Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: impact of tumor segmentation variability

Radiomic analysis based on magnetic resonance imaging for the prediction of VEGF expression in hepatocellular carcinoma patients

OBJECTIVE

The purpose of this study was to investigate the ability of radiomic characteristics of magnetic resonance images to predict vascular endothelial growth factor (VEGF) expression in hepatocellular carcinoma (HCC) patients.

METHODS

One hundred and twenty-four patients with HCC who underwent fat-suppressed T2-weighted imaging (FS-T2WI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) one week before surgical resection were enrolled in this retrospective study. Immunohistochemical analysis was used to evaluate the expression level of VEGF. Radiomic features were extracted from the axial FS-T2WI, DCE-MRI (arterial phase and portal venous phase) images of axial MRI. Least absolute shrinkage and selection operator (LASSO) and stepwise regression analyses were performed to select the best radiomic features. Multivariate logistic regression models were constructed and validated using tenfold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models.

RESULTS

Our results show that there were 94 patients with high VEGF expression and 30 patients with low VEGF expression among the 124 HCC patients. The FS-T2WI, DCE-MRI and combined MRI radiomics models had AUCs of 0.8713, 0.7819, and 0.9191, respectively. There was no significant difference in the AUC between the FS-T2WI radiomics model and the DCE-MRI radiomics model (p > 0.05), but the AUC for the combined model was significantly greater than the AUCs for the other two models (p < 0.05) according to the DeLong test. The combined model had the greatest net benefit according to the DCA results.

CONCLUSION

The radiomic model based on multisequence MR images has the potential to predict VEGF expression in HCC patients. The combined model showed the best performance.

Does consensus contour improve robustness and accuracy in 18F-FDG PET radiomic features?

PURPOSE

The purpose of our study is to validate the robustness and accuracy of consensus contour in 2-deoxy-2-[18 F]fluoro-D-glucose (18 F-FDG) PET radiomic features.

METHODS

225 nasopharyngeal carcinoma (NPC) and 13 extended cardio-torso (XCAT) simulated data were enrolled. All segmentation were performed with four segmentation methods under two different initial masks, respectively. Consensus contour (ConSeg) was then developed using the majority vote rule. 107 radiomic features were extracted by Pyradiomics based on segmentation and the intraclass correlation coefficient (ICC) was calculated for each feature between masks or among segmentation, respectively. In XCAT ICC between segmentation and simulated ground truth were also calculated to access the accuracy.

RESULTS

ICC varied with the dataset, segmentation method, initial mask and feature type. ConSeg presented higher ICC for radiomic features in robustness tests and similar ICC in accuracy tests, compared with the average of four segmentation results. Higher ICC were also generally observed in irregular initial masks compared with rectangular masks in both robustness and accuracy tests. Furthermore, 19 features (17.76%) had ICC ≥ 0.75 in both robustness and accuracy tests for any of the segmentation methods or initial masks. The dataset was observed to have a large impact on the correlation relationships between radiomic features, but not the segmentation method or initial mask.

CONCLUSIONS

The consensus contour combined with irregular initial mask could improve the robustness and accuracy in radiomic analysis to some extent. The correlation relationships between radiomic features and feature clusters largely depended on the dataset, but not segmentation method or initial mask.

Differentiating HCC from ICC and prediction of ICC grade based on MRI deep-radiomics: Using lesions and their extended regions

PURPOSE

This study aimed to evaluate the ability of MRI-based intratumoral and peritumoral radiomics features of liver tumors to differentiate between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) and to predict ICC differentiation.

METHODS

This study retrospectively collected 87 HCC patients and 75 ICC patients who were confirmed pathologically. The standard region of interest (ROI) of the lesion drawn by the radiologist manually shrank inward and expanded outward to form multiple ROI extended regions. A three-step feature selection method was used to select important radiomics features and convolution features from extended regions. The predictive performance of several machine learning classifiers on dominant feature sets was compared. The extended region performance was assessed by area under the curve (AUC), specificity, sensitivity, F1-score and accuracy.

RESULTS

The performance of the model is further improved by incorporating convolution features. Compared with the standard ROI, the extended region obtained better prediction performance, among which 6 mm extended region had the best prediction ability (Classification: AUC = 0.96, F1-score = 0.94, Accuracy: 0.94; Grading: AUC = 0.94, F1-score = 0.93, Accuracy = 0.89).

CONCLUSION

Larger extended region and fusion features can improve tumor predictive performance and have potential value in tumor radiology.

Distinguishing immune checkpoint inhibitor-related pneumonitis from radiation pneumonitis by CT radiomics features in non-small cell lung cancer

PURPOSE

To develop a CT-based model to classify pneumonitis etiology in patients with non-small cell lung cancer(NSCLC) after radiotherapy(RT) and Immune checkpoint inhibitors(ICIs).

METHODS

We retrospectively identified 130 NSCLC patients who developed pneumonitis after receipt of ICIs only (n = 50), thoracic RT only (n = 50) (ICIs only + thoracic RT only, the training cohort, n = 100), and RT + ICIs (the test cohort, n = 30). Clinical and CT radiomics features were described and compared between different groups. We constructed a random forest (RF) classifier and a linear discriminant analysis (LDA) classifier by CT radiomics to discern pneumonitis etiology.

RESULTS

The patients in RT + ICIs group have more high grade (grade 3-4) pneumonitis compared to patients in ICIs only or RT only group (p < 0.05). Pneumonitis after the combined therapy was not a simple superposition mode of RT-related pneumonitis(RP) and ICI-related pneumonitis(CIP), resulting in the distinct characteristics of both RT and ICIs-related pneumonitis. The RF classifier showed favorable discrimination between RP and CIP with an area under the receiver operating curve (AUC) of 0.859 (95 %CI: 0.788-0.929) in the training cohort and 0.851 (95 % CI: 0.700-1) in the test cohort. The LDA classifier achieved an AUC of 0.881 (95 %CI: 0.815-0.947) in the training cohort and 0.842 (95 %CI: 0.686-0.997) in the test cohort. Our analysis revealed four principal CT-based features shared across both models:original_glrlm_LongRunLowGrayLevelEmphasis, wavelet-HLL_firstorder_Median, wavelet-LLL_ngtdm_Busyness， and wavelet-LLL_glcm_JointAverage.

CONCLUSION

CT radiomics-based classifiers could provide a noninvasive method to identify the predominant etiology in NSCLC patients who developed pneumonitis after RT alone, ICIs alone or RT + ICIs.

Repeatability of computed tomography liver radiomic features in a nonhuman primate model of diet-induced steatosis

Purpose

We describe a method to identify repeatable liver computed tomography (CT) radiomic features, suitable for detection of steatosis, in nonhuman primates. Criteria used for feature selection exclude nonrepeatable features and may be useful to improve the performance and robustness of radiomics-based predictive models.

Approach

Six crab-eating macaques were equally assigned to two experimental groups, fed regular chow or an atherogenic diet. High-resolution CT images were acquired over several days for each macaque. First-order and second-order radiomic features were extracted from six regions in the liver parenchyma, either with or without liver-to-spleen intensity normalization from images reconstructed using either a standard (B-filter) or a bone-enhanced (D-filter) kernel. Intrasubject repeatability of each feature was assessed using a paired t -test for all scans and the minimum p -value was identified for each macaque. Repeatable features were defined as having a minimum p -value among all macaques above the significance level after Bonferroni's correction. Features showing a significant difference with respect to diet group were identified using a two-sample t -test.

Results

A list of repeatable features was generated for each type of image. The largest number of repeatable features was achieved from spleen-normalized D-filtered images, which also produced the largest number of second-order radiomic features that were repeatable and different between diet groups.

Conclusions

Repeatability depends on reconstruction kernel and normalization. Features were quantified and ranked based on their repeatability. Features to be excluded for more robust models were identified. Features that were repeatable but different between diet groups were also identified.

Performance of alternative manual and automated deep learning segmentation techniques for the prediction of benign and malignant lung nodules

Purpose

We aim to evaluate the performance of radiomic biopsy (RB), best-fit bounding box (BB), and a deep-learning-based segmentation method called no-new-U-Net (nnU-Net), compared to the standard full manual (FM) segmentation method for predicting benign and malignant lung nodules using a computed tomography (CT) radiomic machine learning model.

Materials and Methods

A total of 188 CT scans of lung nodules from 2 institutions were used for our study. One radiologist identified and delineated all 188 lung nodules, whereas a second radiologist segmented a subset (n = 20 ) of these nodules. Both radiologists employed FM and RB segmentation methods. BB segmentations were generated computationally from the FM segmentations. The nnU-Net, a deep-learning-based segmentation method, performed automatic nodule detection and segmentation. The time radiologists took to perform segmentations was recorded. Radiomic features were extracted from each segmentation method, and models to predict benign and malignant lung nodules were developed. The Kruskal-Wallis and DeLong tests were used to compare segmentation times and areas under the curve (AUC), respectively.

Results

For the delineation of the FM, RB, and BB segmentations, the two radiologists required a median time (IQR) of 113 (54 to 251.5), 21 (9.25 to 38), and 16 (12 to 64.25) s, respectively (p = 0.04 ). In dataset 1, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.964 (0.96 to 0.968), 0.985 (0.983 to 0.987), 0.961 (0.956 to 0.965), and 0.878 (0.869 to 0.888). In dataset 2, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.717 (0.705 to 0.729), 0.919 (0.913 to 0.924), 0.699 (0.687 to 0.711), and 0.644 (0.632 to 0.657).

Conclusion

Radiomic biopsy-based models outperformed FM and BB models in prediction of benign and malignant lung nodules in two independent datasets while deep-learning segmentation-based models performed similarly to FM and BB. RB could be a more efficient segmentation method, but further validation is needed.

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients

PURPOSE

To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) after upfront surgery.

MATERIALS AND METHODS

Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21-27 mm³) and binning (32-128 grey levels) in a 15 parameter's sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10 months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR.

RESULTS

Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60-0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08).

CONCLUSIONS

The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

L-distance ratio: a new distance ratio-based evaluation method for the diagnosis of cirrhosis using enhanced computed tomography

Background

Early detection of liver cirrhosis is of great significance to the formulation of treatment plans and improving prognosis. Computed tomography (CT) is commonly used in the assessment of patients with chronic liver disease. In this study, we proposed a new distance ratio method for accurate diagnosis of cirrhosis using CT images.

Methods

This was a retrospective study of a consecutive series of patients in Guangdong Provincial People's Hospital. Sixty-two patients with pathologically diagnosed cirrhosis but whose morphologic changes were insufficient to diagnose cirrhosis were included in the cirrhosis group. Those who were pathologically confirmed to be free of cirrhosis and fibrosis and without a history of chronic hepatic were classified as the control group. A total of 124 patients underwent abdominal dynamic enhanced CT. Both the L-distance ratio-the ratio of the distance from the right portal vein bifurcation point to the anterior and posterior edges of the liver-and the caudate-right lobe ratio were measured by two independent radiologists. Intraclass correlation coefficients (ICCs) were used to assess the agreement between the radiologists. Binary logistic regression was performed for univariate analysis, and the odds ratio (OR) was also calculated. The discrimination ability of the two methods was evaluated by the area under the receiver operating characteristic curve (AUC).

Results

For both the L-distance ratio and the caudate-right lobe ratio, high agreement was observed between the two radiologists, although the ICC value of the L-distance ratio was slightly higher than that of the caudate-right lobe ratio (0.916 vs. 0.907). Binary logistic regression suggested that higher ratios were correlated with cirrhosis [the L-distance ratio, high vs. low OR =4.41, 95% confidence interval (CI): 2.08-9.36, P<0.001; the caudate-right lobe ratio, high vs. low OR =2.19, 95% CI: 1.07-4.49, P=0.031]. The AUCs of the L-distance ratio and the caudate-right lobe ratio were 0.823 (95% CI: 0.752-0.894) and 0.663 (95% CI: 0.569-0.757), respectively.

Conclusions

The L-distance ratio method proposed in this paper is more simple, accurate, and reliable than the caudate-right lobe ratio method in the diagnosis of cirrhosis.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.

Current status and future perspectives of radiomics in hepatocellular carcinoma

Given the frequent co-existence of an aggressive tumor and underlying chronic liver disease, the management of hepatocellular carcinoma (HCC) patients requires experienced multidisciplinary team discussion. Moreover, imaging plays a key role in the diagnosis, staging, restaging, and surveillance of HCC. Currently, imaging assessment of HCC entails the assessment of qualitative characteristics which are prone to inter-reader variability. Radiomics is an emerging field that extracts high-dimensional mineable quantitative features that cannot be assessed visually with the naked eye from medical imaging. The main potential applications of radiomic models in HCC are to predict histology, response to treatment, genetic signature, recurrence, and survival. Despite the encouraging results to date, there are challenges and limitations that need to be overcome before radiomics implementation in clinical practice. The purpose of this article is to review the main concepts and challenges pertaining to radiomics, and to review recent studies and potential applications of radiomics in HCC.

Radiomics: a primer on high-throughput image phenotyping

Radiomics is a high-throughput approach to image phenotyping. It uses computer algorithms to extract and analyze a large number of quantitative features from radiological images. These radiomic features collectively describe unique patterns that can serve as digital fingerprints of disease. They may also capture imaging characteristics that are difficult or impossible to characterize by the human eye. The rapid development of this field is motivated by systems biology, facilitated by data analytics, and powered by artificial intelligence. Here, as part of Abdominal Radiology's special issue on Quantitative Imaging, we provide an introduction to the field of radiomics. The technique is formally introduced as an advanced application of data analytics, with illustrating examples in abdominal radiology. Artificial intelligence is then presented as the main driving force of radiomics, and common techniques are defined and briefly compared. The complete step-by-step process of radiomic phenotyping is then broken down into five key phases. Potential pitfalls of each phase are highlighted, and recommendations are provided to reduce sources of variation, non-reproducibility, and error associated with radiomics.

Review of Radiomics- and Dosiomics-based Predicting Models for Rectal Cancer

By breaking the traditional medical image analysis framework, precision medicine–radiomics has attracted much attention in the past decade. The use of various mathematical algorithms offers radiomics the ability to extract vast amounts of detailed features from medical images for quantitative analysis and analyzes the confidential information related to the tumor in the image, which can establish valuable disease diagnosis and prognosis models to support personalized clinical decisions. This article summarizes the application of radiomics and dosiomics in radiation oncology. We focus on the application of radiomics in locally advanced rectal cancer and also summarize the latest research progress of dosiomics in radiation tumors to provide ideas for the treatment of future related diseases, especially ¹²⁵I CT-guided radioactive seed implant brachytherapy.

Building reliable radiomic models using image perturbation

Radiomic model reliability is a central premise for its clinical translation. Presently, it is assessed using test–retest or external data, which, unfortunately, is often scarce in reality. Therefore, we aimed to develop a novel image perturbation-based method (IPBM) for the first of its kind toward building a reliable radiomic model. We first developed a radiomic prognostic model for head-and-neck cancer patients on a training (70%) and evaluated on a testing (30%) cohort using C-index. Subsequently, we applied the IPBM to CT images of both cohorts (Perturbed-Train and Perturbed-Test cohort) to generate 60 additional samples for both cohorts. Model reliability was assessed using intra-class correlation coefficient (ICC) to quantify consistency of the C-index among the 60 samples in the Perturbed-Train and Perturbed-Test cohorts. Besides, we re-trained the radiomic model using reliable RFs exclusively (ICC > 0.75) to validate the IPBM. Results showed moderate model reliability in Perturbed-Train (ICC: 0.565, 95%CI 0.518–0.615) and Perturbed-Test (ICC: 0.596, 95%CI 0.527–0.670) cohorts. An enhanced reliability of the re-trained model was observed in Perturbed-Train (ICC: 0.782, 95%CI 0.759–0.815) and Perturbed-Test (ICC: 0.825, 95%CI 0.782–0.867) cohorts, indicating validity of the IPBM. To conclude, we demonstrated capability of the IPBM toward building reliable radiomic models, providing community with a novel model reliability assessment strategy prior to prospective evaluation.

Radiomics for the detection of microvascular invasion in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most common primary liver cancer, accounting for about 90% of liver cancer cases. It is currently the fifth most common cancer in the world and the third leading cause of cancer-related mortality. Moreover, recurrence of HCC is common. Microvascular invasion (MVI) is a major factor associated with recurrence in postoperative HCC. It is difficult to evaluate MVI using traditional imaging modalities. Currently, MVI is assessed primarily through pathological and immunohistochemical analyses of postoperative tissue samples. Needle biopsy is the primary method used to confirm MVI diagnosis before surgery. As the puncture specimens represent just a small part of the tumor, and given the heterogeneity of HCC, biopsy samples may yield false-negative results. Radiomics, an emerging, powerful, and non-invasive tool based on various imaging modalities, such as computed tomography, magnetic resonance imaging, ultrasound, and positron emission tomography, can predict the HCC-MVI status preoperatively by delineating the tumor and/or the regions at a certain distance from the surface of the tumor to extract the image features. Although positive results have been reported for radiomics, its drawbacks have limited its clinical translation. This article reviews the application of radiomics, based on various imaging modalities, in preoperative evaluation of HCC-MVI and explores future research directions that facilitate its clinical translation.

Pretreatment Computed Tomography-Based Machine Learning Models to Predict Outcomes in Hepatocellular Carcinoma Patients who Received Combined Treatment of Trans-Arterial Chemoembolization and Tyrosine Kinase Inhibitor

Aim: Trans-arterial chemoembolization (TACE) in combination with tyrosine kinase inhibitor (TKI) has been evidenced to improve outcomes in a portion of patients with hepatocellular carcinoma (HCC). Developing biomarkers to identify patients who might benefit from the combined treatment is needed. This study aims to investigate the efficacy of radiomics/deep learning features-based models in predicting short-term disease control and overall survival (OS) in HCC patients who received the combined treatment.

Materials and Methods: A total of 103 HCC patients who received the combined treatment from Sep. 2015 to Dec. 2019 were enrolled in the study. We exacted radiomics features and deep learning features of six pre-trained convolutional neural networks (CNNs) from pretreatment computed tomography (CT) images. The robustness of features was evaluated, and those with excellent stability were used to construct predictive models by combining each of the seven feature exactors, 13 feature selection methods and 12 classifiers. The models were evaluated for predicting short-term disease by using the area under the receiver operating characteristics curve (AUC) and relative standard deviation (RSD). The optimal models were further analyzed for predictive performance on overall survival.

Results: A total of the 1,092 models (156 with radiomics features and 936 with deep learning features) were constructed. Radiomics_GINI_Nearest Neighbors (RGNN) and Resnet50_MIM_Nearest Neighbors (RMNN) were identified as optimal models, with the AUC of 0.87 and 0.94, accuracy of 0.89 and 0.92, sensitivity of 0.88 and 0.97, specificity of 0.90 and 0.90, precision of 0.87 and 0.83, F1 score of 0.89 and 0.92, and RSD of 1.30 and 0.26, respectively. Kaplan-Meier survival analysis showed that RGNN and RMNN were associated with better OS (p = 0.006 for RGNN and p = 0.033 for RMNN).

Conclusion: Pretreatment CT-based radiomics/deep learning models could non-invasively and efficiently predict outcomes in HCC patients who received combined therapy of TACE and TKI.

Reproducibility for Hepatocellular Carcinoma CT Radiomic Features: Influence of Delineation Variability Based on 3D-CT, 4D-CT and Multiple-Parameter MR Images

Purpose

Accurate lesion segmentation is a prerequisite for radiomic feature extraction. It helps to reduce the features variability so as to improve the reporting quality of radiomics study. In this research, we aimed to conduct a radiomic feature reproducibility test of inter-/intra-observer delineation variability in hepatocellular carcinoma using 3D-CT images, 4D-CT images and multiple-parameter MR images.

Materials and Methods

For this retrospective study, 19 HCC patients undergoing 3D-CT, 4D-CT and multiple-parameter MR scans were included in this study. The gross tumor volume (GTV) was independently delineated twice by two observers based on contrast-enhanced computed tomography (CECT), maximum intensity projection (MIP), LAVA-Flex, T2W FRFSE and DWI-EPI images. We also delineated the peritumoral region, which was defined as 0 to 5 mm radius surrounding the GTV. 107 radiomic features were automatically extracted from CECT images using 3D-Slicer software. Quartile coefficient of dispersion (QCD) and intraclass correlation coefficient (ICC) were applied to assess the variability of each radiomic feature. QCD<10% and ICC≥0.75 were considered small variations and excellent reliability. Finally, the principal component analysis (PCA) was used to test the feasibility of dimensionality reduction.

Results

For tumor tissues, the numbers of radiomic features with QCD<10% indicated no obvious inter-/intra-observer differences or discrepancies in 3D-CT, 4D-CT and multiple-parameter MR delineation. However, the number of radiomic features (mean 89) with ICC≥0.75 was the highest in the multiple-parameter MR group, followed by the 3DCT group (mean 77) and the MIP group (mean 73). The peritumor tissues also showed similar results. A total of 15 and 7 radiomic features presented excellent reproducibility and small variation in tumor and peritumoral tissues, respectively. Two robust features showed excellent reproducibility and small variation in tumor and peritumoral tissues. In addition, the values of the two features both represented statistically significant differences among tumor and peritumoral tissues (P<0.05). The PCA results indicated that the first seven principal components could preserve at least 90% of the variance of the original set of features.

Conclusion

Delineation on multiple-parameter MR images could help to improve the reproducibility of the HCC CT radiomic features and weaken the inter-/intra-observer influence.

Radiomics Nomogram for Predicting Locoregional Failure in Locally Advanced Non-small Cell Lung Cancer Treated with Definitive Chemoradiotherapy

RATIONALE AND OBJECTIVES

To develop and validate a computed tomography (CT)-based radiomics nomogram for predicting locoregional failure (LRF) in patients with locally advanced non-small cell lung cancer (NSCLC) treated with definitive chemoradiotherapy (CRT).

MATERIALS AND METHODS

A total of 141 patients with locally advanced NSCLC treated with definitive CRT from January 2014 to December 2017 were included and divided into testing cohort (n = 100) and validation (n = 41) cohort. Radiomics features were extracted from pretreatment contrast enhanced CT. The least absolute shrinkage and selection operator logistic regression was processed to select predictive features from the testing cohort and constructed a radiomics signature. Clinical characteristics and the radiomics signature were analyzed using univariable and multivariate Cox regression. The radiomics nomogram was established with the radiomics signature and independent clinical factors. Harrell's C-index, calibration curves and decision curves were used to assess the performance of the radiomics nomogram.

RESULTS

The radiomics signature, which consisted of eight selected features, was an independent factor of LRF. The clinical predictors of LRF were the histologic type and clinical stage. The radiomics nomogram combined with the radiomics signature and clinical prognostic factors showed good performance with C-indexes of 0.796 (95% confidence interval [CI]: 0.709-0.883) and 0.756 (95% CI: 0.674-0.838) in the testing and validation cohorts respectively. Additionally, the combined nomogram resulted in better performance (p < 0.001) for the estimation of LRF than the nomograms with the radiomics signature (C-index: 0.776; 95% CI: 0.686-0.866) or clinical predictors (C-index: 0.641; 95% CI: 0.542-0.740) alone.

CONCLUSION

The radiomics nomogram provided the best performance for LRF prediction in patients with locally advanced NSCLC, which may help optimize individual treatments.

T2 -Weighted MR Imaging-Derived Radiomics for Pretreatment Determination of Therapeutic Response to Glucocorticoid in Patients With Thyroid-Associated Ophthalmopathy: Comparison With Semiquantitative Evaluation

BACKGROUND

MR imaging has been applied to determine therapeutic response to glucocorticoid (GC) before treatment in thyroid-associated ophthalmopathy (TAO), while the performance was still poor.

PURPOSE

To investigate the value of T₂ -weighted imaging (T₂ WI)-derived radiomics for pretreatment determination of therapeutic response to GC in TAO patients, and compare its diagnostic performance with that of semiquantitative parameters.

STUDY TYPE

Retrospective.

POPULATION

A total of 110 patients (49 ± 12 years; male/female, n = 48/62; responsive/unresponsive, n = 62/48), divided into training (n = 78) and validation (n = 32) cohorts.

FIELD STRENGTH/SEQUENCE

3.0 T, T₂ -weighted fast spin echo.

ASSESSMENT

W.C. and H.H. (6 and 10 years of experience, respectively) performed the measurements. Maximum, mean, and minimum signal intensity ratios (SIRs) of extraocular muscle (EOM) bellies were collected to construct a semiquantitative imaging model. Radiomics features from volumes of interest covering EOM bellies were extracted and three machine learning-based (logistic regression [LR]; decision tree [DT]; support vector machine [SVM]) models were built.

STATISTICAL TESTS

The diagnostic performances of models were evaluated using receiver operating characteristic curve analyses, and compared using DeLong test. Two-sided P < 0.05 was considered statistically significant.

RESULTS

The responsive group showed higher minimum signal intensity ratio (SIR_min ) of EOMs than the unresponsive group (training: 1.46 ± 0.34 vs. 1.18 ± 0.39; validation: 1.44 ± 0.33 vs. 1.19 ± 0.20). In both cohorts, LR-based radiomics model demonstrated good diagnostic performance (area under the curve [AUC] = 0.968, 0.916), followed by DT-based (AUC = 0.933, 0.857) and SVM-based models (AUC = 0.919, 0.855). All three radiomics models outperformed semiquantitative imaging model (SIR_min : AUC = 0.805) in training cohort. In validation cohort, only LR-based radiomics model outperformed that of SIR_min (AUC = 0.745). The nomogram integrating LR-based radiomics signature and disease duration further elevated the diagnostic performance in validation cohort (AUC: 0.952 vs. 0.916, P = 0.063).

DATA CONCLUSION

T₂ WI-derived radiomics of EOMs, together with disease duration, provides a promising noninvasive approach for determining therapeutic response before GC administration in TAO patients.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 4.

Locoregional Recurrence Prediction Using a Deep Neural Network of Radiological and Radiotherapy Images

Radiation therapy (RT) is an important and potentially curative modality for head and neck squamous cell carcinoma (HNSCC). Locoregional recurrence (LR) of HNSCC after RT is ranging from 15% to 50% depending on the primary site and stage. In addition, the 5-year survival rate of patients with LR is low. To classify high-risk patients who might develop LR, a deep learning model for predicting LR needs to be established. In this work, 157 patients with HNSCC who underwent RT were analyzed. Based on the National Cancer Institute’s multi-institutional TCIA data set containing FDG-PET/CT/dose, a 3D deep learning model was proposed to predict LR without time-consuming segmentation or feature extraction. Our model achieved an averaged area under the curve (AUC) of 0.856. Adding clinical factors into the model improved the AUC to an average of 0.892 with the highest AUC of up to 0.974. The 3D deep learning model could perform individualized risk quantification of LR in patients with HNSCC without time-consuming tumor segmentation.

Fully Automated MR Based Virtual Biopsy of Cerebral Gliomas

OBJECTIVE

The aim of this study was to investigate the diagnostic accuracy of a radiomics analysis based on a fully automated segmentation and a simplified and robust MR imaging protocol to provide a comprehensive analysis of the genetic profile and grading of cerebral gliomas for everyday clinical use.

METHODS

MRI examinations of 217 therapy-naïve patients with cerebral gliomas, each comprising a non-contrast T1-weighted, FLAIR and contrast-enhanced T1-weighted sequence, were included in the study. In addition, clinical and laboratory parameters were incorporated into the analysis. The BraTS 2019 pretrained DeepMedic network was used for automated segmentation. The segmentations generated by DeepMedic were evaluated with 200 manual segmentations with a DICE score of 0.8082 ± 0.1321. Subsequently, the radiomics signatures were utilized to predict the genetic profile of ATRX, IDH1/2, MGMT and 1p19q co-deletion, as well as differentiating low-grade glioma from high-grade glioma.

RESULTS

The network provided an AUC (validation/test) for the differentiation between low-grade gliomas vs. high-grade gliomas of 0.981 ± 0.015/0.885 ± 0.02. The best results were achieved for the prediction of the ATRX expression loss with AUCs of 0.979 ± 0.028/0.923 ± 0.045, followed by 0.929 ± 0.042/0.861 ± 0.023 for the prediction of IDH1/2. The prediction of 1p19q and MGMT achieved moderate results, with AUCs of 0.999 ± 0.005/0.711 ± 0.128 for 1p19q and 0.854 ± 0.046/0.742 ± 0.050 for MGMT.

CONCLUSION

This fully automated approach utilizing simplified MR protocols to predict the genetic profile and grading of cerebral gliomas provides an easy and efficient method for non-invasive tumor decoding.

Accurate Tumor Delineation vs. Rough Volume of Interest Analysis for 18F-FDG PET/CT Radiomics-Based Prognostic Modeling inNon-Small Cell Lung Cancer

Background

The aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (¹⁸F-FDG PET/CT) images based on a "rough" volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses.

Methods

A cohort of 138 patients with stage II-III NSCLC treated with radiochemotherapy recruited retrospectively (n = 87) and prospectively (n = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined "rough" VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity.

Results

Overall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 vs. 0.88 and 0.78 vs. 0.77).

Conclusion

Our findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.

Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review

Radiomics research is rapidly growing in recent years, but more concerns on radiomics reliability are also raised. This review attempts to update and overview the current status of radiomics reliability research in the ever expanding medical literature from the perspective of a single reliability metric of intraclass correlation coefficient (ICC). To conduct this systematic review, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. After literature search and selection, a total of 481 radiomics studies using CT, PET, or MRI, covering a wide range of subject and disease types, were included for review. In these highly heterogeneous studies, feature reliability to image segmentation was much more investigated than reliability to other factors, such as image acquisition, reconstruction, post-processing, and feature quantification. The reported ICCs also suggested high radiomics feature reliability to image segmentation. Image acquisition was found to introduce much more feature variability than image segmentation, in particular for MRI, based on the reported ICC values. Image post-processing and feature quantification yielded different levels of radiomics reliability and might be used to mitigate image acquisition-induced variability. Some common flaws and pitfalls in ICC use were identified, and suggestions on better ICC use were given. Due to the extremely high study heterogeneities and possible risks of bias, the degree of radiomics feature reliability that has been achieved could not yet be safely synthesized or derived in this review. More future researches on radiomics reliability are warranted.

Deep Semantic Segmentation Feature-Based Radiomics for the Classification Tasks in Medical Image Analysis

Recently, an emerging trend in medical image classification is to combine radiomics framework with deep learning classification network in an integrated system. Although this combination is efficient in some tasks, the deep learning-based classification network is often difficult to capture an effective representation of lesion regions, and prone to face the challenge of overfitting, leading to unreliable features and inaccurate results, especially when the sizes of the lesions are small or the training dataset is small. In addition, these combinations mostly lack an effective feature selection mechanism, which makes it difficult to obtain the optimal feature selection. In this paper, we introduce a novel and effective deep semantic segmentation feature-based radiomics (DSFR) framework to overcome the above-mentioned challenges, which consists of two modules: the deep semantic feature extraction module and the feature selection module. Specifically, the extraction module is utilized to extract hierarchical semantic features of the lesions from a trained segmentation network. The feature selection module aims to select the most representative features by using a novel feature similarity adaptation algorithm. Experiments are extensively conducted to evaluate our method in two clinical tasks: the pathological grading prediction in pancreatic neuroendocrine neoplasms (pNENs), and the prediction of thrombolytic therapy efficacy in deep venous thrombosis (DVT). Experimental results on both tasks demonstrate that the proposed method consistently outperforms the state-of-the-art approaches by a large margin.

A review in radiomics: Making personalized medicine a reality via routine imaging

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

Segmentation of MRI head anatomy using deep volumetric networks and multiple spatial priors

Purpose: Conventional automated segmentation of the head anatomy in magnetic resonance images distinguishes different brain and nonbrain tissues based on image intensities and prior tissue probability maps (TPMs). This works well for normal head anatomies but fails in the presence of unexpected lesions. Deep convolutional neural networks (CNNs) leverage instead spatial patterns and can learn to segment lesions but often ignore prior probabilities. Approach: We add three sources of prior information to a three-dimensional (3D) convolutional network, namely, spatial priors with a TPM, morphological priors with conditional random fields, and spatial context with a wider field-of-view at lower resolution. We train and test these networks on 3D images of 43 stroke patients and 4 healthy individuals which have been manually segmented. Results: We demonstrate the benefits of each source of prior information, and we show that the new architecture, which we call Multiprior network, improves the performance of existing segmentation software, such as SPM, FSL, and DeepMedic for abnormal anatomies. The relevance of the different priors was compared, and the TPM was found to be most beneficial. The benefit of adding a TPM is generic in that it can boost the performance of established segmentation networks such as the DeepMedic and a UNet. We also provide an out-of-sample validation and clinical application of the approach on an additional 47 patients with disorders of consciousness. We make the code and trained networks freely available. Conclusions: Biomedical images follow imaging protocols that can be leveraged as prior information into deep CNNs to improve performance. The network segmentations match human manual corrections performed in 3D and are comparable in performance to human segmentations obtained from scratch in 2D for abnormal brain anatomies.

Radiomics side experiments and DAFIT approach in identifying pulmonary hypertension using Cardiac MRI derived radiomics based machine learning models

Side experiments are performed on radiomics models to improve their reproducibility. We measure the impact of myocardial masks, radiomic side experiments and data augmentation for information transfer (DAFIT) approach to differentiate patients with and without pulmonary hypertension (PH) using cardiac MRI (CMRI) derived radiomics. Feature extraction was performed from the left ventricle (LV) and right ventricle (RV) myocardial masks using CMRI in 82 patients (42 PH and 40 controls). Various side study experiments were evaluated: Original data without and with intraclass correlation (ICC) feature-filtering and DAFIT approach (without and with ICC feature-filtering). Multiple machine learning and feature selection strategies were evaluated. Primary analysis included all PH patients with subgroup analysis including PH patients with preserved LVEF (≥ 50%). For both primary and subgroup analysis, DAFIT approach without feature-filtering was the highest performer (AUC 0.957-0.958). ICC approaches showed poor performance compared to DAFIT approach. The performance of combined LV and RV masks was superior to individual masks alone. There was variation in top performing models across all approaches (AUC 0.862-0.958). DAFIT approach with features from combined LV and RV masks provide superior performance with poor performance of feature filtering approaches. Model performance varies based upon the feature selection and model combination.

Reproducibility of CT-based radiomic features against image resampling and perturbations for tumour and healthy kidney in renal cancer patients

Computed Tomography (CT) is widely used in oncology for morphological evaluation and diagnosis, commonly through visual assessments, often exploiting semi-automatic tools as well. Well-established automatic methods for quantitative imaging offer the opportunity to enrich the radiologist interpretation with a large number of radiomic features, which need to be highly reproducible to be used reliably in clinical practice. This study investigates feature reproducibility against noise, varying resolutions and segmentations (achieved by perturbing the regions of interest), in a CT dataset with heterogeneous voxel size of 98 renal cell carcinomas (RCCs) and 93 contralateral normal kidneys (CK). In particular, first order (FO) and second order texture features based on both 2D and 3D grey level co-occurrence matrices (GLCMs) were considered. Moreover, this study carries out a comparative analysis of three of the most commonly used interpolation methods, which need to be selected before any resampling procedure. Results showed that the Lanczos interpolation is the most effective at preserving original information in resampling, where the median slice resolution coupled with the native slice spacing allows the best reproducibility, with 94.6% and 87.7% of features, in RCC and CK, respectively. GLCMs show their maximum reproducibility when used at short distances.

Contrast-Enhanced CT-Based Radiomics Analysis in Predicting Lymphovascular Invasion in Esophageal Squamous Cell Carcinoma

Objectives

To develop a radiomics model based on contrast-enhanced CT (CECT) to predict the lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC) and provide decision-making support for clinicians.

Patients and Methods

This retrospective study enrolled 334 patients with surgically resected and pathologically confirmed ESCC, including 96 patients with LVI and 238 patients without LVI. All enrolled patients were randomly divided into a training cohort and a testing cohort at a ratio of 7:3, with the training cohort containing 234 patients (68 patients with LVI and 166 without LVI) and the testing cohort containing 100 patients (28 patients with LVI and 72 without LVI). All patients underwent preoperative CECT scans within 2 weeks before operation. Quantitative radiomics features were extracted from CECT images, and the least absolute shrinkage and selection operator (LASSO) method was applied to select radiomics features. Logistic regression (Logistic), support vector machine (SVM), and decision tree (Tree) methods were separately used to establish radiomics models to predict the LVI status in ESCC, and the best model was selected to calculate Radscore, which combined with two clinical CT predictors to build a combined model. The clinical model was also developed by using logistic regression. The receiver characteristic curve (ROC) and decision curve (DCA) analysis were used to evaluate the model performance in predicting the LVI status in ESCC.

Results

In the radiomics model, Sphericity and gray-level non-uniformity (GLNU) were the most significant radiomics features for predicting LVI. In the clinical model, the maximum tumor thickness based on CECT (cThick) in patients with LVI was significantly greater than that in patients without LVI (P<0.001). Patients with LVI had higher clinical N stage based on CECT (cN stage) than patients without LVI (P<0.001). The ROC analysis showed that both the radiomics model (AUC values were 0.847 and 0.826 in the training and testing cohort, respectively) and the combined model (0.876 and 0.867, respectively) performed better than the clinical model (0.775 and 0.798, respectively), with the combined model exhibiting the best performance.

Conclusions

The combined model incorporating radiomics features and clinical CT predictors may potentially predict the LVI status in ESCC and provide support for clinical treatment decisions.

Quantitative assessment of acquisition imaging parameters on MRI radiomics features: a prospective anthropomorphic phantom study using a 3D-T2W-TSE sequence for MR-guided-radiotherapy

Background

MRI pulse sequences and imaging parameters substantially influence the variation of MRI radiomics features, thus impose a critical challenge on MRI radiomics reproducibility and reliability. This study aims to prospectively investigate the impact of various imaging parameters on MRI radiomics features in a 3D T2-weighted (T2W) turbo-spin-echo (TSE) pulse sequence for MR-guided-radiotherapy (MRgRT).

Methods

An anthropomorphic phantom was scanned using a 3D-T2W-TSE MRgRT sequence at 1.5T under a variety of acquisition imaging parameter changes. T1 and T2 relaxation times of the phantom were also measured. 93 first-order and texture radiomics features in the original and 14 transformed images, yielding 1,395 features in total, were extracted from 10 volumes-of-interest (VOIs). The percentage deviation (d%) of radiomics feature values from the baseline values and intra-class correlation coefficient (ICC) with the baseline were calculated. Robust radiomics features were identified based on the excellent agreement of radiomics feature values with the baseline, i.e., the averaged d% <5% and ICC >0.90 in all VOIs for all imaging parameter variations.

Results

The radiomics feature values changed considerably but to different degrees with different imaging parameter adjustments, in the ten VOIs. The deviation d% ranged from 0.02% to 321.3%, with a mean of 12.5% averaged for all original features in all ten VOIs. First-order and GLCM features were generally more robust to imaging parameters than other features in the original images. There were also significantly different radiomics feature values (ANOVA, P<0.001) between the original and the transformed images, exhibiting quite different robustness to imaging parameters. 330 out of 1395 features (23.7%) robust to imaging parameters were identified. GLCM and GLSZM features had the most (42.5%, 153/360) and least (3.8%, 9/240) robust features in the original and transformed images, respectively.

Conclusions

This study helps better understand the quantitative dependence of radiomics feature values on imaging parameters in a 3D-T2W-TSE sequence for MRgRT. Imaging parameter heterogeneity should be considered as a significant source of radiomics variability and uncertainty, which must be well harmonized for reliable clinical use. The identified robust features to imaging parameters are helpful for the pre-selection of radiomics features for reliable radiomics modeling.

Understanding Sources of Variation to Improve the Reproducibility of Radiomics

Radiomics is the method of choice for investigating the association between cancer imaging phenotype, cancer genotype and clinical outcome prediction in the era of precision medicine. The fast dispersal of this new methodology has benefited from the existing advances of the core technologies involved in radiomics workflow: image acquisition, tumor segmentation, feature extraction and machine learning. However, despite the rapidly increasing body of publications, there is no real clinical use of a developed radiomics signature so far. Reasons are multifaceted. One of the major challenges is the lack of reproducibility and generalizability of the reported radiomics signatures (features and models). Sources of variation exist in each step of the workflow; some are controllable or can be controlled to certain degrees, while others are uncontrollable or even unknown. Insufficient transparency in reporting radiomics studies further prevents translation of the developed radiomics signatures from the bench to the bedside. This review article first addresses sources of variation, which is illustrated using demonstrative examples. Then, it reviews a number of published studies and progresses made to date in the investigation and improvement of feature reproducibility and model performance. Lastly, it discusses potential strategies and practical considerations to reduce feature variability and improve the quality of radiomics study. This review focuses on CT image acquisition, tumor segmentation, quantitative feature extraction, and the disease of lung cancer.

Radiomics: The Next Frontier of Cardiac Computed Tomography

Radiomics uses advanced image analysis to extract massive amounts of quantitative information from digital images, which is not otherwise distinguishable to the human eye. The mined data can be used to explore and establish new and undiscovered correlations between these imaging features and clinical end points. Cardiac computed tomography (CT) is a first-line imaging modality for evaluating coronary artery disease and has a primary role in the assessment of cardiac structures. Conventional interpretation of cardiac CT images relies mostly on subjective and qualitative analysis, as well as basic geometric quantification. To date, some proof-of-concept studies have demonstrated the feasibility and diagnostic performance of cardiac CT radiomics analysis. This review describes the current literature on radiomics in cardiac CT and discusses its advantages, challenges, and future directions. Although much evidences are needed in this field, cardiac CT radiomics has a lot to offer to patients and physicians with potential to define cardiac disease phenotypes on imaging with higher precision.

Radiomics of hepatocellular carcinoma

The diagnosis of hepatocellular carcinoma relies largely on non-invasive imaging, and is well suited for radiomics analysis. Radiomics is an emerging method for quantification of tumor heterogeneity by mathematically analyzing the spatial distribution and relationships of gray levels in medical images. The published studies on radiomics analysis of HCC provide encouraging data demonstrating potential utility for prediction of tumor biology, molecular profiles, post-therapy response, and outcome. The combination of radiomics data and clinical/laboratory information provides added value in many studies. Radiomics is a multi-step process that requires optimization and standardization, the development of semi-automated or automated segmentation methods, robust data quality control, and refinement of algorithms and modeling approaches for high-throughput data analysis. While radiomics remains largely in the research setting, the strong associations of predictive models and nomograms with certain pathologic, molecular, and immune markers with tumor aggressiveness and patient outcomes, provide great potential for clinical applications to inform optimized treatment strategies and patient prognosis.

Development and validation of radiomics model built by incorporating machine learning for identifying liver fibrosis and early-stage cirrhosis

BACKGROUND

Liver fibrosis (LF) continues to develop and eventually progresses to cirrhosis. However, LF and early-stage cirrhosis (ESC) can be reversed in some cases, while advanced cirrhosis is almost impossible to cure. Advances in quantitative imaging techniques have made it possible to replace the gold standard biopsy method with non-invasive imaging, such as radiomics. Therefore, the purpose of this study is to develop a radiomics model to identify LF and ESC.

METHODS

Patients with LF (n = 108) and ESC (n = 116) were enrolled in this study. As a control, patients with healthy livers were involved in the study (n = 145). Diffusion-weighted imaging (DWI) data sets with three b-values (0, 400, and 800 s/mm) of enrolled cases were collected in this study. Then, radiomics features were extracted from manually delineated volumes of interest. Two modeling strategies were performed after univariate analysis and feature selection. Finally, an optimal model was determined by the receiver operating characteristic area under the curve (AUC).

RESULTS

The optimal models were built in plan 1. For model 1 in plan 1, the AUCs of the training and validation cohorts were 0.973 (95% confidence interval [CI] 0.946-1.000) and 0.948 (95% CI 0.903-0.993), respectively. For model 2 in plan 1, the AUCs of the training and validation cohorts were 0.944, 95% CI 0.905 to 0.983, and 0.968, 95% CI 0.940 to 0.996, respectively.

CONCLUSIONS

Radiomics analysis of DWI images allows for accurate identification of LF and ESC, and the non-invasive biomarkers extracted from the functional DWI images can serve as a better alternative to biopsy.

Impact of inter-reader contouring variability on textural radiomics of colorectal liver metastases

BACKGROUND

Radiomics is expected to improve the management of metastatic colorectal cancer (CRC). We aimed at evaluating the impact of liver lesion contouring as a source of variability on radiomic features (RFs).

METHODS

After Ethics Committee approval, 70 liver metastases in 17 CRC patients were segmented on contrast-enhanced computed tomography scans by two residents and checked by experienced radiologists. RFs from grey level co-occurrence and run length matrices were extracted from three-dimensional (3D) regions of interest (ROIs) and the largest two-dimensional (2D) ROIs. Inter-reader variability was evaluated with Dice coefficient and Hausdorff distance, whilst its impact on RFs was assessed using mean relative change (MRC) and intraclass correlation coefficient (ICC). For the main lesion of each patient, one reader also segmented a circular ROI on the same image used for the 2D ROI.

RESULTS

The best inter-reader contouring agreement was observed for 2D ROIs according to both Dice coefficient (median 0.85, interquartile range 0.78-0.89) and Hausdorff distance (0.21 mm, 0.14-0.31 mm). Comparing RF values, MRC ranged 0-752% for 2D and 0-1567% for 3D. For 24/32 RFs (75%), MRC was lower for 2D than for 3D. An ICC > 0.90 was observed for more RFs for 2D (53%) than for 3D (34%). Only 2/32 RFs (6%) showed a variability between 2D and circular ROIs higher than inter-reader variability.

CONCLUSIONS

A 2D contouring approach may help mitigate overall inter-reader variability, albeit stable RFs can be extracted from both 3D and 2D segmentations of CRC liver metastases.

How to read and review papers on machine learning and artificial intelligence in radiology: a survival guide to key methodological concepts

In recent years, there has been a dramatic increase in research papers about machine learning (ML) and artificial intelligence in radiology. With so many papers around, it is of paramount importance to make a proper scientific quality assessment as to their validity, reliability, effectiveness, and clinical applicability. Due to methodological complexity, the papers on ML in radiology are often hard to evaluate, requiring a good understanding of key methodological issues. In this review, we aimed to guide the radiology community about key methodological aspects of ML to improve their academic reading and peer-review experience. Key aspects of ML pipeline were presented within four broad categories: study design, data handling, modelling, and reporting. Sixteen key methodological items and related common pitfalls were reviewed with a fresh perspective: database size, robustness of reference standard, information leakage, feature scaling, reliability of features, high dimensionality, perturbations in feature selection, class balance, bias-variance trade-off, hyperparameter tuning, performance metrics, generalisability, clinical utility, comparison with traditional tools, data sharing, and transparent reporting.Key Points• Machine learning is new and rather complex for the radiology community.• Validity, reliability, effectiveness, and clinical applicability of studies on machine learning can be evaluated with a proper understanding of key methodological concepts about study design, data handling, modelling, and reporting.• Understanding key methodological concepts will provide a better academic reading and peer-review experience for the radiology community.

The application of texture quantification in hepatocellular carcinoma using CT and MRI: a review of perspectives and challenges

Recently, radiomic texture quantification of tumors has received much attention from radiologists, scientists, and stakeholders because several results have shown the feasibility of using the technique to diagnose and manage oncological conditions. In patients with hepatocellular carcinoma, radiomics has been applied in all stages of tumor evaluation, including diagnosis and characterization of the genotypic behavior of the tumor, monitoring of treatment responses and prediction of various clinical endpoints. It is also useful in selecting suitable candidates for specific treatment strategies. However, the clinical validation of hepatocellular carcinoma radiomics is limited by challenges in imaging protocol and data acquisition parameters, challenges in segmentation techniques, dimensionality reduction, and modeling methods. Identification of the best segmentation and optimal modeling methods, as well as texture features most stable to imaging protocol variability would go a long way in harmonizing HCC radiomics for personalized patient care. This article reviews the process of HCC radiomics, its clinical applications, associated challenges, and current optimization strategies.

MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variability

Radiomics is an emerging field using the extraction of quantitative features from medical images for tissue characterization. While MRI-based radiomics is still at an early stage, it showed some promising results in studies focusing on breast cancer patients in improving diagnoses and therapy response assessment. Nevertheless, the use of radiomics raises a number of issues regarding feature quantification and robustness. Therefore, our study aim was to determine the robustness of radiomics features extracted by two commonly used radiomics software with respect to variability in manual breast tumor segmentation on MRI. A total of 129 histologically confirmed breast tumors were segmented manually in three dimensions on the first post-contrast T1-weighted MR exam by four observers: a dedicated breast radiologist, a resident, a Ph.D. candidate, and a medical student. Robust features were assessed using the intraclass correlation coefficient (ICC > 0.9). The inter-observer variability was evaluated by the volumetric Dice Similarity Coefficient (DSC). The mean DSC for all tumors was 0.81 (range 0.19–0.96), indicating a good spatial overlap of the segmentations based on observers of varying expertise. In total, 41.6% (552/1328) and 32.8% (273/833) of all RadiomiX and Pyradiomics features, respectively, were identified as robust and were independent of inter-observer manual segmentation variability.

Radiomics in medical imaging-"how-to" guide and critical reflection

Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features.The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical "how-to" guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject.

Development and Validation of a Radiomics Nomogram Model for Predicting Postoperative Recurrence in Patients With Esophageal Squamous Cell Cancer Who Achieved pCR After Neoadjuvant Chemoradiotherapy Followed by Surgery

Background and purpose: Although patients with esophageal squamous cell carcinoma (ESCC) can achieve a pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) followed by surgery, one-third of these patients with a pCR may still experience recurrence. The aim of this study is to develop and validate a predictive model to estimate recurrence-free survival (RFS) in those patients who achieved pCR. Materials and methods: Two hundred six patients with ESCC were enrolled and divided into a training cohort (n = 146) and a validation cohort (n = 60). Radiomic features were extracted from contrast-enhanced computed tomography (CT) images of each patient. Feature reduction was then implemented in two steps, including a multiple segmentation test and least absolute shrinkage and selection operator (LASSO) Cox proportional hazards regression method. A radiomics signature was subsequently constructed and evaluated. For better prediction performance, a clinical nomogram based on clinical risk factors and a nomogram incorporating the radiomics signature and clinical risk factors was built. Finally, the prediction models were further validated by calibration and the clinical usefulness was examined in the validation cohort to determine the optimal prediction model. Results: The radiomics signature was constructed using eight radiomic features and displayed a significant correlation with RFS. The nomogram incorporating the radiomics signature with clinical risk factors achieved optimal performance compared with the radiomics signature (P < 0.001) and clinical nomogram (P < 0.001) in both the training cohort [C-index (95% confidence interval [CI]), 0.746 (0.680-0.812) vs. 0.685 (0.620-0.750) vs. 0.614 (0.538-0.690), respectively] and validation cohort [C-index (95% CI), 0.724 (0.696-0.752) vs. 0.671 (0.624-0.718) vs. 0.629 (0.597-0.661), respectively]. The calibration curve and decision curve analysis revealed that the radiomics nomogram outperformed the other two models. Conclusions: A radiomics nomogram model incorporating radiomics features and clinical factors has been developed and has the improved ability to predict the postoperative recurrence risk in patients with ESCC who achieved pCR after nCRT followed by surgery.

Radiomics feature reproducibility under inter-rater variability in segmentations of CT images

Identifying image features that are robust with respect to segmentation variability is a tough challenge in radiomics. So far, this problem has mainly been tackled in test-retest analyses. In this work we analyse radiomics feature reproducibility in two phases: first with manual segmentations provided by four expert readers and second with probabilistic automated segmentations using a recently developed neural network (PHiseg). We test feature reproducibility on three publicly available datasets of lung, kidney and liver lesions. We find consistent results both over manual and automated segmentations in all three datasets and show that there are subsets of radiomic features which are robust against segmentation variability and other radiomic features which are prone to poor reproducibility under differing segmentations. By providing a detailed analysis of robustness of the most common radiomics features across several datasets, we envision that more reliable and reproducible radiomic models can be built in the future based on this work.

Robustness of CT radiomic features against image discretization and interpolation in characterizing pancreatic neuroendocrine neoplasms

PURPOSE

To explore the variation of the discriminative power of CT radiomic features (RF) against image discretization/interpolation in characterizing pancreatic neuro-endocrine (PanNEN) neoplasms.

MATERIALS AND METHODS

Thirty-nine PanNEN patients with pre-surgical high contrast CT available were considered. Image interpolation and discretization parameters were intentionally changed, including pixel size (0.73-2.19 mm²), slice thickness (2-5 mm) and binning (32-128 grey levels) and their combination generated 27 parameter's set. The ability of 69 RF in discriminating post-surgically assessed tumor grade (>G1), positive nodes, metastases and vascular invasion was tested: AUC changes when changing the parameters were quantified for selected RF, significantly associated to each end-point. The analysis was repeated for the corresponding images with contrast medium and in a sub-group of 29/39 patients scanned on a single scanner.

RESULTS

The median tumor volume was 1.57 cm³ (16%-84% percentiles: 0.62-34.58 cm³). RF variability against discretization/interpolation parameters was large: only 21/69 RF showed %COV < 20%. Despite this variability, AUC changes were limited for all end-points: with typical AUC values around 0.75-0.85, AUC ranges for the 27 parameter's set were on average 0.062 (1SD:0.037) for all end-points with maximum %COV equal to 5.5% (mean:2.3%). Performances significantly improved when excluding the 5 mm thickness case and fixing the binning to 64 (mean AUC range: 0.036, 1SD:0.019). Using contrast images or limiting the population to single-scanner patients had limited impact on AUC variability.

CONCLUSIONS

The discriminative power of CT RF for panNEN is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

Multiphase computed tomography radiomics of pancreatic intraductal papillary mucinous neoplasms to predict malignancy

BACKGROUND

Intraductal papillary mucinous neoplasms (IPMNs) are non-invasive pancreatic precursor lesions that can potentially develop into invasive pancreatic ductal adenocarcinoma. Currently, the International Consensus Guidelines (ICG) for IPMNs provides the basis for evaluating suspected IPMNs on computed tomography (CT) imaging. Despite using the ICG, it remains challenging to accurately predict whether IPMNs harbor high grade or invasive disease which would warrant surgical resection. A supplementary quantitative radiological tool, radiomics, may improve diagnostic accuracy of radiological evaluation of IPMNs. We hypothesized that using CT whole lesion radiomics features in conjunction with the ICG could improve the diagnostic accuracy of predicting IPMN histology.

AIM

To evaluate whole lesion CT radiomic analysis of IPMNs for predicting malignant histology compared to International Consensus Guidelines.

METHODS

Fifty-one subjects who had pancreatic surgical resection at our institution with histology demonstrating IPMN and available preoperative CT imaging were included in this retrospective cohort. Whole lesion semi-automated segmentation was performed on each preoperative CT using Healthmyne software (Healthmyne, Madison, WI). Thirty-nine relevant radiomic features were extracted from each lesion on each available contrast phase. Univariate analysis of the 39 radiomics features was performed for each contrast phase and values were compared between malignant and benign IPMN groups using logistic regression. Conventional quantitative and qualitative CT measurements were also compared between groups, via χ² (categorical) and Mann Whitney U (continuous) variables.

RESULTS

Twenty-nine subjects (15 males, age 71 ± 9 years) with high grade or invasive tumor histology comprised the "malignant" cohort, while 22 subjects (11 males, age 70 ± 7 years) with low grade tumor histology were included in the "benign" cohort. Radiomic analysis showed 18/39 precontrast, 19/39 arterial phase, and 21/39 venous phase features differentiated malignant from benign IPMNs (P < 0.05). Multivariate analysis including only ICG criteria yielded two significant variables: thickened and enhancing cyst wall and enhancing mural nodule < 5 mm with an AUC (95%CI) of 0.817 (0.709-0.926). Multivariable post contrast radiomics achieved an AUC (95%CI) of 0.87 (0.767-0.974) for a model including arterial phase radiomics features and 0.834 (0.716-0.953) for a model including venous phase radiomics features. Combined multivariable model including conventional variables and arterial phase radiomics features achieved an AUC (95%CI) of 0.93 (0.85-1.0) with a 5-fold cross validation AUC of 0.90.

CONCLUSION

Multi-phase CT radiomics evaluation could play a role in improving predictive capability in diagnosing malignancy in IPMNs. Future larger studies may help determine the clinical significance of our findings.

Radiomics in breast cancer classification and prediction

Breast Cancer (BC) is the common form of cancer in women. Its diagnosis and screening are usually performed through different imaging modalities such as mammography, magnetic resonance imaging and ultrasound. However, mammography and ultrasound-imaging techniques have limited sensitivity and specificity both in identifying lesions and in differentiating malign from benign lesions, especially in presence of dense breast parenchyma. Due to the higher resolution of magnetic resonance images, MRI represents the method with the higher specificity and sensitivity among all the available tools, in both lesions' identification and diagnosis. However, especially for diagnosis, even MRI has limitations that are only partially solved if combined with mammography. Unfortunately, due to the limits of all these imaging tools, in order to have a certain diagnosis, patients often receive painful and costly bioptics procedures. In this context, several computational approaches have been developed to increase sensitivity, while maintaining the same specificity, in BC diagnosis and screening. Amongst these, radiomics has been increasingly gaining ground in oncology to improve cancer diagnosis, prognosis and treatment. Radiomics derives multiple quantitative features from single or multiple medical imaging modalities, highlighting image traits which are not visible to the naked eye and hence significantly augmenting the discriminatory and predictive potential of medical imaging. This review article aims to summarize the state of the art in radiomics-based BC research. The dominating evidence extracted from the literature points towards a high potential of radiomics in disentangling malignant from benign breast lesions, classifying BC types and grades and also in predicting treatment response and recurrence risk. In the era of personalized medicine, radiomics has the potential to improve diagnosis, prognosis, prediction, monitoring, image-based intervention, and assessment of therapeutic response in BC.

A Contrast-Enhanced Computed Tomography Based Radiomics Approach for Preoperative Differentiation of Pancreatic Cystic Neoplasm Subtypes: A Feasibility Study

Background: Serous cystadenoma (SCA), mucinous cystadenoma (MCN), and intraductal papillary mucinous neoplasm (IPMN) are three subtypes of pancreatic cystic neoplasm (PCN). Due to the potential of malignant-transforming, patients with MCN and IPMN require radical surgery while patients with SCA need periodic surveillance. However, accurate pre-surgery diagnosis between SCA, MCN, and IPMN remains challenging in the clinic. Methods: This study enrolled 164 patients including 76 with SCA, 40 with MCN and 48 with IPMN. Patients were randomly split into a training cohort (n = 115) and validation cohort (n = 41). We performed statistical analysis and Boruta method to screen significantly distinct clinical factors and radiomics features extracted on pre-surgery contrast-enhanced computed tomography (CECT) images among three subtypes. Three reliable machine-learning algorithms, support vector machine (SVM), random forest (RF) and artificial neural network (ANN), were utilized to construct classifiers based on important radiomics features and clinical parameters. Precision, recall, and F1-score were calculated to assess the performance of the constructed classifiers. Results: Nine of 547 radiomics features and eight clinical factors showed a significant difference among SCA, MCN, and IPMN. Five radiomics features (Histogram_Entropy, Histogram_Skeweness, LLL_GLSZM_GLV, Histogram_Uniformity, HHL_Histogram_Kurtosis), and four clinical factors, including serum carbohydrate antigen 19-9, sex, age, and serum carcinoembryonic antigen, were identified important by Boruta method. The SVM classifier achieved an overall accuracy of 73.04% in training cohort and 71.43% in validation cohort, respectively. The RF classifier achieved overall accuracy of 84.35 and 79.59%, respectively. The constructed ANN model showed an overall accuracy of 77.39% in the training dataset and 71.43% in the validation dataset. All the three classifiers showed high F1 score for differentiation among the three subtypes. Conclusion: Our study proved the feasibility and translational value of CECT-based radiomics classifiers for differentiation among SCA, MCN, and IPMN.

Radiogenomics: bridging imaging and genomics

From diagnostics to prognosis to response prediction, new applications for radiomics are rapidly being developed. One of the fastest evolving branches involves linking imaging phenotypes to the tumor genetic profile, a field commonly referred to as "radiogenomics." In this review, a general outline of radiogenomic literature concerning prominent mutations across different tumor sites will be provided. The field of radiogenomics originates from image processing techniques developed decades ago; however, many technical and clinical challenges still need to be addressed. Nevertheless, increasingly accurate and robust radiogenomic models are being presented and the future appears to be bright.