A biomarker basing on radiomics for the prediction of overall survival in non-small cell lung cancer patients

Cancer diagnosis based on laser-induced breakdown spectroscopy with bagging-voting fusion model

Advances in cancer diagnostics play a pivotal role in increasing early detection of cancer. Integrating laser-induced breakdown spectroscopy (LIBS) with machine learning algorithms has attracted wide interest in cancer diagnosis. However, using a single model`s efficacy is limited by algorithm principles, making it challenging to meet the comprehensive needs of cancer diagnosis. Here, we demonstrate a bagging-voting fusion (BVF) algorithm for the detection and identification of multiple types of cancer. In the BVF model of this paper, support vector machine (SVM), artificial neural network (ANN), k-nearest neighbors (KNN), quadratic discriminant analysis (QDA), and random forest (RF) models, which have relatively small homogeneity to obtain more comprehensive decision boundaries, are fused at both the training and decision levels. LIBS spectral data was collected from four types of serum samples, including liver cancer, lung cancer, esophageal cancer, and healthy control. LIBS detection was conducted on the samples, which were directly dropped onto ordered microarray silicon substrates and dried. The results showed that the BVF model achieved an accuracy of 92.53 % and a recall of 92.92 % across the four types of serum, outperforming the best single machine-learning model (SVM: accuracy 75.86 %, recall 77.50 %). Moreover, the BVF model with manual line selection feature extraction required only 140 s for a single detection and identification. In conclusion, the aforementioned results demonstrated that LIBS with BVF has excellent performance in detecting a multitude of cancers, and is expected to provide a new method for efficient and accurate cancer diagnosis.

Application of computed tomography-based radiomics analysis combined with lung cancer serum tumor markers in the identification of lung squamous cell carcinoma and lung adenocarcinoma

OBJECTIVE

To establish a prediction model of lung cancer classification by computed tomography (CT) radiomics with the serum tumor markers (STM) of lung cancer.

MATERIALS AND METHODS

Two-hundred NSCLC patients were enrolled in our study. Clinical data including age, sex, and STM (squamous cell carcinoma [SCC], neuron-specific enolase [NSE], carcinoembryonic antigen [CEA], pro-gastrin-releasing peptide [PRO-GRP], and cytokeratin 19 fragment [cYFRA21-1]) were collected. A radiomics signature was generated from the training set using the least absolute shrinkage and selection operator (LASSO) algorithm. The risk factors were identified using multivariate logistic regression analysis, and a radiomics nomogram based on the radiomics signature and clinical features was constructed. The capability of the nomogram was evaluated using the training set and validated using the validation set. A correction curve and the Hosmer-Lemeshow test were used to evaluate the predictive performance of the radiomics model for the training and test sets.

RESULTS

Twenty-nine of 1234 radiomics parameters were screened as important factors for establishing the radiomics model. The training (area under the curve [AUC] = 0.925; 95% confidence interval [CI]: 0.885-0.966) and validation sets (AUC = 0.921; 95% CI: 0.854-0.989) showed that the CT radiomics signature, combined with STM, accurately predicted lung squamous cell carcinoma and lung adenocarcinoma. Moreover, the logistic regression model showed good performance based on the Hosmer-Lemeshow test in the training (P = 0.954) and test sets (P = 0.340). Good calibration curve consistency also indicated the good performance of the nomogram.

CONCLUSION

The combination of the CT radiomics signature and lung cancer STM performed well for the pathological classification of NSCLC. Compared with the radiomics signature method, the nomogram based on the radiomics signature and clinical factors had better performance for the differential diagnosis of NSCLC.

Radiomics and Machine Learning for prediction of two-year disease-specific mortality and KRAS mutation status in metastatic colorectal cancer

PURPOSE

Colorectal cancer is usually accompanied by liver metastases. The prediction of patient evolution is essential for the choice of the appropriate therapy. The aim of this study is to develop and evaluate machine learning models to predict KRAS gene mutations and 2-year disease-specific mortality from medical images.

METHODS

Clinical and follow-up information was collected from patients with metastatic colorectal cancer who had undergone computed tomography prior to liver resection. The dominant liver lesion was segmented in each scan and radiomic features were extracted from the volumes of interest. The 65% of the cases were employed to perform feature selection and to train machine learning algorithms through cross-validation. The best performing models were assembled and evaluated in the remaining cases of the cohort.

RESULTS

For the mortality model development, 101 cases were used as training set (64 alive, 37 deceased) and 35 as test set (22 alive, 13 deceased); while for KRAS mutation models, 55 cases were used for training (31 wild-type, 24 mutated) and 30 for testing (17 wild-type, 13 mutated). The ensemble of top performing models resulted in an area under the receiver operating characteristic curve of 0.878 for mortality and 0.905 for KRAS prediction.

CONCLUSIONS

Predicting the prognosis of patients with metastatic colorectal cancer is useful for making timely decisions about the best treatment options. This study presents a noninvasive method based on quantitative analysis of baseline images to identify factors influencing patient outcomes, with the aim of incorporating these tools as support systems.

A CT-based radiomics approach to predict immediate response of radiofrequency ablation in colorectal cancer lung metastases

Objectives

To objectively and accurately assess the immediate efficacy of radiofrequency ablation (RFA) on colorectal cancer (CRC) lung metastases, the novel multimodal data fusion model based on radiomics features and clinical variables was developed.

Methods

This case-control single-center retrospective study included 479 lung metastases treated with RFA in 198 CRC patients. Clinical and radiological data before and intraoperative computed tomography (CT) scans were retrieved. The relative radiomics features were extracted from pre- and immediate post-RFA CT scans by maximum relevance and minimum redundancy algorithm (MRMRA). The Gaussian mixture model (GMM) was used to divide the data of the training dataset and testing dataset. In the process of modeling in the training set, radiomics model, clinical model and fusion model were built based on a random forest classifier. Finally, verification was carried out on an independent test dataset. The receiver operating characteristic curves (ROC) were drawn based on the obtained predicted scores, and the corresponding area under ROC curve (AUC), accuracy, sensitivity, and specificity were calculated and compared.

Results

Among the 479 pulmonary metastases, 379 had complete response (CR) ablation and 100 had incomplete response ablation. Three hundred eighty-six lesions were selected to construct a training dataset and 93 lesions to construct a testing dataset. The multivariate logistic regression analysis revealed cancer antigen 19-9 (CA19-9, p<0.001) and the location of the metastases (p< 0.05) as independent risk factors. Significant correlations were observed between complete ablation and 9 radiomics features. The best prediction performance was achieved with the proposed multimodal data fusion model integrating radiomic features and clinical variables with the highest accuracy (82.6%), AUC value (0.921), sensitivity (80.3%), and specificity (81.4%).

Conclusion

This novel multimodal data fusion model was demonstrated efficient for immediate efficacy evaluation after RFA for CRC lung metastases, which could benefit necessary complementary treatment.

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.

Predicting recurrence risks in lung cancer patients using multimodal radiomics and random survival forests

Purpose

We developed a model integrating multimodal quantitative imaging features from tumor and nontumor regions, qualitative features, and clinical data to improve the risk stratification of patients with resectable non-small cell lung cancer (NSCLC).

Approach

We retrospectively analyzed 135 patients [mean age, 69 years (43 to 87, range); 100 male patients and 35 female patients] with NSCLC who underwent upfront surgical resection between 2008 and 2012. The tumor and peritumoral regions on both preoperative CT and FDG PET-CT and the vertebral bodies L3 to L5 on FDG PET were segmented to assess the tumor and bone marrow uptake, respectively. Radiomic features were extracted and combined with clinical and CT qualitative features. A random survival forest model was developed using the top-performing features to predict the time to recurrence/progression in the training cohort ( n = 101 ), validated in the testing cohort ( n = 34 ) using the concordance, and compared with a stage-only model. Patients were stratified into high- and low-risks of recurrence/progression using Kaplan-Meier analysis.

Results

The model, consisting of stage, three wavelet texture features, and three wavelet first-order features, achieved a concordance of 0.78 and 0.76 in the training and testing cohorts, respectively, significantly outperforming the baseline stage-only model results of 0.67 ( p < 0.005 ) and 0.60 ( p = 0.008 ), respectively. Patients at high- and low-risks of recurrence/progression were significantly stratified in both the training ( p < 0.005 ) and the testing ( p = 0.03 ) cohorts.

Conclusions

Our radiomic model, consisting of stage and tumor, peritumoral, and bone marrow features from CT and FDG PET-CT significantly stratified patients into low- and high-risk of recurrence/progression.

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

AIM

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

MATERIALS AND METHODS

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

RESULTS

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

CONCLUSIONS

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

Quantifying lung cancer heterogeneity using novel CT features: a cross-institute study

Background

Radiomics-based image metrics are not used in the clinic despite the rapidly growing literature. We selected eight promising radiomic features and validated their value in decoding lung cancer heterogeneity.

Methods

CT images of 236 lung cancer patients were obtained from three different institutes, whereupon radiomic features were extracted according to a standardized procedure. The predictive value for patient long-term prognosis and association with routinely used semantic, genetic (e.g., epidermal growth factor receptor (EGFR)), and histopathological cancer profiles were validated. Feature measurement reproducibility was assessed.

Results

All eight selected features were robust across repeat scans (intraclass coefficient range: 0.81–0.99), and were associated with at least one of the cancer profiles: prognostic, semantic, genetic, and histopathological. For instance, “kurtosis” had a high predictive value of early death (AUC at first year: 0.70–0.75 in two independent cohorts), negative association with histopathological grade (Spearman’s r: − 0.30), and altered expression levels regarding EGFR mutation and semantic characteristics (solid intensity, spiculated shape, juxtapleural location, and pleura tag; all p < 0.05). Combined as a radiomic score, the features had a higher area under curve for predicting 5-year survival (train: 0.855, test: 0.780, external validation: 0.760) than routine characteristics (0.733, 0.622, 0.613, respectively), and a better capability in patient death risk stratification (hazard ratio: 5.828, 95% confidence interval: 2.915–11.561) than histopathological staging and grading.

Conclusions

We highlighted the clinical value of radiomic features. Following confirmation, these features may change the way in which we approach CT imaging and improve the individualized care of lung cancer patients.

A Comparative and Summative Study of Radiomics-based Overall Survival Prediction in Glioblastoma Patients

PURPOSE

This study aimed to assess different machine learning models based on radiomic features, Visually Accessible Rembrandt Images features and clinical characteristics in overall survival prediction of glioblastoma and to identify the reproducible features.

MATERIALS AND METHODS

Patients with preoperative magnetic resonance scans were allocated into 3 data sets. The Least Absolute Shrinkage and Selection Operator was used for feature selection. The prediction models were built by random survival forest (RSF) and Cox regression. C-index and integrated Brier scores were calculated to compare model performances.

RESULTS

Patients with cortical involvement had shorter survival times in the training set (P = 0.006). Random survival forest showed higher C-index than Cox, and the RSF model based on the radiomic features was the best one (testing set: C-index = 0.935 ± 0.023). Ten reproducible radiomic features were summarized.

CONCLUSIONS

The RSF model based on radiomic features had promising potential in predicting overall survival of glioblastoma. Ten reproducible features were identified.

Outcome Prediction at Patient Level Derived from Pre-Treatment 18F-FDG PET Due to Machine Learning in Metastatic Melanoma Treated with Anti-PD1 Treatment

(1) Background: As outcome of patients with metastatic melanoma treated with anti-PD1 immunotherapy can vary in success, predictors are needed. We aimed to predict at the patients’ levels, overall survival (OS) and progression-free survival (PFS) after one year of immunotherapy, based on their pre-treatment 18F-FDG PET; (2) Methods: Fifty-six metastatic melanoma patients—without prior systemic treatment—were retrospectively included. Forty-five 18F-FDG PET-based radiomic features were computed and the top five features associated with the patient’s outcome were selected. The analyzed machine learning classifiers were random forest (RF), neural network, naive Bayes, logistic regression and support vector machine. The receiver operating characteristic curve was used to compare model performances, which were validated by cross-validation; (3) Results: The RF model obtained the best performance after validation to predict OS and PFS and presented AUC, sensitivities and specificities (IC95%) of 0.87 ± 0.1, 0.79 ± 0.11 and 0.95 ± 0.06 for OS and 0.9 ± 0.07, 0.88 ± 0.09 and 0.91 ± 0.08 for PFS, respectively. (4) Conclusion: A RF classifier, based on pretreatment 18F-FDG PET radiomic features may be useful for predicting the survival status for melanoma patients, after one year of a first line systemic treatment by immunotherapy.

Learning-based Cancer Treatment Outcome Prognosis using Multimodal Biomarkers

Predicting early in treatment whether a tumor is likely to be responsive is a difficult yet important task to support clinical decision-making. Studies have shown that multimodal biomarkers could provide complementary information and lead to more accurate treatment outcome prognosis than unimodal biomarkers. However, the prognosis accuracy could be affected by multimodal data heterogeneity and incompleteness. The small-sized and imbalance datasets also bring additional challenges for training a designed prognosis model. In this study, a modular framework employing multimodal biomarkers for cancer treatment outcome prediction was proposed. It includes four modules of synthetic data generation, deep feature extraction, multimodal feature fusion, and classification to address the challenges described above. The feasibility and advantages of the designed framework were demonstrated through an example study, in which the goal was to stratify oropharyngeal squamous cell carcinoma (OPSCC) patients with low- and high-risks of treatment failures by use of positron emission tomography (PET) image data and microRNA (miRNA) biomarkers. The superior prognosis performance and the comparison with other methods demonstrated the efficiency of the proposed framework and its ability of enabling seamless integration, validation and comparison of various algorithms in each module of the framework. The limitation and future work was discussed as well.

PET/MR fusion texture analysis for the clinical outcome prediction in soft-tissue sarcoma

BACKGROUND

Various fusion strategies (feature-level fusion, matrix-level fusion, and image-level fusion) were used to fuse PET and MR images, which might lead to different feature values and classification performance. The purpose of this study was to measure the classification capability of features extracted using various PET/MR fusion methods in a dataset of soft-tissue sarcoma (STS).

METHODS

The retrospective dataset included 51 patients with histologically proven STS. All patients had pre-treatment PET and MR images. The image-level fusion was conducted using discrete wavelet transformation (DWT). During the DWT process, the MR weight was set as 0.1, 0.2, 0.3, 0.4, …, 0.9. And the corresponding PET weight was set as 1- (MR weight). The fused PET/MR images was generated using the inverse DWT. The matrix-level fusion was conducted by fusing the feature calculation matrix during the feature extracting process. The feature-level fusion was conducted by concatenating and averaging the features. We measured the predictive performance of features using univariate analysis and multivariable analysis. The univariate analysis included the Mann-Whitney U test and receiver operating characteristic (ROC) analysis. The multivariable analysis was used to develop the signatures by jointing the maximum relevance minimum redundancy method and multivariable logistic regression. The area under the ROC curve (AUC) value was calculated to evaluate the classification performance.

RESULTS

By using the univariate analysis, the features extracted using image-level fusion method showed the optimal classification performance. For the multivariable analysis, the signatures developed using the image-level fusion-based features showed the best performance. For the T1/PET image-level fusion, the signature developed using the MR weight of 0.1 showed the optimal performance (0.9524(95% confidence interval (CI), 0.8413-0.9999)). For the T2/PET image-level fusion, the signature developed using the MR weight of 0.3 showed the optimal performance (0.9048(95%CI, 0.7356-0.9999)).

CONCLUSIONS

For the fusion of PET/MR images in patients with STS, the signatures developed using the image-level fusion-based features showed the optimal classification performance than the signatures developed using the feature-level fusion and matrix-level fusion-based features, as well as the single modality features. The image-level fusion method was more recommended to fuse PET/MR images in future radiomics studies.

Interpretable machine learning for predicting pathologic complete response in patients treated with chemoradiation therapy for rectal adenocarcinoma

Purpose

Pathologic complete response (pCR) is a critical factor in determining whether patients with rectal cancer (RC) should have surgery after neoadjuvant chemoradiotherapy (nCRT). Currently, a pathologist's histological analysis of surgical specimens is necessary for a reliable assessment of pCR. Machine learning (ML) algorithms have the potential to be a non-invasive way for identifying appropriate candidates for non-operative therapy. However, these ML models' interpretability remains challenging. We propose using explainable boosting machine (EBM) to predict the pCR of RC patients following nCRT.

Methods

A total of 296 features were extracted, including clinical parameters (CPs), dose-volume histogram (DVH) parameters from gross tumor volume (GTV) and organs-at-risk, and radiomics (R) and dosiomics (D) features from GTV. R and D features were subcategorized into shape (S), first-order (L1), second-order (L2), and higher-order (L3) local texture features. Multi-view analysis was employed to determine the best set of input feature categories. Boruta was used to select all-relevant features for each input dataset. ML models were trained on 180 cases from our institution, with 37 cases from RTOG 0822 clinical trial serving as the independent dataset for model validation. The performance of EBM in predicting pCR on the test dataset was evaluated using ROC AUC and compared with that of three state-of-the-art black-box models: extreme gradient boosting (XGB), random forest (RF) and support vector machine (SVM). The predictions of all black-box models were interpreted using Shapley additive explanations.

Results

The best input feature categories were CP+DVH+S+R_L1+R_L2 for all models, from which Boruta-selected features enabled the EBM, XGB, RF, and SVM models to attain the AUCs of 0.820, 0.828, 0.828, and 0.774, respectively. Although EBM did not achieve the best performance, it provided the best capability for identifying critical turning points in response scores at distinct feature values, revealing that the bladder with maximum dose >50 Gy, and the tumor with maximum2DDiameterColumn >80 mm, elongation <0.55, leastAxisLength >50 mm and lower variance of CT intensities were associated with unfavorable outcomes.

Conclusions

EBM has the potential to enhance the physician's ability to evaluate an ML-based prediction of pCR and has implications for selecting patients for a "watchful waiting" strategy to RC therapy.

Improving the Subtype Classification of Non-small Cell Lung Cancer by Elastic Deformation Based Machine Learning

Non-invasive image-based machine learning models have been used to classify subtypes of non-small cell lung cancer (NSCLC). However, the classification performance is limited by the dataset size, because insufficient data cannot fully represent the characteristics of the tumor lesions. In this work, a data augmentation method named elastic deformation is proposed to artificially enlarge the image dataset of NSCLC patients with two subtypes (squamous cell carcinoma and large cell carcinoma) of 3158 images. Elastic deformation effectively expanded the dataset by generating new images, in which tumor lesions go through elastic shape transformation. To evaluate the proposed method, two classification models were trained on the original and augmented dataset, respectively. Using augmented dataset for training significantly increased classification metrics including area under the curve (AUC) values of receiver operating characteristics (ROC) curves, accuracy, sensitivity, specificity, and f1-score, thus improved the NSCLC subtype classification performance. These results suggest that elastic deformation could be an effective data augmentation method for NSCLC tumor lesion images, and building classification models with the help of elastic deformation has the potential to serve for clinical lung cancer diagnosis and treatment design.

Prognostic Value of Pre-Treatment CT Radiomics and Clinical Factors for the Overall Survival of Advanced (IIIB-IV) Lung Adenocarcinoma Patients

Purpose

The purpose of this study was to investigate the prognostic value of pre-treatment CT radiomics and clinical factors for the overall survival (OS) of advanced (IIIB–IV) lung adenocarcinoma patients.

Methods

This study involved 165 patients with advanced lung adenocarcinoma. The Lasso–Cox regression model was used for feature selection and radiomics signature building. Then a clinical model was built based on clinical factors; a combined model in the form of nomogram was constructed with both clinical factors and the radiomics signature. Harrell’s concordance index (C-Index) and Receiver operating characteristic (ROC) curves at cut-off time points of 1-, 2-, and 3- year were used to estimate and compare the predictive ability of all three models. Finally, the discriminatory ability and calibration of the nomogram were analyzed.

Results

Thirteen significant features were selected to build the radiomics signature whose C-indexes were 0.746 (95% CI, 0.699 to 0.792) in the training cohort and 0.677 (95% CI, 0.597 to 0.766) in the validation cohort. The C-indexes of combined model achieved 0.799 (95% CI, 0.757 to 0.84) in the training cohort and 0.733 (95% CI, 0.656 to 0.81) in the validation cohort, which outperformed the clinical model and radiomics signature. Moreover, the areas under the curve (AUCs) of the radiomic signature for 2-year prediction was superior to that of the clinical model. The combined model had the best AUCs for 2- and 3-year predictions.

Conclusions

Radiomic signatures and clinical factors have prognostic value for OS in advanced (IIIB–IV) lung adenocarcinoma patients. The optimal model should be selected according to different cut-off time points in clinical application.

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.

A CT-Based Radiomics Approach to Predict Nivolumab Response in Advanced Non-Small-Cell Lung Cancer

Purpose

This study aims to develop a CT-based radiomics model to predict clinical outcomes of advanced non-small-cell lung cancer (NSCLC) patients treated with nivolumab.

Methods

Forty-six stage IIIB/IV NSCLC patients without EGFR mutation or ALK rearrangement who received nivolumab were enrolled. After segmenting primary tumors depicting on the pre-anti-PD1 treatment CT images, 1,106 radiomics features were computed and extracted to decode the imaging phenotypes of these tumors. A L1-based feature selection method was applied to remove the redundant features and build an optimal feature pool. To predict the risk of progression-free survival (PFS) and overall survival (OS), the selected image features were used to train and test three machine-learning classifiers namely, support vector machine classifier, logistic regression classifier, and Gaussian Naïve Bayes classifier. Finally, the overall patients were stratified into high and low risk subgroups by using prediction scores obtained from three classifiers, and Kaplan–Meier survival analysis was conduct to evaluate the prognostic values of these patients.

Results

To predict the risk of PFS and OS, the average area under a receiver operating characteristic curve (AUC) value of three classifiers were 0.73 ± 0.07 and 0.61 ± 0.08, respectively; the corresponding average Harrell’s concordance indexes for three classifiers were 0.92 and 0.79. The average hazard ratios (HR) of three models for predicting PFS and OS were 6.22 and 3.54, which suggested the significant difference of the two subgroup’s PFS and OS (p<0.05).

Conclusion

The pre-treatment CT-based radiomics model provided a promising way to predict clinical outcomes for advanced NSCLC patients treated with nivolumab.

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases

PURPOSE

Predicting early local tumor progression after thermal ablation treatment for colorectal liver metastases patients is critical for the decision of subsequent follow-up and treatment. Radiomics features derived from medical images show great potential for prediction and prognosis. The aim is to develop and validate a machine learning radiomics model to predict local tumor progression based on the pre-ablation CT scan of colorectal liver metastases patients.

MATERIALS AND METHODS

Ninety patients with colorectal liver metastases (140 lesions) treated by ablation were included in the study and were randomly divided into a training (n = 63 patients/n = 94 lesions) and validation (n = 27 patients/n = 46 lesions) cohort. After manual lesion volume segmentation and preprocessing, 1593 radiomics features were extracted for each lesion. Three machine learning survival models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features to predict local tumor progression free survival. Feature reduction and machine learning modeling were performed and optimized with sequential model-based optimization.

RESULTS

Median follow-up was 24 months (range 6-115). Thirty-one (22%) lesions developed local tumor progression. The concordance index in the validation set to predict local tumor progression free survival was 0.78 (95% confidence interval [CI]: 0.77-0.79) for the radiomics model, 0.56 (95%CI: 0.55-0.57) for the clinical model and 0.79 (95%CI: 0.78-0.80) for the combined model.

CONCLUSION

A machine learning-based radiomics analysis of routine clinical CT imaging pre-ablation could act as a valuable biomarker model to predict local tumor progression with curative intent for colorectal liver metastases patients.

Preoperative prediction for lauren type of gastric cancer: A radiomics nomogram analysis based on CT images and clinical features

PURPOSE

To investigate feasibility of predicting Lauren type of gastric cancer based on CT radiomics nomogram before operation.

MATERIALS AND METHODS

The clinical data and pre-treatment CT images of 300 gastric cancer patients with Lauren intestinal or diffuse type confirmed by postoperative pathology were retrospectively analyzed, who were randomly divided into training set and testing set with a ratio of 2:1. Clinical features were compared between the two Lauren types in the training set and testing set, respectively. Gastric tumors on CT images were manually segmented using ITK-SNAP software, and radiomic features of the segmented tumors were extracted, filtered and minimized using the least absolute shrinkage and selection operator (LASSO) regression to select optimal features and develop radiomics signature. A nomogram was constructed with radiomic features and clinical characteristics to predict Lauren type of gastric cancer. Clinical model, radiomics signature model, and the nomogram model were compared using the receiver operating characteristic (ROC) curve analysis with area under the curve (AUC). The calibration curve was used to test the agreement between prediction probability and actual clinical findings, and the decision curve was performed to assess the clinical usage of the nomogram model.

RESULTS

In clinical features, Lauren type of gastric cancer relate to age and CT-N stage of patients (all p < 0.05). Radiomics signature was developed with the retained 10 radiomic features. The nomogram was constructed with the 2 clinical features and radiomics signature. Among 3 prediction models, performance of the nomogram was the best in predicting Lauren type of gastric cancer, with the respective AUC, accuracy, sensitivity and specificity of 0.864, 78.0%, 90.0%, 70.0%in the testing set. In addition, the calibration curve showed a good agreement between prediction probability and actual clinical findings (p > 0.05).

CONCLUSION

The nomogram combining radiomics signature and clinical features is a useful tool with the increased value to predict Lauren type of gastric cancer.

Technical Note: ROdiomiX: A validated software for radiomics analysis of medical images in radiation oncology

PURPOSE

This study introduces an in-house-designed software platform (ROdiomiX) for the radiomics analysis of medical images in radiation oncology. ROdiomiX is a MATLAB-based framework for the computation of radiomic features and feature aggregation techniques in compliance with the Image-Biomarker-Standardization-Initiative (IBSI) guidelines, which includes preprocessing protocols and quantitative benchmark results for analysis of computational phantom images.

METHODS AND MATERIALS

The ROdiomiX software system consists of a series of computation cores implemented on the basis of the guidelines proposed by the IBSI. It is capable of quantitative computation of the following 11 different feature categories: Local-Intensity, Intensity-Histogram, Intensity-Based-Statistical, Intensity-Volume-Histogram, Gray-Level-Co-occurrence, Gray-Level-Run-Length, Gray-Level-Size-Zone, Gray-Level-Distance-Zone, Neighborhood-Grey-Tone-Difference, Neighboring-Grey-Level-Dependence, and Morphological feature. ROdiomiX was validated against benchmark values for the IBSI 3D digital phantom, as well as one designed in-house (HFH). The intraclass correlation coefficient (ICC) for estimating the degree of absolute agreement between ROdiomiX computation and benchmark values for different features at the 95% confidence level (CL) was used for comparison.

RESULTS

Among the 11 feature categories with 149 total features including 10 different feature aggregation methods (following the IBSI guidelines), the percent difference between absolute feature values computed by the ROdiomiX software and benchmark values reported for IBSI and HFH digital phantoms were 0.14% + 0.43% and 0.11% + 0.27%, respectively. The ICC values were >0.997 for all ten feature categories for both the IBSI and HFH digital phantoms.

CONCLUSION

The authors successfully developed a platform for computation of quantitative radiomic features. The image preprocessing and computational software cores were designed following the procedures specified by the IBSI. Benchmarking testing was in excellent agreement against the IBSI- and HFH-designed computational phantoms.

Radiomics as a personalized medicine tool in lung cancer: Separating the hope from the hype

Radiomics has become a popular image analysis method in the last few years. Its key hypothesis is that medical images harbor biological, prognostic and predictive information that is not revealed upon visual inspection. In contrast to previous work with a priori defined imaging biomarkers, radiomics instead calculates image features at scale and uses statistical methods to identify those most strongly associated to outcome. This builds on years of research into computer aided diagnosis and pattern recognition. While the potential of radiomics to aid personalized medicine is widely recognized, several technical limitations exist which hinder biomarker translation. Aspects of the radiomic workflow lack repeatability or reproducibility under particular circumstances, which is a key requirement for the translation of imaging biomarkers into clinical practice. One of the most commonly studied uses of radiomics is for personalized medicine applications in Non-Small Cell Lung Cancer (NSCLC). In this review, we summarize reported methodological limitations in CT based radiomic analyses together with suggested solutions. We then evaluate the current NSCLC radiomics literature to assess the risk associated with accepting the published conclusions with respect to these limitations. We review different complementary scoring systems and initiatives that can be used to critically appraise data from radiomics studies. Wider awareness should improve the quality of ongoing and future radiomics studies and advance their potential as clinically relevant biomarkers for personalized medicine in patients with NSCLC.

Prediction of Non-small Cell Lung Cancer Histology by a Deep Ensemble of Convolutional and Bidirectional Recurrent Neural Network

Histology subtype prediction is a major task for grading non-small cell lung cancer (NSCLC) tumors. Invasive methods such as biopsy often lack in tumor sample, and as a result radiologists or oncologists find it difficult to detect proper histology of NSCLC tumors. The non-invasive methods such as machine learning may play a useful role to predict NSCLC histology by using medical image biomarkers. Few attempts have so far been made to predict NSCLC histology by considering all the major subtypes. The present study aimed to develop a more accurate deep learning model by clubbing convolutional and bidirectional recurrent neural networks. The NSCLC Radiogenomics dataset having 211 subjects was used in the study. Ten best models found during experimentation were averaged to form an ensemble. The model ensemble was executed with 10-fold repeated stratified cross-validation, and the results got were tested with metrics like accuracy, recall, precision, F1-score, Cohen's kappa, and ROC-AUC score. The accuracy of the ensemble model showed considerable improvement over the best model found with the single model. The proposed model may help significantly in the automated prognosis of NSCLC and other types of cancers.

Overall survival prediction of non-small cell lung cancer by integrating microarray and clinical data with deep learning

Non-small cell lung cancer (NSCLC) is one of the most common lung cancers worldwide. Accurate prognostic stratification of NSCLC can become an important clinical reference when designing therapeutic strategies for cancer patients. With this clinical application in mind, we developed a deep neural network (DNN) combining heterogeneous data sources of gene expression and clinical data to accurately predict the overall survival of NSCLC patients. Based on microarray data from a cohort set (614 patients), seven well-known NSCLC biomarkers were used to group patients into biomarker- and biomarker+ subgroups. Then, by using a systems biology approach, prognosis relevance values (PRV) were then calculated to select eight additional novel prognostic gene biomarkers. Finally, the combined 15 biomarkers along with clinical data were then used to develop an integrative DNN via bimodal learning to predict the 5-year survival status of NSCLC patients with tremendously high accuracy (AUC: 0.8163, accuracy: 75.44%). Using the capability of deep learning, we believe that our prediction can be a promising index that helps oncologists and physicians develop personalized therapy and build the foundation of precision medicine in the future.

CT derived radiomic score for predicting the added benefit of adjuvant chemotherapy following surgery in stage I, II resectable non-small cell lung cancer: a retrospective multicohort study for outcome prediction

BACKGROUND

Use of adjuvant chemotherapy in patients with early-stage lung cancer is controversial because no definite biomarker exists to identify patients who would receive added benefit from it. We aimed to develop and validate a quantitative radiomic risk score (QuRiS) and associated nomogram (QuRNom) for early-stage non-small cell lung cancer (NSCLC) that is prognostic of disease-free survival and predictive of the added benefit of adjuvant chemotherapy following surgery.

METHODS

We did a retrospective multicohort study of individuals with early-stage NSCLC (stage I and II) who either received surgery alone or surgery plus adjuvant chemotherapy. We selected patients for whom we had available pre-treatment diagnostic CT scans and corresponding survival information. We used radiomic texture features derived from within and outside the primary lung nodule on chest CT scans of patients from the Cleveland Clinic Foundation (Cleveland, OH, USA; cohort D₁) to develop QuRiS. A least absolute shrinkage and selection operator-Cox regularisation model was used for data dimension reduction, feature selection, and QuRiS construction. QuRiS was independently validated on a cohort of patients from the University of Pennsylvania (Philadephia, PA, USA; cohort D₂) and a cohort of patients whose CT scans were derived from The Cancer Imaging Archive (cohort D₃). QuRNom was constructed by integrating QuRiS with tumour and node descriptors (according to the tumour, node, metastasis staging system) and lymphovascular invasion. The primary endpoint of the study was the assessment of the performance of QuRiS and QuRNom in predicting disease-free survival. The added benefit of adjuvant chemotherapy estimated using QuRiS and QuRNom was validated by comparing patients who received adjuvant chemotherapy versus patients who underwent surgery alone in cohorts D₁-D₃.

FINDINGS

We included: 329 patients in cohort D₁ (73 [22%] had surgery plus adjuvant chemotherapy and 256 (78%) had surgery alone); 114 patients in cohort D₂ (33 [29%] had surgery plus adjuvant chemotherapy and 81 (71%) had surgery alone); and 82 patients in cohort D₃ (24 [29%] had surgery plus adjuvant chemotherapy and 58 (71%) had surgery alone). QuRiS comprised three intratumoral and 10 peritumoral CT-radiomic features and was found to be significantly associated with disease-free survival (ie, prognostic validation of QuRiS; hazard ratio for predicted high-risk vs predicted low-risk groups 1·56, 95% CI 1·08-2·23, p=0·016 for cohort D₁; 2·66, 1·24-5·68, p=0·011 for cohort D₂; and 2·67, 1·39-5·11, p=0·0029 for cohort D₃). To validate the predictive performance of QuRiS, patients were partitioned into three risk groups (high, intermediate, and low risk) on the basis of their corresponding QuRiS. Patients in the high-risk group were observed to have significantly longer survival with adjuvant chemotherapy than patients who underwent surgery alone (0·27, 0·08-0·95, p=0·042, for cohort D₁; 0·08, 0·01-0·42, p=0·0029, for cohorts D₂ and D₃ combined). As concerns QuRNom, the nomogram-estimated survival benefit was predictive of the actual efficacy of adjuvant chemotherapy (0·25, 0·12-0·55, p<0·0001, for cohort D₁; 0·13, <0·01-0·99, p=0·0019 for cohort D₃).

INTERPRETATION

QuRiS and QuRNom were validated as being prognostic of disease-free survival and predictive of the added benefit of adjuvant chemotherapy, especially in clinically defined low-risk groups. Since QuRiS is based on routine chest CT imaging, with additional multisite independent validation it could potentially be employed for decision management in non-invasive treatment of resectable lung cancer.

FUNDING

National Cancer Institute of the US National Institutes of Health, National Center for Research Resources, US Department of Veterans Affairs Biomedical Laboratory Research and Development Service, Department of Defence, National Institute of Diabetes and Digestive and Kidney Diseases, Wallace H Coulter Foundation, Case Western Reserve University, and Dana Foundation.

Computed Tomography-Based Radiomic Features Could Potentially Predict Microsatellite Instability Status in Stage II Colorectal Cancer: A Preliminary Study

RATIONALE AND OBJECTIVES

To investigate whether quantitative radiomics features extracted from computed tomography (CT) can predict microsatellite instability (MSI) status in an Asian cohort of patients with stage Ⅱ colorectal cancer (CRC).

MATERIALS AND METHODS

This retrospective study was approved by our institutional review board, and the informed consent requirement was waived. From March 2016 to March 2018, 119 Chinese patients with pathologically confirmed stage Ⅱ CRC, available MSI status, and preoperative contrast-enhanced CT images were included in this study. Clinical and pathological information was obtained from the institutional database. The radiomics features were extracted from portal venous-phase CT images of segmented volumes of each entire primary tumor by using Matrix Laboratory (MATLAB), and radiomics signatures were generated using the least absolute shrinkage and selection operator logistic regression model. The minority group was balanced via synthetic minority over-sampling technique method. The association between the clinicopathologic characteristics and MSI status was assessed using Student's t test, Chi-square, or Fisher's exact test. The predictive efficacy of MSI status using radiomics features, clinical factors (including age, gender, CT-reported tumor location, differentiation degree of tumor, smoking history, hypertension history, family history of cancer, diabetes history, level of the Ki-67 expression, and laboratory analysis) and the combined models were evaluated, respectively. Predictive performance was evaluated by the area under receiver operating characteristic curve, accuracy, sensitivity, and specificity.

RESULTS

MSI status was significantly associated with tumor location (p = 0.043); differentiation degree of tumor (p < 0.0001), hypertension history (p = 0.012), and the level of the Ki-67 expression (p = 0.015). Six radiomics features and 11 clinical characteristics were selected for predicting MSI status. The model that used the combination of clinical factors and radiomics features achieved the overall best performance than using either of the two features alone, yielding the area under the curve, sensitivity, and specificity of 0.752, 0.663, 0.841 for the combined model, 0.598, 0.371, 0.825 for clinical factors alone, and 0.688, 0.517, 0.858 for radiomics features alone, respectively.

CONCLUSION

CT-based radiomic features of stage Ⅱ CRC are associated with MSI status. Combining analysis of clinical features and CT features could improve predictive efficacy and could potentially select the patients for individualized therapy noninvasively.

CT radiomics and PET radiomics: ready for clinical implementation?

INTRODUCTION

Today, rapid technical and clinical developments result in an increasing number of treatment options for oncological diseases. Thus, decision support systems are needed to offer the right treatment to the right patient. Imaging biomarkers hold great promise in patient-individual treatment guidance. Routinely performed for diagnosis and staging, imaging datasets are expected to hold more information than used in the clinical practice. Radiomics describes the extraction of a large number of meaningful quantitative features from medical images, such as computed tomography (CT) and positron emission tomography (PET). Due to the non-invasive nature and ability to capture 3D image-based heterogeneity, radiomic features are potential surrogate markers of the cancer phenotype. Several radiomic studies are published per day, owing to encouraging results of many radiomics-based patient outcome models. Despite this comparably large number of studies, radiomics is mainly studied in proof of principle concept. Hence, a translation of radiomics from a hot topic research field into an essential clinical decision-making tool is lacking, but of high clinical interest.

EVIDENCE ACQUISITION

Herein, we present a literature review addressing the clinical evidence of CT and PET radiomics. An extensive literature review was conducted in PubMed, including papers on robustness and clinical applications.

EVIDENCE SYNTHESIS

We summarize image-modality related influences on the robustness of radiomic features and provide an overview of clinical evidence reported in the literature. Today, more evidence has been provided for CT imaging, however, PET imaging offers the promise of direct imaging of biological processes and functions. We provide a summary of future research directions, which needs to be addressed in order to successfully introduce radiomics into clinical medicine. In comparison to CT, more focus should be directed towards harmonization of PET acquisition and reconstruction protocols, which is important for transferable modelling.

CONCLUSIONS

Both CT and PET radiomics are promising pre-treatment and intra-treatment biomarkers for outcome prediction. Most studies are performed in retrospective setting, however their validation in prospective data collections is ongoing.

Pathologic response after modern radiotherapy for non-small cell lung cancer

In non-small cell lung cancer (NSCLC), pathologic complete response (pCR) following radiotherapy treatment has been shown to be an independent prognostic factor for long-term survival, progression-free survival and locoregional control. PCR is considered a surrogate to therapeutic efficacy, years before survival data are available, and therefore can be used to guide treatment plans and additional therapeutic interventions post-surgical resection. Given the extensive fibrotic changes induced by radiotherapy in the lung, radiological assessment of response can potentially misrepresent pathologic response. The optimal timing for assessment of pathologic response after conventionally fractionated radiotherapy and stereotactic ablative radiotherapy (SABR) remains poorly understood. In this review, we summarize recent literature on pathologic response after radiotherapy for early stage and locally advanced NSCLC, we discuss current controversies around radiobiological considerations, and we present upcoming trials that will provide insight into current knowledge gaps.

Radiomics study for differentiating gastric cancer from gastric stromal tumor based on contrast-enhanced CT images

PURPOSE

To test the feasibility of differentiate gastric cancer from gastric stromal tumor using a radiomics study based on contrast-enhanced CT images.

MATERIALS AND METHODS

The contrast-enhanced CT image data of 60 patients with gastric cancer and 40 patients with gastric stromal tumor confirmed by postoperative pathology were retrospectively analyzed. First, CT images were read by two senior radiologists to acquire subjective CT signs model, including perigastric fatty infiltration, perigastric enlarged lymph nodes, the enhancement and growth modes of gastric tumors. Second, the manual segmentation of gastric tumors from the CT images was performed by the two radiologists to extract radiomics features via ITK-SNAP software, and to construct radiomics signature model. Finally, a diagnostic model integrated with subjective CT signs and radiomics signatures was constructed. The diagnostic efficacy of three models in differentiating gastric cancer from gastric stromal tumor was compared by using receiver operating characteristic curves (ROC).

RESULTS

There are statistically significant differences between the gastric cancer and gastric stromal tumor in the perigastric enlarged lymph nodes, growth mode and radiomics signature (p < 0.05). The area under ROC curve (AUC), sensitivity and accuracy of subjective CT signs model were the lowest among the three models. While the combined model yields the highest AUC value (0.903), specificity (93.33%) and accuracy (86.00%) among the three models (p = 0.03).

CONCLUSION

The diagnostic model integrating subjective CT signs and radiomics signature can improve the diagnostic accuracy of gastric tumors.