Cardiac SPECT radiomic features repeatability and reproducibility: A multi-scanner phantom study

Radiomics-Based Computed Tomography Urogram Approach for the Prediction of Survival and Recurrence in Upper Urinary Tract Urothelial Carcinoma

Upper tract urothelial carcinoma (UTUC) is a rare and aggressive malignancy with a poor prognosis. The accurate prediction of survival and recurrence in UTUC is crucial for effective risk stratification and guiding therapeutic decisions. Models combining radiomics and clinicopathological data features derived from computed tomographic urograms (CTUs) can be a way to predict survival and recurrence in UTUC. Thus, preoperative CTUs and clinical data were analyzed from 106 UTUC patients who underwent radical nephroureterectomy. Radiomics features were extracted from segmented tumors, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was used to select the most relevant features. Multivariable Cox models combining radiomics features and clinical factors were developed to predict the survival and recurrence. Harrell's concordance index (C-index) was applied to evaluate the performance and survival distribution analyses were assessed by a Kaplan-Meier analysis. The significant outcome predictors were identified by multivariable Cox models. The combined model achieved a superior predictive accuracy (C-index: 0.73) and higher recurrence prediction (C-index: 0.84). The Kaplan-Meier analysis showed significant differences in the survival (p < 0.0001) and recurrence (p < 0.002) probabilities for the combined datasets. The CTU-based radiomics models effectively predicted survival and recurrence in the UTUC patients, and enhanced the prognostic performance by combining radiomics features with clinical factors.

Radiomics Nomogram Derived from Gated Myocardial Perfusion SPECT for Identifying Ischemic Cardiomyopathy

Personalized management involving heart failure (HF) etiology is crucial for better prognoses. We aim to evaluate the utility of a radiomics nomogram based on gated myocardial perfusion imaging (GMPI) in distinguishing ischemic from non-ischemic origins of HF. A total of 172 heart failure patients with reduced left ventricular ejection fraction (HFrEF) who underwent GMPI scan were divided into training (n = 122) and validation sets (n = 50) based on chronological order of scans. Radiomics features were extracted from the resting GMPI. Four machine learning algorithms were used to construct radiomics models, and the model with the best performances were selected to calculate the Radscore. A radiomics nomogram was constructed based on the Radscore and independent clinical factors. Finally, the model performance was validated using operating characteristic curves, calibration curve, decision curve analysis, integrated discrimination improvement values (IDI), and the net reclassification index (NRI). Three optimal radiomics features were used to build a radiomics model. Total perfusion deficit (TPD) was identified as the independent factors of conventional GMPI metrics for building the GMPI model. In the validation set, the radiomics nomogram integrating the Radscore, age, systolic blood pressure, and TPD significantly outperformed the GMPI model in distinguishing ischemic cardiomyopathy (ICM) from non-ischemic cardiomyopathy (NICM) (AUC 0.853 vs. 0.707, p = 0.038). IDI analysis indicated that the nomogram improved diagnostic accuracy by 28.3% compared to the GMPI model in the validation set. By combining radiomics signatures with clinical indicators, we developed a GMPI-based radiomics nomogram that helps to identify the ischemic etiology of HFrEF.

Comparing various AI approaches to traditional quantitative assessment of the myocardial perfusion in [82Rb] PET for MACE prediction

Assessing the individual risk of Major Adverse Cardiac Events (MACE) is of major importance as cardiovascular diseases remain the leading cause of death worldwide. Quantitative Myocardial Perfusion Imaging (MPI) parameters such as stress Myocardial Blood Flow (sMBF) or Myocardial Flow Reserve (MFR) constitutes the gold standard for prognosis assessment. We propose a systematic investigation of the value of Artificial Intelligence (AI) to leverage [82 Rb] Silicon PhotoMultiplier (SiPM) PET MPI for MACE prediction. We establish a general pipeline for AI model validation to assess and compare the performance of global (i.e. average of the entire MPI signal), regional (17 segments), radiomics and Convolutional Neural Network (CNN) models leveraging various MPI signals on a dataset of 234 patients. Results showed that all regional AI models significantly outperformed the global model ( p < 0.001 ), where the best AUC of 73.9% (CI 72.5-75.3) was obtained with a CNN model. A regional AI model based on MBF averages from 17 segments fed to a Logistic Regression (LR) constituted an excellent trade-off between model simplicity and performance, achieving an AUC of 73.4% (CI 72.3-74.7). A radiomics model based on intensity features revealed that the global average was the least important feature when compared to other aggregations of the MPI signal over the myocardium. We conclude that AI models can allow better personalized prognosis assessment for MACE.

Machine learning based on SPECT/CT to differentiate bone metastasis and benign bone lesions in lung malignancy patients

BACKGROUND

Bone metastasis is a common event in lung cancer progression. Early diagnosis of lung malignant tumor with bone metastasis is crucial for selecting effective treatment strategies. However, 14.3% of patients are still difficult to diagnose after SPECT/CT examination.

PURPOSE

Machine learning analysis of [99mTc]-methylene diphosphate (99mTc-MDP) SPECT/CT scans to distinguish bone metastases from benign bone lesions in patients with lung cancer.

METHODS

One hundred forty-one patients (69 with bone metastases and 72 with benign bone lesions) were randomly assigned to the training group or testing group in a 7:3 ratio. Lesions were manually delineated using ITK-SNAP, and 944 radiomics features were extracted from SPECT and CT images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the radiomics features in the training set, and the single/bimodal radiomics models were established based on support vector machine (SVM). To further optimize the model, the best bimodal radiomics features were combined with clinical features to establish an integrated Radiomics-clinical model. The diagnostic performance of models was evaluated using receiver operating characteristic (ROC) curve and confusion matrix, and performance differences between models were evaluated using the Delong test.

RESULTS

The optimal radiomics model comprised of structural modality (CT) and metabolic modality (SPECT), with an area under curve (AUC) of 0.919 and 0.907 for the training and testing set, respectively. The integrated model, which combined SPECT, CT, and two clinical features, exhibited satisfactory differentiation in the training and testing set, with AUC of 0.939 and 0.925, respectively.

CONCLUSIONS

The machine learning can effectively differentiate between bone metastases and benign bone lesions. The Radiomics-clinical integrated model demonstrated the best performance.

Computed Tomography-derived intratumoral and peritumoral radiomics in predicting EGFR mutation in lung adenocarcinoma

OBJECTIVE

To investigate the value of Computed Tomography (CT) radiomics derived from different peritumoral volumes of interest (VOIs) in predicting epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients.

MATERIALS AND METHODS

A retrospective cohort of 779 patients who had pathologically confirmed lung adenocarcinoma were enrolled. 640 patients were randomly divided into a training set, a validation set, and an internal testing set (3:1:1), and the remaining 139 patients were defined as an external testing set. The intratumoral VOI (VOI_I) was manually delineated on the thin-slice CT images, and seven peritumoral VOIs (VOI_P) were automatically generated with 1, 2, 3, 4, 5, 10, and 15 mm expansion along the VOI_I. 1454 radiomic features were extracted from each VOI. The t-test, the least absolute shrinkage and selection operator (LASSO), and the minimum redundancy maximum relevance (mRMR) algorithm were used for feature selection, followed by the construction of radiomics models (VOI_I model, VOI_P model and combined model). The performance of the models were evaluated by the area under the curve (AUC).

RESULTS

399 patients were classified as EGFR mutant (EGFR+), while 380 were wild-type (EGFR-). In the training and validation sets, internal and external testing sets, VOI4 (intratumoral and peritumoral 4 mm) model achieved the best predictive performance, with AUCs of 0.877, 0.727, and 0.701, respectively, outperforming the VOI_I model (AUCs of 0.728, 0.698, and 0.653, respectively).

CONCLUSIONS

Radiomics extracted from peritumoral region can add extra value in predicting EGFR mutation status of lung adenocarcinoma patients, with the optimal peritumoral range of 4 mm.

Radiomics in Carotid Plaque: A Systematic Review and Radiomics Quality Score Assessment

Imaging modalities provide information on plaque morphology and vulnerability; however, they are operator dependent and miss a great deal of microscopic information. Recently, many radiomics models for carotid plaque that identify unstable plaques and predict cardiovascular outcomes have been proposed. This systematic review was aimed at assessing whether radiomics is a reliable and reproducible method for the clinical prediction of carotid plaque. A systematic search was conducted to identify studies published in PubMed and Cochrane library from January 1, 2001, to September 30, 2022. Both retrospective and prospective studies that developed and/or validated machine learning models based on radiomics data to classify or predict carotid plaques were included. The general characteristics of each included study were selected, and the methodological quality of radiomics reports and risk of bias were evaluated using the radiomics quality score (RQS) tool and Quality Assessment of Diagnostic Accuracy Studies-2, respectively. Two investigators independently reviewed each study, and the consensus data were used for analysis. A total of 2429 patients from 16 studies were included. The mean area under the curve of radiomics models for diagnostic or predictive performance of the included studies was 0.88 ± 0.02, with a range of 0.741-0.989. The mean RQS was 9.25 (standard deviation: 6.04), representing 25.7% of the possible maximum value of 36, whereas the lowest point was -2, and the highest score was 22. Radiomics models have revealed additional information on patients with carotid plaque, but with respect to methodological quality, radiomics reports are still in their infancy, and many hurdles need to be overcome.

Development and validation of a contrast-enhanced CT-based radiomics nomogram for differentiating mass-like thymic hyperplasia and low-risk thymoma

PURPOSE

To explore the efficiency of a contrast-enhanced CT-based radiomics nomogram integrated with radiomics signature and clinically independent predictors to distinguish mass-like thymic hyperplasia (ml-TH) from low-risk thymoma (LRT) preoperatively.

METHODS

135 Patients with histopathology confirmed ml-TH (n = 65) and LRT (n = 70) were randomly divided into training set (n = 94) and validation set (n = 41) at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used to obtain the optimal features. Based on the selected features, four machine learning models, support vector machine (SVM), logistic regression (LR), extreme gradient boosting (XGBOOST), and random forest (RF) were constructed. Multivariate logistic regression was used to establish a radiomics nomogram containing clinically independent predictors and radiomics signature. Receiver operating characteristic (ROC), DeLong test, and calibration curves were used to detect the performance of the radiomics nomogram in training set and validation set.

RESULTS

In the validation set, the area under the curve (AUC) value of LR (0.857; 95% CI: 0.741, 0.973) was the highest of the four machine learning models. Radiomics nomogram containing radiomics signature and clinically independent predictors (including age, shape, and net enhancement degree) had better calibration and identification in the training set (AUC: 0.959; 95% CI: 0.922, 0.996) and validation set (AUC: 0.895; 95% CI: 0.795, 0.996).

CONCLUSION

We constructed a contrast-enhanced CT-based radiomics nomogram containing clinically independent predictors and radiomics signature as a noninvasive preoperative prediction method to distinguish ml-TH from LRT. The radiomics nomogram we constructed has potential for preoperative clinical decision making.

Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study

This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models' evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process.

Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study

In this study, the ability of radiomics features extracted from myocardial perfusion imaging with SPECT (MPI-SPECT) was investigated for the prediction of ejection fraction (EF) post-percutaneous coronary intervention (PCI) treatment. A total of 52 patients who had undergone pre-PCI MPI-SPECT were enrolled in this study. After normalization of the images, features were extracted from the left ventricle, initially automatically segmented by k-means and active contour methods, and finally edited and approved by an expert radiologist. More than 1700 2D and 3D radiomics features were extracted from each patient's scan. A cross-combination of three feature selections and seven classifier methods was implemented. Three classes of no or dis-improvement (class 1), improved EF from 0 to 5% (class 2), and improved EF over 5% (class 3) were predicted by using tenfold cross-validation. Lastly, the models were evaluated based on accuracy, AUC, sensitivity, specificity, precision, and F-score. Neighborhood component analysis (NCA) selected the most predictive feature signatures, including Gabor, first-order, and NGTDM features. Among the classifiers, the best performance was achieved by the fine KNN classifier, which yielded mean accuracy, AUC, sensitivity, specificity, precision, and F-score of 0.84, 0.83, 0.75, 0.87, 0.78, and 0.76, respectively, in 100 iterations of classification, within the 52 patients with 10-fold cross-validation. The MPI-SPECT-based radiomic features are well suited for predicting post-revascularization EF and therefore provide a helpful approach for deciding on the most appropriate treatment.

Radiomics for the detection of diffusely impaired myocardial perfusion: A proof-of-concept study using 13N-ammonia positron emission tomography

AIM

The current proof-of-concept study investigates the value of radiomic features from normal 13N-ammonia positron emission tomography (PET) myocardial retention images to identify patients with reduced global myocardial flow reserve (MFR).

METHODS

Data from 100 patients with normal retention 13N-ammonia PET scans were divided into two groups, according to global MFR (i.e., < 2 and ≥ 2), as derived from quantitative PET analysis. We extracted radiomic features from retention images at each of five different gray-level (GL) discretization (8, 16, 32, 64, and 128 bins). Outcome independent and dependent feature selection and subsequent univariate and multivariate analyses was performed to identify image features predicting reduced global MFR.

RESULTS

A total of 475 radiomic features were extracted per patient. Outcome independent and dependent feature selection resulted in a remainder of 35 features. Discretization at 16 bins (GL16) yielded the highest number of significant predictors of reduced MFR and was chosen for the final analysis. GLRLM_GLNU was the most robust parameter and at a cut-off of 948 yielded an accuracy, sensitivity, specificity, negative and positive predictive value of 67%, 74%, 58%, 64%, and 69%, respectively, to detect diffusely impaired myocardial perfusion.

CONCLUSION

A single radiomic feature (GLRLM_GLNU) extracted from visually normal 13N-ammonia PET retention images independently predicts reduced global MFR with moderate accuracy. This concept could potentially be applied to other myocardial perfusion imaging modalities based purely on relative distribution patterns to allow for better detection of diffuse disease.

Radiomics Analysis of Breast Lesions in Combination with Coronal Plane of ABVS and Strain Elastography

Background

Breast cancer is the most common tumor globally. Automated Breast Volume Scanner (ABVS) and strain elastography (SE) can provide more useful breast information. The use of radiomics combined with ABVS and SE images to predict breast cancer has become a new focus. Therefore, this study developed and validated a radiomics analysis of breast lesions in combination with coronal plane of ABVS and SE to improve the differential diagnosis of benign and malignant breast diseases.

Patients and Methods

620 pathologically confirmed breast lesions from January 2017 to August 2021 were retrospectively analyzed and randomly divided into a training set (n=434) and a validation set (n=186). Radiomic features of the lesions were extracted from ABVS, B-ultrasound, and strain elastography (SE) images, respectively. These were then filtered by Gradient Boosted Decision Tree (GBDT) and multiple logistic regression. The ABVS model is based on coronal plane features for the breast, B+SE model is based on features of B-ultrasound and SE, and the multimodal model is based on features of three examinations. The evaluation of the predicted performance of the three models used the receiver operating characteristic (ROC) and decision curve analysis (DCA).

Results

The area under the curve, accuracy, specificity, and sensitivity of the multimodal model in the training set are 0.975 (95% CI:0.959-0.991),93.78%, 92.02%, and 96.49%, respectively, and 0.946 (95% CI:0.913 -0.978), 87.63%, 83.93%, and 93.24% in the validation set, respectively. The multimodal model outperformed the ABVS model and B+SE model in both the training (P < 0.001, P = 0.002, respectively) and validation sets (P < 0.001, P = 0.034, respectively).

Conclusion

Radiomics from the coronal plane of the breast lesion provide valuable information for identification. A multimodal model combination with radiomics from ABVS, B-ultrasound, and SE could improve the diagnostic efficacy of breast masses.

Myocardial Perfusion SPECT Imaging Radiomic Features and Machine Learning Algorithms for Cardiac Contractile Pattern Recognition

A U-shaped contraction pattern was shown to be associated with a better Cardiac resynchronization therapy (CRT) response. The main goal of this study is to automatically recognize left ventricular contractile patterns using machine learning algorithms trained on conventional quantitative features (ConQuaFea) and radiomic features extracted from Gated single-photon emission computed tomography myocardial perfusion imaging (GSPECT MPI). Among 98 patients with standard resting GSPECT MPI included in this study, 29 received CRT therapy and 69 did not (also had CRT inclusion criteria but did not receive treatment yet at the time of data collection, or refused treatment). A total of 69 non-CRT patients were employed for training, and the 29 were employed for testing. The models were built utilizing features from three distinct feature sets (ConQuaFea, radiomics, and ConQuaFea + radiomics (combined)), which were chosen using Recursive feature elimination (RFE) feature selection (FS), and then trained using seven different machine learning (ML) classifiers. In addition, CRT outcome prediction was assessed by different treatment inclusion criteria as the study's final phase. The MLP classifier had the highest performance among ConQuaFea models (AUC, SEN, SPE = 0.80, 0.85, 0.76). RF achieved the best performance in terms of AUC, SEN, and SPE with values of 0.65, 0.62, and 0.68, respectively, among radiomic models. GB and RF approaches achieved the best AUC, SEN, and SPE values of 0.78, 0.92, and 0.63 and 0.74, 0.93, and 0.56, respectively, among the combined models. A promising outcome was obtained when using radiomic and ConQuaFea from GSPECT MPI to detect left ventricular contractile patterns by machine learning.

Texture analysis of SPECT myocardial perfusion provides prognostic value for dilated cardiomyopathy

BACKGROUND

Texture analysis (TA) has demonstrated clinical values in extracting information, quantifying inhomogeneity, evaluating treatment outcomes, and predicting long-term prognosis for cardiac diseases. The aim of this study was to explore whether TA of SPECT myocardial perfusion could contribute to improving the prognosis of dilated cardiomyopathy (DCM) patients.

METHODS

Eighty-eight patients were recruited in our study between 2009 and 2020 who were diagnosed with DCM and underwent single-photon emission tomography myocardial perfusion imaging (SPECT MPI). Forty TA features were obtained from quantitative analysis of SPECT imaging in subjects with myocardial perfusion at rest. All patients were divided into two groups: the all-cause death group and the survival group. The prognostic value of texture parameters was assessed by Cox regression and Kaplan-Meier analysis.

RESULTS

Twenty-five all-cause deaths (28.4%) were observed during the follow-up (39.2±28.7 months). Compared with the survival group, NT-proBNP and total perfusion deficit (TPD) were higher and left ventricular ejection fraction (LVEF) was lower in the all-cause death group. In addition, 26 out of 40 texture parameters were significantly different between the two groups. Univariate Cox regression analysis revealed that NT-proBNP, LVEF, and 25 texture parameters were significantly associated with all-cause death. The multivariate Cox regression analysis showed that low gray-level emphasis (LGLE) (P = 0.010, HR = 4.698, 95% CI 1.457-15.145) and long-run low gray-level emphasis (LRLGE) (P =0.002, HR = 6.085, 95% CI 1.906-19.422) were independent predictors of the survival outcome. When added to clinical parameters, LVEF, TPD, and TA parameters, including LGLE and LRLGE, were incrementally associated with all-cause death (global chi-square statistic of 26.246 vs. 33.521; P = 0.028, global chi-square statistic of 26.246 vs. 34.711; P = 0.004).

CONCLUSION

TA based on gated SPECT MPI could discover independent prognostic predictors of all-cause death in medically treated patients with DCM. Moreover, TA parameters, including LGLE and LRLGE, independent of the total perfusion deficit of the cardiac myocardium, appeared to provide incremental prognostic value for DCM patients.

[18F]FDG-PET/CT radiomics and artificial intelligence in lung cancer: Technical aspects and potential clinical applications

Lung cancer is the second most common cancer and the leading cause of cancer-related death worldwide. Molecular imaging using [¹⁸F]fluorodeoxyglucose Positron Emission Tomography and/or Computed Tomography ([¹⁸F]FDG-PET/CT) plays an essential role in the diagnosis, evaluation of response to treatment, and prediction of outcomes. The images are evaluated using qualitative and conventional quantitative indices. However, there is far more information embedded in the images, which can be extracted by sophisticated algorithms. Recently, the concept of uncovering and analyzing the invisible data extracted from medical images, called radiomics, is gaining more attention. Currently, [¹⁸F]FDG-PET/CT radiomics is growingly evaluated in lung cancer to discover if it enhances the diagnostic performance or implication of [¹⁸F]FDG-PET/CT in the management of lung cancer. In this review, we provide a short overview of the technical aspects, as they are discussed in different articles of this special issue. We mainly focus on the diagnostic performance of the [¹⁸F]FDG-PET/CT-based radiomics and the role of artificial intelligence in non-small cell lung cancer, impacting the early detection, staging, prediction of tumor subtypes, biomarkers, and patient's outcomes.

Risk Factors for Unilateral Trigeminal Neuralgia Based on Machine Learning

Purpose

Neurovascular compression (NVC) is considered as the main factor leading to the classical trigeminal neuralgia (CTN), and a part of idiopathic TN (ITN) may be caused by NVC (ITN-nvc). This study aimed to explore the risk factors for unilateral CTN or ITN-nvc (UC-ITN), which have bilateral NVC, using machine learning (ML).

Methods

A total of 89 patients with UC-ITN were recruited prospectively. According to whether there was NVC on the unaffected side, patients with UC-ITN were divided into two groups. All patients underwent a magnetic resonance imaging (MRI) scan. The bilateral cisternal segment of the trigeminal nerve was manually delineated, which avoided the offending vessel (Ofv), and the features were extracted. Dimensionality reduction, feature selection, model construction, and model evaluation were performed step-by-step.

Results

Four textural features with greater weight were selected in patients with UC-ITN without NVC on the unaffected side. For UC-ITN patients with NVC on the unaffected side, six textural features with greater weight were selected. The textural features (rad_score) showed significant differences between the affected and unaffected sides (p < 0.05). The nomogram model had optimal diagnostic power, and the area under the curve (AUC) in the training and validation cohorts was 0.76 and 0.77, respectively. The Ofv and rad_score were the risk factors for UC-ITN according to nomogram.

Conclusion

Besides NVC, the texture features of trigeminal-nerve cisternal segment and Ofv were also the risk factors for UC-ITN. These findings provided a basis for further exploration of the microscopic etiology of UC-ITN.

Synergistic impact of motion and acquisition/reconstruction parameters on 18 F-FDG PET radiomic features in non-small cell lung cancer: phantom and clinical studies

Objectives

This study is aimed at examining the synergistic impact of motion and acquisition/reconstruction parameters on ¹⁸F‐FDG PET image radiomic features in non‐small cell lung cancer (NSCLC) patients, and investigating the robustness of features performance in differentiating NSCLC histopathology subtypes.

Methods

An in‐house developed thoracic phantom incorporating lesions with different sizes was used with different reconstruction settings, including various reconstruction algorithms, number of subsets and iterations, full‐width at half‐maximum of post‐reconstruction smoothing filter and acquisition parameters, including injected activity and test–retest with and without motion simulation. To simulate motion, a special motor was manufactured to simulate respiratory motion based on a normal patient in two directions. The lesions were delineated semi‐automatically to extract 174 radiomic features. All radiomic features were categorized according to the coefficient of variation (COV) to select robust features. A cohort consisting of 40 NSCLC patients with adenocarcinoma (n = 20) and squamous cell carcinoma (n = 20) was retrospectively analyzed. Statistical analysis was performed to discriminate robust features in differentiating histopathology subtypes of NSCLC lesions.

Results

Overall, 29% of radiomic features showed a COV ≤5% against motion. Forty‐five percent and 76% of the features showed a COV ≤ 5% against the test–retest with and without motion in large lesions, respectively. Thirty‐three percent and 45% of the features showed a COV ≤ 5% against different reconstruction parameters with and without motion, respectively. For NSCLC histopathological subtype differentiation, statistical analysis showed that 31 features were significant (p‐value < 0.05). Two out of the 31 significant features, namely, the joint entropy of GLCM (AUC = 0.71, COV = 0.019) and median absolute deviation of intensity histogram (AUC = 0.7, COV = 0.046), were robust against the motion (same reconstruction setting).

Conclusions

Motion, acquisition, and reconstruction parameters significantly impact radiomic features, just as their synergies. Radiomic features with high predictive performance (statistically significant) in differentiating histopathological subtype of NSCLC may be eliminated due to non‐reproducibility.

Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection

OBJECTIVE

Robust differentiation between infarcted and normal tissue is important for clinical diagnosis and precision medicine. The aim of this work is to investigate the radiomic features and to develop a machine learning algorithm for the differentiation of myocardial infarction (MI) and viable tissues/normal cases in the left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images.

METHODS

Seventy-two patients (52 with MI and 20 healthy control patients) were enrolled in this study. MR imaging was performed on a 1.5 T MRI using the following parameters: TR = 43.35 ms, TE = 1.22 ms, flip angle = 65°, temporal resolution of 30-40 ms. N4 bias field correction algorithm was applied to correct the inhomogeneity of images. All images were segmented and verified simultaneously by two cardiac imaging experts in consensus. Subsequently, features extraction was performed within the whole left ventricular myocardium (3D volume) in end-diastolic volume phase. Re-sampling to 1 × 1 × 1 mm³ voxels was performed for MR images. All intensities within the VOI of MR images were discretized to 64 bins. Radiomic features were normalized to obtain Z-scores, followed by Student's t-test statistical analysis for comparison. A p-value < 0.05 was used as a threshold for statistically significant differences and false discovery rate (FDR) correction performed to report q-value (FDR adjusted p-value). The extracted features were ranked using the MSVM-RFE algorithm, then Spearman correlation between features was performed to eliminate highly correlated features (R2 > 0.80). Ten different machine learning algorithms were used for classification and different metrics used for evaluation and various parameters used for models' evaluation.

RESULTS

In univariate analysis, the highest area under the curve (AUC) of receiver operating characteristic (ROC) value was achieved for the Maximum 2D diameter slice (M2DS) shape feature (AUC = 0.88, q-value = 1.02E-7), while the average of univariate AUCs was 0.62 ± 0.08. In multivariate analysis, Logistic Regression (AUC = 0.93 ± 0.03, Accuracy = 0.86 ± 0.05, Recall = 0.87 ± 0.1, Precision = 0.93 ± 0.03 and F1 Score = 0.90 ± 0.04) and SVM (AUC = 0.92 ± 0.05, Accuracy = 0.85 ± 0.04, Recall = 0.92 ± 0.01, Precision = 0.88 ± 0.04 and F1 Score = 0.90 ± 0.02) yielded optimal performance as the best machine learning algorithm for this radiomics analysis.

CONCLUSION

This study demonstrated that using radiomics analysis on non-contrast Cine-CMR images enables to accurately detect MI, which could potentially be used as an alternative diagnostic method for Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR).

Machine Learning-Based Radiomics Nomogram With Dynamic Contrast-Enhanced MRI of the Osteosarcoma for Evaluation of Efficacy of Neoadjuvant Chemotherapy

OBJECTIVES

This study aims to evaluate the value of machine learning-based dynamic contrast-enhanced MRI (DCE-MRI) radiomics nomogram in prediction treatment response of neoadjuvant chemotherapy (NAC) in patients with osteosarcoma.

METHODS

A total of 102 patients with osteosarcoma and who underwent NAC were enrolled in this study. All patients received a DCE-MRI scan before NAC. The Response Evaluation Criteria in Solid Tumors was used as the standard to evaluate the NAC response with complete remission and partial remission in the effective group, stable disease, and progressive disease in the ineffective group. The following semi-quantitative parameters of DCE-MRI were calculated: early dynamic enhancement wash-in slope (Slope), time to peak (TTP), and enhancement rate (R). The acquired data is randomly divided into 70% for training and 30% for testing. Variance threshold, univariate feature selection, and least absolute shrinkage and selection operator were used to select the optimal features. Three classifiers (K-nearest neighbor, KNN; support vector machine, SVM; and logistic regression, LR) were implemented for model establishment. The performance of different classifiers and conventional semi-quantitative parameters was evaluated by confusion matrix and receiver operating characteristic curves. Furthermore, clinically relevant risk factors including age, tumor size and site, pathological fracture, and surgical staging were collected to evaluate their predictive values for the efficacy of NAC. The selected clinical features and imaging features were combined to establish the model and the nomogram, and then the predictive efficacy was evaluated.

RESULTS

The clinical relevance risk factor analysis demonstrates that only surgical stage was an independent predictor of NAC. A total of seven radiomic features were selected, and three machine learning models (KNN, SVM, and LR) were established based on such features. The prediction accuracy (ACC) of these three models was 0.89, 0.84, and 0.84, respectively. The area under the subject curve (AUC) of these three models was 0.86, 0.92, and 0.93, respectively. As for Slope, TTP, and R parameters, the prediction ACC was 0.91, 0.89, and 0.81, respectively, while the AUC was 0.87, 0.85, and 0.83, respectively. In both the training and testing sets, the ACC and AUC of the combined model were higher than those of the radiomics models (ACC = 0.91 and AUC = 0.95), which indicate an outstanding performance of our proposed model.

CONCLUSIONS

The radiomics nomogram demonstrates satisfactory predictive results for the treatment response of patients with osteosarcoma before NAC. This finding may provide a new decision basis to improve the treatment plan.

Multi-level multi-modality (PET and CT) fusion radiomics: prognostic modeling for non-small cell lung carcinoma

We developed multi-modality radiomic models by integrating information extracted from¹⁸F-FDG PET and CT images using feature- and image-level fusions, toward improved prognosis for non-small cell lung carcinoma (NSCLC) patients. Two independent cohorts of NSCLC patients from two institutions (87 and 95 patients) were cycled as training and testing datasets. Fusion approaches were applied at two levels, namely feature- and image-levels. For feature-level fusion, radiomic features were extracted individually from CT and PET images and concatenated. Alternatively, radiomic features extracted separately from CT and PET images were averaged. For image-level fusion, wavelet fusion was utilized and tuned with two parameters, namely CT weight and Wavelet Band Pass Filtering Ratio. Clinical and combined clinical + radiomic models were developed. Gray level discretization was performed at 3 different levels (16, 32 and 64) and 225 radiomics features were extracted. Overall survival (OS) was considered as the endpoint. For feature reduction, correlated (redundant) features were excluded using Spearman's correlation, and best combination of top ten features with highest concordance-indices (via univariate Cox model) were selected in each model for further multivariate Cox model. Moreover, prognostic score's median, obtained from the training cohort, was used intact in the testing cohort as a threshold to classify patients into low- versus high-risk groups, and log-rank test was applied to assess differences between the Kaplan-Meier curves. Overall, while models based on feature-level fusion strategy showed limited superiority over single-modalities, image-level fusion strategy significantly outperformed both single-modality and feature-level fusion strategies. As such, the clinical model (C-index = 0.656) outperformed all models from single-modality and feature-level strategies, but was outperformed by certain models from image-level fusion strategy. Our findings indicated that image-level fusion multi-modality radiomics models outperformed single-modality, feature-level fusion, and clinical models for OS prediction of NSCLC patients.

Artificial intelligence-driven assessment of radiological images for COVID-19

Artificial Intelligence (AI) methods have significant potential for diagnosis and prognosis of COVID-19 infections. Rapid identification of COVID-19 and its severity in individual patients is expected to enable better control of the disease individually and at-large. There has been remarkable interest by the scientific community in using imaging biomarkers to improve detection and management of COVID-19. Exploratory tools such as AI-based models may help explain the complex biological mechanisms and provide better understanding of the underlying pathophysiological processes. The present review focuses on AI-based COVID-19 studies as applies to chest x-ray (CXR) and computed tomography (CT) imaging modalities, and the associated challenges. Explicit radiomics, deep learning methods, and hybrid methods that combine both deep learning and explicit radiomics have the potential to enhance the ability and usefulness of radiological images to assist clinicians in the current COVID-19 pandemic. The aims of this review are: first, to outline COVID-19 AI-analysis workflows, including acquisition of data, feature selection, segmentation methods, feature extraction, and multi-variate model development and validation as appropriate for AI-based COVID-19 studies. Secondly, existing limitations of AI-based COVID-19 analyses are discussed, highlighting potential improvements that can be made. Finally, the impact of AI and radiomics methods and the associated clinical outcomes are summarized. In this review, pipelines that include the key steps for AI-based COVID-19 signatures identification are elaborated. Sample size, non-standard imaging protocols, segmentation, availability of public COVID-19 databases, combination of imaging and clinical information and full clinical validation remain major limitations and challenges. We conclude that AI-based assessment of CXR and CT images has significant potential as a viable pathway for the diagnosis, follow-up and prognosis of COVID-19.

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.

Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature

OBJECTIVE

The aim of this study was to identify the most important features and assess their discriminative power in the classification of the subtypes of NSCLC.

METHODS

This study involved 354 pathologically proven NSCLC patients including 134 squamous cell carcinoma (SCC), 110 large cell carcinoma (LCC), 62 not other specified (NOS), and 48 adenocarcinoma (ADC). In total, 1433 radiomics features were extracted from 3D volumes of interest drawn on the malignant lesion identified on CT images. Wrapper algorithm and multivariate adaptive regression splines were implemented to identify the most relevant/discriminative features. A multivariable multinomial logistic regression was employed with 1000 bootstrapping samples based on the selected features to classify four main subtypes of NSCLC.

RESULTS

The results revealed that the texture features, specifically gray level size zone matrix features (GLSZM), were the significant indicators of NSCLC subtypes. The optimized classifier achieved an average precision, recall, F1-score, and accuracy of 0.710, 0.703, 0.706, and 0.865, respectively, based on the selected features by the wrapper algorithm.

CONCLUSIONS

Our CT radiomics approach demonstrated impressive potential for the classification of the four main histological subtypes of NSCLC, It is anticipated that CT radiomics could be useful in treatment planning and precision medicine.

Exploration of an Integrative Prognostic Model of Radiogenomics Features With Underlying Gene Expression Patterns in Clear Cell Renal Cell Carcinoma

Background

Clear cell renal cell carcinoma (ccRCC) is one of the most common malignancies in urinary system, and radiomics has been adopted in tumor staging and prognostic evaluation in renal carcinomas. This study aimed to integrate image features of contrast-enhanced CT and underlying genomics features to predict the overall survival (OS) of ccRCC patients.

Method

We extracted 107 radiomics features out of 205 patients with available CT images obtained from TCIA database and corresponding clinical and genetic information from TCGA database. LASSO-COX and SVM-RFE were employed independently as machine-learning algorithms to select prognosis-related imaging features (PRIF). Afterwards, we identified prognosis-related gene signature through WGCNA. The random forest (RF) algorithm was then applied to integrate PRIF and the genes into a combined imaging-genomics prognostic factors (IGPF) model. Furthermore, we constructed a nomogram incorporating IGPF and clinical predictors as the integrative prognostic model for ccRCC patients.

Results

A total of four PRIF and four genes were identified as IGPF and were represented by corresponding risk score in RF model. The integrative IGPF model presented a better prediction performance than the PRIF model alone (average AUCs for 1-, 3-, and 5-year were 0.814 vs. 0.837, 0.74 vs. 0.806, and 0.689 vs. 0.751 in test set). Clinical characteristics including gender, TNM stage and IGPF were independent risk factors. The nomogram integrating clinical predictors and IGPF provided the best net benefit among the three models.

Conclusion

In this study we established an integrative prognosis-related nomogram model incorporating imaging-genomic features and clinical indicators. The results indicated that IGPF may contribute to a comprehensive prognosis assessment for ccRCC patients.

Assessing robustness of carotid artery CT angiography radiomics in the identification of culprit lesions in cerebrovascular events

Radiomics, quantitative feature extraction from radiological images, can improve disease diagnosis and prognostication. However, radiomic features are susceptible to image acquisition and segmentation variability. Ideally, only features robust to these variations would be incorporated into predictive models, for good generalisability. We extracted 93 radiomic features from carotid artery computed tomography angiograms of 41 patients with cerebrovascular events. We tested feature robustness to region-of-interest perturbations, image pre-processing settings and quantisation methods using both single- and multi-slice approaches. We assessed the ability of the most robust features to identify culprit and non-culprit arteries using several machine learning algorithms and report the average area under the curve (AUC) from five-fold cross validation. Multi-slice features were superior to single for producing robust radiomic features (67 vs. 61). The optimal image quantisation method used bin widths of 25 or 30. Incorporating our top 10 non-redundant robust radiomics features into ElasticNet achieved an AUC of 0.73 and accuracy of 69% (compared to carotid calcification alone [AUC: 0.44, accuracy: 46%]). Our results provide key information for introducing carotid CT radiomics into clinical practice. If validated prospectively, our robust carotid radiomic set could improve stroke prediction and target therapies to those at highest risk.

Radiomics-based machine learning model to predict risk of death within 5-years in clear cell renal cell carcinoma patients

PURPOSE

The aim of this study was to develop radiomics-based machine learning models based on extracted radiomic features and clinical information to predict the risk of death within 5 years for prognosis of clear cell renal cell carcinoma (ccRCC) patients.

METHODS

According to image quality and clinical data availability, we eventually selected 70 ccRCC patients that underwent CT scans. Manual volume-of-interest (VOI) segmentation of each image was performed by an experienced radiologist using the 3D slicer software package. Prior to feature extraction, image pre-processing was performed on CT images to extract different image features, including wavelet, Laplacian of Gaussian, and resampling of the intensity values to 32, 64 and 128 bin levels. Overall, 2544 3D radiomics features were extracted from each VOI for each patient. Minimum Redundancy Maximum Relevance (MRMR) algorithm was used as feature selector. Four classification algorithms were used, including Generalized Linear Model (GLM), Support Vector Machine (SVM), K-nearest Neighbor (KNN) and XGBoost. We used the Bootstrap resampling method to create validation sets. Area under the receiver operating characteristic (ROC) curve (AUROC), accuracy, sensitivity, and specificity were used to assess the performance of the classification models.

RESULTS

The best single performance among 8 different models was achieved by the XGBoost model using a combination of radiomic features and clinical information (AUROC, accuracy, sensitivity, and specificity with 95% confidence interval were 0.95-0.98, 0.93-0.98, 0.93-0.96 and ~1.0, respectively).

CONCLUSIONS

We developed a robust radiomics-based classifier that is capable of accurately predicting overall survival of RCC patients for prognosis of ccRCC patients. This signature may help identifying high-risk patients who require additional treatment and follow up regimens.

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test-retest and image registration analyses

PURPOSE

To assess the repeatability of radiomic features in magnetic resonance (MR) imaging of glioblastoma (GBM) tumors with respect to test-retest, different image registration approaches and inhomogeneity bias field correction.

METHODS

We analyzed MR images of 17 GBM patients including T1- and T2-weighted images (performed within the same imaging unit on two consecutive days). For image segmentation, we used a comprehensive segmentation approach including entire tumor, active area of tumor, necrotic regions in T1-weighted images, and edema regions in T2-weighted images (test studies only; registration to retest studies is discussed next). Analysis included N3, N4 as well as no bias correction performed on raw MR images. We evaluated 20 image registration approaches, generated by cross-combination of four transformation and five cost function methods. In total, 714 images (17 patients × 2 images × ((4 transformations × 5 cost functions) + 1 test image) and 2856 segmentations (714 images × 4 segmentations) were prepared for feature extraction. Various radiomic features were extracted, including the use of preprocessing filters, specifically wavelet (WAV) and Laplacian of Gaussian (LOG), as well as discretization into fixed bin width and fixed bin count (16, 32, 64, 128, and 256), Exponential, Gradient, Logarithm, Square and Square Root scales. Intraclass correlation coefficients (ICC) were calculated to assess the repeatability of MRI radiomic features (high repeatability defined as ICC ≥ 95%).

RESULTS

In our ICC results, we observed high repeatability (ICC ≥ 95%) with respect to image preprocessing, different image registration algorithms, and test-retest analysis, for example: RLNU and GLNU from GLRLM, GLNU and DNU from GLDM, Coarseness and Busyness from NGTDM, GLNU and ZP from GLSZM, and Energy and RMS from first order. Highest fraction (percent) of repeatable features was observed, among registration techniques, for the method Full Affine transformation with 12 degrees of freedom using Mutual Information cost function (mean 32.4%), and among image processing methods, for the method Laplacian of Gaussian (LOG) with Sigma (2.5-4.5 mm) (mean 78.9%). The trends were relatively consistent for N4, N3, or no bias correction.

CONCLUSION

Our results showed varying performances in repeatability of MR radiomic features for GBM tumors due to test-retest and image registration. The findings have implications for appropriate usage in diagnostic and predictive models.