Comparison of prediction models with radiological semantic features and radiomics in lung cancer diagnosis of the pulmonary nodules: a case-control study

MRI-Based Clinical-Imaging-Radiomics Nomogram Model for Discriminating Between Benign and Malignant Solid Pulmonary Nodules or Masses

RATIONALE AND OBJECTIVES

Pulmonary nodules or masses are highly prevalent worldwide, and differential diagnosis of benign and malignant lesions remains difficult. Magnetic resonance imaging (MRI) can provide functional and metabolic information of pulmonary lesions. This study aimed to establish a nomogram model based on clinical features, imaging features, and multi-sequence MRI radiomics to identify benign and malignant solid pulmonary nodules or masses.

MATERIALS AND METHODS

A total of 145 eligible patients (76 male; mean age, 58.4 years ± 13.7 [SD]) with solid pulmonary nodules or masses were retrospectively analyzed. The patients were randomized into two groups (training cohort, n = 102; validation cohort, n = 43). The nomogram was used for predicting malignant pulmonary lesions. The diagnostic performance of different models was evaluated by receiver operating characteristic (ROC) curve analysis.

RESULTS

Of these patients, 95 patients were diagnosed with benign lesions and 50 with malignant lesions. Multivariate analysis showed that age, DWI value, LSR value, and ADC value were independent predictors of malignant lesions. Among the radiomics models, the multi-sequence MRI-based model (T1WI+T2WI+ADC) achieved the best diagnosis performance with AUCs of 0.858 (95%CI: 0.775, 0.919) and 0.774 (95%CI: 0.621, 0.887) for the training and validation cohorts, respectively. Combining multi-sequence radiomics, clinical and imaging features, the predictive efficacy of the clinical-imaging-radiomics model was significantly better than the clinical model, imaging model and radiomics model (all P < 0.05).

CONCLUSION

The MRI-based clinical-imaging-radiomics model is helpful to differentiate benign and malignant solid pulmonary nodules or masses, and may be useful for precision medicine of pulmonary diseases.

Prediction of high Ki-67 proliferation index of gastrointestinal stromal tumors based on CT at non-contrast-enhanced and different contrast-enhanced phases

OBJECTIVES

To evaluate and analyze radiomics models based on non-contrast-enhanced computed tomography (CT) and different phases of contrast-enhanced CT in predicting Ki-67 proliferation index (PI) among patients with pathologically confirmed gastrointestinal stromal tumors (GISTs).

METHODS

A total of 383 patients with pathologically proven GIST were divided into a training set (n = 218, vendor 1) and 2 validation sets (n = 96, vendor 2; n = 69, vendors 3-5). Radiomics features extracted from the most recent non-contrast-enhanced and three contrast-enhanced CT scan prior to pathological examination. Random forest models were trained for each phase to predict tumors with high Ki-67 proliferation index (Ki-67>10%) and were evaluated using the area under the receiver operating characteristic curve (AUC) and other metrics on the validation sets.

RESULTS

Out of 107 radiomics features extracted from each phase of CT images, four were selected for analysis. The model trained using the non-contrast-enhanced phase achieved an AUC of 0.792 in the training set and 0.822 and 0.711 in the two validation sets, similar to models trained on different contrast-enhanced phases (p > 0.05). Several relevant features, including NGTDM Busyness and tumor size, remained predictive in non-contrast-enhanced and different contrast-enhanced images.

CONCLUSION

The results of this study indicate that a radiomics model based on non-contrast-enhanced CT matches that of models based on different phases of contrast-enhanced CT in predicting the Ki-67 PI of GIST. GIST may exhibit similar radiological patterns irrespective of the use of contrast agent, and such radiomics features may help quantify these patterns to predict Ki-67 PI of GISTs.

CLINICAL RELEVANCE STATEMENT

GIST may exhibit similar radiomics patterns irrespective of contrast agent; thus, radiomics models based on non-contrast-enhanced CT could be an alternative for risk stratification in GIST patients with contraindication to contrast agent.

KEY POINTS

• Performance of radiomics models in predicting Ki-67 proliferation based on different CT phases is evaluated. • Non-contrast-enhanced CT-based radiomics models performed similarly to contrast-enhanced CT in risk stratification in GIST patients. • NGTDM Busyness remains stable to contrast agents in GISTs in radiomics models.

CT-Based Radiomics Predicts the Malignancy of Pulmonary Nodules: A Systematic Review and Meta-Analysis

RATIONALE AND OBJECTIVES

More pulmonary nodules (PNs) have been detected with the wide application of computed tomography (CT) in lung cancer screening. Radiomics is a noninvasive approach to predict the malignancy of PNs. We aimed to systematically evaluate the methodological quality of the eligible studies regarding CT-based radiomics models in predicting the malignancy of PNs and evaluate the model performance of the available studies.

MATERIALS AND METHODS

PubMed, Embase, and Web of Science were searched to retrieve relevant studies. The methodological quality of the included studies was assessed using the Radiomics Quality Score (RQS) and Prediction model Risk of Bias Assessment Tool. A meta-analysis was conducted to evaluate the performance of CT-based radiomics model. Meta-regression and subgroup analyses were employed to investigate the source of heterogeneity.

RESULTS

In total, 49 studies were eligible for qualitative analysis and 27 studies were included in quantitative synthesis. The median RQS of 49 studies was 13 (range -2 to 20). The overall risk of bias was found to be high, and the overall applicability was of low concern in all included studies. The pooled sensitivity, specificity, and diagnostic odds ratio were 0.86 95% confidence interval (CI): 0.79-0.91, 0.84 95% CI: 0.78-0.88, and 31.55 95% CI: 21.31-46.70, respectively. The overall area under the curve was 0.91 95% CI: 0.89-0.94. Meta-regression showed the type of PNs on heterogeneity. CT-based radiomics models performed better in studies including only solid PNs.

CONCLUSION

CT-based radiomics models exhibited excellent diagnostic performance in predicting the malignancy of PNs. Prospective, large sample size, and well-devised studies are desired to verify the prediction capabilities of CT-based radiomics model.

Predicting micropapillary or solid pattern of lung adenocarcinoma with CT-based radiomics, conventional radiographic and clinical features

BACKGROUND

To build prediction models with radiomics features, clinical/conventional radiographic signs and combined scores for the discrimination of micropapillary or solid subtypes (high-risk subtypes) of lung adenocarcinoma.

METHODS

This retrospective study enrolled 351 patients with and without high-risk subtypes. Least Absolute Shrinkage and Selection Operator (LASSO) regression with cross-validation was performed to determine the optimal features of radiomics model. Missing clinical data were imputed by Multiple Imputation with Chain Equations (MICE). Clinical model with radiographic signs was built and scores of both models were integrated to establish combined model. Receiver operating characteristics (ROC) curves, area under ROC curves and decision curve analysis (DCA) were plotted to evaluate the model performance and clinical application.

RESULTS

Stratified splitting allocated 246 patients into training set. MICE for missing values obtained complete and unbiased data for the following analysis. Ninety radiomic features and four clinical/conventional radiographic signs were used to predict the high-risk subtypes. The radiomic model, clinical model and combined model achieved AUCs of 0.863 (95%CI: 0.817-0.909), 0.771 (95%CI: 0.713-0.713) and 0.872 (95%CI: 0.829-0.916) in the training set, and 0.849 (95%CI: 0.774-0.924), 0.778 (95%CI: 0.687-0.868) and 0.853 (95%CI: 0.782-0.925) in the test set. Decision curve showed that the radiomic and combined models were more clinically useful when the threshold reached 37.5%.

CONCLUSIONS

Radiomics features could facilitate the prediction of subtypes of lung adenocarcinoma. A simple combination of radiomics and clinical scores generated a robust model with high performance for the discrimination of micropapillary or solid subtype of lung adenocarcinoma.

A CT-based radiomics integrated model for discriminating pulmonary cryptococcosis granuloma from lung adenocarcinoma-a diagnostic test

Background

Chest computed tomography (CT) is a critical tool in the diagnosis of pulmonary cryptococcosis as approximately 30% of normal immunity individuals may not exhibit any significant symptoms or laboratory findings. Pulmonary cryptococcosis granuloma and lung adenocarcinoma can appear similar on noncontrast chest CT. This study evaluates the use of an integrated model that was developed based on radiomic features combined with demographic and radiological features to differentiate pulmonary cryptococcosis nodules from lung adenocarcinomas.

Methods

Preoperative chest CT images for 215 patients with solid pulmonary nodules with histopathologically confirmed lung adenocarcinoma and cryptococcosis infection were collected from two clinical centers (108 cases in the training set and 107 cases in the test set divided by the different hospitals). Radiomics models were constructed based on nodular lesion volume (LV), 5-mm extended lesion volume (ELV), and perilesion volume (PLV). A demoradiological model was constructed using logistic regression based on demographic information (age, sex) and 12 radiological features (location, number, shape and specific imaging signs). Both models were used to build an integrated model, the performance of which was assessed using the test set. A junior and a senior radiologist evaluated the nodules. Receiver operating characteristic (ROC) curve analysis was conducted, and areas under the curve (AUCs), sensitivity (SEN), and specificity (SPE) of the models were calculated and compared.

Results

Among the radiomics models, AUCs of the LV, ELV, and PLV were 0.558, 0.757, and 0.470, respectively. Age, lesion number, and lobular sign were identified as independent discriminative features providing an AUC of 0.77 in the demoradiological model (SEN 0.815, SPE 0.642). The integrated model achieved the highest AUC of 0.801 (SEN 0.759, SPE 0.755), which was significantly higher than that obtained by a junior radiologist (AUC =0.689, P=0.024) but showed no significant difference from that of the senior radiologist (AUC =0.784, P=0.388).

Conclusions

An integrated model with radiomics and demoradiological features improves discrimination of cryptococcosis granulomas from solid adenocarcinomas on noncontrast CT. This model may be an effective strategy for machine complementation to discrimination by radiologists, and whole-lung automated recognition methods might dominate in the future.

Performance of radiomics models derived from different CT reconstruction parameters for lung cancer risk prediction

BACKGROUND

This study analysed the performance of radiomics features extracted from computed tomography (CT) images with different reconstruction parameters in differentiating malignant and benign pulmonary nodules.

METHODS

We evaluated routine chest CT images acquired from 148 participants with pulmonary nodules, which were pathologically diagnosed during surgery in West China Hospital, including a 5 mm unenhanced lung window, a 5 mm unenhanced mediastinal window, a 5 mm contrast-enhanced mediastinal window and a 1 mm unenhanced lung window. The pulmonary nodules were segmented, and 1409 radiomics features were extracted for each window. Then, we created 15 cohorts consisting of single windows or multiple windows. Univariate correlation analysis and principal component analysis were performed to select the features, and logistic regression analysis was performed to establish models for each cohort. The area under the curve (AUC) was applied to compare model performance.

RESULTS

There were 75 benign and 73 malignant pulmonary nodules, with mean diameters of 18.63 and 19.86 mm, respectively. For the single-window setting, the AUCs of the radiomics model from the 5 mm unenhanced lung window, 5 mm unenhanced mediastinal window, 5 mm contrast-enhanced mediastinal window and 1 mm unenhanced lung window were 0.771, 0.808, 0.750, and 0.771 in the training set and 0.711, 0.709, 0.684, and 0.674 in the test set, respectively. Regarding the multiple-window setting, the radiomics model based on all four windows showed an AUC of 0.825 in the training set and 0.743 in the test set. Statistically, the 15 models demonstrated comparable performances (P > 0.05).

CONCLUSION

A single chest CT window was acceptable in predicting the malignancy of pulmonary nodules, and additional windows did not statistically improve the performance of the radiomics models. In addition, slice thickness and contrast enhancement did not affect the diagnostic performance.

Radiomics nomogram integrating intratumoural and peritumoural features to predict lymph node metastasis and prognosis in clinical stage IA non-small cell lung cancer: a two-centre study

AIM

To investigate the value of a radiomics nomogram integrating intratumoural and peritumoural features in predicting lymph node metastasis and overall survival (OS) in patients with clinical stage IA non-small-cell lung cancer (NSCLC).

MATERIALS AND METHODS

This study retrospectively enrolled 199 patients (training cohort: 71 patients from Affiliated Tumour Hospital of Nantong University; internal validation cohort: 46 patients from Affiliated Tumour Hospital of Nantong University; external validation cohort: 82 patients from the public database). CT radiomics models were constructed based on four volumes of interest: gross tumour volume (GTV), gross and 3 mm peritumoural volume (GPTV₃), gross and 6 mm peritumoural volume (GPTV₆), and gross and 9 mm peritumoural volume (GPTV₉). The optimal radiomics signature was further combined with independent clinical predictors to develop a nomogram. Univariable and multivariable Cox regression analysis were applied to determine the relationship between factors and OS.

RESULTS

GPTV₆ radiomics yielded better performance than GTV, GPTV₃, and, GPTV₉ radiomics in the training (area under the curve [AUC], 0.81), internal validation (AUC, 0.79), and external validation cohorts (AUC, 0.71), respectively. The nomogram integrating GPTV₆ radiomics and spiculation improved predictive ability, with AUCs of 0.85, 0.80, and 0.74 in three cohorts, respectively. Pathological lymph node metastasis, nomogram-predicted lymph node metastasis, and pleural indentation were independent risk predictors of OS (p<0.05).

CONCLUSIONS

The nomogram integrating GPTV₆ radiomics features and independent clinical predictors performed well in predicting lymph node metastasis and prognosis in patients with clinical stage IA NSCLC.

3D SAACNet with GBM for the classification of benign and malignant lung nodules

In view of the low diagnostic accuracy of the current classification methods of benign and malignant pulmonary nodules, this paper proposes a 3D segmentation attention network integrating asymmetric convolution (SAACNet) classification model combined with a gradient boosting machine (GBM). This can make full use of the spatial information of pulmonary nodules. First, the asymmetric convolution (AC) designed in SAACNet can not only strengthen feature extraction but also improve the network's robustness to object flip and rotation detection and improve network performance. Second, the segmentation attention network integrating AC (SAAC) block can effectively extract more fine-grained multiscale spatial information while adaptively recalibrating multidimensional channel attention weights. The SAACNet also uses a dual-path connection for feature reuse, where the model makes full use of features. In addition, this article makes the loss function pay more attention to difficult and misclassified samples by adding adjustment factors. Third, the GBM is used to splice the nodule size, originally cropped nodule pixels, and the depth features learned by SAACNet to improve the prediction accuracy of the overall model. A comprehensive ablation experiment is carried out on the public dataset LUNA16 and compared with other lung nodule classification models. The classification accuracy (ACC) is 95.18%, and the area under the curve (AUC) is 0.977. The results show that this method effectively improves the classification performance of pulmonary nodules. The proposed method has advantages in the classification of benign and malignant pulmonary nodules, and it can effectively assist radiologists in pulmonary nodule classification.

Feature selection methods and predictive models in CT lung cancer radiomics

Radiomics is a technique that extracts quantitative features from medical images using data-characterization algorithms. Radiomic features can be used to identify tissue characteristics and radiologic phenotyping that is not observable by clinicians. A typical workflow for a radiomics study includes cohort selection, radiomic feature extraction, feature and predictive model selection, and model training and validation. While there has been increasing attention given to radiomic feature extraction, standardization, and reproducibility, currently, there is a lack of rigorous evaluation of feature selection methods and predictive models. Herein, we review the published radiomics investigations in CT lung cancer and provide an overview of the commonly used radiomic feature selection methods and predictive models. We also compare limitations of various methods in clinical applications and present sources of uncertainty associated with those methods. This review is expected to help raise awareness of the impact of radiomic feature and model selection methods on the integrity of radiomics studies.

A novel nomogram model combining CT texture features and urine energy metabolism to differentiate single benign from malignant pulmonary nodule

Objective

To investigate a novel diagnostic model for benign and malignant pulmonary nodule diagnosis based on radiomic and clinical features, including urine energy metabolism index.

Methods

A total of 107 pulmonary nodules were prospectively recruited and pathologically confirmed as malignant in 86 cases and benign in 21 cases. A chest CT scan and urine energy metabolism test were performed in all cases. A nomogram model was established in combination with radiomic and clinical features, including urine energy metabolism levels. The nomogram model was compared with the radiomic model and the clinical feature model alone to test its diagnostic validity, and receiver operating characteristic (ROC) curves were plotted to assess diagnostic validity.

Results

The nomogram was established using a logistic regression algorithm to combine radiomic features and clinical characteristics including urine energy metabolism results. The predictive performance of the nomogram was evaluated using the area under the ROC and calibration curve, which showed the best performance, area under the curve (AUC) = 0.982, 95% CI = 0.940-1.000, compared to clinical and radiomic models in the testing cohort. The clinical benefit of the model was assessed using the decision curve analysis (DCA) and using the nomogram for benign and malignant pulmonary nodules, and preoperative prediction of benign and malignant pulmonary nodules using nomograms showed better clinical benefit.

Conclusion

This study shows that a coupled model combining CT imaging features and clinical features (including urine energy metabolism) in combination with the nomogram model has higher diagnostic performance than the radiomic and clinical models alone, suggesting that the combination of both methods is more advantageous in identifying benign and malignant pulmonary nodules.

Radiomics based on enhanced CT for differentiating between pulmonary tuberculosis and pulmonary adenocarcinoma presenting as solid nodules or masses

PURPOSE

To investigate the incremental value of enhanced CT-based radiomics in discriminating between pulmonary tuberculosis (PTB) and pulmonary adenocarcinoma (PAC) presenting as solid nodules or masses and to develop an optimal radiomics model.

METHODS

A total of 128 lesions (from 123 patients) from three hospitals were retrospectively analyzed and were randomly divided into training and test datasets at a ratio of 7:3. Independent predictors in subjective image features were used to develop the subjective image model (SIM). The plain CT-based and enhanced CT-based radiomics features were screened by the correlation coefficient method, univariate analysis, and the least absolute shrinkage and selection operator, then used to build the plain CT radiomics model (PRM) and enhanced CT radiomics model (ERM), respectively. Finally, the combined model (CM) combining PRM and ERM was established. In addition, the performance of three radiologists and one respiratory physician was evaluated. The areas under the receiver operating characteristic curve (AUCs) were used to assess the performance of each model.

RESULTS

The differential diagnostic capability of the ERM (training: AUC = 0.933; test: AUC = 0.881) was better than that of the PRM (training: AUC = 0.861; test: AUC = 0.756) and the SIM (training: AUC = 0.760; test: AUC = 0.611). The CM was optimal (training: AUC = 0.948; test: AUC = 0.917) and outperformed the respiratory physician and most radiologists.

CONCLUSIONS

The ERM was more helpful than the PRM for identifying PTB and PAC that present as solid nodules or masses, and the CM was the best.

Form Factors as Potential Imaging Biomarkers to Differentiate Benign vs. Malignant Lung Lesions on CT Scans

Indeterminate lung nodules detected on CT scans are common findings in clinical practice. Their correct assessment is critical, as early diagnosis of malignancy is crucial to maximise the treatment outcome. In this work, we evaluated the role of form factors as imaging biomarkers to differentiate benign vs. malignant lung lesions on CT scans. We tested a total of three conventional imaging features, six form factors, and two shape features for significant differences between benign and malignant lung lesions on CT scans. The study population consisted of 192 lung nodules from two independent datasets, containing 109 (38 benign, 71 malignant) and 83 (42 benign, 41 malignant) lung lesions, respectively. The standard of reference was either histological evaluation or stability on radiological followup. The statistical significance was determined via the Mann-Whitney U nonparametric test, and the ability of the form factors to discriminate a benign vs. a malignant lesion was assessed through multivariate prediction models based on Support Vector Machines. The univariate analysis returned four form factors (Angelidakis compactness and flatness, Kong flatness, and maximum projection sphericity) that were significantly different between the benign and malignant group in both datasets. In particular, we found that the benign lesions were on average flatter than the malignant ones; conversely, the malignant ones were on average more compact (isotropic) than the benign ones. The multivariate prediction models showed that adding form factors to conventional imaging features improved the prediction accuracy by up to 14.5 pp. We conclude that form factors evaluated on lung nodules on CT scans can improve the differential diagnosis between benign and malignant lesions.

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.

Artificial intelligence and infrared thermography as auxiliary tools in the diagnosis of temporomandibular disorder

OBJECTIVE

To assess three machine learning (ML) attribute extraction methods: radiomic, semantic and radiomic-semantic association on temporomandibular disorder (TMD) detection using infrared thermography (IT); and to determine which ML classifier, KNN, SVM and MLP, is the most efficient for this purpose.

METHODS AND MATERIALS

78 patients were selected by applying the Fonseca questionnaire and RDC/TMD to categorize control patients (37) and TMD patients (41). IT lateral projections of each patient were acquired. The masseter and temporal muscles were selected as regions of interest (ROI) for attribute extraction. Three methods of extracting attributes were assessed: radiomic, semantic and radiomic-semantic association. For radiomic attribute extraction, 20 texture attributes were assessed using co-occurrence matrix in a standardized angulation of 0°. The semantic features were the ROI mean temperature and pain intensity data. For radiomic-semantic association, a single dataset composed of 28 features was assessed. The classification algorithms assessed were KNN, SVM and MLP. Hopkins's statistic, Shapiro-Wilk, ANOVA and Tukey tests were used to assess data. The significance level was set at 5% (p < 0.05).

RESULTS

Training and testing accuracy values differed statistically for the radiomic-semantic association (p = 0.003). MLP differed from the other classifiers for the radiomic-semantic association (p = 0.004). Accuracy, precision and sensitivity values of semantic and radiomic-semantic association differed statistically from radiomic features (p = 0.008, p = 0.016 and p = 0.013).

CONCLUSION

Semantic and radiomic-semantic-associated ML feature extraction methods and MLP classifier should be chosen for TMD detection using IT images and pain scale data. IT associated with ML presents promising results for TMD detection.

A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images

OBJECTIVES

Both radiomics and deep learning methods have shown great promise in predicting lesion malignancy in various image-based oncology studies. However, it is still unclear which method to choose for a specific clinical problem given the access to the same amount of training data. In this study, we try to compare the performance of a series of carefully selected conventional radiomics methods, end-to-end deep learning models, and deep-feature based radiomics pipelines for pulmonary nodule malignancy prediction on an open database that consists of 1297 manually delineated lung nodules.

METHODS

Conventional radiomics analysis was conducted by extracting standard handcrafted features from target nodule images. Several end-to-end deep classifier networks, including VGG, ResNet, DenseNet, and EfficientNet were employed to identify lung nodule malignancy as well. In addition to the baseline implementations, we also investigated the importance of feature selection and class balancing, as well as separating the features learned in the nodule target region and the background/context region. By pooling the radiomics and deep features together in a hybrid feature set, we investigated the compatibility of these two sets with respect to malignancy prediction.

RESULTS

The best baseline conventional radiomics model, deep learning model, and deep-feature based radiomics model achieved AUROC values (mean ± standard deviations) of 0.792 ± 0.025, 0.801 ± 0.018, and 0.817 ± 0.032, respectively through 5-fold cross-validation analyses. However, after trying out several optimization techniques, such as feature selection and data balancing, as well as adding context features, the corresponding best radiomics, end-to-end deep learning, and deep-feature based models achieved AUROC values of 0.921 ± 0.010, 0.824 ± 0.021, and 0.936 ± 0.011, respectively. We achieved the best prediction accuracy from the hybrid feature set (AUROC: 0.938 ± 0.010).

CONCLUSION

The end-to-end deep-learning model outperforms conventional radiomics out of the box without much fine-tuning. On the other hand, fine-tuning the models lead to significant improvements in the prediction performance where the conventional and deep-feature based radiomics models achieved comparable results. The hybrid radiomics method seems to be the most promising model for lung nodule malignancy prediction in this comparative study.

Role of 18F-FDG PET/CT Radiomics Features in the Differential Diagnosis of Solitary Pulmonary Nodules: Diagnostic Accuracy and Comparison between Two Different PET/CT Scanners

The aim of this retrospective study was to investigate the ability of 18 fluorine-fluorodeoxyglucose positron emission tomography/CT (¹⁸F-FDG-PET/CT) metrics and radiomics features (RFs) in predicting the final diagnosis of solitary pulmonary nodules (SPN). We retrospectively recruited 202 patients who underwent a ¹⁸F-FDG-PET/CT before any treatment in two PET scanners. After volumetric segmentation of each lung nodule, 8 PET metrics and 42 RFs were extracted. All the features were tested for significant differences between the two PET scanners. The performances of all features in predicting the nature of SPN were analyzed by testing three classes of final logistic regression predictive models: two were built/trained through exploiting the separate data from the two scanners, and the other joined the data together. One hundred and twenty-seven patients had a final diagnosis of malignancy, while 64 were of a benign nature. Comparing the two PET scanners, we found that all metabolic features and most of RFs were significantly different, despite the cross correlation being quite similar. For scanner 1, a combination between grey level co-occurrence matrix (GLCM), histogram, and grey-level zone length matrix (GLZLM) related features presented the best performances to predict the diagnosis; for scanner 2, it was GLCM and histogram-related features and metabolic tumour volume (MTV); and for scanner 1 + 2, it was histogram features, standardized uptake value (SUV) metrics, and MTV. RFs had a significant role in predicting the diagnosis of SPN, but their accuracies were directly related to the scanner.

Machine Learning-Based CT Radiomics Analysis for Prognostic Prediction in Metastatic Non-Small Cell Lung Cancer Patients With EGFR-T790M Mutation Receiving Third-Generation EGFR-TKI Osimertinib Treatment

Background and Purpose

As a third-generation EGFR tyrosine kinase inhibitor (TKI), osimertinib is approved for treating advanced non-small cell lung cancer (NSCLC) patients with EGFR-T790M mutation after progression on first- or second-generation EGFR-TKIs such as gefitinib, erlotinib and afatinib. We aim at exploring the feasibility and effectiveness of using radiomic features from chest CT scan to predict the prognosis of metastatic non-small cell lung cancer (NSCLC) patients with EGFR-T790M mutation receiving second-line osimertinib therapy.

Methods

Contrast-enhanced and unenhanced chest CT images before osimertinib treatment were collected from 201 and 273 metastatic NSCLC patients with EGFR-T790M mutation, respectively. Radiomic features were extracted from the volume of interest. LASSO regression was used to preliminarily evaluate the prognostic values of different radiomic features. We then performed machine learning-based analyses including random forest (RF), support vector machine (SVM), stepwise regression (SR) and LASSO regression with 5-fold cross-validation (CV) to establish the optimal radiomic model for predicting the progression-free survival (PFS) of osimertinib treatment. Finally, a combined clinical-radiomic model was developed and validated using the concordance index (C-index), decision-curve analysis (DCA) and calibration curve analysis.

Results

Disease progression occurred in 174/273 (63.7%) cases. CT morphological features had no ability in predicting patients’ prognosis in osimertinib treatment. Univariate COX regression followed by LASSO regression analyses identified 23 and 6 radiomic features from the contrast-enhanced and unenhanced CT with prognostic value, respectively. The 23 contrast-enhanced radiomic features were further used to construct radiomic models using different machine learning strategies. Radiomic model built by SR exhibited superior predictive accuracy than RF, SVR or LASSO model (mean C-index of the 5-fold CV: 0.660 vs. 0.560 vs. 0.598 vs. 0.590). Adding the SR radiomic model to the clinical model could remarkably strengthen the C-index of the latter from 0.672 to 0.755. DCA and calibration curve analyses also demonstrated good performance of the combined clinical-radiomic model.

Conclusions

Radiomic features extracted from the contrast-enhanced chest CT could be used to evaluate metastatic NSCLC patients’ prognosis in osimertinib treatment. Prognostic models combing both radiomic features and clinical factors had a great performance in predicting patients’ outcomes.

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.

Performance of Lung Nodule Management Algorithms for Lung-RADS Category 4 Lesions

PURPOSE

To test the performance of the American College of Chest Physicians (ACCP) and British Thoracic Society (BTS) algorithms to stratify high-risk nodules identified at lung cancer screening.

METHOD AND MATERIALS

Patients with Lung-RADS category 4 nodules identified on lung cancer screening computed tomography (CT) between March 2014 and August 2018 were identified, and a subset of 150 were randomly selected. Nodule characteristics and, if available, fluorodeoxyglucose (FDG) uptake on positron emission tomography (PET)-CT scan were recorded. Radiologists blinded to final diagnosis and downstream testing performed five-point visual assessment score for probability of nodule malignancy; their accuracies are averaged below. Probabilities of malignancy according to Brock and Herder models were calculated. ACCP and BTS algorithms were applied to the nodules.

RESULTS

Final diagnosis of malignancy was made in 65/150 (43%) of patients. The sensitivity, specificity and accuracy for nodule malignancy were: radiologist visual score (92%, 85%, 88%); BTS (76%, 91%, 85%); ACCP (63%, 89%, 78%); and Brock calculator (77%, 71%, 73%). The sensitivity, specificity, and accuracy for nodule malignancy in patients with FDG PET-CT scan (n = 78) were: FDG uptake (91%, 64%, 83%); Herder probability (91%, 68%, 83%); radiologist visual score (93%, 69%, 86%); BTS (84%, 64%, 78%); Brock probability (82%, 50%, 72%); and ACCP (68%, 59%, 65%).

CONCLUSION

Thoracic radiologist visual analysis yielded the greatest accuracy for nodule triage in the entire cohort. BTS performed better than ACCP guidelines and both performed better than the Brock model alone.

Comparative evaluation of conventional and deep learning methods for semi-automated segmentation of pulmonary nodules on CT

Background

Accurate segmentation of pulmonary nodules on computed tomography (CT) scans plays a crucial role in the evaluation and management of patients with suspicion of lung cancer (LC). When performed manually, not only the process requires highly skilled operators, but is also tiresome and time-consuming. To assist the physician in this task several automated and semi-automated methods have been proposed in the literature. In recent years, in particular, the appearance of deep learning has brought about major advances in the field.

Methods

Twenty-four (12 conventional and 12 based on deep learning) semi-automated-'one-click'-methods for segmenting pulmonary nodules on CT were evaluated in this study. The experiments were carried out on two datasets: a proprietary one (383 images from a cohort of 111 patients) and a public one (259 images from a cohort of 100). All the patients had a positive transcript for suspect pulmonary nodules.

Results

The methods based on deep learning clearly outperformed the conventional ones. The best performance [Sørensen-Dice coefficient (DSC)] in the two datasets was, respectively, 0.853 and 0.763 for the deep learning methods, and 0.761 and 0.704 for the traditional ones.

Conclusions

Deep learning is a viable approach for semi-automated segmentation of pulmonary nodules on CT scans.

Radiomics Is Effective for Distinguishing Coronavirus Disease 2019 Pneumonia From Influenza Virus Pneumonia

Objectives: To develop and validate a radiomics model for distinguishing coronavirus disease 2019 (COVID-19) pneumonia from influenza virus pneumonia.

Materials and Methods: A radiomics model was developed on the basis of 56 patients with COVID-19 pneumonia and 90 patients with influenza virus pneumonia in this retrospective study. Radiomics features were extracted from CT images. The radiomics features were reduced by the Max-Relevance and Min-Redundancy algorithm and the least absolute shrinkage and selection operator method. The radiomics model was built using the multivariate backward stepwise logistic regression. A nomogram of the radiomics model was established, and the decision curve showed the clinical usefulness of the radiomics nomogram.

Results: The radiomics features, consisting of nine selected features, were significantly different between COVID-19 pneumonia and influenza virus pneumonia in both training and validation data sets. The receiver operator characteristic curve of the radiomics model showed good discrimination in the training sample [area under the receiver operating characteristic curve (AUC), 0.909; 95% confidence interval (CI), 0.859–0.958] and in the validation sample (AUC, 0.911; 95% CI, 0.753–1.000). The nomogram was established and had good calibration. Decision curve analysis showed that the radiomics nomogram was clinically useful.

Conclusions: The radiomics model has good performance for distinguishing COVID-19 pneumonia from influenza virus pneumonia and may aid in the diagnosis of COVID-19 pneumonia.

The Role of Radiomics in Lung Cancer: From Screening to Treatment and Follow-Up

Purpose

Lung cancer represents the first cause of cancer-related death in the world. Radiomics studies arise rapidly in this late decade. The aim of this review is to identify important recent publications to be synthesized into a comprehensive review of the current status of radiomics in lung cancer at each step of the patients’ care.

Methods

A literature review was conducted using PubMed/Medline for search of relevant peer-reviewed publications from January 2012 to June 2020

Results

We identified several studies at each point of patient’s care: detection and classification of lung nodules (n=16), determination of histology and genomic (n=10) and finally treatment outcomes predictions (=23). We reported the methodology of those studies and their results and discuss the limitations and the progress to be made for clinical routine applications.

Conclusion

Promising perspectives arise from machine learning applications and radiomics based models in lung cancers, yet further data are necessary for their implementation in daily care. Multicentric collaboration and attention to quality and reproductivity of radiomics studies should be further consider.

Combining liquid biopsy and radiomics for personalized treatment of lung cancer patients. State of the art and new perspectives

Lung cancer has become a paradigm for precision medicine in oncology, and liquid biopsy (LB) together with radiomics may have a great potential in this scenario. They are both minimally invasive, easy to perform, and can be repeated during patient's follow-up. Also, increasing evidence suggest that LB and radiomics may provide an efficient way to screen and diagnose tumors at an early stage, including the monitoring of any change in the tumor molecular profile. This could allow treatment optimization, improvement of patients' quality of life, and healthcare-related costs reduction. Latest reports on lung cancer patients suggest a combination of these two strategies, along with cutting-edge data analysis, to decode valuable information regarding tumor type, aggressiveness, progression, and response to treatment. The approach seems more compatible with clinical practice than the current standard, and provides new diagnostic companions being able to suggest the best treatment strategy compared to conventional methods. To implement radiomics and liquid biopsy directly into clinical practice, an artificial intelligence (AI)-based system could help to link patients' clinical data together with tumor molecular profiles and imaging characteristics. AI could also solve problems and limitations related to LB and radiomics methodologies. Further work is needed, including new health policies and the access to large amounts of high-quality and well-organized data, allowing a complementary and synergistic combination of LB and imaging, to provide an attractive choice e in the personalized treatment of lung cancer.

Radiomics model of dual-time 2-[18F]FDG PET/CT imaging to distinguish between pancreatic ductal adenocarcinoma and autoimmune pancreatitis

OBJECTIVES

Pancreatic ductal adenocarcinoma (PDAC) and autoimmune pancreatitis (AIP) are diseases with a highly analogous visual presentation that are difficult to distinguish by imaging. The purpose of this research was to create a radiomics-based prediction model using dual-time PET/CT imaging for the noninvasive classification of PDAC and AIP lesions.

METHODS

This retrospective study was performed on 112 patients (48 patients with AIP and 64 patients with PDAC). All cases were confirmed by imaging and clinical follow-up, and/or pathology. A total of 502 radiomics features were extracted from the dual-time PET/CT images to develop a radiomics decision model. An additional 12 maximum intensity projection (MIP) features were also calculated to further improve the radiomics model. The optimal radiomics feature set was selected by support vector machine recursive feature elimination (SVM-RFE), and the final classifier was built using a linear SVM. The performance of the proposed dual-time model was evaluated using nested cross-validation for accuracy, sensitivity, specificity, and area under the curve (AUC).

RESULTS

The final prediction model was developed from a combination of the SVM-RFE and linear SVM with the required quantitative features. The multimodal and multidimensional features performed well for classification (average AUC: 0.9668, accuracy: 89.91%, sensitivity: 85.31%, specificity: 96.04%).

CONCLUSIONS

The radiomics model based on 2-[¹⁸F]fluoro-2-deoxy-D-glucose (2-[¹⁸F]FDG) PET/CT dual-time images provided promising performance for discriminating between patients with benign AIP and malignant PDAC lesions, which shows its potential for use as a diagnostic tool for clinical decision-making.

KEY POINTS

• The clinical symptoms and imaging visual presentations of PDAC and AIP are highly similar, and accurate differentiation of PDAC and AIP lesions is difficult. • Radiomics features provided a potential noninvasive method for differentiation of AIP from PDAC. • The diagnostic performance of the proposed radiomics model indicates its potential to assist doctors in making treatment decisions.

Radiomics in immuno-oncology

With the ongoing advances in imaging techniques, increasing volumes of anatomical and functional data are being generated as part of the routine clinical workflow. This surge of available imaging data coincides with increasing research in quantitative imaging, particularly in the domain of imaging features. An important and novel approach is radiomics, where high-dimensional image properties are extracted from routine medical images. The fundamental principle of radiomics is the hypothesis that biomedical images contain predictive information, not discernible to the human eye, that can be mined through quantitative image analysis. In this review, a general outline of radiomics and artificial intelligence (AI) will be provided, along with prominent use cases in immunotherapy (e.g. response and adverse event prediction) and targeted therapy (i.e. radiogenomics). While the increased use and development of radiomics and AI in immuno-oncology is highly promising, the technology is still in its early stages, and different challenges still need to be overcome. Nevertheless, novel AI algorithms are being constructed with an ever-increasing scope of applications.

Utility of CT texture analysis to differentiate olfactory neuroblastoma from sinonasal squamous cell carcinoma

The purpose of this study was to examine differences in texture features between olfactory neuroblastoma (ONB) and sinonasal squamous cell carcinoma (SCC) on contrast-enhanced CT (CECT) images, and to evaluate the predictive accuracy of texture analysis compared to radiologists’ interpretations. Forty-three patients with pathologically-diagnosed primary nasal and paranasal tumor (17 ONB and 26 SCC) were included. We extracted 42 texture features from tumor regions on CECT images obtained before treatment. In univariate analysis, each texture features were compared, with adjustment for multiple comparisons. In multivariate analysis, the elastic net was used to select useful texture features and to construct a texture-based prediction model with leave-one-out cross-validation. The prediction accuracy was compared with two radiologists’ visual interpretations. In univariate analysis, significant differences were observed for 28 of 42 texture features between ONB and SCC, with areas under the receiver operating characteristic curve between 0.68 and 0.91 (median: 0.80). In multivariate analysis, the elastic net model selected 18 texture features that contributed to differentiation. It tended to show slightly higher predictive accuracy than radiologists’ interpretations (86% and 74%, respectively; P = 0.096). In conclusion, several texture features contributed to differentiation of ONB from SCC, and the texture-based prediction model was considered useful.

Cancer Biomarkers and Big Data: A Planetary Science Approach

Cancer biomarker research has become a data-intensive discipline requiring innovative approaches for data analysis that can combine traditional and data-driven methods. Significant leveraging can be done transferring methodologies and capabilities across scientific disciplines, such as planetary science and astronomy, each of which are grappling with and developing similar solutions for the analysis of massive scientific data.

Value of Shape and Texture Features from 18F-FDG PET/CT to Discriminate between Benign and Malignant Solitary Pulmonary Nodules: An Experimental Evaluation

In this paper, we investigate the role of shape and texture features from 18F-FDG PET/CT to discriminate between benign and malignant solitary pulmonary nodules. To this end, we retrospectively evaluated cross-sectional data from 111 patients (64 males, 47 females, age = 67.5 ± 11.0) all with histologically confirmed benign (n=39) or malignant (n=72) solitary pulmonary nodules. Eighteen three-dimensional imaging features, including conventional, texture, and shape features from PET and CT were tested for significant differences (Wilcoxon-Mann-Withney) between the benign and malignant groups. Prediction models based on different feature sets and three classification strategies (Classification Tree, k-Nearest Neighbours, and Naïve Bayes) were also evaluated to assess the potential benefit of shape and texture features compared with conventional imaging features alone. Eight features from CT and 15 from PET were significantly different between the benign and malignant groups. Adding shape and texture features increased the performance of both the CT-based and PET-based prediction models with overall accuracy gain being 3.4-11.2 pp and 2.2-10.2 pp, respectively. In conclusion, we found that shape and texture features from 18F-FDG PET/CT can lead to a better discrimination between benign and malignant lung nodules by increasing the accuracy of the prediction models by an appreciable margin.

Radiomics: an overview in lung cancer management-a narrative review

Radiomics is a novel approach for optimizing the analysis massive data from medical images to provide auxiliary guidance in clinical issues. Quantitative feature extraction is one of the critical steps of radiomics. The association between radiomics features and the clinicopathological information of diseases can be identified by several statistics methods. For instance, although significant progress has been made in the field of lung cancer, too many questions remain, especially for the individualized decisions. Radiomics offers a new tool to encode the characteristics of lung cancer which is the leading cause of cancer-related deaths worldwide. Here, we reviewed the workflow and clinical utility of radiomics in lung cancer management, including pulmonary nodules detection, classification, histopathology and genetics evaluation, clinical staging, therapy response, and prognosis prediction. Most of these studies showed positive results, indicating the potential value of radiomics in clinical practice. The implementation of radiomics is both feasible and invaluable, and has aided clinicians in ascertaining the nature of a disease with greater precision. However, it should be noted that radiomics in its current state cannot completely replace the work of therapists or tissue examination. The potential future trends of this modality were also remarked. More efforts are needed to overcome the limitations identified above in order to facilitate the widespread application of radiomics in the reasonably near future.

A diagnostic model for coronavirus disease 2019 (COVID-19) based on radiological semantic and clinical features: a multi-center study

OBJECTIVES

Rapid and accurate diagnosis of coronavirus disease 2019 (COVID-19) is critical during the epidemic. We aim to identify differences in CT imaging and clinical manifestations between pneumonia patients with and without COVID-19, and to develop and validate a diagnostic model for COVID-19 based on radiological semantic and clinical features alone.

METHODS

A consecutive cohort of 70 COVID-19 and 66 non-COVID-19 pneumonia patients were retrospectively recruited from five institutions. Patients were divided into primary (n = 98) and validation (n = 38) cohorts. The chi-square test, Student's t test, and Kruskal-Wallis H test were performed, comparing 1745 lesions and 67 features in the two groups. Three models were constructed using radiological semantic and clinical features through multivariate logistic regression. Diagnostic efficacies of developed models were quantified by receiver operating characteristic curve. Clinical usage was evaluated by decision curve analysis and nomogram.

RESULTS

Eighteen radiological semantic features and seventeen clinical features were identified to be significantly different. Besides ground-glass opacities (p = 0.032) and consolidation (p = 0.001) in the lung periphery, the lesion size (1-3 cm) is also significant for the diagnosis of COVID-19 (p = 0.027). Lung score presents no significant difference (p = 0.417). Three diagnostic models achieved an area under the curve value as high as 0.986 (95% CI 0.966~1.000). The clinical and radiological semantic models provided a better diagnostic performance and more considerable net benefits.

CONCLUSIONS

Based on CT imaging and clinical manifestations alone, the pneumonia patients with and without COVID-19 can be distinguished. A model composed of radiological semantic and clinical features has an excellent performance for the diagnosis of COVID-19.

KEY POINTS

• Based on CT imaging and clinical manifestations alone, the pneumonia patients with and without COVID-19 can be distinguished. • A diagnostic model for COVID-19 was developed and validated using radiological semantic and clinical features, which had an area under the curve value of 0.986 (95% CI 0.966~1.000) and 0.936 (95% CI 0.866~1.000) in the primary and validation cohorts, respectively.

Implementation of eHealth and AI integrated diagnostics with multidisciplinary digitized data: are we ready from an international perspective?

Digitization of medicine requires systematic handling of the increasing amount of health data to improve medical diagnosis. In this context, the integration of the versatile diagnostic information, e.g., from anamnesis, imaging, histopathology, and clinical chemistry, and its comprehensive analysis by artificial intelligence (AI)–based tools is expected to improve diagnostic precision and the therapeutic conduct. However, the complex medical environment poses a major obstacle to the translation of integrated diagnostics into clinical research and routine. There is a high need to address aspects like data privacy, data integration, interoperability standards, appropriate IT infrastructure, and education of staff. Besides this, a plethora of technical, political, and ethical challenges exists. This is complicated by the high diversity of approaches across Europe. Thus, we here provide insights into current international activities on the way to digital comprehensive diagnostics. This includes a technical view on challenges and solutions for comprehensive diagnostics in terms of data integration and analysis. Current data communications standards and common IT solutions that are in place in hospitals are reported. Furthermore, the international hospital digitalization scoring and the European funding situation were analyzed. In addition, the regional activities in radiomics and the related publication trends are discussed. Our findings show that prerequisites for comprehensive diagnostics have not yet been sufficiently established throughout Europe. The manifold activities are characterized by a heterogeneous digitization progress and they are driven by national efforts. This emphasizes the importance of clear governance, concerted investments, and cooperation at various levels in the health systems.

Key Points

• Europe is characterized by heterogeneity in its digitization progress with predominantly national efforts. Infrastructural prerequisites for comprehensive diagnostics are not given and not sufficiently funded throughout Europe, which is particularly true for data integration.

• The clinical establishment of comprehensive diagnostics demands for a clear governance, significant investments, and cooperation at various levels in the healthcare systems.

• While comprehensive diagnostics is on its way, concerted efforts should be taken in Europe to get consensus concerning interoperability and standards, security, and privacy as well as ethical and legal concerns.

Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial

OBJECTIVE

To enhance the positive predictive value (PPV) of chest digital tomosynthesis (DTS) in the lung cancer detection with the analysis of radiomics features.

METHOD

The investigation was carried out within the SOS clinical trial (NCT03645018) for lung cancer screening with DTS. Lung nodules were identified by visual analysis and then classified using the diameter and the radiological aspect of the nodule following lung-RADS. Haralick texture features were extracted from the segmented nodules. Both semantic variables and radiomics features were used to build a predictive model using logistic regression on a subset of variables selected with backward feature selection and using two machine learning: a Random Forest and a neural network with the whole subset of variables. The methods were applied to a train set and validated on a test set where diagnostic accuracy metrics were calculated.

RESULTS

Binary visual analysis had a good sensitivity (0.95) but a low PPV (0.14). Lung-RADS classification increased the PPV (0.19) but with an unacceptable low sensitivity (0.65). Logistic regression showed a mildly increased PPV (0.29) but a lower sensitivity (0.20). Random Forest demonstrated a moderate PPV (0.40) but with a low sensitivity (0.30). Neural network demonstrated to be the best predictor with a high PPV (0.95) and a high sensitivity (0.90).

CONCLUSIONS

The neural network demonstrated the best PPV. The use of visual analysis along with neural network could help radiologists to reduce the number of false positive in DTS.

KEY POINTS

• We investigated several approaches to enhance the positive predictive value of chest digital tomosynthesis in the lung cancer detection. • Neural network demonstrated to be the best predictor with a nearly perfect PPV. • Neural network could help radiologists to reduce the number of false positive in DTS.

PET/CT Radiomics in Lung Cancer: An Overview

Quantitative extraction of imaging features from medical scans (‘radiomics’) has attracted a lot of research attention in the last few years. The literature has consistently emphasized the potential use of radiomics for computer-assisted diagnosis, as well as for predicting survival and response to treatment. Radiomics is appealing in that it enables full-field analysis of the lesion, provides nearly real-time results, and is non-invasive. Still, a lot of studies suffer from a series of drawbacks such as lack of standardization and repeatability. Such limitations, along with the unmet demand for large enough image datasets for training the algorithms, are major hurdles that still limit the application of radiomics on a large scale. In this paper, we review the current developments, potential applications, limitations, and perspectives of PET/CT radiomics with specific focus on the management of patients with lung cancer.