Radiomics in Lung Metastases: A Systematic Review

Clinical application of optical and electromagnetic navigation system in CT-guided radiofrequency ablation of lung metastases

PURPOSE

To evaluate the clinical value of CT-guided radiofrequency ablation (RFA) in the diagnosis and treatment of pulmonary metastases under optical and electromagnetic navigation.

METHODS

Data on CT-guided radiofrequency ablation treatment of 93 metastatic lung lesions in 70 patients were retrospectively analyzed. There were 46 males and 24 females with a median age of 60.0 years (16-85 years). All lesions were ≤3cm in diameter. 57 patients were treated with 17 G radiofrequency ablation needle puncture directly ablated the lesion without biopsy, and 13 patients were treated with 16 G coaxial needle biopsy followed by radiofrequency ablation. There were 25 cases in the optical navigation group, 25 in the electromagnetic navigation group, and 20 in the non-navigation group. The navigation group was performed by primary interventionalists with less than 5 years of experience, and the non-navigation group was performed by interventionalists with more than 5 years of experience.

RESULT

All operations were successfully performed. There was no statistically significant difference in the overall distribution of follow-up results among the optical, electromagnetic, and no navigation groups. Complete ablation was achieved in 84 lesions (90.3%). 7 lesions showed incomplete ablation and were completely inactivated after repeat ablation. 2 lesions progressed locally, and one of them still had an increasing trend after repeat ablation. No serious complications occurred after the operation.

CONCLUSIONS

Treatment with optical and electromagnetic navigation systems by less experienced operators has similar outcomes to traditional treatments without navigational systems performed by more experienced operators.

CT-based radiomics prediction of complete response after stereotactic body radiation therapy for patients with lung metastases

PURPOSE

Stereotactic body radiotherapy (SBRT) is a key treatment modality for lung cancer patients. This study aims to develop a machine learning-based prediction model of complete response for lung oligometastatic cancer patients undergoing SBRT.

MATERIALS AND METHODS

CT images of 80 pulmonary oligometastases from 56 patients treated with SBRT were analyzed. The gross tumor volumes (GTV) were contoured on CT images. Patients that achieved complete response (CR) at 4 months were defined as responders. For each GTV, 107 radiomic features were extracted using the Pyradiomics software. The concordance correlation coefficients (CCC) between the region of interest (ROI)-based radiomics features obtained by the two segmentations were calculated. Pairwise feature interdependencies were evaluated using the Spearman rank correlation coefficient. The association of clinical variables and radiomics features with CR was evaluated with univariate logistic regression. Two supervised machine learning models, the logistic regression (LR) and the classification and regression tree analysis (CART), were trained to predict CR. The models were cross-validated using a five-fold cross-validation. The performance of models was assessed by receiver operating characteristic curve (ROC) and class-specific accuracy, precision, recall, and F1-measure evaluation metrics.

RESULTS

Complete response was associated with four radiomics features, namely the surface to volume ratio (SVR; p = 0.003), the skewness (Skew; p = 0.027), the correlation (Corr; p = 0.024), and the grey normalized level uniformity (GNLU; p = 0.015). No significant relationship between clinical parameters and CR was found. In the validation set, the developed LR and CART machine learning models had an accuracy, precision, and recall of 0.644 and 0.750, 0.644 and 0.651, and 0.635 and 0.754, respectively. The area under the curve for CR prediction was 0.707 and 0.753 for the LR and CART models, respectively.

CONCLUSION

This analysis demonstrates that radiomics features obtained from pretreatment CT could predict complete response of lung oligometastases following SBRT.

Transfer-Learning Deep Radiomics and Hand-Crafted Radiomics for Classifying Lymph Nodes from Contrast-Enhanced Computed Tomography in Lung Cancer

OBJECTIVES

Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of this study was to predict the PET result from traditional contrast-enhanced computed tomography (CT) and to test different feature extraction strategies.

METHODS

In this study, 100 lung cancer patients underwent a contrast-enhanced ¹⁸F-fluorodeoxyglucose (FDG) PET/CT scan between August 2012 and December 2019. We trained machine learning models to predict FDG uptake in the subsequent PET scan. Model inputs were composed of (i) traditional "hand-crafted" radiomics features from the segmented lymph nodes, (ii) deep features derived from a pretrained EfficientNet-CNN, and (iii) a hybrid approach combining (i) and (ii).

RESULTS

In total, 2734 lymph nodes [555 (20.3%) PET-positive] from 100 patients [49% female; mean age 65, SD: 14] with lung cancer (60% adenocarcinoma, 21% plate epithelial carcinoma, 8% small-cell lung cancer) were included in this study. The area under the receiver operating characteristic curve (AUC) ranged from 0.79 to 0.87, and the scaled Brier score (SBS) ranged from 16 to 36%. The random forest model (iii) yielded the best results [AUC 0.871 (0.865-0.878), SBS 35.8 (34.2-37.2)] and had significantly higher model performance than both approaches alone (AUC: p < 0.001, z = 8.8 and z = 22.4; SBS: p < 0.001, z = 11.4 and z = 26.6, against (i) and (ii), respectively).

CONCLUSION

Both traditional radiomics features and transfer-learning deep radiomics features provide relevant and complementary information for non-invasive N-staging in lung cancer.

Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors

BACKGROUND

preoperative risk assessment of gastrointestinal stromal tumors (GISTS) is required for optimal and personalized treatment planning. Radiomics features are promising tools to predict risk assessment. The purpose of this study is to develop and validate an artificial intelligence classification algorithm, based on CT features, to define GIST's prognosis as determined by the Miettinen classification.

METHODS

patients with histological diagnosis of GIST and CT studies were retrospectively enrolled. Eight morphologic and 30 texture CT features were extracted from each tumor and combined to obtain three models (morphologic, texture and combined). Data were analyzed using a machine learning classification (WEKA). For each classification process, sensitivity, specificity, accuracy and area under the curve were evaluated. Inter- and intra-reader agreement were also calculated.

RESULTS

52 patients were evaluated. In the validation population, highest performances were obtained by the combined model (SE 85.7%, SP 90.9%, ACC 88.8%, and AUC 0.954) followed by the morphologic (SE 66.6%, SP 81.8%, ACC 76.4%, and AUC 0.742) and texture (SE 50%, SP 72.7%, ACC 64.7%, and AUC 0.613) models. Reproducibility was high of all manual evaluations.

CONCLUSIONS

the AI-based radiomics model using a CT feature demonstrates good predictive performance for preoperative risk stratification of GISTs.