optimal cutoff value was determined by maximizing the Youden index in each subcohort. A radiology score and integrated models were then constructed by combining the qualitative CT features and clinical features, respectively, using multivariate logistic regression with stepwise elimination. Results: A total of 962 patients (aged, 61.7 ± 19.6 years; 490 men) were included; 179 (18.6%) were classified as severe/critical COVID-19, while 344 (35.8%) had a typical Radiological Society of North America (RSNA) COVID-19 appearance. The AUCs of the CT score models reached 0.91 (95% confidence interval (CI) 0.88-0.94), 0.82 (95% CI 0.76-0.87), and 0.83 (95% CI 0.77-0.89) during the early, intermediate, and late phases, respectively. The best cutoff values of the CT scores during each phase were 1.5, 4.5, and 5.5. The predictive accuracies associated with the time-dependent cutoff values reached 88% (vs.78%), 73% (vs. 63%), and 87% (vs. 57%), which were greater than those associated with universal cutoff value (all P < 0.001). The radiology score models reached AUCs of 0.96 (95% CI 0.94-0.98), 0.90 (95% CI 0.87-0.94), and 0.89 (95% CI 0.84-0.94) during the early, intermediate, and late phases, respectively. The integrated models including demographic and clinical risk factors greatly enhanced the AUC during the intermediate and late phases compared with the values obtained with the radiology score models; however, an improvement in accuracy was not observed. Conclusion: The time interval between symptom onset and CT examination should be tracked to determine the cutoff value for the CT score for identifying severe/critical COVID-19. The radiology score combining qualitative CT features and the CT score complements clinical factors for identifying severe/critical COVID-19 patients and facilitates timely hierarchical diagnoses and treatment.

U-Net-based computed tomography quantification of viral pneumonia can predict fibrotic interstitial lung abnormalities at 3-month follow-up.

Background: Given the high prevalence of fibrotic interstitial lung abnormalities (ILAs) post-COVID-19, this study aims to evaluate the effectiveness of quantitative CT features in predicting fibrotic ILAs at 3-month follow-up. Methods: This retrospective study utilized cohorts from distinct clinical settings: the training dataset comprised individuals presenting at the fever clinic and emergency department, while the validation dataset included patients hospitalized with COVID-19 pneumonia. They were classified into fibrotic group and nonfibrotic group based on whether the fibrotic ILAs were present at follow-up. A U-Net-based AI tool was used for quantification of both pneumonia lesions and pulmonary blood volumes. Receiver operating characteristic (ROC) curve analysis and multivariate analysis were used to assess their predictive abilities for fibrotic ILAs. Results: Among the training dataset, 122 patients (mean age of 68 years ±16 [standard deviation], 73 men), 55.74% showed fibrotic ILAs at 3-month follow-up. The multivariate analysis identified the pneumonia volume [PV, odd ratio (OR) 3.28, 95% confidence interval (CI): 1.20-9.31, p = 0.02], consolidation volume (CV, OR 3.77, 95% CI: 1.37-10.75, p = 0.01), ground-glass opacity volume (GV, OR 3.38, 95% CI: 1.26-9.38, p = 0.02), pneumonia mass (PM, OR 3.58, 95% CI: 1.28-10.46, p = 0.02), and the CT score (OR 12.06, 95% CI: 3.15-58.89, p < 0.001) as independent predictors of fibrotic ILAs, and all quantitative parameters were as effective as CT score (all p > 0.05). And the area under the curve (AUC) values were PV (0.79), GV (0.78), PM (0.79), CV (0.80), and the CT score (0.77). The validation dataset, comprising 45 patients (mean age 67.29 ± 14.29 years, 25 males) with 57.78% showing fibrotic ILAs at follow-up, confirmed the predictive validity of these parameters with AUC values for PV (0.86), CV (0.90), GV (0.83), PM (0.88), and the CT score (0.85). Additionally, the percentage of blood volume in vessels <5mm2 relative to the total pulmonary blood volume (BV5%) was significantly lower in patients with fibrotic ILAs (p = 0.048) compared to those without. Conclusion: U-Net based quantification of pneumonia lesion and BV5% on baseline CT scan has the potential to predict fibrotic ILAs at follow-up in COVID-19 patients.

Differentiating lung neuroendocrine neoplasms from tumor-like infection using CT in patients with ectopic ACTH syndrome.

OBJECTIVES: Pulmonary neuroendocrine neoplasms (NENs) are the most frequent cause of ectopic adrenocorticotropic hormone syndrome (EAS); lung infection is common in EAS. An imaging finding of infection in EAS patients can mimic NENs. This retrospective study investigated EAS-associated pulmonary imaging indicators. METHODS: Forty-five pulmonary NENs and 27 tumor-like infections from 59 EAS patients (45 NEN and 14 infection patients) were included. Clinical manifestations, CT features, 18F-FDG, or 68Ga-DOTATATE-PET/CT images and pathological results were collected. RESULTS: High-sensitivity C-reactive protein (p < 0.001) and expectoration occurrence (p = 0.04) were higher, and finger oxygen saturation (p = 0.01) was lower in the infection group than the NENs group. Higher-grade NENs were underrepresented in our cohort. Pulmonary NENs were solitary primary tumors, 80% of which were peripheral tumors. Overlying vessel sign and airway involvement were more frequent in the NENs group (p < 0.001). Multifocal (p = 0.001) and peripheral (p = 0.02) lesions, cavity (p < 0.001), spiculation (p = 0.01), pleural retraction (p < 0.001), connection to pulmonary veins (p = 0.02), and distal atelectasis or inflammatory exudation (p = 0.001) were more frequent in the infection group. The median CT value increment between the non-contrast and arterial phases was significantly higher in NENs lesions (p < 0.001). Receiver operating characteristic curve analysis indicated a moderate predictive ability at 48.3 HU of delta CT value (sensitivity, 95.0%; specificity, 54.1%). CONCLUSION: Chest CT scans are valuable for localizing and characterizing pulmonary lesions in rare EAS, thereby enabling prompt differential diagnosis and treatment. CRITICAL RELEVANCE STATEMENT: Thin-slice CT images are valuable for the localization and identification of pulmonary ectopic adrenocorticotropic hormone syndrome lesions, leading to prompt differential diagnosis and effective treatment. KEY POINTS: Lung tumor-like infections can mimic neuroendocrine neoplasms (NENs) in ectopic adrenocorticotropic hormone syndrome (EAS) patients. NENs are solitary lesions, whereas infections are multiple peripheral pseudotumors each with identifying imaging findings. Typical CT signs aid in localization and creating an appropriate differential diagnosis.

A Multi-Dataset Evaluation of Frame Censoring for Motion Correction in Task-Based fMRI.

Subject motion during fMRI can affect our ability to accurately measure signals of interest. In recent years, frame censoring-that is, statistically excluding motion-contaminated data within the general linear model using nuisance regressors-has appeared in several task-based fMRI studies as a mitigation strategy. However, there have been few systematic investigations quantifying its efficacy. In the present study, we compared the performance of frame censoring to several other common motion correction approaches for task-based fMRI using open data and reproducible workflows. We analyzed eight publicly available datasets representing 11 distinct tasks in child, adolescent, and adult participants. Performance was quantified using maximum t-values in group analyses, and region of interest-based mean activation and split-half reliability in single subjects. We compared frame censoring across several thresholds to the use of 6 and 24 canonical motion regressors, wavelet despiking, robust weighted least squares, and untrained ICA-based denoising, for a total of 240 separate analyses. Thresholds used to identify censored frames were based on both motion estimates (FD) and image intensity changes (DVARS). Relative to standard motion regressors, we found consistent improvements for modest amounts of frame censoring (e.g., 1-2% data loss), although these gains were frequently comparable to what could be achieved using other techniques. Importantly, no single approach consistently outperformed the others across all datasets and tasks. These findings suggest that the choice of a motion mitigation strategy depends on both the dataset and the outcome metric of interest.

A Multi-Classification Model for Predicting the Invasiveness of Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodules.

Objectives: To establish a multi-classification model for precisely predicting the invasiveness (pre-invasive adenocarcinoma, PIA; minimally invasive adenocarcinoma, MIA; invasive adenocarcinoma, IAC) of lung adenocarcinoma manifesting as pure ground-glass nodules (pGGNs). Methods: By the inclusion and exclusion criteria, this retrospective study enrolled 346 patients (female, 297, and male, 49; age, 55.79 ± 10.53 (24-83)) presenting as pGGNs from 1292 consecutive patients with pathologically confirmed lung adenocarcinoma. A total of 27 clinical were collected and 1409 radiomics features were extracted by PyRadiomics package on python. After feature selection with L2,1-norm minimization, logistic regression (LR), extra w(ET) and gradient boosting decision tree (GBDT) were used to construct the three-classification model. Then, an ensemble model of the three algorithms based on model ensemble strategy was established to further improve the classification performance. Results: After feature selection, a hybrid of 166 features consisting of 1 clinical (short-axis diameter, ranked 27th) and 165 radiomics (4 shape, 71 intensity and 90 texture) features were selected. The three most important features are wavelet-HLL_firstorder_Minimum, wavelet-HLL_ngtdm_Busyness and square_firstorder_Kurtosis. The hybrid-ensemble model based on hybrid clinical-radiomics features and the ensemble strategy showed more accurate predictive performance than other models (hybrid-LR, hybrid-ET, hybrid-GBDT, clinical-ensemble and radiomics-ensemble). On the training set and test set, the model can obtain the accuracy values of 0.918 ± 0.022 and 0.841, and its F1-scores respectively were 0.917 ± 0.024 and 0.824. Conclusion: The multi-classification of invasive pGGNs can be precisely predicted by our proposed hybrid-ensemble model to assist patients in the early diagnosis of lung adenocarcinoma and prognosis.

Hybrid Clinical-Radiomics Model for Precisely Predicting the Invasiveness of Lung Adenocarcinoma Manifesting as Pure Ground-Glass Nodule.

RATIONALE AND OBJECTIVES: To identify whether the radiomics features of computed tomography (CT) allowed for the preoperative discrimination of the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs) and further to develop and compare different predictive models. MATERIALS AND METHODS: We retrospectively included 187 lung adenocarcinomas presenting as pGGNs (66 preinvasive lesions and 121 invasive lesions), which were randomly divided into the training and test sets (8:2). Radiomics features were extracted from non-enhanced CT images. Clinical features, including patient's demographic characteristics, smoking status, and conventional CT features that reflect tumor's morphology and surrounding information were also collected. Intraclass correlation coefficient and ℓ2.1-norm minimization were used to identify influential feature subset which was then used to build three predictive models (clinical, radiomics, and clinical-radiomics models) with the gradient boosting regression tree classifier. The performances of the predictive models were evaluated using the area under the curve (AUC). RESULTS: Of the 1409 radiomics features and 27 clinical feature subtypes, 102 features were selected to construct the hybrid clinical-radiomics model, which achieved the best discriminative power (AUC = 0.934 and 0.929 in training and test set). The radiomics model showed comparable predictive performance (AUC = 0.911 and 0.901 in training and test set) compared to the clinical model (AUC = 0.911 and 0.894 in training and test set). CONCLUSION: The radiomics model showed good predictive performance in discriminating invasive lesions from preinvasive lesions for lung adenocarcinomas presenting as pGGNs. Its performance can be further improved by adding clinical features.

Clinical, Conventional CT and Radiomic Feature-Based Machine Learning Models for Predicting ALK Rearrangement Status in Lung Adenocarcinoma Patients.

Objectives: To predict the anaplastic lymphoma kinase (ALK) mutations in lung adenocarcinoma patients non-invasively with machine learning models that combine clinical, conventional CT and radiomic features. Methods: This retrospective study included 335 lung adenocarcinoma patients who were randomly divided into a primary cohort (268 patients; 90 ALK-rearranged; and 178 ALK wild-type) and a test cohort (67 patients; 22 ALK-rearranged; and 45 ALK wild-type). One thousand two hundred and eighteen quantitative radiomic features were extracted from the semi-automatically delineated volume of interest (VOI) of the entire tumor using both the original and the pre-processed non-enhanced CT images. Twelve conventional CT features and seven clinical features were also collected. Normalized features were selected using a sequential of the F-test-based method, the density-based spatial clustering of applications with noise (DBSCAN) method, and the recursive feature elimination (RFE) method. Selected features were then used to build three predictive models (radiomic, radiological, and integrated models) for the ALK-rearranged phenotype by a soft voting classifier. Models were evaluated in the test cohort using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity, and the performances of three models were compared using the DeLong test. Results: Our results showed that the addition of clinical information and conventional CT features significantly enhanced the validation performance of the radiomic model in the primary cohort (AUC = 0.83-0.88, P = 0.01), but not in the test cohort (AUC = 0.80-0.88, P = 0.29). The majority of radiomic features associated with ALK mutations reflected information around and within the high-intensity voxels of lesions. The presence of the cavity and left lower lobe location were new imaging phenotypic patterns in association with ALK-rearranged tumors. Current smoking was strongly correlated with non-ALK-mutated lung adenocarcinoma. Conclusions: Our study demonstrates that radiomics-derived machine learning models can potentially serve as a non-invasive tool to identify ALK mutation of lung adenocarcinoma.