Comparison of a radiomic biomarker with volumetric analysis for decoding tumour phenotypes of lung adenocarcinoma with different disease-specific survival

Machine learning-based CT texture analysis in the differentiation of testicular masses

Purpose

To evaluate the ability of texture features for distinguishing between benign and malignant testicular masses, and furthermore, for identifying primary testicular lymphoma in malignant tumors and identifying seminoma in testicular germ cell tumors, respectively.

Methods

We retrospectively collected 77 patients with an abdominal and pelvic enhanced computed tomography (CT) examination and a histopathologically confirmed testicular mass from a single center. The ROI of each mass was split into two parts by the largest cross-sectional slice and deemed to be two samples. After all processing steps, three-dimensional texture features were extracted from unenhanced and contrast-enhanced CT images. Excellent reproducibility of texture features was defined as intra-class correlation coefficient ≥0.8 (ICC ≥0.8). All the groups were balanced via the synthetic minority over-sampling technique (SMOTE) method. Dimension reduction was based on pearson correlation coefficient (PCC). Before model building, minimum-redundancy maximum-relevance (mRMR) selection and recursive feature elimination (RFE) were used for further feature selection. At last, three ML classifiers with the highest cross validation with 5-fold were selected: autoencoder (AE), support vector machine(SVM), linear discriminant analysis (LAD). Logistics regression (LR) and LR-LASSO were also constructed to compare with the ML classifiers.

Results

985 texture features with ICC ≥0.8 were extracted for further feature selection process. With the highest AUC of 0.946 (P <0.01), logistics regression was proved to be the best model for the identification of benign or malignant testicular masses. Besides, LR also had the best performance in identifying primary testicular lymphoma in malignant testicular tumors and in identifying seminoma in testicular germ cell tumors, with the AUC of 0.982 (P <0.01) and 0.928 (P <0.01), respectively.

Conclusion

Until now, this is the first study that applied CT texture analysis (CTTA) to assess the heterogeneity of testicular tumors. LR model based on CTTA might be a promising non-invasive tool for the diagnosis and differentiation of testicular masses. The accurate diagnosis of testicular masses would assist urologists in correct preoperative and perioperative decision making.

Radiomics model based on intravoxel incoherent motion and diffusion kurtosis imaging for predicting histopathological grade and Ki-67 expression level of soft tissue sarcomas

BACKGROUND

Accurate identification of the histopathological grade and the Ki-67 expression level is important in clinical cases of soft tissue sarcomas (STSs).

PURPOSE

To explore the feasibility of a radiomics model based on intravoxel incoherent motion (IVIM) magnetic resonance imaging (MRI) and diffusion kurtosis imaging (DKI) MRI parameter maps in predicting the histopathological grade and Ki-67 expression level of STSs.

MATERIAL AND METHODS

In total, 42 patients diagnosed with STSs between May 2018 and January 2020 were selected. The MADC software in Functool of GE ADW 4.7 workstation was used to obtain standard apparent diffusion coefficient (ADC), D, D*, f, mean diffusivity, and mean kurtosis (MK). The histopathological grade and Ki-67 expression level of STSs were identified. The radiomics features of IVIM and DKI parameter maps were used as the dataset. The area under the receiver operating characteristic curve (AUC) and F1-score were calculated.

RESULTS

D-SVM achieved the best diagnostic performance for histopathological grade. The AUC in the validation cohort was 0.88 (sensitivity: 0.75 [low level] and 0.83 [high level]; specificity: 0.83 [low level] and 0.75 [high level]; F1-score: 0.75 [low level] and 0.83 [high level]). MK-SVM achieved the best diagnostic performance for Ki-67 expression level. The AUC in the validation cohort was 0.83 (sensitivity: 0.83 [low level] and 0.50 [high level; specificity: 0.50 [low level] and 0.83 [high level]; F1-score: 0.77 [low level] and 0.57 [high level]).

CONCLUSION

The proposed radiomics classifier could predict the pathological grade of STSs and the Ki-67 expression level in STSs.

Computed Tomography-Based Deep Learning Nomogram Can Accurately Predict Lymph Node Metastasis in Gastric Cancer

BACKGROUND

Computed tomography is the most commonly used imaging modality for preoperative assessment of lymph node status, but the reported accuracy is unsatisfactory.

AIMS

To evaluate and verify the predictive performance of computed tomography deep learning on the presurgical evaluation of lymph node metastasis in patients with gastric cancer.

METHODS

347 patients were retrospectively selected (training cohort: 242, test cohort: 105). The enhanced computed tomography arterial phase images of gastric cancer were used for lesion segmentation, radiomics and deep learning feature extraction. Three methods were used for feature selection. Support vector machine (SVM) or random forest (RF) was used to build models. The classification performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC). We also established a nomogram that included clinical predictors.

RESULTS

The model based on ResNet50-RF showed favorable classification performance and was verified in the test cohort (AUC = 0.9803). The nomogram based on deep learning feature scores and the lymph node status reported by computed tomography showed excellent discrimination. AUC of 0.9978 was achieved in the training cohort and verified in the test cohort (AUC = 0.9914). Decision analysis curve showed the value of nomogram in clinical application.

CONCLUSION

The computed tomography-based deep learning nomogram can accurately and effectively evaluate lymph node metastasis in patients with gastric cancer before surgery.

Predicting the Efficacy of SBRT for Lung Cancer with 18F-FDG PET/CT Radiogenomics

Purpose: to develop a radiogenomic model on the basis of 18F-FDG PET/CT radiomics and clinical-parameter EGFR for predicting PFS stratification in lung-cancer patients after SBRT treatment. Methods: A total of 123 patients with lung cancer who had undergone 18F-FDG PET/CT examination before SBRT from September 2014 to December 2021 were retrospectively analyzed. All patients’ PET/CT images were manually segmented, and the radiomic features were extracted. LASSO regression was used to select radiomic features. Logistic regression analysis was used to screen clinical features to establish the clinical EGFR model, and a radiogenomic model was constructed by combining radiomics and clinical EGFR. We used the receiver operating characteristic curve and calibration curve to assess the efficacy of the models. The decision curve and influence curve analysis were used to evaluate the clinical value of the models. The bootstrap method was used to validate the radiogenomic model, and the mean AUC was calculated to assess the model. Results: A total of 2042 radiomics features were extracted. Five radiomic features were related to the PFS stratification of lung-cancer patients with SBRT. T-stage and overall stages (TNM) were independent factors for predicting PFS stratification. AUCs under the ROC curve of the radiomics, clinical EGFR, and radiogenomic models were 0.84, 0.67, and 0.86, respectively. The calibration curve shows that the predicted value of the radiogenomic model was in good agreement with the actual value. The decision and influence curve showed that the model had high clinical application values. After Bootstrap validation, the mean AUC of the radiogenomic model was 0.850(95%CI 0.849–0.851). Conclusions: The radiogenomic model based on 18F-FDG PET/CT radiomics and clinical EGFR has good application value in predicting the PFS stratification of lung-cancer patients after SBRT treatment.

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.

A radiomics nomogram for invasiveness prediction in lung adenocarcinoma manifesting as part-solid nodules with solid components smaller than 6 mm

Objective

To investigate whether radiomics can help radiologists and thoracic surgeons accurately predict invasive adenocarcinoma (IAC) manifesting as part-solid nodules (PSNs) with solid components <6 mm and provide a basis for rational clinical decision-making.

Materials and Methods

In total, 1,210 patients (mean age ± standard deviation: 54.28 ± 11.38 years, 374 men and 836 women) from our hospital and another hospital with 1,248 PSNs pathologically diagnosed with adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or IAC were enrolled in this study. Among them, 1,050 cases from our hospital were randomly divided into a derivation set (n = 735) and an internal validation set (n = 315), 198 cases from another hospital were used for external validation. Each labeled nodule was segmented, and 105 radiomics features were extracted. Least absolute shrinkage and selection operator (LASSO) was used to calculate Rad-score and build the radiomics model. Multivariable logistic regression was conducted to identify the clinicoradiological predictors and establish the clinical-radiographic model. The combined model and predictive nomogram were developed based on identified clinicoradiological independent predictors and Rad-score using multivariable logistic regression analysis. The predictive performances of the three models were compared via receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was performed on both the internal and external validation sets to evaluate the clinical utility of the nomogram.

Results

The radiomics model showed superior predictive performance than the clinical-radiographic model in both internal and external validation sets (Az values, 0.884 vs. 0.810, p = 0.001; 0.924 vs. 0.855, p < 0.001, respectively). The combined model showed comparable predictive performance to the radiomics model (Az values, 0.887 vs. 0.884, p = 0.398; 0.917 vs. 0.924, p = 0.271, respectively). The clinical application value of the nomogram developed based on the Rad-score, maximum diameter, and lesion shape was confirmed, and DCA demonstrated that application of the Rad-score would be beneficial for radiologists predicting invasive lesions.

Conclusions

Radiomics has the potential as an independent diagnostic tool to predict the invasiveness of PSNs with solid components <6 mm.

Evaluation of Epidermal Growth Factor Receptor 2 Status in Gastric Cancer by CT-Based Deep Learning Radiomics Nomogram

Purpose

To explore the role of computed tomography (CT)-based deep learning and radiomics in preoperative evaluation of epidermal growth factor receptor 2 (HER2) status in gastric cancer.

Materials and methods

The clinical data on gastric cancer patients were evaluated retrospectively, and 357 patients were chosen for this study (training cohort: 249; test cohort: 108). The preprocessed enhanced CT arterial phase images were selected for lesion segmentation, radiomics and deep learning feature extraction. We integrated deep learning features and radiomic features (Inte). Four methods were used for feature selection. We constructed models with support vector machine (SVM) or random forest (RF), respectively. The area under the receiver operating characteristics curve (AUC) was used to assess the performance of these models. We also constructed a nomogram including Inte-feature scores and clinical factors.

Results

The radiomics-SVM model showed good classification performance (AUC, training cohort: 0.8069; test cohort: 0.7869). The AUC of the ResNet50-SVM model and the Inte-SVM model in the test cohort were 0.8955 and 0.9055. The nomogram also showed excellent discrimination achieving greater AUC (training cohort, 0.9207; test cohort, 0.9224).

Conclusion

CT-based deep learning radiomics nomogram can accurately and effectively assess the HER2 status in patients with gastric cancer before surgery and it is expected to assist physicians in clinical decision-making and facilitates individualized treatment planning.

Radiomics Model for Predicting TP53 Status Using CT and Machine Learning Approach in Laryngeal Squamous Cell Carcinoma

Objective

We aim to establish and validate computed tomography (CT)-based radiomics model for predicting TP53 status in patients with laryngeal squamous cell carcinoma (LSCC).

Methods

We divided all patients into a training set 1 (n=66) and a testing set 1 (n=30) to establish and validate radiomics model to predict TP53. Radiomics features were selected by analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (Lasso) regression analysis. Five radiomics models were established by using K-Nearest Neighbor, logistics regressive, linear-support vector machine (SVM), gaussian-SVM, and polynomial-SVM in training set 1. We also divided all patients into a training set 2 and a testing set 2 according to different CT equipment to establish and evaluate the stability of the radiomics models.

Results

After ANOVA and subsequent Lasso regression analysis, 22 radiomics features were selected to build the radiomics model in training set 1. The radiomics model based on linear-SVM has the best predictive performance of the five models, and the area under the receiver operating characteristic curve in training set 1 and testing set 1 were 0.831(95% confidence interval [CI] 0.692–0.970) and 0.797(95% CI 0.632–0.957) respectively. The specificity, sensitivity, and accuracy were 0.971(95% CI 0.834–0.999), 0.714(95% CI 0.535–0.848), and 0.843(95% CI 0.657–0.928) in training set 1 and 0.750(95% CI 0.500–0.938), 0.786(95% CI 0.571–1.000), and 0.667(95% CI 0.467–0.720) in testing set 1, respectively. In addition, the radiomics model also achieved stable prediction results even in different CT equipment. Decision curve analysis showed that the radiomics model for predicting TP53 status could benefit LSCC patients.

Conclusion

We developed and validated a relatively optimal radiomics model for TP53 status prediction by trying five different machine learning methods in patients with LSCC. It shown great potential of radiomics features for predicting TP53 status preoperatively and guiding clinical treatment.

A narrative review of artificial intelligence-assisted histopathologic diagnosis and decision-making for non-small cell lung cancer: achievements and limitations

Objective

To summarize the current evidence regarding the applications, workflow, and limitations of artificial intelligence (AI) in the management of patients pathologically-diagnosed with lung cancer.

Background

Lung cancer is one of the most common cancers and the leading cause of cancer-related deaths worldwide. AI technologies have been applied to daily medical workflow and have achieved an excellent performance in predicting histopathologic subtypes, analyzing gene mutation profiles, and assisting in clinical decision-making for lung cancer treatment. More advanced deep learning for classifying pathologic images with minimal human interactions has been developed in addition to the conventional machine learning scheme.

Methods

Studies were identified by searching databases, including PubMed, EMBASE, Web of Science, and Cochrane Library, up to February 2021 without language restrictions.

Conclusions

A number of studies have evaluated AI pipelines and confirmed that AI is robust and efficacious in lung cancer diagnosis and decision-making, demonstrating that AI models are a useful tool for assisting oncologists in health management. Although several limitations that pose an obstacle for the widespread use of AI schemes persist, the unceasing refinement of AI techniques is poised to overcome such problems. Thus, AI technology is a promising tool for use in diagnosing and managing lung cancer.

Development and Validation of Machine Learning Models to Predict Epidermal Growth Factor Receptor Mutation in Non-Small Cell Lung Cancer: A Multi-Center Retrospective Radiomics Study

Objective

To develop and validate a generalized prediction model that can classify epidermal growth factor receptor (EGFR) mutation status in non–small cell lung cancer patients.

Methods

A total of 346 patients (296 in the training cohort and 50 in the validation cohort) from four centers were included in this retrospective study. First, 1085 features were extracted using IBEX from the computed tomography images. The features were screened using the intraclass correlation coefficient, hypothesis tests and least absolute shrinkage and selection operator. Logistic regression (LR), decision tree (DT), random forest (RF), and support vector machine (SVM) were used to build a radiomics model for classification. The models were evaluated using the following metrics: area under the curve (AUC), calibration curve (CAL), decision curve analysis (DCA), concordance index (C-index), and Brier score.

Results

Sixteen features were selected, and models were built using LR, DT, RF, and SVM. In the training cohort, the AUCs was .723, .842, .995, and .883; In the validation cohort, the AUCs were .658, 0567, .88, and .765. RF model with the best AUC, its CAL, C-index (training cohort=.998; validation cohort=.883), and Brier score (training cohort=.007; validation cohort=0.137) showed a satisfactory predictive accuracy; DCA indicated that the RF model has better clinical application value.

Conclusion

Machine learning models based on computed tomography images can be used to evaluate EGFR status in patients with non–small cell lung cancer, and the RF model outperformed LR, DT, and SVM.

Radiomics for Survival Risk Stratification of Clinical and Pathologic Stage IA Pure-Solid Non-Small Cell Lung Cancer

Background Radiomics-based biomarkers enable the prognostication of resected non-small cell lung cancer (NSCLC), but their effectiveness in clinical stage and pathologic stage IA pure-solid tumors requires further determination. Purpose To construct an efficient radiomics signature for survival risk stratification personalized for patients with clinical stage and pathologic stage IA pure-solid NSCLC. Materials and Methods In this retrospective study, six radiomics signatures were constructed for patients with stage IA pure-solid NSCLC who underwent resection between January 2011 and December 2013 at authors' institution and were tested in the radiogenomics data set. The radiomics features were extracted from the intratumoral two-dimensional region, three-dimensional volume, and peritumoral area using PyRadiomics. The discriminative abilities of the signatures were quantified using the area under the time-dependent receiver operating characteristic curve (AUC), and the optimal signature was selected for patient stratification. Results The study included 592 patients with stage IA pure-solid NSCLC (median age, 61 years; interquartile range, 55-66 years; 269 women) for radiomics analysis: 381 patients for training, 163 for internal validation, and 48 for external validation. The radiomics signature combining three-region features yielded the highest 3- and 5-year AUCs of 0.77 and 0.78, respectively, in the internal validation set and 0.76 and 0.75, respectively, in the external validation set. Multivariable analysis suggested that the radiomics signature remained an independent prognostic factor (hazard ratio, 6.2; 95% CI: 3.5, 11.0; P < .001) and improved the discriminative ability and clinical usefulness of conventional clinical predictors. Conclusion The radiomics signature with multiregional features helped stratify the survival risk of patients with clinical stage and pathologic stage IA pure-solid non-small cell lung cancer. Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Hsu and Sohn in this issue.

Nomogram-aided individual induction chemotherapy regimen selection in advanced nasopharyngeal carcinoma

OBJECTIVE

We undertook this study to clarify how TPF, TP and PF induction chemotherapy (IC) regimens benefit for nasopharyngeal carcinoma (NPC) patients with different risk of disease progression.

MATERIALS AND METHODS

Patients with newly diagnosed, stage III-IVA NPC were included. A quantitative nomogram was built using the independent prognostic factors identified for disease-free survival (DFS). Patients were stratified into low-risk and high-risk groups by the nomogram. Survival outcomes and toxicities between different IC regimens were compared.

RESULTS

In total, 1647 (41.0%), 1123 (28.0%) and 1242 (31.0%) patients received TPF, PF and TP regimen, respectively. Consequently, 2253 (56.2%) patients were clarified as low-risk group and the other 1759 (43.8%) as high-risk group. Survival outcomes did not significantly differ between TPF, PF and TP regimens within the low-risk group. However, TPF was associated with significantly improved 3-year DFS (76.2% vs. 67.5% vs. 68.3%), overall survival (88.3% vs. 84.1% vs. 83.9%), distant metastasis-free survival (81.9% vs. 75.0% vs. 77.4%) and locoregional relapse-free survival (92.0% vs. 87.5% vs. 86.9%; all P < 0.05) compared with PF and TP within high-risk group. Multivariate analysis also confirmed these findings. Toxicity analysis showed that TP regimen has the highest percentage of grade 3-5 hematologic toxicities while PF regimen achieved the lowest percentages of overall grade 3-5 adverse events.

CONCLUSIONS

Patients with high risk should receive TPF for better efficacy and PF may be a better choice for low-risk patients with regard to less grade 3-5 toxicities.

Exploring MRI Characteristics of Brain Diffuse Midline Gliomas With the H3 K27M Mutation Using Radiomics

Objectives

To explore the magnetic resonance imaging (MRI) characteristics of brain diffuse midline gliomas with the H3 K27M mutation (DMG-M) using radiomics.

Materials and Methods

Thirty patients with diffuse midline gliomas, including 16 with the H3 K27M mutant and 14 with wild type tumors, were retrospectively included in this study. A total of 272 radiomic features were initially extracted from MR images of each tumor. Principal component analysis, univariate analysis, and three other feature selection methods, including variance thresholding, recursive feature elimination, and the elastic net, were used to analyze the radiomic features. Based on the results, related visually accessible features of the tumors were further evaluated.

Results

Patients with DMG-M were younger than those with diffuse midline gliomas with H3 K27M wild (DMG-W) (median, 25.5 and 48 years old, respectively; p=0.005). Principal component analysis showed that there were obvious overlaps in the first two principal components for both DMG-M and DMG-W tumors. The feature selection results showed that few features from T2-weighted images (T2WI) were useful for differentiating DMG-M and DMG-W tumors. Thereafter, four visually accessible features related to T2WI were further extracted and analyzed. Among these features, only cystic formation showed a significant difference between the two types of tumors (OR=7.800, 95% CI 1.476-41.214, p=0.024).

Conclusions

DMGs with and without the H3 K27M mutation shared similar MRI characteristics. T2W sequences may be valuable, and cystic formation a useful MRI biomarker, for diagnosing brain DMG-M.

Positron Emission Tomography-Based Short-Term Efficacy Evaluation and Prediction in Patients With Non-Small Cell Lung Cancer Treated With Hypo-Fractionated Radiotherapy

Background

Positron emission tomography is known to provide more accurate estimates than computed tomography when staging non–small cell lung cancer. The aims of this prospective study were to contrast the short-term efficacy of the two imaging methods while evaluating the effects of hypo-fractionated radiotherapy in non-small cell lung cancer, and to establish a short-term efficacy prediction model based on the radiomics features of positron emission tomography.

Methods

This nonrandomized-controlled trial was conducted from March 2015 to June 2019. Thirty-one lesions of 30 patients underwent the delineation of the regions of interest on positron emission tomography and computed tomography 1 month before, and 3 months after hypo-fractionated radiotherapy. Each patient was evaluated for the differences in local objective response rate between the two images. The Kaplan Meier method was used to analyze the local objective response and subsequent survival duration of the two imaging methods. The 3D Slicer was used to extract the radiomics features based on positron emission tomography. Least absolute shrinkage and selection operator regression was used to eliminate redundant features, and logistic regression analysis was used to develop the curative-effect-predicting model, which was displayed through a radiomics nomogram. Receiver operating characteristic curve and decision curve were used to evaluate the accuracy and clinical usefulness of the prediction model.

Results

Positron emission tomography-based local objective response rate was significantly higher than that based on computed tomography [70.97% (22/31) and 12.90% (4/31), respectively (p<0.001)]. The mean survival time of responders and non-responders assessed by positron emission tomography was 28.6 months vs. 11.4 months (p=0.29), whereas that assessed by computed tomography was 24.5 months vs. 26 months (p=0.66), respectively. Three radiomics features were screened to establish a personalized prediction nomogram with high area under curve (0.94, 95% CI 0.85–0.99, p<0.001). The decision curve showed a high clinical value of the radiomics nomogram.

Conclusions

We recommend positron emission tomography for evaluating the short-term efficacy of hypo-fractionated radiotherapy in non-small cell lung cancer, and that the radiomics nomogram could be an important technique for the prediction of short-term efficacy, which might enable an improved and precise treatment.

Registration number/URL

ChiCTR1900027768/http://www.chictr.org.cn/showprojen.aspx?proj=46057

Radiomics-based machine-learning method for prediction of distant metastasis from soft-tissue sarcomas

AIM

To construct and validate a radiomics-based machine-learning method for preoperative prediction of distant metastasis (DM) from soft-tissue sarcoma.

MATERIALS AND METHODS

Seventy-seven soft-tissue sarcomas were divided into a training set (n=54) and a validation set (n=23). The performance of three feature selection methods (ReliefF, least absolute shrinkage and selection operator [LASSO], and regularised discriminative feature selection for unsupervised learning [UDFS]) and four classifiers, random forest (RF), logistic regression (LOG), K nearest neighbour (KNN), and support vector machines (SVMs), were compared for predicting the likelihood of DM. To counter the imbalance in the frequencies of DM, each machine-learning method was trained first without subsampling, then with the synthetic minority oversampling technique (SMOTE). The performance of the radiomics model was assessed using area under the receiver-operating characteristic curve (AUC) and accuracy (ACC) values.

RESULTS

The performance of the LASSO and SVM algorithm combination used with SMOTE was superior to that of the algorithm combination alone. The combination of SMOTE with feature screening by LASSO and SVM classifiers had an AUC of 0.9020 and ACC of 91.30% in the validation dataset.

CONCLUSION

A machine-learning model based on radiomics was favourable for predicting the likelihood of DM from soft-tissue sarcoma. This will help decide treatment strategies.

CT features associated with EGFR mutations and ALK positivity in patients with multiple primary lung adenocarcinomas

Background

In multiple primary lung adenocarcinomas (MPLAs), the relationship between imaging and gene mutations remains unclear. This retrospective study aimed to identify the correlation of epidermal growth factor receptor (EGFR) mutations and anaplastic lymphoma kinase (ALK) status with CT characteristics in MPLA patients.

Methods

Sixty-seven patients (135 lesions) with MPLAs confirmed by pathology were selected from our institution. All subjects were tested for EGFR mutations and ALK status and underwent chest CT prior to any treatment. The criteria for MPLA definitions closely adhered to the comprehensive histologic assessment (CHA).

Results

Among MPLA patients, EGFR mutations were more common in females (p = 0.002), in those who had never smoked (p = 0.010), and in those with less lymph node metastasis (p < 0.001), and the tumours typically presented with ground-glass opacity (GGO) (p = 0.003), especially mixed GGO (p < 0.001), and with air bronchograms (p = 0.012). Logistics regression analysis showed that GGO (OR = 6.550, p = 0.010) was correlated with EGFR mutation, while air bronchograms were not correlated with EGFR mutation (OR = 3.527, p = 0.060). A receiver operating characteristic (ROC) curve yielded area under the curve (AUC) values of 0.647 and 0.712 for clinical-only or combined CT features, respectively, for prediction of EGFR mutations, and a significant difference was found between them (p = 0.0344). ALK-positive status was found most frequently in MPLA patients who were younger (p = 0.002) and had never smoked (p = 0.010). ALK positivity was associated with solid nodules or masses in MPLAs (p < 0.004) on CT scans. Logistics regression analysis showed that solid nodules (OR = 6.550, p = 0.010) were an independent factor predicting ALK positivity in MPLAs. For prediction of ALK positivity, the ROC curve yielded AUC values of 0.767 and 0.804 for clinical-only or combined CT features, respectively, but no significant difference was found between them (p = 0.2267).

Conclusion

Among MPLA patients, nonsmoking women with less lymph node metastasis and patients with lesions presenting GGO or mixed GGO and air bronchograms on CT were more likely to exhibit EGFR mutations. In nonsmoking patients, young patients with solid lesions on CT are recommended to undergo an ALK status test.

Prediction of prognostic risk factors in hepatocellular carcinoma with transarterial chemoembolization using multi-modal multi-task deep learning

BACKGROUND

Due to heterogeneity of hepatocellular carcinoma (HCC), outcome assessment of HCC with transarterial chemoembolization (TACE) is challenging.

METHODS

We built histologic-related scores to determine microvascular invasion (MVI) and Edmondson-Steiner grade by training CT radiomics features using machine learning classifiers in a cohort of 494 HCCs with hepatic resection. Meanwhile, we developed a deep learning (DL)-score for disease-specific survival by training CT imaging using DL networks in a cohort of 243 HCCs with TACE. Then, three newly built imaging hallmarks with clinicoradiologic factors were analyzed with a Cox-Proportional Hazard (Cox-PH) model.

FINDINGS

In HCCs with hepatic resection, two imaging hallmarks resulted in areas under the curve (AUCs) of 0.79 (95% confidence interval [CI]: 0.71-0.85) and 0.72 (95% CI: 0.64-0.79) for predicting MVI and Edmondson-Steiner grade, respectively, using test data. In HCCs with TACE, higher DL-score (hazard ratio [HR]: 3.01; 95% CI: 2.02-4.50), American Joint Committee on Cancer (AJCC) stage III+IV (HR: 1.71; 95% CI: 1.12-2.61), Response Evaluation Criteria in Solid Tumors (RECIST) with stable disease + progressive disease (HR: 2.72; 95% CI: 1.84-4.01), and TACE-course > 3 (HR: 0.65; 95% CI: 0.45-0.76) were independent prognostic factors. Using these factors via a Cox-PH model resulted in a concordance index of 0.73 (95% CI: 0.71-0.76) for predicting overall survival and AUCs of 0.85 (95% CI: 0.81-0.89), 0.90 (95% CI: 0.86-0.94), and 0.89 (95% CI: 0.84-0.92), respectively, for predicting 3-year, 5-year, and 10-year survival.

INTERPRETATION

Our study offers a DL-based, noninvasive imaging hallmark to predict outcome of HCCs with TACE.

FUNDING

This work was supported by the key research and development program of Jiangsu Province (Grant number: BE2017756).

A quantitative imaging biomarker for predicting disease-free-survival-associated histologic subgroups in lung adenocarcinoma

OBJECTIVES

Classification of histologic subgroups has significant prognostic value for lung adenocarcinoma patients who undergo surgical resection. However, clinical histopathology assessment is generally performed on only a small portion of the overall tumor from biopsy or surgery. Our objective is to identify a noninvasive quantitative imaging biomarker (QIB) for the classification of histologic subgroups in lung adenocarcinoma patients.

METHODS

We retrospectively collected and reviewed 1313 CT scans of patients with resected lung adenocarcinomas from two geographically distant institutions who were seen between January 2014 and October 2017. Three study cohorts, the training, internal validation, and external validation cohorts, were created, within which lung adenocarcinomas were divided into two disease-free-survival (DFS)-associated histologic subgroups, the mid/poor and good DFS groups. A comprehensive machine learning- and deep learning-based analytical system was adopted to identify reproducible QIBs and help to understand QIBs' significance.

RESULTS

Intensity-Skewness, a QIB quantifying tumor density distribution, was identified as the optimal biomarker for predicting histologic subgroups. Intensity-Skewness achieved high AUCs (95% CI) of 0.849(0.813,0.881), 0.820(0.781,0.856) and 0.863(0.827,0.895) on the training, internal validation, and external validation cohorts, respectively. A criterion of Intensity-Skewness ≤ 1.5, which indicated high tumor density, showed high specificity of 96% (sensitivity 46%) and 99% (sensitivity 53%) on predicting the mid/poor DFS group in the training and external validation cohorts, respectively.

CONCLUSIONS

A QIB derived from routinely acquired CT was able to predict lung adenocarcinoma histologic subgroups, providing a noninvasive method that could potentially benefit personalized treatment decision-making for lung cancer patients.

KEY POINTS

• A noninvasive imaging biomarker, Intensity-Skewness, which described the distortion of pixel-intensity distribution within lesions on CT images, was identified as a biomarker to predict disease-free-survival-associated histologic subgroups in lung adenocarcinoma. • An Intensity-Skewness of ≤ 1.5 has high specificity in predicting the mid/poor disease-free survival histologic patient group in both the training cohort and the external validation cohort. • The Intensity-Skewness is a feature that can be automatically computed with high reproducibility and robustness.

Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers

OBJECTIVE

To differentiate supratentorial single brain metastasis (MET) from glioblastoma (GBM) by using radiomic features derived from the peri-enhancing oedema region and multiple classifiers.

METHODS

One hundred and twenty single brain METs and GBMs were retrospectively reviewed and then randomly divided into a training data set (70%) and validation data set (30%). Quantitative radiomic features of each case were extracted from the peri-enhancing oedema region of conventional MR images. After feature selection, five classifiers were built. Additionally, the combined use of the classifiers was studied. Accuracy, sensitivity, and specificity were used to evaluate the classification performance.

RESULTS

A total of 321 features were extracted, and 3 features were selected for each case. The 5 classifiers showed an accuracy of 0.70 to 0.76, sensitivity of 0.57 to 0.98, and specificity of 0.43 to 0.93 for the training data set, with an accuracy of 0.56 to 0.64, sensitivity of 0.39 to 0.78, and specificity of 0.50 to 0.89 for the validation data set. When combining the classifiers, the classification performance differed according to the combined mode and the agreement pattern of classifiers, and the greatest benefit was obtained when all the classifiers reached agreement using the same weight and simple majority vote method.

CONCLUSIONS

Three features derived from the peri-enhancing oedema region had moderate value in differentiating supratentorial single brain MET from GBM with five single classifiers. Combined use of classifiers, like multi-disciplinary team (MDT) consultation, could confer extra benefits, especially for those cases when all classifiers reach agreement.

KEY POINTS

• Radiomics provides a way to differentiate single brain MET between GBM by using conventional MR images. • The results of classifiers or algorithms themselves are also data, the transformation of the primary data. • Like MDT consultation, the combined use of multiple classifiers may confer extra benefits.

Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics

PURPOSE

The aim of this systematic review was to analyse literature on artificial intelligence (AI) and radiomics, including all medical imaging modalities, for oncological and non-oncological applications, in order to assess how far the image mining research stands from routine medical application. To do this, we applied a trial phases classification inspired from the drug development process.

METHODS

Among the articles we considered for inclusion from PubMed were multimodality AI and radiomics investigations, with a validation analysis aimed at relevant clinical objectives. Quality assessment of selected papers was performed according to the QUADAS-2 criteria. We developed the phases classification criteria for image mining studies.

RESULTS

Overall 34,626 articles were retrieved, 300 were selected applying the inclusion/exclusion criteria, and 171 high-quality papers (QUADAS-2 ≥ 7) were identified and analysed. In 27/171 (16%), 141/171 (82%), and 3/171 (2%) studies the development of an AI-based algorithm, radiomics model, and a combined radiomics/AI approach, respectively, was described. A total of 26/27(96%) and 1/27 (4%) AI studies were classified as phase II and III, respectively. Consequently, 13/141 (9%), 10/141 (7%), 111/141 (79%), and 7/141 (5%) radiomics studies were classified as phase 0, I, II, and III, respectively. All three radiomics/AI studies were categorised as phase II trials.

CONCLUSIONS

The results of the studies are promising but still not mature enough for image mining tools to be implemented in the clinical setting and be widely used. The transfer learning from the well-known drug development process, with some specific adaptations to the image mining discipline could represent the most effective way for radiomics and AI algorithms to become the standard of care tools.

CT radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer

PURPOSE

To investigate the role of computed tomography (CT) radiomics for the preoperative prediction of lymph node (LN) metastasis in gastric cancer.

MATERIALS AND METHODS

This retrospective study included 247 consecutive patients (training cohort, 197 patients; test cohort, 50 patients) with surgically proven gastric cancer. Dedicated radiomics prototype software was used to segment lesions on preoperative arterial phase (AP) CT images and extract features. A radiomics model was constructed to predict the LN metastasis by using a random forest (RF) algorithm. Finally, a nomogram was built incorporating the radiomics scores and selected clinical predictors. Receiver operating characteristic (ROC) curves were used to validate the capability of the radiomics model and nomogram on both the training and test cohorts.

RESULTS

The radiomics model showed a favorable discriminatory ability in the training cohort with an area under the curve (AUC) of 0.844 (95% CI, 0.759 to 0.909), which was confirmed in the test cohort with an AUC of 0.837 (95% CI, 0.705 to 0.926). The nomogram consisted of radiomics scores and the CT-reported LN status showed excellent discrimination in the training and test cohorts with AUCs of 0.886 (95% CI, 0.808 to 0.941) and 0.881 (95% CI, 0.759 to 0.956), respectively.

CONCLUSIONS

The CT-based radiomics nomogram holds promise for use as a noninvasive tool in the individual prediction of LN metastasis in gastric cancer.

KEY POINTS

• CT radiomics showed a favorable performance for the prediction of LN metastasis in gastric cancer. • Radiomics model outperformed the routine CT in predicting LN metastasis in gastric cancer. • The radiomics nomogram holds potential in the individualized prediction of LN metastasis in gastric cancer.

Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement

OBJECTIVES

To evaluate radiomics studies according to radiomics quality score (RQS) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to provide objective measurement of radiomics research.

MATERIALS AND METHODS

PubMed and Embase were searched for studies published in high clinical imaging journals until December 2018 using the terms "radiomics" and "radiogenomics." Studies were scored against the items in the RQS and TRIPOD guidelines. Subgroup analyses were performed for journal type (clinical vs. imaging), intended use (diagnostic vs. prognostic), and imaging modality (CT vs. MRI), and articles were compared using Fisher's exact test and Mann-Whitney analysis.

RESULTS

Seventy-seven articles were included. The mean RQS score was 26.1% of the maximum (9.4 out of 36). The RQS was low in demonstration of clinical utility (19.5%), test-retest analysis (6.5%), prospective study (3.9%), and open science (3.9%). None of the studies conducted a phantom or cost-effectiveness analysis. The adherence rate for TRIPOD was 57.8% (mean) and was particularly low in reporting title (2.6%), stating study objective in abstract and introduction (7.8% and 16.9%), blind assessment of outcome (14.3%), sample size (6.5%), and missing data (11.7%) categories. Studies in clinical journals scored higher and more frequently adopted external validation than imaging journals.

CONCLUSIONS

The overall scientific quality and reporting of radiomics studies is insufficient. Scientific improvements need to be made to feature reproducibility, analysis of clinical utility, and open science categories. Reporting of study objectives, blind assessment, sample size, and missing data is deemed to be necessary.

KEY POINTS

• The overall scientific quality and reporting of radiomics studies is insufficient. • The RQS was low in demonstration of clinical utility, test-retest analysis, prospective study, and open science. • Room for improvement was shown in TRIPOD in stating study objective in abstract and introduction, blind assessment of outcome, sample size, and missing data categories.

Radiomics: an Introductory Guide to What It May Foretell

PURPOSE OF REVIEW

To briefly review the radiomics concept, its applications, and challenges in oncology in the era of precision medicine.

RECENT FINDINGS

Over the last 5 years, more than 500 studies have evaluated the role of radiomics to predict tumor diagnosis, genetic pattern, tumor response to therapy, and survival in multiple cancers. This new post-processing method is aimed at extracting multiple quantitative features from the image and converting them into mineable data. Radiomics models developed have shown promising results and may play a role in the near future in the daily patient management especially to assess tumor heterogeneity acting as a whole tumor virtual biopsy. For now, radiomics is limited by its lack of standardization; future challenges will be to provide robust and reproducible metrics extracted from large multicenter databases.

[Study Progress of Radiomics in Precision Medicine for Lung Cancer]

Precision medicine, imaging first. Radiomics, a method of machine learning in artificial intelligence, provides valuable diagnostic, prognostic or predictive information through quantitative analysis on the tumor's region of interest to support personalized clinical decisions and improve individualized treatment, which could lay a solid foundation for achieving the precision medicine. This review provides a latest advance of the radiomic application of the precision medicine for lung cancer.

Predicting malignant potential of subsolid nodules: can radiomics preempt longitudinal follow up CT?

Background

To assess if radiomics can differentiate benign and malignant subsolid lung nodules (SSNs) on baseline or follow up chest CT examinations. If radiomics can differentiate between benign and malignant subsolid lung nodules, the clinical implications are shorter follow up CT imaging and early recognition of lung adenocarcinoma on imaging.

Materials and methods

The IRB approved retrospective study included 36 patients (mean age 69 ± 8 years; 5 males, 31 females) with 108 SSNs (31benign, 77 malignant) who underwent follow up chest CT for evaluation of indeterminate SSN. All SSNs were identified on both baseline and follow up chest CT. DICOM CT images were deidentified and exported into the open access 3D Slicer software (version 4.7) to obtain radiomic features. Logistic regression analyses and receiver operating characteristic (ROC) curves for various quantitative parameters were generated with SPSS statistical software.

Results

Only 2/92 radiomic features (cluster shade and surface volume ratio) enabled differentiation between malignant and benign SSN on baseline chest CT (P = 0.01 and 0.03) with moderate accuracy [AUC 0.624 (0.505–0.743)]. On follow-up CT, 52/92 radiomic features were significantly different between benign and malignant SSN (P: 0.04 - < 0.0001) with improved accuracy [AUC: 0.708 (0.605–0.811), P = 0.04 - < 0.0001]. Radiomics of benign SSN were stable over time, whereas 63/92 radiomic features of malignant SSNs changed significantly between the baseline and follow up chest CT (P: 0.04 - < 0.0001).

Conclusions

Temporal changes in radiomic features of subsolid lung nodules favor malignant etiology over benign. The change in radiomics features of subsolid lung nodules can allow shorter follow up CT imaging and early recognition of lung adenocarcinoma on imaging. Radiomic features have limited application in differentiating benign and early malignant SSN on baseline chest CT.

A deep learning radiomics model for preoperative grading in meningioma

OBJECTIVES

To noninvasively differentiate meningioma grades by deep learning radiomics (DLR) model based on routine post-contrast MRI.

METHODS

We enrolled 181 patients with histopathologic diagnosis of meningioma who received post-contrast MRI preoperative examinations from 2 hospitals (99 in the primary cohort and 82 in the validation cohort). All the tumors were segmented based on post-contrast axial T1 weighted images (T1WI), from which 2048 deep learning features were extracted by the convolutional neural network. The random forest algorithm was used to select features with importance values over 0.001, upon which a deep learning signature was built by a linear discriminant analysis classifier. The performance of our DLR model was assessed by discrimination and calibration in the independent validation cohort. For comparison, a radiomic model based on hand-crafted features and a fusion model were built.

RESULTS

The DLR signature comprised 39 deep learning features and showed good discrimination performance in both the primary and validation cohorts. The area under curve (AUC), sensitivity, and specificity for predicting meningioma grades were 0.811(95% CI, 0.635-0.986), 0.769, and 0.898 respectively in the validation cohort. DLR performance was superior over the hand-crafted features. Calibration curves of DLR model showed good agreements between the prediction probability and the observed outcome of high-grade meningioma.

CONCLUSIONS

Using routine MRI data, we developed a DLR model with good performance for noninvasively individualized prediction of meningioma grades, which achieved a quantization capability superior over the hand-crafted features. This model has potential to guide and facilitate the clinical decision-making of whether to observe or to treat patients by providing prognostic information.

CT-Based Radiomics Model for Predicting Brain Metastasis in Category T1 Lung Adenocarcinoma

OBJECTIVE. The purpose of this study is to develop and evaluate an unenhanced CT-based radiomics model to predict brain metastasis (BM) in patients with category T1 lung adenocarcinoma. MATERIALS AND METHODS. A total of 89 eligible patients with category T1 lung adenocarcinoma were enrolled and classified as patients with BM (n = 35) or patients without BM (n = 54). A total of 1160 quantitative radiomic features were extracted from unenhanced CT images of each patient. Three prediction models (the clinical model, the radiomics model, and a hybrid [clinical plus radiomics] model) were established. The ROC AUC value and 10-fold cross-validation were used to evaluate the prediction performance of the models. RESULTS. In terms of predictive performance, the mean AUC value was 0.759 (95% CI, 0.643-0.867; sensitivity, 82.9%; specificity, 57.4%) for the clinical model, 0.847 (95% CI, 0.739-0.915; sensitivity, 80.0%; specificity, 81.5%) for the radiomics model, and 0.871 (95% CI, 0.767-0.933; sensitivity = 82.9%, specificity = 83.3%) for the hybrid model. The hybrid and radiomics models (p = 0.0072 and 0.0492, respectively) performed significantly better than the clinical model. No significant difference was found between the radiomics model and the hybrid model (p = 0.1022). CONCLUSION. A CT-based radiomics model presented good predictive performance and great potential for predicting BM in patients with category T1 lung adenocarcinoma. As a promising adjuvant tool, it can be helpful for guiding BM screening and thus benefiting personalized surveillance for patients with lung cancer.

Histogram analysis combined with morphological characteristics to discriminate adenocarcinoma in situ or minimally invasive adenocarcinoma from invasive adenocarcinoma appearing as pure ground-glass nodule

OBJECTIVE

To construct a predictive model to discriminate adenocarcinoma in situ (AIS) or minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma (IAC) appearing as pure ground-glass nodules (pGGNs) using computed tomography (CT) histogram analysis combined with morphological characteristics and to evaluate its diagnostic performance.

MATERIALS AND METHODS

Two hundred eighty-nine patients with surgically resected solitary pGGN and pathologically diagnosed with AIS, MIA, or IAC in our institution from January 2014 to May 2018 were enrolled in our study. Two hundred twenty-six pGGNs (79 AIS, 84 MIA, and 63 IAC) were randomly selected and assigned to a model-development cohort, and the remaining 63 pGGNs (11 AIS, 29 MIA and 23 IAC) were assigned to a validation cohort. The morphological characteristics were established as model A and histogram parameters as model B. The diagnostic performances of model A, model B, and model A + B were evaluated and compared via receiver operating curve (ROC) analysis and logistic regression analysis.

RESULTS

Entropy (odd ratio [OR] = 23.25, 95%CI: 6.83-79.15, p < 0.001), microvascular sign (OR = 8.62, 95%CI: 3.72-19.98, p < 0.001) and the maximum diameter (OR = 4.37, 95%CI: 2.44-7.84, p < 0.001) were identified as independent predictors in the IAC group. The area under the ROC (Az value), accuracy, sensitivity and specificity of model A + B were 0.896, 88.1%, 79.4% and 91.4%, respectively, exhibiting a significantly higher Az value than either model A or model B alone (0.785 vs 0.896, p < 0.001; 0.849 vs 0.896, p = 0.029). Model A + B also conveyed a good diagnostic performance in the validation cohort, with an Az value of 0.851.

CONCLUSION

Histogram analysis combined with morphological characteristics exhibit a superior diagnostic performance in discriminating AIS-MIA from IAC appearing as pGGNs.

Differentiation between pilocytic astrocytoma and glioblastoma: a decision tree model using contrast-enhanced magnetic resonance imaging-derived quantitative radiomic features

OBJECTIVE

To differentiate brain pilocytic astrocytoma (PA) from glioblastoma (GBM) using contrast-enhanced magnetic resonance imaging (MRI) quantitative radiomic features by a decision tree model.

METHODS

Sixty-six patients from two centres (PA, n = 31; GBM, n = 35) were randomly divided into training and validation data sets (about 2:1). Quantitative radiomic features of the tumours were extracted from contrast-enhanced MR images. A subset of features was selected by feature stability and Boruta algorithm. The selected features were used to build a decision tree model. Predictive accuracy, sensitivity and specificity were used to assess model performance. The classification outcome of the model was combined with tumour location, age and gender features, and multivariable logistic regression analysis and permutation test using the entire data set were performed to further evaluate the decision tree model.

RESULTS

A total of 271 radiomic features were successfully extracted for each tumour. Twelve features were selected as input variables to build the decision tree model. Two features S(1, -1) Entropy and S(2, -2) SumAverg were finally included in the model. The model showed an accuracy, sensitivity and specificity of 0.87, 0.90 and 0.83 for the training data set and 0.86, 0.80 and 0.91 for the validation data set. The classification outcome of the model related to the actual tumour types and did not rely on the other three features (p < 0.001).

CONCLUSIONS

A decision tree model with two features derived from the contrast-enhanced MR images performed well in differentiating PA from GBM.

KEY POINTS

• MRI findings of PA and GBM are sometimes very similar. • Radiomics provides much more quantitative information about tumours. • Radiomic features can help to distinguish PA from GBM.

Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on 3D computed tomography features

OBJECTIVE

We aimed to identify optimal machine-learning methods for preoperative differentiation of sacral chordoma (SC) and sacral giant cell tumour (SGCT) based on 3D non-enhanced computed tomography (CT) and CT-enhanced (CTE) features.

METHODS

A total of 95 patients were divided into a training set and a validation set. Three best feature selection methods (Relief, least absolute shrinkage and selection operator (LASSO) and Random Forest (RF)) and three classification methods, including generalised linear models (GLM), support vector machines (SVM) and RF, were compared for their performance in distinguishing SC and SGCT. The performance of the radiomics model was investigated via area under the receiver-operating characteristic curve (AUC) and accuracy (ACC) analysis.

RESULTS

The selection method LASSO + classifier GLM had the highest AUC of 0.984 and ACC of 0.897 in the validating set, followed by Relief + GLM (AUC = 0.909, ACC = 0.862) and LASSO + SVM (AUC = 0.900, ACC = 0.862) based on CTE features. For CT features, RF + GLM had the highest AUC of 0.889, while LASSO + GLM achieved a high ACC of 0.793 in the validating set. Regardless of the methods, CTE features significantly outperformed those from CT for the differentiation of SC and SGCT (Z_AUC = -3.029, Z_ACC = -4.553; p < 0.05).

CONCLUSIONS

Our study demonstrated CTE features performed better than CT features. The selection method LASSO + classifier GLM had the best performance in differentiation of SC and SGCT, which could enhance the application of radiomics methods in sacral tumours.

KEY POINTS

• Sacral chordoma and sacral giant cell tumour are the two most common primary tumours of the sacrum with many common clinical and imaging characteristics. • A radiomics model helps clinicians to identify the histology of a sacral tumour. • CTE features should be preferred.

[Radiomics: Big Data Instead of Biopsies in the Future?]

Precision medicine is increasingly pushed forward, also with respect to upcoming new targeted therapies. Individual characterization of diseases on the basis of biomarkers is a prerequisite for this development. So far, biomarkers are characterized clinically, histologically or on a molecular level. The implementation of broad screening methods (“Omics”) and the analysis of big data – in addition to single markers – allow to define biomarker signatures. Next to “Genomics”, “Proteomics”, and “Metabolicis”, “Radiomics” gained increasing interest during the last years. Based on radiologic imaging, multiple radiomic markers are extracted with the help of specific algorithms. These are correlated with clinical, (immuno-) histopathological, or genomic data. Underlying structural differences are based on the imaging metadata and are often not visible and therefore not detectable without specific software. Radiomics are depicted numerically or by graphs. The fact that radiomic information can be extracted from routinely performed imaging adds a specific appeal to this method. Radiomics could potentially replace biopsies and additional investigations. Alternatively, radiomics could complement other biomarkers and thus lead to a more precise, multimodal prediction. Until now, radiomics are primarily used to investigate solid tumors. Some promising studies in head and neck cancer have already been published.

Radiomics Approach to Prediction of Occult Mediastinal Lymph Node Metastasis of Lung Adenocarcinoma

OBJECTIVE

The purpose of this study was to evaluate the prognostic impact of radiomic features from CT scans in predicting occult mediastinal lymph node (LN) metastasis of lung adenocarcinoma.

MATERIALS AND METHODS

A total of 492 patients with lung adenocarcinoma who underwent preoperative unenhanced chest CT were enrolled in the study. A total of 300 radiomics features quantifying tumor intensity, texture, and wavelet were extracted from the segmented entire-tumor volume of interest of the primary tumor. A radiomics signature was generated by use of the relief-based feature method and the support vector machine classification method. A ROC regression curve was drawn for the predictive performance of radiomics features. Multivariate logistic regression models based on clinicopathologic and radiomics features were compared for discriminating mediastinal LN metastasis.

RESULTS

Clinical variables (sex, tumor diameter, tumor location) and predominant subtype were risk factors for pathologic mediastinal LN metastasis. The accuracy of radiomics signature for predicting mediastinal LN metastasis was 91.1% in ROC analysis (AUC, 0.972; sensitivity, 94.8%; specificity, 92%). Radiomics signature (Akaike information criterion [AIC] value, 80.9%) showed model fit superior to that of the clinicohistopathologic model (AIC value, 61.1%) for predicting mediastinal LN metastasis.

CONCLUSION

The radiomics signature of a primary tumor based on CT scans can be used for quantitative and noninvasive prediction of occult mediastinal LN metastasis of lung adenocarcinoma.

Advanced nasopharyngeal carcinoma: pre-treatment prediction of progression based on multi-parametric MRI radiomics

We aimed to investigate the potential of radiomic features of magnetic resonance imaging (MRI) to predict progression in patients with advanced nasopharyngeal carcinoma (NPC). One hundred and thirteen consecutive patients (01/2007-07/2013) (training cohort: n = 80; validation cohort: n = 33) with advanced NPC were enrolled. A total of 970 initial features were extracted from T2-weighted (T2-w) (n = 485) and contrast-enhanced T1-weighted (CET1-w) MRI (n = 485) for each patient. We used least absolute shrinkage and selection operator (Lasso) method to select features that were most significantly associated with the progression. The selected features were used to construct radiomics-based models and the predictive performance of which were assessed with respect to the area under the curve (AUC). As a result, eight features significantly associated with the progression of advanced NPC were identified. In the training cohort, a radiomic model based on combined CET1-w and T2-w images (AUC: 0.886, 95%CI: 0.815-0.956) demonstrated better prognostic performance than models based on CET1-w (AUC: 0.793, 95%CI: 0.698-0.889) or T2-w images alone (AUC: 0.813, 95%CI: 0.721-0.904). These results were confirmed in the validation cohort. Accordingly, MRI-based radiomic biomarkers present high accuracy in the pre-treatment prediction of progression in advanced NPC.