Radiomics signature: a biomarker for the preoperative discrimination of lung invasive adenocarcinoma manifesting as a ground-glass nodule

Deep learning-based characterization of pathological subtypes in lung invasive adenocarcinoma utilizing 18F-deoxyglucose positron emission tomography imaging

OBJECTIVE

To evaluate the diagnostic efficacy of a deep learning (DL) model based on PET/CT images for distinguishing and predicting various pathological subtypes of invasive lung adenocarcinoma.

METHODS

A total of 250 patients diagnosed with invasive lung cancer were included in this retrospective study. The pathological subtypes of the cancer were recorded. PET/CT images were analyzed, including measurements and recordings of the short and long diameters on the maximum cross-sectional plane of the CT image, the density of the lesion, and the associated imaging signs. The SUVmax, SUVmean, and the lesion's long and short diameters on the PET image were also measured. A manual diagnostic model was constructed to analyze its diagnostic performance across different pathological subtypes. The acquired images were first denoised, followed by data augmentation to expand the dataset. The U-Net network architecture was then employed for feature extraction and network segmentation. The classification network was based on the ResNet residual network to address the issue of gradient vanishing in deep networks. Batch normalization was applied to ensure the feature matrix followed a distribution with a mean of 0 and a variance of 1. The images were divided into training, validation, and test sets in a ratio of 6:2:2 to train the model. The deep learning model was then constructed to analyze its diagnostic performance across different pathological subtypes.

RESULTS

Statistically significant differences (P < 0.05) were observed among the four different subtypes in PET/CT imaging performance. The AUC and diagnostic accuracy of the manual diagnostic model for different pathological subtypes were as follows: APA: 0.647, 0.664; SPA: 0.737, 0.772; PPA: 0.698, 0.780; LPA: 0.849, 0.904. Chi-square tests indicated significant statistical differences among these subtypes (P < 0.05). The AUC and diagnostic accuracy of the deep learning model for the different pathological subtypes were as follows: APA: 0.854, 0.864; SPA: 0.930, 0.936; PPA: 0.878, 0.888; LPA: 0.900, 0.920. Chi-square tests also indicated significant statistical differences among these subtypes (P < 0.05). The Delong test showed that the diagnostic performance of the deep learning model was superior to that of the manual diagnostic model (P < 0.05).

CONCLUSIONS

The deep learning model based on PET/CT images exhibits high diagnostic efficacy in distinguishing and diagnosing various pathological subtypes of invasive lung adenocarcinoma, demonstrating the significant potential of deep learning techniques in accurately identifying and predicting disease subgroups.

Evaluation of the invasiveness of pure ground-glass nodules based on dual-head ResNet technique

OBJECTIVE

To intelligently evaluate the invasiveness of pure ground-glass nodules with multiple classifications using deep learning.

METHODS

pGGNs in 1136 patients were pathologically confirmed as lung precursor lesions [atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS)], minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). Four different models [EfficientNet-b0 2D, dual-head ResNet_3D, a 3D model combining three features (3D_3F), and a 3D model combining 19 features (3D_19F)] were constructed to evaluate the invasiveness of pGGNs using the EfficientNet and ResNet networks. The Obuchowski index was used to evaluate the differences in diagnostic efficiency among the four models.

RESULTS

The patients with pGGNs (360 men, 776 women; mean age, 54.63 ± 12.36 years) included 235 cases of AAH + AIS, 332 cases of MIA, and 569 cases of IAC. In the validation group, the areas under the curve in detecting the invasiveness of pGGNs as a three-category classification (AAH + AIS, MIA, IAC) were 0.8008, 0.8090, 0.8165, and 0.8158 for EfficientNet-b0 2D, dual-head ResNet_3D, 3D_3F, and 3D_19F, respectively, whereas the accuracies were 0.6422, 0.6158, 0.651, and 0.6364, respectively. The Obuchowski index revealed no significant differences in the diagnostic performance of the four models.

CONCLUSIONS

The dual-head ResNet_3D_3F model had the highest diagnostic efficiency for evaluating the invasiveness of pGGNs in the four models.

Evolving and Novel Applications of Artificial Intelligence in Thoracic Imaging

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

Subsolid Nodules: Significance and Current Understanding

Subsolid nodules are heterogeneously appearing and behaving entities, commonly encountered incidentally and in high-risk populations. Accurate characterization of subsolid nodules, and application of evolving surveillance guidelines, facilitates evidence-based and multidisciplinary patient-centered management.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

Predicting the Invasiveness of Pulmonary Adenocarcinomas in Pure Ground-Glass Nodules Using the Nodule Diameter: A Systematic Review, Meta-Analysis, and Validation in an Independent Cohort

The nodule diameter was commonly used to predict the invasiveness of pulmonary adenocarcinomas in pure ground-glass nodules (pGGNs). However, the diagnostic performance and optimal cut-off values were inconsistent. We conducted a meta-analysis to evaluate the diagnostic performance of the nodule diameter for predicting the invasiveness of pulmonary adenocarcinomas in pGGNs and validated the cut-off value of the diameter in an independent cohort. Relevant studies were searched through PubMed, MEDLINE, Embase, and the Cochrane Library, from inception until December 2022. The inclusion criteria comprised studies that evaluated the diagnostic accuracy of the nodule diameter to differentiate invasive adenocarcinomas (IAs) from non-invasive adenocarcinomas (non-IAs) in pGGNs. A bivariate mixed-effects regression model was used to obtain the diagnostic performance. Meta-regression analysis was performed to explore the heterogeneity. An independent sample of 220 pGGNs (82 IAs and 128 non-IAs) was enrolled as the validation cohort to evaluate the performance of the cut-off values. This meta-analysis finally included 16 studies and 2564 pGGNs (761 IAs and 1803 non-IAs). The pooled area under the curve, the sensitivity, and the specificity were 0.85 (95% confidence interval (CI), 0.82-0.88), 0.82 (95% CI, 0.78-0.86), and 0.73 (95% CI, 0.67-0.78). The diagnostic performance was affected by the measure of the diameter, the reconstruction matrix, and patient selection bias. Using the prespecified cut-off value of 10.4 mm for the mean diameter and 13.2 mm for the maximal diameter, the mean diameter showed higher sensitivity than the maximal diameter in the validation cohort (0.85 vs. 0.72, p < 0.01), while there was no significant difference in specificity (0.83 vs. 0.86, p = 0.13). The nodule diameter had adequate diagnostic performance in differentiating IAs from non-IAs in pGGNs and could be replicated in a validation cohort. The mean diameter with a cut-off value of 10.4 mm was recommended.

The Value of Topological Radiomics Analysis in Predicting Malignant Risk of Pulmonary Ground-Glass Nodules: A Multi-Center Study

BACKGROUND

Early detection and accurate differentiation of malignant ground-glass nodules (GGNs) in lung CT scans are crucial for the effective treatment of lung adenocarcinoma. However, existing imaging diagnostic methods often struggle to distinguish between benign and malignant GGNs in the early stages. This study aims to predict the malignancy risk of GGNs observed in lung CT scans by applying two radiomics methods: topological data analysis and texture analysis.

METHODS

A retrospective analysis was conducted on 3223 patients from two centers between January 2018 and June2023. The dataset was divided into training, testing, and validation sets to ensure robust model development and validation. We developed topological features applied to GGNs using radiomics analysis based on homology. This innovative approach emphasizes the integration of topological information, capturing complex geometric and spatial relationships within GGNs. By combining machine learning and deep learning algorithms, we established a predictive model that integrates clinical parameters, previous radiomics features, and topological radiomics features.

RESULTS

Incorporating topological radiomics into our model significantly enhanced the ability to distinguish between benign and malignant GGNs. The topological radiomics model achieved areas under the curve (AUC) of 0.85 and 0.862 in two independent validation sets, outperforming previous radiomics models. Furthermore, this model demonstrated higher sensitivity compared to models based solely on clinical parameters, with sensitivities of 80.7% in validation set 1 and 82.3% in validation set 2. The most comprehensive model, which combined clinical parameters, previous radiomics features, and topological radiomics features, achieved the highest AUC value of 0.879 across all datasets.

CONCLUSION

This study validates the potential of topological radiomics in improving the predictive performance for distinguishing between benign and malignant GGNs. By integrating topological features with previous radiomics and clinical parameters, our comprehensive model provides a more accurate and reliable basis for developing treatment strategies for patients with GGNs.

Predicting visceral pleural invasion in lung adenocarcinoma presenting as part-solid density utilizing a nomogram model combined with radiomics and clinical features

BACKGROUND

To develop and validate a preoperative nomogram model combining the radiomics signature and clinical features for preoperative prediction of visceral pleural invasion (VPI) in lung nodules presenting as part-solid density.

METHODS

We retrospectively reviewed 156 patients with pathologically confirmed invasive lung adenocarcinomas after surgery from January 2016 to August 2019. The patients were split into training and validation sets by a ratio of 7:3. The radiomic features were extracted with the aid of FeAture Explorer Pro (FAE). A CT-based radiomics model was constructed to predict the presence of VPI and internally validated. Multivariable regression analysis was conducted to construct a nomogram model, and the performance of the models were evaluated with the area under the receiver operating characteristic curve (AUC) and compared with each other.

RESULTS

The enrolled patients were split into training (n = 109) and validation sets (n = 47). A total of 806 features were extracted and the selected 10 optimal features were used in the construction of the radiomics model among the 707 stable features. The AUC of the nomogram model was 0.888 (95% CI: 0.762-0.961), which was superior to the clinical model (0.787, 95% CI: 0.643-0.893; p = 0.049) and comparable to the radiomics model (0.879, 95% CI: 0.751-0.965; p > 0.05). The nomogram model achieved a sensitivity of 90.5% and a specificity of 76.9% in the validation dataset.

CONCLUSIONS

The nomogram model could be considered as a noninvasive method to predict VPI with either highly sensitive or highly specific diagnoses depending on clinical needs.

Combined model integrating deep learning, radiomics, and clinical data to classify lung nodules at chest CT

OBJECTIVES

The study aimed to develop a combined model that integrates deep learning (DL), radiomics, and clinical data to classify lung nodules into benign or malignant categories, and to further classify lung nodules into different pathological subtypes and Lung Imaging Reporting and Data System (Lung-RADS) scores.

MATERIALS AND METHODS

The proposed model was trained, validated, and tested using three datasets: one public dataset, the Lung Nodule Analysis 2016 (LUNA16) Grand challenge dataset (n = 1004), and two private datasets, the Lung Nodule Received Operation (LNOP) dataset (n = 1027) and the Lung Nodule in Health Examination (LNHE) dataset (n = 1525). The proposed model used a stacked ensemble model by employing a machine learning (ML) approach with an AutoGluon-Tabular classifier. The input variables were modified 3D convolutional neural network (CNN) features, radiomics features, and clinical features. Three classification tasks were performed: Task 1: Classification of lung nodules into benign or malignant in the LUNA16 dataset; Task 2: Classification of lung nodules into different pathological subtypes; and Task 3: Classification of Lung-RADS score. Classification performance was determined based on accuracy, recall, precision, and F1-score. Ten-fold cross-validation was applied to each task.

RESULTS

The proposed model achieved high accuracy in classifying lung nodules into benign or malignant categories in LUNA 16 with an accuracy of 92.8%, as well as in classifying lung nodules into different pathological subtypes with an F1-score of 75.5% and Lung-RADS scores with an F1-score of 80.4%.

CONCLUSION

Our proposed model provides an accurate classification of lung nodules based on the benign/malignant, different pathological subtypes, and Lung-RADS system.

Preoperative 18F-FDG PET/CT and CT radiomics for identifying aggressive histopathological subtypes in early stage lung adenocarcinoma

Lung adenocarcinoma (ADC) is the most common non-small cell lung cancer. Surgical resection is the primary treatment for early-stage lung ADC while lung-sparing surgery is an alternative for non-aggressive cases. Identifying histopathologic subtypes before surgery helps determine the optimal surgical approach. Predominantly solid or micropapillary (MIP) subtypes are aggressive and associated with a higher likelihood of recurrence and metastasis and lower survival rates. This study aims to non-invasively identify these aggressive subtypes using preoperative 18F-FDG PET/CT and diagnostic CT radiomics analysis. We retrospectively studied 119 patients with stage I lung ADC and tumors ≤ 2 cm, where 23 had aggressive subtypes (18 solid and 5 MIPs). Out of 214 radiomic features from the PET/CT and CT scans and 14 clinical parameters, 78 significant features (3 CT and 75 PET features) were identified through univariate analysis and hierarchical clustering with minimized feature collinearity. A combination of Support Vector Machine classifier and Least Absolute Shrinkage and Selection Operator built predictive models. Ten iterations of 10-fold cross-validation (10 ×10-fold CV) evaluated the model. A pair of texture feature (PET GLCM Correlation) and shape feature (CT Sphericity) emerged as the best predictor. The radiomics model significantly outperformed the conventional predictor SUVmax (accuracy: 83.5% vs. 74.7%, p = 9e-9) and identified aggressive subtypes by evaluating FDG uptake in the tumor and tumor shape. It also demonstrated a high negative predictive value of 95.6% compared to SUVmax (88.2%, p = 2e-10). The proposed radiomics approach could reduce unnecessary extensive surgeries for non-aggressive subtype patients, improving surgical decision-making for early-stage lung ADC patients.

Invasiveness identification in pure ground-glass nodules: exploring the generalizability of radiomics based on external validation and stress testing

PURPOSE

This study aimed to apply external validation and stress tests to evaluate the generalizability of radiomics models built using various machine-learning methods for identifying the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs).

METHODS

This retrospective study enrolled 495 patients (514 pGGNs) confirmed as lung adenocarcinomas by postoperative pathology from three centers. All nodules were included in the primary cohort (randomly divided into training and test cohorts), two external validation cohorts, and two stress test cohorts. Six machine-learning radiomics models were constructed in the training cohort using the optimal features. Performance of radiomics models and clinical models were compared in primary cohort and external validation cohorts. The stress tests included stratified performance evaluation and shifted performance evaluation and contrastive evaluation under three single-condition modification settings. The predictive performance was validated by area under curve (AUC) of receiver operating characteristic (ROC).

RESULTS

Of the six radiomics models, the best logistic regression (LR) model was able to maintain high differential diagnostic capability (AUC: 0.849 ± 0.049) and good stability (relative standard deviation, 5.719%), but it showed poorer performance (AUC = 0.835) than the clinical model (AUC = 0.862) in the external validation cohort E1. The stress tests suggested LR model had no significant difference in performance between subgroups after stratification and had good consistency in the predictions before and after the three transformations (Kappa = 0.960, 0.840, and 0.933, respectively; p < 0.05, all).

CONCLUSION

The rigorous testing procedure facilitates the selection of high-performance radiomics models with good clinical generalizability.

Invasiveness assessment by artificial intelligence against intraoperative frozen section for pulmonary nodules ≤ 3 cm

PURPOSE

To investigate the performance of an artificial intelligence (AI) algorithm for assessing the malignancy and invasiveness of pulmonary nodules in a multicenter cohort.

METHODS

A previously developed deep learning system based on a 3D convolutional neural network was used to predict tumor malignancy and invasiveness. Dataset of pulmonary nodules no more than 3 cm was integrated with CT images and pathologic information. Receiver operating characteristic curve analysis was used to evaluate the performance of the system.

RESULTS

A total of 466 resected pulmonary nodules were included in this study. The areas under the curves (AUCs) of the deep learning system in the prediction of malignancy as compared with pathological reports were 0.80, 0.80, and 0.75 for all, subcentimeter, and solid nodules, respectively. Additionally, the AUC in the AI-assisted prediction of invasive adenocarcinoma (IA) among subsolid lesions (n = 184) was 0.88. Most malignancies that were misdiagnosed by the AI system as benign diseases with a diameter measuring greater than 1 cm (26/250, 10.4%) presented as solid nodules (19/26, 73.1%) on CT. In an exploratory analysis involving nodules underwent intraoperative pathologic examination, the concordance rate in identifying IA between the AI model and frozen section examination was 0.69, with a sensitivity of 0.50 and specificity of 0.97.

CONCLUSION

The deep learning system can discriminate malignant diseases for pulmonary nodules measuring no more than 3 cm. The AI model has a high positive predictive value for invasive adenocarcinoma with respect to intraoperative frozen section examination, which might help determine the individualized surgical strategy.

An ensemble deep learning model for risk stratification of invasive lung adenocarcinoma using thin-slice CT

Lung cancer screening using computed tomography (CT) has increased the detection rate of small pulmonary nodules and early-stage lung adenocarcinoma. It would be clinically meaningful to accurate assessment of the nodule histology by CT scans with advanced deep learning algorithms. However, recent studies mainly focus on predicting benign and malignant nodules, lacking of model for the risk stratification of invasive adenocarcinoma. We propose an ensemble multi-view 3D convolutional neural network (EMV-3D-CNN) model to study the risk stratification of lung adenocarcinoma. We include 1075 lung nodules (≤30 mm and ≥4 mm) with preoperative thin-section CT scans and definite pathology confirmed by surgery. Our model achieves a state-of-art performance of 91.3% and 92.9% AUC for diagnosis of benign/malignant and pre-invasive/invasive nodules, respectively. Importantly, our model outperforms senior doctors in risk stratification of invasive adenocarcinoma with 77.6% accuracy [i.e., Grades 1, 2, 3]). It provides detailed predictive histological information for the surgical management of pulmonary nodules. Finally, for user-friendly access, the proposed model is implemented as a web-based system ( https://seeyourlung.com.cn ).

Confluent cavitated nodules in invasive mucinous adenocarcinoma: A case report

Invasive mucinous adenocarcinoma is a rare variant of lung adenocarcinoma. Here, we present the case of a patient with invasive mucinous adenocarcinoma with cavitary lung lesions. A 61-year-old painter-and-bricklayer. She was admitted due to mMRC2 dyspnea, a dry cough that during hospitalization mobilizes dense, abundant secretions, and becomes demanding. Differential diagnoses were made based on clinical symptoms and images, performing multiple laboratory tests ruling out immunosuppression, and two video-bronchofibroscopies finding the diagnosis in the transbronchial lung biopsy: Invasive mucinous adenocarcinoma that would explain the abundant bronchorrhea, advanced stage and poor prognosis led to ventilatory failure and death of the patient.

Integrated Multi-omics Analysis of Early Lung Adenocarcinoma Links Tumor Biological Features with Predicted Indolence or Aggressiveness

Lung adenocarcinoma (LUAD) is a heterogeneous group of tumors associated with different survival rates, even when detected at an early stage. Here, we aim to investigate the biological determinants of early LUAD indolence or aggressiveness using radiomics as a surrogate of behavior. We present a set of 92 patients with LUAD with data collected across different methodologies. Patients were risk-stratified using the CT-based Score Indicative of Lung cancer Aggression (SILA) tool (0 = least aggressive, 1 = most aggressive). We grouped the patients as indolent (x ≤ 0.4, n = 14), intermediate (0.4 > x ≤ 0.6, n = 27), and aggressive (0.6 > x ≤ 1, n = 52). Using Cytometry by time of flight (CyTOF), we identified subpopulations with high HLA-DR expression that were associated with indolent behavior. In the RNA sequencing (RNA-seq) dataset, pathways related to immune response were associated with indolent behavior, while pathways associated with cell cycle and proliferation were associated with aggressive behavior. We extracted quantitative radiomics features from the CT scans of the patients. Integrating these datasets, we identified four feature signatures and four patient clusters that were associated with survival. Using single-cell RNA-seq, we found that indolent tumors had significantly more T cells and less B cells than aggressive tumors, and that the latter had a higher abundance of regulatory T cells and Th cells. In conclusion, we were able to uncover a correspondence between radiomics and tumor biology, which could improve the discrimination between indolent and aggressive LUAD tumors, enhance our knowledge in the biology of these tumors, and offer novel and personalized avenues for intervention.

Significance

This study provides a comprehensive profiling of LUAD indolence and aggressiveness at the biological bulk and single-cell levels, as well as at the clinical and radiomics levels. This hypothesis generating study uncovers several potential future research avenues. It also highlights the importance and power of data integration to improve our systemic understanding of LUAD and to help reduce the gap between basic science research and clinical practice.

Benign-malignant classification of pulmonary nodules by low-dose spiral computerized tomography and clinical data with machine learning in opportunistic screening

BACKGROUND

Many people were found with pulmonary nodules during physical examinations. It is of great practical significance to discriminate benign and malignant nodules by using data mining technology.

METHODS

The subjects' demographic data, baseline examination results, and annual follow-up low-dose spiral computerized tomography (LDCT) results were recorded. The findings from annual physical examinations of positive nodules, including highly suspicious nodules and clinically tentative benign nodules, was analyzed. The extreme gradient boosting (XGBoost) model was constructed and the Grid Search CV method was used to select the super parameters. External unit data were used as an external validation set to evaluate the generalization performance of the model.

RESULTS

A total of 135,503 physical examinees were enrolled. Baseline testing found that 27,636 (20.40%) participants had clinically tentative benign nodules and 611 (0.45%) participants had highly suspicious nodules. The proportion of highly suspicious nodules in participants with negative baseline was about 0.12%-0.46%, which was lower than the baseline level except the follow-up of >5 years. In the 27,636 participants with clinically tentative benign nodules, only in the first year of LDCT re-examination was the proportion of highly suspicious nodules (1.40%) significantly greater than that of baseline screening (0.45%) (p < 0.001), and the proportion of highly suspicious nodules was not different between the baseline screening and other follow-up years (p > 0.05). Furthermore, 322 cases with benign nodules and 196 patients with malignant nodules confirmed by surgery and pathology were compared. A model and the top 15 most important clinical variables were determined by XGBoost algorithm. The area under the curve (AUC) of the model was 0.76 [95% CI: 0.67-0.84], and the accuracy was 0.75. The sensitivity and specificity of the model under this threshold were 0.78 and 0.73, respectively. In the validation of model using external data, the AUC was 0.87 and the accuracy was 0.80. The sensitivity and specificity were 0.83 and 0.77, respectively.

CONCLUSIONS

It is important that pulmonary nodules could be more accurately identified at the first LDCT examination. A model with 15 variables which are routinely measured in the clinic could be helpful to distinguish benign and malignant nodules. It could help the radiological team issue a more accurate report; and it may guide the clinical team regarding LDCT follow-up.

Software-based quantitative CT analysis to predict the growth trend of persistent nonsolid pulmonary nodules: a retrospective study

PURPOSE

Persistent nonsolid nodules (NSNs) usually exhibit an indolent course and may remain stable for several years; however, some NSNs grow quickly and require surgical excision. Therefore, identifying quantitative features capable of early discrimination between growing and nongrowing NSNs is becoming a crucial aspect of radiological analysis. The main purpose of this study was to evaluate the performance of an open-source software (ImageJ) to predict the future growth of NSNs detected in a Caucasian (Italian) population.

MATERIAL AND METHODS

We retrospectively selected 60 NSNs with an axial diameter of 6-30 mm scanned with the same acquisition-reconstruction parameters and the same computed tomography (CT) scanner. Software-based analysis was performed on thin-section CT images using ImageJ. For each NSNs, several quantitative features were extracted from the baseline CT images. The relationships of NSN growth with quantitative CT features and other categorical variables were analyzed using univariate and multivariable logistic regression analyses.

RESULTS

In multivariable analysis, only the skewness and linear mass density (LMD) were significantly associated with NSN growth, and the skewness was the strongest predictor of growth. In receiver operating characteristic curve analyses, the optimal cutoff values of skewness and LMD were 0.90 and 19.16 mg/mm, respectively. The two predictive models that included the skewness, with or without LMD, exhibited an excellent power for predicting NSN growth.

CONCLUSION

According to our results, NSNs with a skewness value > 0.90, specifically those with a LMD > 19.16 mg/mm, should require closer follow-up due to their higher growth potential, and higher risk of becoming an active cancer.

Radiomics-based analysis of CT imaging for the preoperative prediction of invasiveness in pure ground-glass nodule lung adenocarcinomas

OBJECTIVE

The purpose of the study is to investigate the performance of radiomics-based analysis in prediction of pure ground-glass nodule (pGGN) lung adenocarcinomas invasiveness using thin-section computed tomography images.

METHODS

A total of 382 patients surgically resected single pGGN and pathologically confirmed were enrolled in the retrospective study. The pGGN cases were divided into two groups: the noninvasive group and the invasive adenocarcinoma (IAC) group. 330 patients were randomly assigned to the training and testing cohorts with a ratio of 7:3 (245 noninvasive lesions, 85 IAC lesions), while 52 patients (30 noninvasive lesions, 22 IAC lesions) were assigned to the external validation cohort. A model, radiomics model, and combined clinical-radiographic-radiomic model were built using the LASSO and multivariate backward stepwise regression analysis on the basis of the selected and radiomics features. The area under the curve (AUC) and decision curve analysis (DCA) were used to evaluate and compare the model performance for invasiveness discrimination among the three cohorts.

RESULTS

Three clinical-radiographic features (including age, gender and the mean CT value) and three radiomics features were selected for model building. The combined model and radiomics model performed better than the clinical-radiographic model. The AUCs of the combined model in the training, testing, and validation cohorts were 0.856, 0.859, and 0.765, respectively. The DCA demonstrated the radiomics signatures incorporating clinical-radiographic feature was clinically useful in predicting pGGN invasiveness.

CONCLUSIONS

The proposed radiomics-based analysis incorporating the clinical-radiographic feature could accurately predict pGGN invasiveness, providing a noninvasive biomarker for the individualized and precise medical treatment of patients.

Computed tomography radiomics in growth prediction of pulmonary ground-glass nodules

PURPOSE

Individualized follow-up of pulmonary ground-glass nodules (GGNs) remains challenging in clinical practice. Accurate prediction of the growth or long-term stability of persistent GGNs is essential to optimize the follow-up intervals.

METHODS

In this retrospective study, 253 patients with 1115 computed tomography (CT) images were recruited. In total, 1115 CT images were randomized into training (70%) and validation sets (30%). We developed models for the growth or long-term stable prediction of GGNs using radiomics and clinical features. We evaluated the prediction accuracy of the models using receiver operating characteristic (ROC) curve analysis, and the areas under the curve (AUCs) were established. The ROC curves of the models were compared using the DeLong method.

RESULTS

The growth and stable groups contained 535 and 580 GGNs, respectively. Traditional radiographic features have limited value in the prediction of growth or long-term stability of GGNs. The prediction nomogram model combining radiomics and clinical features (size, location, and age) yielded the best AUC in both the training and validation sets (AUC = 0.843 and 0.824, respectively). The radiomics model outperformed the clinical model in both sets (AUC: 0.836 vs 0.772 and 0.818 vs 0.735, respectively). The radiomics signature and nomogram model achieved similar AUCs (Delong test, training set: P = 0.09; validation set: P = 0.37).

CONCLUSIONS

We developed and validated a nomogram model combining radiomics signature, size, age, and location to predict the growth or long-term stability of GGNs. The model achieved good performance and may provide a basis for the improvement of follow-up management of GGNs.

Preoperative levels of folate receptor-positive circulating tumor cells in different subtypes of early-stage lung adenocarcinoma: Predictive value for determining extent of surgical resection

Background

The objective was to measure the correlations of preoperative levels of folate receptor-positive circulating tumor cells (FR⁺CTCs) with clinical characteristics and histologic subtype in early-stage lung adenocarcinoma, and to determine the predictive value of FR⁺CTC level in preoperative determination of the extent of surgical resection.

Patients and methods

In this retrospective, single-institution, observational study, preoperative FR⁺CTC levels were measured via ligand-targeted enzyme-linked polymerization in patients with early-stage lung adenocarcinoma. Receiver operating characteristic (ROC) analysis was used to identify the optimal cutoff value of FR⁺CTC level for prediction of various clinical characteristics and histologic subtypes.

Results

No significant difference in FR⁺CTC level was observed among patients with adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) (P = 0.813). Within the non-mucinous adenocarcinoma group, no difference was observed among patients with tumors whose predominant growth patterns were lepidic, acinar, papillary, micropapillary, solid, and complex gland (P = 0.053). However, significant differences in FR⁺CTC level were observed between patients with and without the micropapillary subtype [11.21 (8.22-13.61) vs. 9.85 (7.43-12.63), P = 0.017], between those with and without the solid subtype [12.16 (8.27-14.90) vs. 9.87 (7.50-12.49), P = 0.022], and between those with any of the advanced subtypes (micropapillary, solid, or complex glands) vs. none of these [10.48 (7.83-13.67) vs. 9.76 (7.42-12.42), P = 0.032]. FR⁺CTC level was also correlated with degree of differentiation of lung adenocarcinoma (P = 0.033), presence of visceral pleural invasion (VPI) of lung carcinoma (P = 0.003), and lymph node metastasis of lung carcinoma (P = 0.035).

Conclusion

FR⁺CTC level is of potential predictive value in determining the presence of aggressive histologic patterns (micropapillary, solid, and advanced subtypes), degree of differentiation, and occurrence of VPI and lymph node metastasis in IAC. Measurement of FR⁺CTC level combined with intraoperative frozen sections may represent a more effective method of guiding resection strategy in cases of cT1N0M0 IAC with high-risk factors.

Artificial intelligence in lung cancer: current applications and perspectives

Artificial intelligence (AI) has been a very active research topic over the last years and thoracic imaging has particularly benefited from the development of AI and in particular deep learning. We have now entered a phase of adopting AI into clinical practice. The objective of this article was to review the current applications and perspectives of AI in thoracic oncology. For pulmonary nodule detection, computer-aided detection (CADe) tools have been commercially available since the early 2000s. The more recent rise of deep learning and the availability of large annotated lung nodule datasets have allowed the development of new CADe tools with fewer false-positive results per examination. Classical machine learning and deep-learning methods were also used for pulmonary nodule segmentation allowing nodule volumetry and pulmonary nodule characterization. For pulmonary nodule characterization, radiomics and deep-learning approaches were used. Data from the National Lung Cancer Screening Trial (NLST) allowed the development of several computer-aided diagnostic (CADx) tools for diagnosing lung cancer on chest computed tomography. Finally, AI has been used as a means to perform virtual biopsies and to predict response to treatment or survival. Thus, many detection, characterization and stratification tools have been proposed, some of which are commercially available.

Artificial intelligence: A critical review of applications for lung nodule and lung cancer

Artificial intelligence (AI) is a broad concept that usually refers to computer programs that can learn from data and perform certain specific tasks. In the recent years, the growth of deep learning, a successful technique for computer vision tasks that does not require explicit programming, coupled with the availability of large imaging databases fostered the development of multiple applications in the medical imaging field, especially for lung nodules and lung cancer, mostly through convolutional neural networks (CNN). Some of the first applications of AI is this field were dedicated to automated detection of lung nodules on X-ray and computed tomography (CT) examinations, with performances now reaching or exceeding those of radiologists. For lung nodule segmentation, CNN-based algorithms applied to CT images show excellent spatial overlap index with manual segmentation, even for irregular and ground glass nodules. A third application of AI is the classification of lung nodules between malignant and benign, which could limit the number of follow-up CT examinations for less suspicious lesions. Several algorithms have demonstrated excellent capabilities for the prediction of the malignancy risk when a nodule is discovered. These different applications of AI for lung nodules are particularly appealing in the context of lung cancer screening. In the field of lung cancer, AI tools applied to lung imaging have been investigated for distinct aims. First, they could play a role for the non-invasive characterization of tumors, especially for histological subtype and somatic mutation predictions, with a potential therapeutic impact. Additionally, they could help predict the patient prognosis, in combination to clinical data. Despite these encouraging perspectives, clinical implementation of AI tools is only beginning because of the lack of generalizability of published studies, of an inner obscure working and because of limited data about the impact of such tools on the radiologists' decision and on the patient outcome. Radiologists must be active participants in the process of evaluating AI tools, as such tools could support their daily work and offer them more time for high added value tasks.

CT-Based Radiomic Analysis for Preoperative Prediction of Tumor Invasiveness in Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodule

It remains a challenge to preoperatively forecast whether lung pure ground-glass nodules (pGGNs) have invasive components. We aimed to construct a radiomic model using tumor characteristics to predict the histologic subtype associated with pGGNs. We retrospectively reviewed clinicopathologic features of pGGNs resected in 338 patients with lung adenocarcinoma between 2011-2016 at a single institution. A radiomic prediction model based on forward sequential selection and logistic regression was constructed to differentiate adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma. The study cohort included 133 (39.4%), 128 (37.9%), and 77 (22.8%) patients with AIS, MIA, and invasive adenocarcinoma (acinar 55.8%, lepidic 33.8%, papillary 10.4%), respectively. The majority (83.7%) underwent sublobar resection. There were no nodal metastases or tumor recurrence during a mean follow-up period of 78 months. Three radiomic features-cluster shade, homogeneity, and run-length variance-were identified as predictors of histologic subtype and were selected to construct a prediction model to classify the AIS/MIA and invasive adenocarcinoma groups. The model achieved accuracy, sensitivity, specificity, and AUC of 70.6%, 75.0%, 70.0%, and 0.7676, respectively. Applying the developed radiomic feature model to predict the histologic subtypes of pGGNs observed on CT scans can help clinically in the treatment selection process.

Non-contrast and contrast enhanced computed tomography radiomics in preoperative discrimination of lung invasive and non-invasive adenocarcinoma

Objective

This study aimed to assess the value of radiomics based on non-contrast computed tomography (NCCT) and contrast-enhanced computed tomography (CECT) images in the preoperative discrimination between lung invasive adenocarcinomas (IAC) and non-invasive adenocarcinomas (non-IAC).

Methods

We enrolled 1,185 pulmonary nodules (478 non-IACs and 707 IACs) to build and validate radiomics models. An external testing set comprising 63 pulmonary nodules was collected to verify the generalization of the models. Radiomic features were extracted from both NCCT and CECT images. The predictive performance of radiomics models in the validation and external testing sets were evaluated and compared with radiologists’ evaluations. The predictive performances of the radiomics models were also compared between three subgroups in the validation set (Group 1: solid nodules, Group 2: part-solid nodules, and Group 3: pure ground-glass nodules).

Results

The NCCT, CECT, and combined models showed good ability to discriminate between IAC and non-IAC [respective areas under the curve (AUCs): validation set = 0.91, 0.90, and 0.91; Group 1 = 0.82, 0.79, and 0.81; Group 2 = 0.93, 0.92, and 0.93; and Group 3 = 0.90, 0.90, and 0.89]. In the external testing set, the AUC of the three models were 0.89, 0.91, and 0.89, respectively. The accuracies of these three models were comparable to those of the senior radiologist and better those that of the junior radiologist.

Conclusion

Radiomic models based on CT images showed good predictive performance in discriminating between lung IAC and non-IAC, especially in part solid nodule group. However, radiomics based on CECT images provided no additional value compared to NCCT images.

Folate receptor-positive circulating tumor cells in the preoperative diagnosis of indeterminate pulmonary nodules

BACKGROUND

The use of FR + CTC to distinguish lung cancer from benign lung disease has been well studied. However, the effective method to differentiate precursor glandular lesions from benign/malignant pulmonary diseases is rare.

METHODS

380 patients with indeterminate pulmonary nodules were prospectively recruited. Peripheral blood samples were collected from all participants before surgery for analyzing FR + CTC levels. The performance of FR + CTC to identify lung precursor lesions were analyzed by receiver operating characteristic (ROC) curve.

RESULTS

FR + CTC can effectively differentiate precursor from benign pulmonary diseases in all included patients (cutoff: 9.22 FU/3 ml, AUC = 0.807, (p < 0.0001, sensitivity: 69.17%, specificity: 82.46%) and patients with single pulmonary lesion (cutoff: 9.03 FU/3 ml, AUC = 0.842, p = 0.0001, sensitivity: 75.20%, specificity: 83.00%). However, FR + CTC cannot differentiate precursor from benign pulmonary diseases in multiple lesions patients (p = 0.110). FR + CTC neither differentiate precursor from malignant pulmonary lesions in all included patients (p = 0.715), single nor multiple lesions patients (p = 0.867, p = 0.692, respectively). Total number of pulmonary nodules, MTD, location (lower vs upper) were independent risk factors for malignancy (AOR, 95% CI: 3.104 (1.525, 6.316), 3.148 (1.722, 5.754), 2.098 (1.132, 3.888), respectively.

CONCLUSION

Preoperative FR + CTC can be identified in precursor glandular lesions and utilized to differentiate from benign pulmonary diseases. Total number of pulmonary nodules, MTD, location (lower vs upper) were independent risk factors for malignancy.

Association between quantitative spectral CT parameters, Ki-67 expression, and invasiveness in lung adenocarcinoma manifesting as ground-glass nodules

BACKGROUND

Few studies about lung ground-glass nodules (GGNs) have been done using non-enhancement spectral computed tomography (CT) imaging.

PURPOSE

To examine the association between spectral CT parameters, Ki-67 expression, and invasiveness in lung adenocarcinoma manifesting as GGNs.

MATERIAL AND METHODS

Spectral CT parameters were analyzed in 106 patients with lung GGNs. The Ki-67 labeling index (Ki-67 LI) was measured, and patients were divided into low expression and high expression groups according to the number of positive-stained cells (low expression ≤10%; high expression >10%). Spectral CT parameters were compared between low and high expression groups. The correlation between spectral CT parameters and Ki-67 LI was estimated by Spearman correlation analysis. Cases were divided into a preinvasive and minimally invasive adenocarcinoma (MIA) group (atypical adenomatous hyperplasia, adenocarcinoma in situ, and MIA) and invasive adenocarcinoma (IA) group. Spectral CT parameters were compared between the two groups. The diagnostic performance was evaluated using receiver operating characteristic analysis.

RESULTS

There were significant differences in water concentration of lesions (WCL) and monochromatic CT values between the low and high expression groups. CT 40 keV had the highest correlation coefficient with Ki-67 LI. WCL and monochromatic CT values were significantly higher in the IA group than in the pre/MIA group. The value of area under the curve of CT 40 keV was 0.946 (95% confidence interval=0.905-0.988) for differentiating the two groups; the cutoff was -280.66 Hu.

CONCLUSION

Spectral CT is an effective non-invasive method for the prediction of proliferation and invasiveness in lung adenocarcinoma manifesting as GGNs.

Fusion of CT images and clinical variables based on deep learning for predicting invasiveness risk of stage I lung adenocarcinoma

PURPOSE

To develop a novel multimodal data fusion model by incorporating computed tomography (CT) images and clinical variables based on deep learning for predicting the invasiveness risk of stage I lung adenocarcinoma that manifests as ground-glass nodules (GGNs), and compare the diagnostic performance of it with that of radiologists.

METHODS

A total of 1946 patients with solitary and histopathologically confirmed GGNs with maximum diameter less than 3 cm were retrospectively enrolled. The training dataset containing 1704 GGNs was augmented by resampling, scaling, random cropping, etc., to generate new training data. A multimodal data fusion model based on residual learning architecture and two multilayer perceptron with attention mechanism combining CT images with patient general data and serum tumor markers was built. The distance-based confidence scores (DCS) were calculated and compared among multimodal data models with different combinations. An observer study was conducted and the prediction performance of the fusion algorithms was compared with that of the two radiologists by an independent testing dataset with 242 GGNs.

RESULTS

Among the whole GGNs, 606 GGNs are confirmed as invasive adenocarcinoma (IA) and 1340 are non-IA. The proposed novel multimodal data fusion model combining CT images, patient general data and serum tumor markers achieved the highest accuracy (88.5%), Area under a ROC curve (AUC) (0.957), F1 (81.5%), F1_weighted (81.9%) and Matthews correlation coefficient (MCC) (73.2%) for classifying between IA and non-IA GGNs, which was even better than the senior radiologist's performance (accuracy, 86.1%). In addition, the DCSs for multimodal data suggested that CT image had a stronger influence (0.9540) quantitatively than general data (0.6726) or tumor marker (0.6971).

CONCLUSION

This study demonstrated that the feasibility of integrating different types of data including CT images and clinical variables, and the multimodal data fusion model yielded higher performance for distinguishing IA from non-IA GGNs. This article is protected by copyright. All rights reserved.

A triple-classification for the evaluation of lung nodules manifesting as pure ground-glass sign: a CT-based radiomic analysis

OBJECTIVES

To construct a noninvasive radiomics model for evaluating the pathological degree and an individualized treatment strategy for patients with the manifestation of ground glass nodules (GGNs) on CT images.

METHODS

The retrospective primary cohort investigation included patients with GGNs on CT images who underwent resection between June 2015 and June 2020. The intratumoral regions of interest were segmented semiautomatically, and radiomics features were extracted from the intratumoral and peritumoral regions. After feature selection by ANOVA, Max-Relevance and Min-Redundancy (mRMR) and Least Absolute Shrinkage and Selection Operator (Lasso) regression, a random forest (RF) model was generated. Receiver operating characteristic (ROC) analysis was calculated to evaluate each classification. Shapley additive explanations (SHAP) was applied to interpret the radiomics features.

RESULTS

In this study, 241 patients including atypical adenomatous hyperplasia (AAH) or adenocarcinoma in situ (AIS) (n = 72), minimally invasive adenocarcinoma (MIA) (n = 83) and invasive adenocarcinoma (IAC) (n = 86) were selected for radiomics analysis. Three intratumoral radiomics features and one peritumoral feature were finally identified by the triple RF classifier with an average area under the curve (AUC) of 0.960 (0.963 for AAH/AIS, 0.940 for MIA, 0.978 for IAC) in the training set and 0.944 (0.955 for AAH/AIS, 0.952 for MIA, 0.926 for IAC) in the testing set for evaluation of the GGNs.

CONCLUSION

The triple classification based on intra- and peritumoral radiomics features derived from the noncontrast CT images had satisfactory performance and may be used as a noninvasive tool for preoperative evaluation of the pure ground-glass nodules and developing of individualized treatment strategies.

MRI-based radiomics analysis in differentiating solid non-small-cell from small-cell lung carcinoma: a pilot study

AIM

To investigate the ability of a T2-weighted (W) magnetic resonance imaging (MRI)-based radiomics signature to differentiate solid non-small-cell lung carcinoma (NSCLC) from small-cell lung carcinoma (SCLC).

MATERIALS AND METHODS

The present retrospective study enrolled 152 eligible patients (NSCLC = 125, SCLC = 27). All patients underwent MRI using a 3 T scanner and radiomics features were extracted from T2W MRI. The least absolute shrinkage and selection operator (LASSO) logistic regression model was used to identify the optimal radiomics features for the construction of a radiomics model to differentiate solid NSCLC from SCLC. Threefold cross validation repeated 10 times was used for model training and evaluation. The conventional MRI morphology features of the lesions were also evaluated. The performance of the conventional MRI morphological features, and the radiomics signature model and nomogram model (combining radiomics signature with conventional MRI morphological features) was evaluated using receiver operating characteristic (ROC) curve analysis.

RESULTS

Five optimal features were chosen to build a radiomics signature. There was no significant difference in age, gender, and the largest diameter. The radiomics signature and conventional MRI morphological features (only pleural indentation and lymph node enlargement) were independent predictive factors for differentiating solid NSCLC from SCLC. The area under the ROC curves (AUCs) for MRI morphological features, and the radiomics model, and nomogram model was 0.69, 0.85, and 0.90 (ROC), respectively.

CONCLUSIONS

The T2W MRI-based radiomics signature is a potential non-invasive approach for distinguishing solid NSCLC from SCLC.

Radiomics for differentiating minimally invasive adenocarcinoma from precursor lesions in pure ground-glass opacities on chest computed tomography

OBJECTIVE

To explore the correlation between radiomic features and the pathology of pure ground-glass opacities (pGGOs), we established a radiomics model for predicting the pathological subtypes of minimally invasive adenocarcinoma (MIA) and precursor lesions.

METHODS

CT images of 1521 patients with lung adenocarcinoma or precursor lesions appearing as pGGOs on CT in our hospital (The Third Affiliated Hospital of Sun Yat-sen University) from January 2015 to March 2021 were analyzed retrospectively and selected based on inclusion and exclusion criteria. pGGOs were divided into an atypical adenomatous hyperplasia (AAH)/adenocarcinoma in situ (AIS) group and an MIA group. Radiomic features were extracted from the original and preprocessed images of the region of interest. ANOVA and least absolute shrinkage and selection operator feature selection algorithm were used for feature selection. Logistic regression algorithm was used to construct radiomics prediction model. Receiver operating characteristic curves were used to evaluate the classification efficiency.

RESULTS

129 pGGOs were included. 2107 radiomic features were extracted from each region of interest. 18 radiomic features were eventually selected for model construction. The area under the curve of the radiomics model was 0.884 [95% confidence interval (CI), 0.818-0.949] in the training set and 0.872 (95% CI, 0.756-0.988) in the test set, with a sensitivity of 72.73%, specificity of 88.24% and accuracy of 79.47%. The decision curve indicated that the model had a high net benefit rate.

CONCLUSION

The prediction model for pathological subtypes of MIA and precursor lesions in pGGOs demonstrated a high diagnostic accuracy.

ADVANCES IN KNOWLEDGE

We focused on lesions appearing as pGGOs on CT and revealed the differences in radiomic features between MIA and precursor lesions. We constructed a radiomics prediction model and improved the diagnostic accuracy for the pathology of MIA and precursor lesions.

Predictive Efficacy of a Radiomics Random Forest Model for Identifying Pathological Subtypes of Lung Adenocarcinoma Presenting as Ground-Glass Nodules

Purpose

To establish and verify the ability of a radiomics prediction model to distinguish invasive adenocarcinoma (IAC) and minimal invasive adenocarcinoma (MIA) presenting as ground-glass nodules (GGNs).

Methods

We retrospectively analyzed 118 lung GGN images and clinical data from 106 patients in our hospital from March 2016 to April 2019. All pathological classifications of lung GGN were confirmed as IAC or MIA by two pathologists. R language software (version 3.5.1) was used for the statistical analysis of the general clinical data. ITK-SNAP (version 3.6) and A.K. software (Analysis Kit, American GE Company) were used to manually outline the regions of interest of lung GGNs and collect three-dimensional radiomics features. Patients were randomly divided into training and verification groups (ratio, 7:3). Random forest combined with hyperparameter tuning was used for feature selection and prediction modeling. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate model prediction efficacy. The calibration curve was used to evaluate the calibration effect.

Results

There was no significant difference between IAC and MIA in terms of age, gender, smoking history, tumor history, and lung GGN location in both the training and verification groups (P>0.05). For each lung GGN, the collected data included 396 three-dimensional radiomics features in six categories. Based on the training cohort, nine optimal radiomics features in three categories were finally screened out, and a prediction model was established. We found that the training group had a high diagnostic efficacy [accuracy, sensitivity, specificity, and AUC of the training group were 0.89 (95%CI, 0.73 - 0.99), 0.98 (95%CI, 0.78 - 1.00), 0.81 (95%CI, 0.59 - 1.00), and 0.97 (95%CI, 0.92-1.00), respectively; those of the validation group were 0.80 (95%CI, 0.58 - 0.93), 0.82 (95%CI, 0.55 - 1.00), 0.78 (95%CI, 0.57 - 1.00), and 0.92 (95%CI, 0.83 - 1.00), respectively]. The model calibration curve showed good consistency between the predicted and actual probabilities.

Conclusions

The radiomics prediction model established by combining random forest with hyperparameter tuning effectively distinguished IAC from MIA presenting as GGNs and represents a noninvasive, low-cost, rapid, and reproducible preoperative prediction method for clinical application.

Radiomics: a quantitative imaging biomarker in precision oncology

Cancer treatment is heading towards precision medicine driven by genetic and biochemical markers. Various genetic and biochemical markers are utilized to render personalized treatment in cancer. In the last decade, noninvasive imaging biomarkers have also been developed to assist personalized decision support systems in oncology. The imaging biomarkers i.e., radiomics is being researched to develop specific digital phenotype of tumor in cancer. Radiomics is a process to extract high throughput data from medical images by using advanced mathematical and statistical algorithms. The radiomics process involves various steps i.e., image generation, segmentation of region of interest (e.g. a tumor), image preprocessing, radiomic feature extraction, feature analysis and selection and finally prediction model development. Radiomics process explores the heterogeneity, irregularity and size parameters of the tumor to calculate thousands of advanced features. Our study investigates the role of radiomics in precision oncology. Radiomics research has witnessed a rapid growth in the last decade with several studies published that show the potential of radiomics in diagnosis and treatment outcome prediction in oncology. Several radiomics based prediction models have been developed and reported in the literature to predict various prediction endpoints i.e., overall survival, progression-free survival and recurrence in various cancer i.e., brain tumor, head and neck cancer, lung cancer and several other cancer types. Radiomics based digital phenotypes have shown promising results in diagnosis and treatment outcome prediction in oncology. In the coming years, radiomics is going to play a significant role in precision oncology.

Prediction of invasive adenocarcinomas manifesting as pure ground-glass nodules based on radiomic signature of low-dose CT in lung cancer screening

OBJECTIVE

To develop a radiomic model based on low-dose CT (LDCT) to distinguish invasive adenocarcinomas (IAs) from adenocarcinoma in situ/minimally invasive adenocarcinomas (AIS/MIAs) manifesting as pure ground-glass nodules (pGGNs) and compare its performance with conventional quantitative and semantic features of LDCT, radiomic model of standard-dose CT, and intraoperative frozen section (FS).

METHODS

A total of 147 consecutive pathologically confirmed pGGNs were divided into primary cohort (43 IAs and 60 AIS/MIAs) and validation cohort (19 IAs and 25 AIS/MIAs). Logistic regression models were built using conventional quantitative and semantic features, selected radiomic features of LDCT and standard-dose CT, and intraoperative FS diagnosis, respectively. The diagnostic performance was assessed by area under curve (AUC) of receiver operating characteristic curve, sensitivity, and specificity.

RESULTS

The AUCs of quantitative-semantic model, radiomic model of LDCT, radiomic model of standard-dose CT, and FS model were 0.879 (95% CI, 0.801-0.935), 0.929 (95% CI, 0.862-0.971), 0.941 (95% CI, 0.876-0.978), and 0.884 (95% CI, 0.805-0.938) in the primary cohort and 0.897 (95% CI, 0.768-0.968), 0.933 (95% CI, 0.815-0.986), 0.901 (95% CI, 0.773-0.970), and 0.828 (95% CI, 0.685-0.925) in the validation cohort. No significant difference of the AUCs was found among these models in both the primary and validation cohorts (all p > 0.05).

CONCLUSION

The LDCT-based quantitative-semantic score and radiomic signature, with good predictive performance, can be pre-operative and non-invasive biomarkers for assessing the invasive risk of pGGNs in lung cancer screening.

ADVANCES IN KNOWLEDGE

The LDCT-based quantitative-semantic score and radiomic signature, with the equivalent performance to the radiomic model of standard-dose CT, can be pre-operative predictors for assessing the invasiveness of pGGNs in lung cancer screening and reducing excess examination and treatment.

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.

Radiomics in Early Lung Cancer Diagnosis: From Diagnosis to Clinical Decision Support and Education

Lung cancer is the most frequent cause of cancer-related death around the world. With the recent introduction of low-dose lung computed tomography for lung cancer screening, there has been an increasing number of smoking- and non-smoking-related lung cancer cases worldwide that are manifesting with subsolid nodules, especially in Asian populations. However, the pros and cons of lung cancer screening also follow the implementation of lung cancer screening programs. Here, we review the literature related to radiomics for early lung cancer diagnosis. There are four main radiomics applications: the classification of lung nodules as being malignant/benign; determining the degree of invasiveness of the lung adenocarcinoma; histopathologic subtyping; and prognostication in lung cancer prediction models. In conclusion, radiomics offers great potential to improve diagnosis and personalized risk stratification in early lung cancer diagnosis through patient–doctor cooperation and shared decision making.

A computerized tomography-based radiomic model for assessing the invasiveness of lung adenocarcinoma manifesting as ground-glass opacity nodules

Background

Clinically differentiating preinvasive lesions (atypical adenomatous hyperplasia, AAH and adenocarcinoma in situ, AIS) from invasive lesions (minimally invasive adenocarcinomas, MIA and invasive adenocarcinoma, IA) manifesting as ground-glass opacity nodules (GGOs) is difficult due to overlap of morphological features. Hence, the current study was performed to explore the diagnostic efficiency of radiomics in assessing the invasiveness of lung adenocarcinoma manifesting as GGOs.

Methods

A total of 1018 GGOs pathologically confirmed as lung adenocarcinoma were enrolled in this retrospective study and were randomly divided into a training set (n = 712) and validation set (n = 306). The nodules were delineated manually and 2446 intra-nodular and peri-nodular radiomic features were extracted. Univariate analysis and least absolute shrinkage and selection operator (LASSO) were used for feature selection. Clinical and semantic computerized tomography (CT) feature model, radiomic model and a combined nomogram were constructed and compared. Decision curve analysis (DCA) was used to evaluate the clinical value of the established nomogram.

Results

16 radiomic features were selected and used for model construction. The radiomic model exhibited significantly better performance (AUC = 0.828) comparing to the clinical-semantic model (AUC = 0.746). Further analysis revealed that peri-nodular radiomic features were useful in differentiating between preinvasive and invasive lung adenocarcinomas appearing as GGOs with an AUC of 0.808. A nomogram based on lobulation sign and radiomic features showed the best performance (AUC = 0.835), and was found to have potential clinical value in assessing nodule invasiveness.

Conclusions

Radiomic model based on both intra-nodular and peri-nodular features showed good performance in differentiating between preinvasive lung adenocarcinoma lesions and invasive ones appearing as GGOs, and a nomogram based on clinical, semantic and radiomic features could provide clinicians with added information in nodule management and preoperative evaluation.

How AI Can Help in the Diagnostic Dilemma of Pulmonary Nodules

Simple Summary

Pulmonary nodules are considered a sign of bronchogenic carcinoma, detecting them early will reduce their progression and can save lives. Lung cancer is the second most common type of cancer in both men and women. This manuscript discusses the current applications of artificial intelligence (AI) in lung segmentation as well as pulmonary nodule segmentation and classification using computed tomography (CT) scans, published in the last two decades, in addition to the limitations and future prospects in the field of AI.

Abstract

Pulmonary nodules are the precursors of bronchogenic carcinoma, its early detection facilitates early treatment which save a lot of lives. Unfortunately, pulmonary nodule detection and classification are liable to subjective variations with high rate of missing small cancerous lesions which opens the way for implementation of artificial intelligence (AI) and computer aided diagnosis (CAD) systems. The field of deep learning and neural networks is expanding every day with new models designed to overcome diagnostic problems and provide more applicable and simply used models. We aim in this review to briefly discuss the current applications of AI in lung segmentation, pulmonary nodule detection and classification.

A multi-task two-path deep learning system for predicting the invasiveness of craniopharyngioma

BACKGROUND AND OBJECTIVE

Craniopharyngioma is a kind of benign brain tumor in histography. However, it might be clinically aggressive and have severe manifestations, such as increased intracranial pressure, hypothalamic-pituitary dysfunction, and visual impairment. It is considered challenging for radiologists to predict the invasiveness of craniopharyngioma through MRI images. Therefore, developing a non-invasive method that can predict the invasiveness and boundary of CP as a reference before surgery is of clinical value for making more appropriate and individualized treatment decisions and reducing the occurrence of inappropriate surgical plan choices.

METHODS

The MT-Brain system has consisted of two pathways, a sub-path based on 2D CNN for capturing the features from each slice of MRI images, and a 3D sub-network for capturing additional context information between slices. By introducing the two-path architecture, our system can make full use of the fusion of the above 2D and 3D features for classification. Furthermore, position encoding and mask-guided attention also have been introduced to improve the segmentation and diagnosis performance. To verify the performance of the MT-Brain system, we have enrolled 1032 patients with craniopharyngioma (302 invasion and 730 non-invasion patients), segmented the tumors on postcontrast coronal T1WI and randomized them into a training dataset and a testing dataset at a ratio of 8:2.

RESULTS

The MT-Brain system achieved a remarkable performance in diagnosing the invasiveness of craniopharyngioma with the AUC of 83.84%, the accuracy of 77.94%, the sensitivity of 70.97%, and the specificity of 80.99%. In the lesion segmentation task, the predicted boundaries of lesions were similar to those labeled by radiologists with the dice of 66.36%. In addition, some explorations also have been made on the interpretability of deep learning models, illustrating the reliability of the model.

CONCLUSIONS

To the best of our knowledge, this study is the first to develop an integrated deep learning model to predict the invasiveness of craniopharyngioma preoperatively and locate the lesion boundary synchronously on MRI. The excellent performances indicate that the MT-Brain system has great potential in real-world clinical applications.

Progression-Free Survival Prediction in Small Cell Lung Cancer Based on Radiomics Analysis of Contrast-Enhanced CT

Purposes and Objectives

The aim of this study was to predict the progression-free survival (PFS) in patients with small cell lung cancer (SCLC) by radiomic signature from the contrast-enhanced computed tomography (CT).

Methods

A total of 186 cases with pathological confirmed small cell lung cancer were retrospectively assembled. First, 1,218 radiomic features were automatically extracted from tumor region of interests (ROIs) on the lung window and mediastinal window, respectively. Then, the prognostic and robust features were selected by machine learning methods, such as (1) univariate analysis based on a Cox proportional hazard (CPH) model, (2) redundancy removing using the variance inflation factor (VIF), and (3) multivariate importance analysis based on random survival forests (RSF). Finally, PFS predictive models were established based on RSF, and their performances were evaluated using the concordance index (C-index) and the cumulative/dynamic area under the curve (C/D AUC).

Results

In total, 11 radiomic features (6 for mediastinal window and 5 for lung window) were finally selected, and the predictive model constructed from them achieved a C-index of 0.7531 and a mean C/D AUC of 0.8487 on the independent test set, better than the predictions by single clinical features (C-index = 0.6026, mean C/D AUC = 0.6312), and single radiomic features computed in lung window (C-index = 0.6951, mean C/D AUC = 0.7836) or mediastinal window (C-index = 0.7192, mean C/D AUC = 0.7964).

Conclusion

The radiomic features computed from tumor ROIs on both lung window and mediastinal window can predict the PFS for patients with SCLC by a high accuracy, which could be used as a useful tool to support the personalized clinical decision for the diagnosis and patient management of patients with SCLC.

Accurate prediction of epidermal growth factor receptor mutation status in early-stage lung adenocarcinoma, using radiomics and clinical features

OBJECTIVES

To develop a nomogram based on CT radiomics and clinical features to predict the epidermal growth factor receptor (EGFR) mutations in early-stage lung adenocarcinomas.

METHODS

A retrospective analysis of postoperative patients with pathologically confirmed lung adenocarcinoma, which had been tested for EGFR mutations was performed from January 2015 to December 2015. Patients were randomly assigned to training and validation cohorts. A total of 1,078 radiomics features were extracted. least absolute shrinkage and selection operator (LASSO) regression analysis was applied to select clinical and radiomics features, and to establish predictive models. The radiomics score (rad-score) of each patient was calculated. The discrimination of the model was evaluated with area under the curve.

RESULTS

1092 patients (444 men and 648 women; mean age: 59.59±9.6) were enrolled. The radiomics signature consisted of 28 radiomics features and emphysema. The mean validation cohort result of the rad-score for patients with EGFR mutations (0.814±0.988) was significantly higher than those with EGFR wild-type (0.315±1.237; p = 0.001). When combined with clinical features, LASSO regression analysis revealed four radiomics features, emphysema, and three clinical features including sex, age, and histologic subtype as associated with to EGFR mutation status. The nomogram that combined radiomics and clinical features significantly improved the predictive discrimination (AUC: 0.723), which is better than that of the radiomics signature alone (AUC: 0.646).

CONCLUSION

A relationship between selected radiomics features and EGFR mutant lung adenocarcinomas is demonstrated. A nomogram, combining radiomics features and clinical features for EGFR prediction in early-stage lung adenocarcinomas, has shown a moderate discriminatory efficiency and high sensitivity, providing additional information for clinicians.

OUP accepted manuscript

The recent, rapid advances in immuno-oncology have revolutionized cancer treatment and spurred further research into tumor biology. Yet, cancer patients respond variably to immunotherapy despite mounting evidence to support its efficacy. Current methods for predicting immunotherapy response are unreliable, as these tests cannot fully account for tumor heterogeneity and microenvironment. An improved method for predicting response to immunotherapy is needed. Recent studies have proposed radiomics—the process of converting medical images into quantitative data (features) that can be processed using machine learning algorithms to identify complex patterns and trends—for predicting response to immunotherapy. Because patients undergo numerous imaging procedures throughout the course of the disease, there exists a wealth of radiological imaging data available for training radiomics models. And because radiomic features reflect cancer biology, such as tumor heterogeneity and microenvironment, these models have enormous potential to predict immunotherapy response more accurately than current methods. Models trained on preexisting biomarkers and/or clinical outcomes have demonstrated potential to improve patient stratification and treatment outcomes. In this review, we discuss current applications of radiomics in oncology, followed by a discussion on recent studies that use radiomics to predict immunotherapy response and toxicity.

A wavelet features derived radiomics nomogram for prediction of malignant and benign early-stage lung nodules

This study was to develop a radiomics nomogram mainly using wavelet features for identifying malignant and benign early-stage lung nodules for high-risk screening. A total of 116 patients with early-stage solitary pulmonary nodules (SPNs) (≤ 3 cm) were divided into a training set (N = 70) and a validation set (N = 46). Radiomics features were extracted from plain LDCT images of each patient. A radiomics signature was then constructed with the LASSO with the training set. Combined with independent risk factors, a radiomics nomogram was built with a multivariate logistic regression model. This radiomics signature, consisting of one original and nine wavelet features, achieved favorable predictive efficacy than Mayo Clinic Model. The radiomics nomogram with radiomics signature and age also showed good calibration and discrimination in the training set (AUC 0.9406; 95% CI 0.8831-0.9982) and the validation set (AUC 0.8454; 95% CI 0.7196-0.9712). The decision curve indicated the clinical usefulness of our nomogram. The presented radiomics nomogram shows favorable predictive accuracy for identifying malignant and benign lung nodules in early-stage patients and is much better than the Mayo Clinic Model.

CT-based radiomics for differentiating invasive adenocarcinomas from indolent lung adenocarcinomas appearing as ground-glass nodules: Asystematic review

PURPOSE

To provide an overview of the available studies investigating the use of computer tomography (CT) radiomics features for differentiating invasive adenocarcinomas (IAC) from indolent lung adenocarcinomas presenting as ground-glass nodules (GGNs), to identify the bias of the studies and to propose directions for future research.

METHOD

PubMed, Embase, Web of Science Core Collection were searched for relevant studies. The studies differentiating IAC from indolent lung adenocarcinomas appearing as GGNs based on CT radiomics features were included. Basic information, patient information, CT-scanner information, technique information and performance information were extracted for each included study. The quality of each study was assessed using the Radiomic Quality Score (RQS) and the Prediction model Risk of Bias Assessment Tool (PROBAST).

RESULTS

Twenty-eight studies were included with patients ranging from 34 to 794. All of them were retrospective. Patients in three studies were from multiple centers. Most studies segmented regions of interest manually. Pyradiomics and AK software were the most frequently used for features extraction. The number of radiomics features extracted varied from 7 to 10329. Logistic regression was the most frequently chosen model. Entropy was identified as radiomics signature in seven studies. The AUC of included studies ranged from 0.77 to 0.98 in 15 validation sets. The percentage RQS ranged from 3% to 50%. According to PROBAST, the overall risk of bias (ROB) was high in 89.3% (25/28) of included studies, unclear in 7.1% (2/28) of included studies, and low in 3.6% (1/28) of included studies. All studies were low concern regarding the applicability of primary studies to the review question.

CONCLUSION

CT radiomics-based model is promising and encouraging in differentiating IAC from indolent lung adenocarcinomas, though they require methodological rigor. Well-designed studies are necessary to demonstrate their validity and standardization of methods and results can prompt their use in daily clinical practice.

Predicting the histological invasiveness of pulmonary adenocarcinoma manifesting as persistent pure ground-glass nodules by ultra-high-resolution CT target scanning in the lateral or oblique body position

Background

Ultra-high-resolution computed tomography (U-HRCT) has improved image quality for displaying the detailed characteristics of disease states and lung anatomy. The purpose of this study was to retrospectively examine whether U-HRCT target scanning in the lateral or oblique body position (protocol G scan) could predict histological invasiveness of pulmonary adenocarcinoma manifesting as pure ground-glass nodules (pGGNs).

Methods

From January 2015 to December 2016, 260 patients with 306 pathologically confirmed pGGNs who underwent preoperative protocol G scans were retrospectively reviewed and analyzed. The U-HRCT findings of preinvasive lesions [atypical adenomatous hyperplasias (AAH) and adenocarcinomas in situ (AIS)] and invasive pulmonary adenocarcinomas [minimally invasive adenocarcinomas (MIA) and invasive adenocarcinomas (IAC)] were manually compared and analyzed using orthogonal multiplanar reformation (MPR) images. The logistic regression model was established to determine variables that could predict the invasiveness of pGGNs. Receiver operating characteristic (ROC) curve analysis was performed to evaluate their diagnostic performance.

Results

There were 213 preinvasive lesions (59 AAHs and 154 AISs) and 93 invasive pulmonary adenocarcinomas (53 MIAs and 40 IACs). Compared with the preinvasive lesions, invasive adenocarcinomas exhibited a larger diameter (13.5 vs. 9.3 mm, P=0.000), higher mean attenuation (-571 vs. -613 HU, P=0.002), higher representative attenuation (-475 vs. -547 HU, P=0.000), lower relative attenuation (-339 vs. -292 HU, P=0.000) and greater frequencies of heterogeneity (P=0.001), air bronchogram (P=0.000), bubble lucency (P=0.000), and pleural indentation (P=0.000). Multiple logistic analysis revealed that larger diameter [odds ratio (OR), 1.328; 95% CI: 1.208-1.461; P=0.000] and higher representative attenuation (OR, 1.005; 95% CI: 1.003-1.007; P=0.000) were significant predictive factors of invasive pulmonary adenocarcinomas from preinvasive lesions. The optimal cut-off value of the maximum diameter for invasive pulmonary adenocarcinomas was larger than 10 mm (sensitivity, 66.7%; specificity, 72.8%).

Conclusions

The imaging features based on protocol G scanning can effectively help predict the histological invasiveness of pGGNs. The maximum diameter and representative attenuation are important parameters for predicting invasiveness.

Evaluation of the Radiomics Method for the Prediction of Atypical Adenomatous Hyperplasia in Patients With Subcentimeter Pulmonary Ground-Glass Nodules

Objectives

We aimed to develop a prediction model to distinguish atypical adenomatous hyperplasia (AAH) from early lung adenocarcinomas in patients with subcentimeter pulmonary ground-glass nodules (GGNs), which may help avoid aggressive surgical resection for patients with AAH.

Methods

Surgically confirmed cases of AAH and lung adenocarcinomas manifesting as GGNs of less than 1 cm were retrospectively collected. A prediction model based on radiomics and clinical features identified from a training set of cases was built to differentiate AAH from lung adenocarcinomas and tested on a validation set.

Results

Four hundred and eighty-five eligible cases were included and randomly assigned to the training (n = 339) or the validation sets (n = 146). The developed radiomics prediction model showed good discrimination performance to distinguish AAH from adenocarcinomas in both the training and the validation sets, with, respectively, 84.1% and 82.2% of accuracy, and AUCs of 0.899 (95% CI: 0.867–0.931) and 0.881 (95% CI: 0.827–0.936).

Conclusion

The prediction model based on radiomics and clinical features can help differentiate AAH from adenocarcinomas manifesting as subcentimeter GGNs and may prevent aggressive resection for AAH patients, while reserving this treatment for adenocarcinomas.

Developing of risk models for small solid and subsolid pulmonary nodules based on clinical and quantitative radiomics features

Background

Accurate evaluation of pulmonary nodule malignancy is important for lung cancer management. This current study aimed to develop risk models for small solid and subsolid pulmonary nodules based on clinical and quantitative radiomics features.

Methods

This study enrolled 5–20 mm pulmonary nodules detected on thoracic high-resolution computed tomography (HRCT), which were all confirmed pathologically. There were 548 solid nodules (242 malignant vs. 306 benign) and 623 subsolid nodules (SSNs 519 malignant vs. 104 benign). Relevant clinical characteristics were recorded. The CT image prior to the initial treatment was chosen for manual segmentation of the targeted nodule using the ITK-SNAP software. Subsequently, the marked image was processed to quantitatively extract 1218 radiomics features using PyRadiomics. We performed five-fold cross-validation to select potential predictors from clinical and radiomics features using the LASSO method and to evaluate the performance of the established models. In total, four types of models were tried: random forest, XGBOOST, SVM, and logistic models. The established models were compared with the Mayo model.

Results

Lung cancer risk models were developed among four nodule groups: all nodules (410 benign vs. 761 malignant; 1:1.86), nodules ≤10 mm (185 benign vs. 224 malignant; 1:1.21), solid nodules (306 benign vs. 242 malignant; 1.26:1), and SSNs (104 benign vs. 104 malignant; 1:1 matched). Significant clinical and radiomics predictors were selected for each group. The accuracy, area under the ROC curve, sensitivity, and specificity of the best model on validation dataset was 0.86, 0.91, 0.93, 0.73 for all nodules (XGBOOST), 0.82, 0.90, 0.86, 0.76 for nodules ≤10 mm (XGBOOST), 0.80, 0.89, 0.78, 0.82 for solid nodules (XGBOOST) and 0.70, 0.73, 0.73, 0.67 for SSNs (Random Forest). Except for the SSN models, the established clinical-radiomics models were superior to the Mayo model.

Conclusions

Predictive models based on both clinical and radiomics features can be used to assess the malignancy of small solid and subsolid pulmonary nodules, even for nodules that are 10 mm or smaller.

Deep Learning-Based Stage-Wise Risk Stratification for Early Lung Adenocarcinoma in CT Images: A Multi-Center Study

Simple Summary

Prediction of the malignancy and invasiveness of ground glass nodules (GGNs) from computed tomography images is a crucial task for radiologists in risk stratification of early-stage lung adenocarcinoma. In order to solve this challenge, a two-stage deep neural network (DNN) was developed based on the images collected from four centers. A multi-reader multi-case observer study was conducted to evaluate the model capability. The performance of our model was comparable or even more accurate than that of senior radiologists, with average area under the curve values of 0.76 and 0.95 for two tasks, respectively. Findings suggest (1) a positive trend between the diagnostic performance and radiologist’s experience, (2) DNN yielded equivalent or even higher performance in comparison with senior radiologists, and (3) low image resolution reduced the model performance in predicting the risks of GGNs.

Abstract

This study aims to develop a deep neural network (DNN)-based two-stage risk stratification model for early lung adenocarcinomas in CT images, and investigate the performance compared with practicing radiologists. A total of 2393 GGNs were retrospectively collected from 2105 patients in four centers. All the pathologic results of GGNs were obtained from surgically resected specimens. A two-stage deep neural network was developed based on the 3D residual network and atrous convolution module to diagnose benign and malignant GGNs (Task1) and classify between invasive adenocarcinoma (IA) and non-IA for these malignant GGNs (Task2). A multi-reader multi-case observer study with six board-certified radiologists’ (average experience 11 years, range 2–28 years) participation was conducted to evaluate the model capability. DNN yielded area under the receiver operating characteristic curve (AUC) values of 0.76 ± 0.03 (95% confidence interval (CI): (0.69, 0.82)) and 0.96 ± 0.02 (95% CI: (0.92, 0.98)) for Task1 and Task2, which were equivalent to or higher than radiologists in the senior group with average AUC values of 0.76 and 0.95, respectively (p > 0.05). With the CT image slice thickness increasing from 1.15 mm ± 0.36 to 1.73 mm ± 0.64, DNN performance decreased 0.08 and 0.22 for the two tasks. The results demonstrated (1) a positive trend between the diagnostic performance and radiologist’s experience, (2) the DNN yielded equivalent or even higher performance in comparison with senior radiologists, and (3) low image resolution decreased model performance in predicting the risks of GGNs. Once tested prospectively in clinical practice, the DNN could have the potential to assist doctors in precision diagnosis and treatment of early lung adenocarcinoma.

CT-Based Radiomics Analysis for Preoperative Diagnosis of Pancreatic Mucinous Cystic Neoplasm and Atypical Serous Cystadenomas

Objectives

To investigate the value of CT-based radiomics analysis in preoperatively discriminating pancreatic mucinous cystic neoplasms (MCN) and atypical serous cystadenomas (ASCN).

Methods

A total of 103 MCN and 113 ASCN patients who underwent surgery were retrospectively enrolled. A total of 764 radiomics features were extracted from preoperative CT images. The optimal features were selected by Mann-Whitney U test and minimum redundancy and maximum relevance method. The radiomics score (Rad-score) was then built using random forest algorithm. Radiological/clinical features were also assessed for each patient. Multivariable logistic regression was used to construct a radiological model. The performance of the Rad-score and the radiological model was evaluated using 10-fold cross-validation for area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy.

Results

Ten screened optimal features were identified and the Rad-score was then built based on them. The radiological model was built based on four radiological/clinical factors. In the 10-fold cross-validation, the Rad-score was proved to be robust and reliable (average AUC: 0.784, sensitivity: 0.847, specificity: 0.745, PPV: 0.767, NPV: 0.849, accuracy: 0.793). The radiological model performed slightly less well in classification (average AUC: average AUC: 0.734 sensitivity: 0.748, specificity: 0.705, PPV: 0.732, NPV: 0.798, accuracy: 0.728.

Conclusions

The CT-based radiomics analysis provided promising performance for preoperatively discriminating MCN from ASCN and showed good potential in improving diagnostic power, which may serve as a novel tool for guiding clinical decision-making for these patients.