Combining Multiple Magnetic Resonance Imaging Sequences Provides Independent Reproducible Radiomics Features

Radiomics in Diagnosis, Grading, and Treatment Response Assessment of Soft Tissue Sarcomas: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance.

METHODS

In this diagnostic accuracy study, radiomics was applied using multiple MRI sequences and AI classifiers, with histopathological diagnosis as the reference standard. Statistical analysis involved meta-analysis, random-effects model, and Deeks' funnel plot asymmetry test.

RESULTS

Among 579 unique titles and abstracts, 24 articles were included in the systematic review, with 21 used for meta-analysis. Radiomics demonstrated a pooled sensitivity of 84% (95% CI: 80-87) and specificity of 63% (95% CI: 56-70), AUC of 0.93 for diagnosis, sensitivity of 84% (95% CI: 82-87) and specificity of 73% (95% CI: 68-77), AUC of 0.91 for grading, and sensitivity of 83% (95% CI: 67-94) and specificity of 67% (95% CI: 59-74), AUC of 0.87 for treatment response assessment.

CONCLUSION

Radiomics exhibits potential for accurate diagnosis, grading, and treatment response assessment in STSs, emphasizing the need for standardization and prospective trials.

CLINICAL RELEVANCE STATEMENT

Radiomics offers precise tools for STS diagnosis, grading, and treatment response assessment, with implications for optimizing patient care and treatment strategies in this complex malignancy.

Radiogenomics models for predicting prognosis in locally advanced non-small cell lung cancer patients undergoing definitive chemoradiotherapy

Background

Definitive chemoradiotherapy (dCRT) is the cornerstone for locally advanced non-small cell lung cancer (LA-NSCLC). The study aimed to construct a multi-omics model integrating baseline clinical data, computed tomography (CT) images and genetic information to predict the prognosis of dCRT in LA-NSCLC patients.

Methods

The study retrospectively enrolled 105 stage III LA-NSCLC patients who had undergone dCRT. The pre-treatment CT images were collected, and the primary tumor was delineated as a region of interest (ROI) on the image using 3D-Slicer, and the radiomics features were extracted. The least absolute shrinkage and selection operator (LASSO) was employed for dimensionality reduction and selection of features. Genomic information was obtained from the baseline tumor tissue samples. We then constructed a multi-omics model by combining baseline clinical data, radiomics and genomics features. The predictive performance of the model was evaluated by the area under the curve (AUC) of the receiver operating characteristic (ROC) and the concordance index (C-index).

Results

The median follow-up time was 30.1 months, and the median progression-free survival (PFS) was 10.60 months. Four features were applied to construct the radiomics model. Multivariable analysis demonstrated the Rad-score, KEAP1 and MET mutations were independent prognostic factors for PFS. The C-index of radiomics model, genomics model and radiogenomics model all performed well in the training group (0.590 vs. 0.606 vs. 0.663) and the validation group (0.599 vs. 0.594 vs. 0.650).

Conclusions

The radiomics model, genomics model and radiogenomics model can all predict the prognosis of dCRT for LA-NSCLC, and the radiogenomics model is superior to the single type model.

Magnetic Resonance Image Radiomic Reproducibility: The Impact of Preprocessing on Extracted Features from Gross and High-Risk Clinical Tumor Volumes in Cervical Cancer Patients before Brachytherapy

Background

Radiomic feature reproducibility assessment is critical in radiomics-based image biomarker discovery. This study aims to evaluate the impact of preprocessing parameters on the reproducibility of magnetic resonance image (MRI) radiomic features extracted from gross tumor volume (GTV) and high-risk clinical tumor volume (HR-CTV) in cervical cancer (CC) patients.

Methods

This study included 99 patients with pathologically confirmed cervical cancer who underwent an MRI prior to receiving brachytherapy. The GTV and HR-CTV were delineated on T2-weighted MRI and inputted into 3D Slicer for radiomic analysis. Before feature extraction, all images were preprocessed to a combination of several parameters of Laplacian of Gaussian (1 and 2), resampling (0.5 and 1), and bin width (5, 10, 25, and 50). The reproducibility of radiomic features was analyzed using the intra-class correlation coefficient (ICC).

Results

Almost all shapes and first-order features had ICC values > 0.95. Most second-order texture features were not reproducible (ICC < 0.95) in GTV and HR-CTV. Furthermore, 20% of all neighboring gray-tone difference matrix texture features had ICC > 0.90 in both GTV and HR-CTV.

Conclusion

The results presented here showed that MRI radiomic features are vulnerable to changes in preprocessing, and this issue must be understood and applied before any clinical decision-making. Features with ICC > 0.90 were considered the most reproducible features. Shape and first-order radiomic features were the most reproducible features in both GTV and HR-CTV. Our results also showed that GTV and HR-CTV radiomic features had similar changes against preprocessing sets.

MRI quantitative assessment of the effects of low-carbohydrate therapy on Hashimoto's thyroiditis

Objective

Hashimoto's thyroiditis is an inflammatory disease, and research suggests that a low-carbohydrate diet may have potential anti-inflammatory effects. This study aims to utilize Dixon-T2-weighted imaging (WI) sequence for a semi-quantitative assessment of the impact of a low-carbohydrate diet on the degree of thyroid inflammation in patients with Hashimoto's thyroiditis.

Methods

Forty patients with Hashimoto's thyroiditis were recruited for this study and randomly divided into two groups: one with a normal diet and the other with a low-carbohydrate diet. Antibodies against thyroid peroxidase (TPOAb) and thyroglobulin (TgAb) were measured for all participants. Additionally, thyroid water content was semi-quantitatively measured using Dixon-T2WI. The same tests and measurements were repeated for all participants after 6 months.

Results

After 6 months of a low-carbohydrate diet, patients with Hashimoto's thyroiditis showed a significant reduction in thyroid water content (94.84 ± 1.57% vs 93.07 ± 2.05%, P < 0.05). Concurrently, a decrease was observed in levels of TPOAb and TgAb (TPOAb: 211.30 (92.63-614.62) vs 89.45 (15.9-215.67); TgAb: 17.05 (1.47-81.64) vs 4.1 (0.51-19.42), P < 0.05). In contrast, there were no significant differences in thyroid water content or TPOAb and TgAb levels for patients with Hashimoto's thyroiditis following a normal diet after 6 months (P < 0.05).

Conclusion

Dixon-T2WI can quantitatively assess the degree of thyroid inflammation in patients with Hashimoto's thyroiditis. Following a low-carbohydrate diet intervention, there is a significant reduction in thyroid water content and a decrease in levels of TPOAb and TgAb. These results suggest that a low-carbohydrate diet may help alleviate inflammation in patients with Hashimoto's thyroiditis.

Magnetic resonance imaging radiomic features stability in brain metastases: Impact of image preprocessing, image-, and feature-level harmonization

Background and purpose

Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs).

Materials and methods

Two T1 contrast enhanced brain MRI data-sets were used in this study. The first contained 25 BMs patients with scans at two different time points and was used for features stability analysis. The effect of gray level discretization (GLD), intensity normalization (Z-score, Nyul, WhiteStripe, and in house-developed method named N-Peaks), and ComBat harmonization on features stability was investigated and features with intraclass correlation coefficient >0.8 were considered as stable. The second data-set containing 64 BMs patients was used for a classification task to investigate the informativeness of stable features and the effects of harmonization methods on radiomic model performance.

Results

Applying fixed bin number (FBN) GLD, resulted in higher number of stable features compare to fixed bin size (FBS) discretization (10 ± 5.5 % higher). `Harmonization in feature domain improved the stability for non-normalized and normalized images with Z-score and WhiteStripe methods. For the classification task, keeping the stable features resulted in good performance only for normalized images with N-Peaks along with FBS discretization.

Conclusions

To develop a robust MRI based radiomic model we recommend using an intensity normalization method based on a reference tissue (e.g N-Peaks) and then using FBS discretization.

Diagnostic Performance of Dynamic Contrast-Enhanced 3T MR Imaging for Characterization of Orbital Lesions: Validation in a Large Prospective Study

BACKGROUND AND PURPOSE

Orbital lesions are rare but serious. Their characterization remains challenging. Diagnosis is based on biopsy or surgery, which implies functional risks. It is necessary to develop noninvasive diagnostic tools. The goal of this study was to evaluate the diagnostic performance of dynamic contrast-enhanced MR imaging at 3T when distinguishing malignant from benign orbital tumors on a large prospective cohort.

MATERIALS AND METHODS

This institutional review board-approved prospective single-center study enrolled participants presenting with an orbital lesion undergoing a 3T MR imaging before surgery from December 2015 to May 2021. Morphologic, diffusion-weighted, and dynamic contrast-enhanced MR images were assessed by 2 readers blinded to all data. Univariable and multivariable analyses were performed. To assess diagnostic performance, we used the following metrics: area under the curve, sensitivity, and specificity. Histologic analysis, obtained through biopsy or surgery, served as the criterion standard for determining the benign or malignant status of the tumor.

RESULTS

One hundred thirty-one subjects (66/131 [50%] women and 65/131 [50%] men; mean age, 52 [SD, 17.1] years; range, 19-88 years) were enrolled. Ninety of 131 (69%) had a benign lesion, and 41/131 (31%) had a malignant lesion. Univariable analysis showed a higher median of transfer constant from blood plasma to the interstitial environment (K trans) and of transfer constant from the interstitial environment to the blood plasma (minute-1) (Kep) and a higher interquartile range of K trans in malignant-versus-benign lesions (1.1 minute-1 versus 0.65 minute-1, P = .03; 2.1 minute-1 versus 1.1 minute-1, P = .01; 0.81 minute-1 versus 0.65 minute-1, P = .009, respectively). The best-performing multivariable model in distinguishing malignant-versus-benign lesions included parameters from dynamic contrast-enhanced imaging, ADC, and morphology and reached an area under the curve of 0.81 (95% CI, 0.67-0.96), a sensitivity of 0.82 (95% CI, 0.55-1), and a specificity of 0.81 (95% CI, 0.65-0.96).

CONCLUSIONS

Dynamic contrast-enhanced MR imaging at 3T appears valuable when characterizing orbital lesions and provides complementary information to morphologic imaging and DWI.

Achieving imaging and computational reproducibility on multiparametric MRI radiomics features in brain tumor diagnosis: phantom and clinical validation

OBJECTIVES

The Image Biomarker Standardization Initiative has helped improve the computational reproducibility of MRI radiomics features. Nonetheless, the MRI sequences and features with high imaging reproducibility are yet to be established. To determine reproducible multiparametric MRI radiomics features across test-retest, multi-scanner, and computational reproducibility comparisons, and to evaluate their clinical value in brain tumor diagnosis.

METHODS

To assess reproducibility, T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) were acquired from three 3-T MRI scanners using standardized phantom, and radiomics features were extracted using two computational algorithms. Reproducible radiomics features were selected when the concordance correlation coefficient value above 0.9 across multiple sessions, scanners, and computational algorithms. Random forest classifiers were trained with reproducible features (n = 117) and validated in a clinical cohort (n = 50) to evaluate whether features with high reproducibility improved the differentiation of glioblastoma from primary central nervous system lymphomas (PCNSLs).

RESULTS

Radiomics features from T2WI demonstrated higher repeatability (65-94%) than those from DWI (38-48%) or T1WI (2-92%). Across test-retest, multi-scanner, and computational comparisons, T2WI provided 41 reproducible features, DWI provided six, and T1WI provided two. The performance of the classification model with reproducible features was higher than that using non-reproducible features in both training set (AUC, 0.916 vs. 0.877) and validation set (AUC, 0.957 vs. 0.869).

CONCLUSION

Radiomics features with high reproducibility across multiple sessions, scanners, and computational algorithms were identified, and they showed higher diagnostic performance than non-reproducible radiomics features in the differentiation of glioblastoma from PCNSL.

CLINICAL RELEVANCE STATEMENT

By identifying the radiomics features showing higher multi-machine reproducibility, our results also demonstrated higher radiomics diagnostic performance in the differentiation of glioblastoma from PCNSL, paving the way for further research designs and clinical application in neuro-oncology.

KEY POINTS

• Highly reproducible radiomics features across multiple sessions, scanners, and computational algorithms were identified using phantom and applied to clinical diagnosis. • Radiomics features from T2-weighted imaging were more reproducible than those from T1-weighted and diffusion-weighted imaging. • Radiomics features with good reproducibility had better diagnostic performance for brain tumors than features with poor reproducibility.

Accuracy of Radiomics in Predicting IDH Mutation Status in Diffuse Gliomas: A Bivariate Meta-Analysis

Purpose To perform a systematic review and meta-analysis assessing the predictive accuracy of radiomics in the noninvasive determination of isocitrate dehydrogenase (IDH) status in grade 4 and lower-grade diffuse gliomas. Materials and Methods A systematic search was performed in the PubMed, Scopus, Embase, Web of Science, and Cochrane Library databases for relevant articles published between January 1, 2010, and July 7, 2021. Pooled sensitivity and specificity across studies were estimated. Risk of bias was evaluated using Quality Assessment of Diagnostic Accuracy Studies-2, and methods were evaluated using the radiomics quality score (RQS). Additional subgroup analyses were performed according to tumor grade, RQS, and number of sequences used (PROSPERO ID: CRD42021268958). Results Twenty-six studies that included 3280 patients were included for analysis. The pooled sensitivity and specificity of radiomics for the detection of IDH mutation were 79% (95% CI: 76, 83) and 80% (95% CI: 76, 83), respectively. Low RQS scores were found overall for the included works. Subgroup analyses showed lower false-positive rates in very low RQS studies (RQS < 6) (meta-regression, z = -1.9; P = .02) compared with adequate RQS studies. No substantial differences were found in pooled sensitivity and specificity for the pure grade 4 gliomas group compared with the all-grade gliomas group (81% and 86% vs 79% and 79%, respectively) and for studies using single versus multiple sequences (80% and 77% vs 79% and 82%, respectively). Conclusion The pooled data showed that radiomics achieved good accuracy performance in distinguishing IDH mutation status in patients with grade 4 and lower-grade diffuse gliomas. The overall methodologic quality (RQS) was low and introduced potential bias. Keywords: Neuro-Oncology, Radiomics, Integration, Application Domain, Glioblastoma, IDH Mutation, Radiomics Quality Scoring Supplemental material is available for this article. Published under a CC BY 4.0 license.

Artificial Intelligence-Assisted Processing of Anterior Segment OCT Images in the Diagnosis of Vitreoretinal Lymphoma

Anterior segment optical coherence tomography (AS-OCT) allows the explore not only the anterior chamber but also the front part of the vitreous cavity. Our cross-sectional single-centre study investigated whether AS-OCT can distinguish between vitreous involvement due to vitreoretinal lymphoma (VRL) and vitritis in uveitis. We studied AS-OCT images from 28 patients (11 with biopsy-proven VRL and 17 with differential diagnosis uveitis) using publicly available radiomics software written in MATLAB. Patients were divided into two balanced groups: training and testing. Overall, 3260/3705 (88%) AS-OCT images met our defined quality criteria, making them eligible for analysis. We studied five different sets of grey-level samplings (16, 32, 64, 128, and 256 levels), finding that 128 grey levels performed the best. We selected the five most effective radiomic features ranked by the ability to predict the class (VRL or uveitis). We built a classification model using the xgboost python function; through our model, 87% of eyes were correctly diagnosed as VRL or uveitis, regardless of exam technique or lens status. Areas under the receiver operating characteristic curves (AUC) in the 128 grey-level model were 0.95 [CI 0.94, 0.96] and 0.84 for training and testing datasets, respectively. This preliminary retrospective study highlights how AS-OCT can support ophthalmologists when there is clinical suspicion of VRL.

Statistical Analysis on Impact of Image Preprocessing of CT Texture Patterns and Its CT Radiomic Feature Stability: A Phantom Study

AIM

To examine computed tomography (CT) radiomic feature stability on various texture patterns during pre-processing utilizing the Credence Cartridge Radiomics (CCR) phantom textures.

MATERIALS AND METHODS

Imaging Biomarker Explorer (IBEX) expansion for the abbreviation IBEX extracted 51 radiomic features of 4 categories from 11 textures image regions of interest (ROI) of the phantom. 19 software pre-processing algorithms processed each CCR phantom ROI. All ROI texture processed image features were retrieved. Pre-processed CT image radiomic features were compared to non-processed features to measure its textural influence. Wilcoxon T-tests measured the pre-processing relevance of CT radiomic features on various textures. Hierarchical cluster analysis (HCA) was performed to cluster processer potency and texture impression likeness.

RESULTS

The pre-processing filter, CT texture Cartridge, and feature category affect the CCR phantom CT image's radiomic properties. Pre-processing is statistically unaltered by Gray Level Run Length Matrix (GLRLM ) expansion  for the abbreviation GLRLM and Neighborhood Intensity Difference matrix (NID) expansion for the abbreviation NID feature categories. The 30%, 40%, and 50% honeycomb are regular directional textures and smooth 3D-printed plaster resin, most of the image pre-processing feature alterations exhibited significant p-values in the histogram feature category. The Laplacian Filter, Log Filter, Resample, and Bit Depth Rescale Range pre-processing algorithms hugely influenced histogram and Gray Level Co-occurrence Matrix (GLCM) image features.

CONCLUSION

We found that homogenous intensity phantom inserts, CT radiomic feature, are less sensitive to feature swaps during pre-processing than normal directed honeycomb and regular projected smooth 3D-printed plaster resin CT image textures. Because they lose fewer information during image enhancement, This feature concentration empowerment of the images also enhances texture pattern recognition.

Combination of vertebral bone quality scores from different magnetic resonance imaging sequences improves prognostic value for the estimation of osteoporosis

BACKGROUND CONTEXT

Recent findings revealed a correlation between vertebral bone quality based on T1-weighted (VBQ_T1) magnetic resonance imaging (MRI) and volumetric bone mass density (vBMD) measured using quantitative computerized tomography. The coherence of VBQ for other MRI sequences, such as T2 or short tau inversion recovery (STIR), has not been examined. The combination of different VBQs has not been studied.

PURPOSE

The aims of the study were to confirm the correlation between VBQ_T1 and vBMD and to examine VBQs from other MRI sequences and their combination with vBMD.

STUDY DESIGN/SETTING

This was a retrospective cross-sectional study.

PATIENT SAMPLE

The sample consisted of patients older than 18 years, who received treatment at a level-one university spine center of the German Spine Society for degenerative or traumatic reasons in 2017-2021.

OUTCOME MEASURES

The outcome measures were the correlation of VBQs from different MRI sequences with vBMD and the association of VBQs with osteopenia/osteoporosis.

METHODS

Patients' VBQ was calculated based on the signal intensities of the vertebral bodies L1-4 in T1-, T2-, and STIR-weighted MRI. The VBQ was standardized according to the signal intensity of the cerebrospinal fluid. The vBMD was determined using data from a calibrated scanner (SOMATOM Definition AS+) and processed with CliniQCT (Mindways Software, Inc., USA). Groups were divided according to vBMD into the following groups: (I) osteoporosis/osteopenia (< 120 mg/m³) and (II) healthy (≥120 mg/m³). An analysis of the correlation between various VBQs and vBMD as well as receiver operating characteristic (ROC) and binary regression analyses were performed for the prediction of osteoporosis/osteopenia.

RESULTS

We included 136 patients (women: 56.6%) in the study (69.7 ± 15.0 years). According to vBMD, 108 patients (79.4%) had osteoporosis/osteopenia. Women were affected significantly more often than men (p = .045) and had significantly higher VBQ_T1 and VBQ_T2 values than men (VBQ_T1: p = .048; VBQ_T2: p = .013). VBQ_T1 and VBQ_T2 values were significantly higher in patients with osteoporosis/osteopenia than in healthy persons (VBQ_T1: p<.001; VBQ_T2: p = .025). VBQ_T1 and VBQ_T2 were significantly negatively correlated with vBMD with a moderate effect size (p<.001), while VBQ_STIR was not significantly correlated with vBMD, although it showed a positive coherence. The combination of different VBQs in terms of VBQ_T1 × VBQ_T2 / VBQ_STIR distinctly increased the effect size of the negative correlation with vBMD compared to VBQ alone. A cutoff value for VBQ_T1 × VBQ_T2 / VBQ_STIR of 2.9179 achieved a sensitivity of 80.0%, a specificity of 75.0%, and an area under the curve (AUC) of 0.775 for the determination of osteoporosis. The mathematical model derived from the binary logistic regression showed an excellent AUC of 0.846.

CONCLUSIONS

This study confirms a significant correlation between VBQ_T1 and vBMD. The combination of VBQs from different MRI sequences enhances the prognostic value of VBQ for the determination of osteoporosis. While safe clinical application of VBQ for the determination of osteoporosis requires further validation, VBQ might offer opportunistic estimation for further diagnostics.

Robustness of radiomics to variations in segmentation methods in multimodal brain MRI

Radiomics in neuroimaging uses fully automatic segmentation to delineate the anatomical areas for which radiomic features are computed. However, differences among these segmentation methods affect radiomic features to an unknown extent. A scan-rescan dataset (n = 46) of T1-weighted and diffusion tensor images was used. Subjects were split into a sleep-deprivation and a control group. Scans were segmented using four segmentation methods from which radiomic features were computed. First, we measured segmentation agreement using the Dice-coefficient. Second, robustness and reproducibility of radiomic features were measured using the intraclass correlation coefficient (ICC). Last, difference in predictive power was assessed using the Friedman-test on performance in a radiomics-based sleep deprivation classification application. Segmentation agreement was generally high (interquartile range = 0.77–0.90) and median feature robustness to segmentation method variation was higher (ICC > 0.7) than scan-rescan reproducibility (ICC 0.3–0.8). However, classification performance differed significantly among segmentation methods (p < 0.001) ranging from 77 to 84%. Accuracy was higher for more recent deep learning-based segmentation methods. Despite high agreement among segmentation methods, subtle differences significantly affected radiomic features and their predictive power. Consequently, the effect of differences in segmentation methods should be taken into account when designing and evaluating radiomics-based research methods.

The Diagnostic Value of MRI-Based Radiomic Analysis of Lacrimal Glands in Patients with Sjögren's Syndrome

This study aimed to assess the effectiveness of MRI-based texture features of the lacrimal glands (LG) in augmenting the imaging differentiation between primary Sjögren’s Syndrome (pSS) affected LG and healthy LG, as well as to emphasize the possible importance of radiomics in pSS early-imaging diagnosis. The MRI examinations of 23 patients diagnosed with pSS and 23 healthy controls were retrospectively included. Texture features of both LG were extracted from a coronal post-contrast T1-weighted sequence, using a dedicated software. The ability of texture features to discriminate between healthy and pSS lacrimal glands was performed through univariate, multivariate, and receiver operating characteristics analysis. Two quantitative textural analysis features, RunLengthNonUniformityNormalized (RLNonUN) and Maximum2DDiameterColumn (Max2DDC), were independent predictors of pSS-affected glands (p < 0.001). Their combined ability was able to identify pSS LG with 91.67% sensitivity and 83.33% specificity. MRI-based texture features have the potential to function as quantitative additional criteria that could increase the diagnostic accuracy of pSS-affected LG.

Preoperative Prediction of Inferior Vena Cava Wall Invasion of Tumor Thrombus in Renal Cell Carcinoma: Radiomics Models Based on Magnetic Resonance Imaging

Objective

To develop radiomics models to predict inferior vena cava (IVC) wall invasion by tumor thrombus (TT) in patients with renal cell carcinoma (RCC).

Methods

Preoperative MR images were retrospectively collected from 91 patients with RCC who underwent radical nephrectomy (RN) and thrombectomy. The images were randomly allocated into a training (n = 64) and validation (n = 27) cohort. The inter-and intra-rater agreements were organized to compare masks delineated by two radiologists. The masks of TT and IVC were manually annotated on axial fat-suppression T2-weighted images (fsT2WI) by one radiologist. The following models were trained to predict the probability of IVC wall invasion: two radiomics models using radiomics features extracted from the two masks (model 1, radiomics model_IVC; model 2, radiomics model_TT), two combined models using radiomics features and radiological features (model 3, combined model_IVC; model 4, combined model_TT), and one radiological model (model 5) using radiological features. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were applied to validate the discriminatory effect and clinical benefit of the models.

Results

Model 1 to model 5 yielded area under the curves (AUCs) of 0.881, 0.857, 0.883, 0.889, and 0.769, respectively, in the validation cohort. No significant differences were found between these models (p = 0.108-0.951). The dicision curve analysis (DCA) showed that the model 3 had a higher overall net benefit than the model 1, model 2, model 4, and model 5.

Conclusions

The combined model_IVC (model 3) based on axial fsT2WI exhibited excellent predictive performance in predicting IVC wall invasion status.

Image resampling and discretization effect on the estimate of myocardial radiomic features from T1 and T2 mapping in hypertrophic cardiomyopathy

Radiomics is emerging as a promising and useful tool in cardiac magnetic resonance (CMR) imaging applications. Accordingly, the purpose of this study was to investigate, for the first time, the effect of image resampling/discretization and filtering on radiomic features estimation from quantitative CMR T1 and T2 mapping. Specifically, T1 and T2 maps of 26 patients with hypertrophic cardiomyopathy (HCM) were used to estimate 98 radiomic features for 7 different resampling voxel sizes (at fixed bin width), 9 different bin widths (at fixed resampling voxel size), and 7 different spatial filters (at fixed resampling voxel size/bin width). While we found a remarkable dependence of myocardial radiomic features from T1 and T2 mapping on image filters, many radiomic features showed a limited sensitivity to resampling voxel size/bin width, in terms of intraclass correlation coefficient (> 0.75) and coefficient of variation (< 30%). The estimate of most textural radiomic features showed a linear significant (p < 0.05) correlation with resampling voxel size/bin width. Overall, radiomic features from T2 maps have proven to be less sensitive to image preprocessing than those from T1 maps, especially when varying bin width. Our results might corroborate the potential of radiomics from T1/T2 mapping in HCM and hopefully in other myocardial diseases.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

Evaluation of lateral pterygoid muscle in patients with temporomandibular joint anterior disk displacement using T1-weighted Dixon sequence: a retrospective study

Background

Pathological alterations of lateral pterygoid muscle (LPM) are implicated in temporomandibular joint anterior disk displacement (ADD). However, quantification of the fatty infiltration of LPM and its correlation with ADD have rarely been reported. The aim of this study was to evaluate the fatty infiltration, morphological features and texture features of LPM in patients with ADD using T1-weighted Dixon sequence.

Methods

This retrospective study included patients who underwent temporomandibular joint MRI with T1-weighted Dixon sequence between December 2018 and August 2020. The temporomandibular joints of the included patients were divided into three groups according to the position of disk: Normal position disk (NP) group, Anterior disk displacement with reduction (ADDWR) group and Anterior disk displacement without reduction (ADDWOR) group. Fat fraction, morphological features (Length; Width; Thickness), and texture features (Angular second moment; Contrast; Correlation; Inverse different moment; Entropy) extracted from in-phase image of LPM were evaluated. One-way ANOVA, Welch’s ANOVA, Kruskal–Wallis test, Spearman and Pearson correlation analysis were performed. Intra-class correlation coefficient was used to evaluate the reproducibility.

Results

A total of 53 patients with 106 temporomandibular joints were evaluated. Anterior disk displacement without reduction group showed higher fat fraction than normal position disk group (P = 0.024). Length of LPM was negatively correlated with fat fraction (r = -0.22, P = 0.026). Angular second moment (ρ = -0.32, P < 0.001), correlation (ρ = -0.28, P = 0.003) and inverse different moment (ρ = -0.27, P = 0.005) were negatively correlated with fat fraction, while positive correlation was found between entropy and fat fraction (ρ = 0.31, P = 0.001). The intra-class correlation coefficients for all values were ranged from 0.80 to 0.97.

Conclusions

Patients with ADDWOR present more fatty infiltration in the LPM compared to NP or ADDWR patients. Fatty infiltration of LPM was associated with more atrophic and higher intramuscular heterogeneity in patients with ADD. Fat fraction of LPM quantitatively and noninvasively evaluated by Dixon sequence may has utility as an imaging-based marker of the structural severity of ADD disease process, which could be clinical helpful for the early diagnose of ADD and predication of disease progression.

Can we use radiomics in ultrasound imaging? Impact of preprocessing on feature repeatability

PURPOSE

The purpose of this study was to assess the inter-slice radiomic feature repeatability in ultrasound imaging and the impact of preprocessing using intensity standardization and grey-level discretization to help improve radiomics reproducibility.

MATERIALS AND METHODS

This single-center study enrolled consecutive patients with an orbital lesion who underwent ultrasound examination of the orbit from December 2015 to July 2019. Two images per lesion were randomly assigned to two subsets. Radiomic features were extracted and inter-slice repeatability was assessed using the intraclass correlation coefficient (ICC) between the subsets. The impact of preprocessing on feature repeatability was assessed using image intensity standardization with or without outliers removal on whole images, bounding boxes or regions of interest (ROI), and fixed bin size or fixed bin number grey-level discretization. Number of inter-slice repeatable features (ICC ≥0.7) between methods was compared.

RESULTS

Eighty-eight patients (37 men, 51 women) with a mean age of 51.5 ± 17 (SD) years (range: 20-88 years) were enrolled. Without preprocessing, 29/101 features (28.7%) were repeatable between slices. The greatest number of repeatable features (41/101) was obtained using intensity standardization with outliers removal on the ROI and fixed bin size discretization. Standardization performed better with outliers removal than without (P < 0.001), and on ROIs than on native images (P < 0.001). Fixed bin size discretization performed better than fixed bin number (P = 0.008).

CONCLUSION

Radiomic features extracted from ultrasound images are impacted by the slice and preprocessing. The use of intensity standardization with outliers removal applied to the ROI and a fixed bin size grey-level discretization may improve feature repeatability.

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.

Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer

Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.

Generating Virtual Short Tau Inversion Recovery (STIR) Images from T1- and T2-Weighted Images Using a Conditional Generative Adversarial Network in Spine Imaging

Short tau inversion recovery (STIR) sequences are frequently used in magnetic resonance imaging (MRI) of the spine. However, STIR sequences require a significant amount of scanning time. The purpose of the present study was to generate virtual STIR (vSTIR) images from non-contrast, non-fat-suppressed T1- and T2-weighted images using a conditional generative adversarial network (cGAN). The training dataset comprised 612 studies from 514 patients, and the validation dataset comprised 141 studies from 133 patients. For validation, 100 original STIR and respective vSTIR series were presented to six senior radiologists (blinded for the STIR type) in independent A/B-testing sessions. Additionally, for 141 real or vSTIR sequences, the testers were required to produce a structured report of 15 different findings. In the A/B-test, most testers could not reliably identify the real STIR (mean error of tester 1-6: 41%; 44%; 58%; 48%; 39%; 45%). In the evaluation of the structured reports, vSTIR was equivalent to real STIR in 13 of 15 categories. In the category of the number of STIR hyperintense vertebral bodies (p = 0.08) and in the diagnosis of bone metastases (p = 0.055), the vSTIR was only slightly insignificantly equivalent. By virtually generating STIR images of diagnostic quality from T1- and T2-weighted images using a cGAN, one can shorten examination times and increase throughput.

Reproducibility of lung nodule radiomic features: Multivariable and univariable investigations that account for interactions between CT acquisition and reconstruction parameters

PURPOSE

Recent studies have demonstrated a lack of reproducibility of radiomic features in response to variations in CT parameters. In addition, reproducibility of radiomic features has not been well established in clinical datasets. We aimed to investigate the effects of a wide range of CT acquisition and reconstruction parameters on radiomic features in a realistic setting using clinical low dose lung cancer screening cases. We performed univariable and multivariable explorations to consider the effects of individual parameters and the simultaneous interactions between three different acquisition/reconstruction parameters of radiation dose level, reconstructed slice thickness, and kernel.

METHOD

A cohort of 89 lung cancer screening patients were collected that each had a solid lung nodule >4mm diameter. A computational pipeline was used to perform a simulation of dose reduction of the raw projection data, collected from patient scans. This was followed by reconstruction of raw data with weighted filter back projection (wFBP) algorithm and automatic lung nodule detection and segmentation using a computer-aided detection tool. For each patient, 36 different image datasets were created corresponding to dose levels of 100%, 50%, 25%, and 10% of the original dose level, three slice thicknesses of 0.6 mm, 1 mm, and 2 mm, as well as three reconstruction kernels of smooth, medium, and sharp. For each nodule, 226 well-known radiomic features were calculated at each image condition. The reproducibility of radiomic features was first evaluated by measuring the intercondition agreement of the feature values among the 36 image conditions. Then in a series of univariable analyses, the impact of individual CT parameters was assessed by selecting subsets of conditions with one varying and two constant CT parameters. In each subset, intraparameter agreements were assessed. Overall concordance correlation coefficient (OCCC) served as the measure of agreement. An OCCC ≥ 0.9 implied strong agreement and reproducibility of radiomic features in intercondition or intraparameter comparisons. Furthermore, the interaction of CT parameters in impacting radiomic feature values was investigated via ANOVA.

RESULTS

All included radiomic features lacked intercondition reproducibility (OCCC < 0.9) among all the 36 conditions. Out of 226 radiomic features analyzed, only 17 and 18 features were considered reproducible (OCCC ≥ 0.9) to dose and kernel variation, respectively, within the corresponding condition subsets. Slice thickness demonstrated the largest impact on radiomic feature values where only one to five features were reproducible at a few condition subsets. ANOVA revealed significant interactions (P < 0.05) between CT parameters affecting the variability of >50% of radiomic features.

CONCLUSION

We systematically explored the multidimensional space of CT parameters in affecting lung nodule radiomic features. Univariable and multivariable analyses of this study not only showed the lack of reproducibility of the majority of radiomic features but also revealed existing interactions among CT parameters, meaning that the effect of individual CT parameters on radiomic features can be conditional upon other CT acquisition and reconstruction parameters. Our findings advise on careful radiomic feature selection and attention to the inclusion criteria for CT image acquisition protocols within the datasets of radiomic studies.

Radiomics Based on Lumbar Spine Magnetic Resonance Imaging to Detect Osteoporosis

RATIONALE AND OBJECTIVES

Signal intensity of the lumbar spine in magnetic resonance imaging (MRI) correlates to bone mineral density (BMD). This study aims to explore a lumbar spine magnetic resonance imaging based on the radiomics model for detecting osteoporosis.

MATERIALS AND METHODS

A total of 109 patients, who underwent both dual-energy X-ray absorptiometry (DEXA) and MRI of the lumbar spine, were recruited. Among these patients, 38 patients were normal, 32 patients had osteopenia, and 39 patients had osteoporosis, according to the DEXA results. A total of 396 × 2 radiomic features were extracted from the T1WI and T2WI images of the segmentation images in the lumbar magnetic resonance imaging. The correlated radiomic features were selected to establish the radiomic classification model. Then, the classification models (based on T1WI, T2WI, and T1WI+T2WI) of normal vs. osteopenia, normal vs. osteoporosis, and osteopenia vs. osteoporosis were established. The performance of the classification models was evaluated through the estimated area under the receiver operating characteristic curve.

RESULTS

The area under the receiver operating characteristic curves based on T1WI, T2WI, and T1WI+T2WI were 0.772, 0.772, and 0.810, respectively, for the models of normal vs. osteopenia, 0.724, 0.682, and 0.797, respectively, for the models of normal vs. osteoporosis, and 0.730, 0.734, and 0.769, respectively, for the models of osteopenia vs. osteoporosis.

CONCLUSION

Radiomic models established based on lumbar spine MRI can be used to detect osteoporosis.

MRI-Based Radiomics Models for Predicting Risk Classification of Gastrointestinal Stromal Tumors

Background

We conduct a study in developing and validating four MRI-based radiomics models to preoperatively predict the risk classification of gastrointestinal stromal tumors (GISTs).

Methods

Forty-one patients (low-risk = 17, intermediate-risk = 13, high-risk = 11) underwent MRI before surgery between September 2013 and March 2019 in this retrospective study. The Kruskal–Wallis test with Bonferonni correction and variance threshold was used to select appropriate features, and the Random Forest model (three classification model) was used to select features among the high-risk, intermediate-risk, and low-risk of GISTs. The predictive performance of the models built by the Random Forest was estimated by a 5-fold cross validation (5FCV). Their performance was estimated using the receiver operating characteristic (ROC) curve, summarized as the area under the ROC curve (AUC). Area under the curve (AUC), accuracy, sensitivity, and specificity for risk classification were reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics models.

Results

The high-risk, intermediate-risk, and low-risk of GISTs were well classified by radiomics models, the micro-average of ROC curves was 0.85, 0.81, 0.87 and 0.94 for T1WI, T2WI, ADC and combined three MR sequences. And ROC curves achieved excellent AUCs for T1WI (0.85, 0.75 and 0.82), T2WI (0.69, 0.78 and 0.78), ADC (0.85, 0.77 and 0.80) and combined three MR sequences (0.96, 0.92, 0.81) for the diagnosis of high-risk, intermediate-risk, and low-risk of GISTs, respectively. In addition, LDA demonstrated the different risk of GISTs were correctly classified by radiomics analysis (61.0% for T1WI, 70.7% for T2WI, 83.3% for ADC, and 78.9% for the combined three MR sequences).

Conclusions

Radiomics models based on a single sequence and combined three MR sequences can be a noninvasive method to evaluate the risk classification of GISTs, which may help the treatment of GISTs patients in the future.

A Magnetic Resonance Imaging Radiomics Signature to Distinguish Benign From Malignant Orbital Lesions

OBJECTIVES

Distinguishing benign from malignant orbital lesions remains challenging both clinically and with imaging, leading to risky biopsies. The objective was to differentiate benign from malignant orbital lesions using radiomics on 3 T magnetic resonance imaging (MRI) examinations.

MATERIALS AND METHODS

This institutional review board-approved prospective single-center study enrolled consecutive patients presenting with an orbital lesion undergoing a 3 T MRI prior to surgery from December 2015 to July 2019. Radiomics features were extracted from 6 MRI sequences (T1-weighted images [WIs], DIXON-T2-WI, diffusion-WI, postcontrast DIXON-T1-WI) using the Pyradiomics software. Features were selected based on their intraobserver and interobserver reproducibility, nonredundancy, and with a sequential step forward feature selection method. Selected features were used to train and optimize a Random Forest algorithm on the training set (75%) with 5-fold cross-validation. Performance metrics were computed on a held-out test set (25%) with bootstrap 95% confidence intervals (95% CIs). Five residents, 4 general radiologists, and 3 expert neuroradiologists were evaluated on their ability to visually distinguish benign from malignant lesions on the test set. Performance comparisons between reader groups and the model were performed using McNemar test. The impact of clinical and categorizable imaging data on algorithm performance was also assessed.

RESULTS

A total of 200 patients (116 [58%] women and 84 [42%] men; mean age, 53.0 ± 17.9 years) with 126 of 200 (63%) benign and 74 of 200 (37%) malignant orbital lesions were included in the study. A total of 606 radiomics features were extracted. The best performing model on the training set was composed of 8 features including apparent diffusion coefficient mean value, maximum diameter on T1-WIs, and texture features. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity on the test set were respectively 0.869 (95% CI, 0.834-0.898), 0.840 (95% CI, 0.806-0.874), 0.684 (95% CI, 0.615-0.751), and 0.935 (95% CI, 0.905-0.961). The radiomics model outperformed all reader groups, including expert neuroradiologists (P < 0.01). Adding clinical and categorizable imaging data did not significantly impact the algorithm performance (P = 0.49).

CONCLUSIONS

An MRI radiomics signature is helpful in differentiating benign from malignant orbital lesions and may outperform expert radiologists.

Radiomics in immuno-oncology

With the ongoing advances in imaging techniques, increasing volumes of anatomical and functional data are being generated as part of the routine clinical workflow. This surge of available imaging data coincides with increasing research in quantitative imaging, particularly in the domain of imaging features. An important and novel approach is radiomics, where high-dimensional image properties are extracted from routine medical images. The fundamental principle of radiomics is the hypothesis that biomedical images contain predictive information, not discernible to the human eye, that can be mined through quantitative image analysis. In this review, a general outline of radiomics and artificial intelligence (AI) will be provided, along with prominent use cases in immunotherapy (e.g. response and adverse event prediction) and targeted therapy (i.e. radiogenomics). While the increased use and development of radiomics and AI in immuno-oncology is highly promising, the technology is still in its early stages, and different challenges still need to be overcome. Nevertheless, novel AI algorithms are being constructed with an ever-increasing scope of applications.

Dixon-T2WI magnetic resonance imaging at 3 tesla outperforms conventional imaging for thyroid eye disease

OBJECTIVES

To determine the diagnostic performances of a single Dixon-T2-weighted imaging (WI) sequence compared to a conventional protocol including T1-, T2-, and fat-suppressed T2-weighted MRI at 3 T when assessing thyroid eye disease (TED).

MATERIALS AND METHODS

This IRB-approved prospective single-center study enrolled participants presenting with confirmed TED from April 2015 to October 2019. They underwent an MRI, including a conventional protocol and a Dixon-T2WI sequence. Two neuroradiologists, blinded to all data, read both datasets independently and randomly. They assessed the presence of extraocular muscle (EOM) inflammation, enlargement, fatty degeneration, or fibrosis as well as the presence of artifacts. The Wilcoxon signed-rank test was used.

RESULTS

Two hundred six participants were enrolled (135/206 [66%] women, 71/206 [34%] men, age 52.3 ± 13.2 years). Dixon-T2WI was significantly more likely to detect at least one inflamed EOM as compared to the conventional set (248/412 [60%] versus 228/412 [55%] eyes; (p = 0.02). Dixon-T2WI was more sensitive and specific than the conventional set for assessing muscular inflammation (100% versus 94.7% and 71.2% versus 68.5%, respectively). Dixon-T2WI was significantly less likely to show major or minor artifacts as compared to fat-suppressed T2WI (20/412 [5%] versus 109/412 [27%] eyes, p < 0.001, and 175/412 [42%] versus 257/412 [62%] eyes, p < 0.001). Confidence was significantly higher with Dixon-T2WI than with the conventional set (2.35 versus 2.24, p = 0.003).

CONCLUSION

Dixon-T2WI showed higher sensitivity and specificity and showed fewer artifacts than a conventional protocol when assessing thyroid eye disease, in addition to higher self-reported confidence.

KEY POINTS

• Dixon-T2WI has better sensitivity and specificity than a conventional protocol for assessing inflamed extraocular muscles in patients with thyroid eye disease. • Dixon-T2WI shows significantly fewer artifacts than fat-suppressed T2WI. • Dixon-T2WI is faster and is associated with significantly higher self-reported reader confidence as compared to a conventional protocol when assessing inflammatory extraocular muscles.

Radiomic analysis of the optic nerve at the first episode of acute optic neuritis: an indicator of optic nerve pathology and a predictor of visual recovery?

OBJECTIVE

Retinal nerve fiber layer thickness (RNFL) is a biomarker of neuroaxonal loss and index of visual function in multiple sclerosis (MS). We aimed to assess the correlation between radiomic features and RNFL, visual acuity (VA) at patients' presentation, visual outcome (VO), and clinical diagnosis.

METHODS

We reviewed imaging and clinical data of 25 patients with a first episode of optic neuritis (ON) (14 females, 11 males; 5 bilateral ON; 7 left ON; 13 right ON). All patients underwent a complete ophthalmological assessment, including visual acuity and RNFL, neurological evaluation, orbits MRI. Segmentation of the optic nerves was performed through 3D slicer open software to get radiomics analysis. All patients underwent a complete neuro-ophthalmological follow-up at 6 months to assess the VO, classified as: complete recovery, partial recovery, deficit persistence/relapse, or visual worsening and were diagnosed as MS or clinically isolated syndrome.

RESULTS

We observed significant correlations between radiomic features and RNFL and between radiomic features and VA. Regression model analysis identified 1 radiomic feature with significant association with VO (Gray Level non-uniformity Normalized, p = 0.004) and 6 radiomic features with significant correlation with diagnosis (High Gray Level Zone Emphasis, p < 0.001; Entropy, p < 0.001, for T1 segmentation; Mean Absolute Deviation, p < 0.001; Coarseness < 0.001; Small Area Low Gray Level Emphasis, p < 0.001; Contrast, p = 0.008, for STIR segmentation).

CONCLUSION

Orbits MRI analysis at the first episode of ON has the potential to assess the visual function and VO in ON patients, and predict MS development.

Artificial intelligence in gastrointestinal cancer: Recent advances and future perspectives

Artificial intelligence (AI) using machine or deep learning algorithms is attracting increasing attention because of its more accurate image recognition ability and prediction performance than human-aid analyses. The application of AI models to gastrointestinal (GI) clinical oncology has been investigated for the past decade. AI has the capacity to automatically detect and diagnose GI tumors with similar diagnostic accuracy to expert clinicians. AI may also predict malignant potential, such as tumor histology, metastasis, patient survival, resistance to cancer treatments and the molecular biology of tumors, through image analyses of radiological or pathological imaging data using complex deep learning models beyond human cognition. The introduction of AI-assisted diagnostic systems into clinical settings is expected in the near future. However, limitations associated with the evaluation of GI tumors by AI models have yet to be resolved. Recent studies on AI-assisted diagnostic models of gastric and colorectal cancers in the endoscopic, pathological, and radiological fields were herein reviewed. The limitations and future perspectives for the application of AI systems in clinical settings have also been discussed. With the establishment of a multidisciplinary team containing AI experts in each medical institution and prospective studies, AI-assisted medical systems will become a promising tool for GI cancer.

Radiomics Signatures of Cardiovascular Risk Factors in Cardiac MRI: Results From the UK Biobank

Cardiovascular magnetic resonance (CMR) radiomics is a novel technique for advanced cardiac image phenotyping by analyzing multiple quantifiers of shape and tissue texture. In this paper, we assess, in the largest sample published to date, the performance of CMR radiomics models for identifying changes in cardiac structure and tissue texture due to cardiovascular risk factors. We evaluated five risk factor groups from the first 5,065 UK Biobank participants: hypertension (n = 1,394), diabetes (n = 243), high cholesterol (n = 779), current smoker (n = 320), and previous smoker (n = 1,394). Each group was randomly matched with an equal number of healthy comparators (without known cardiovascular disease or risk factors). Radiomics analysis was applied to short axis images of the left and right ventricles at end-diastole and end-systole, yielding a total of 684 features per study. Sequential forward feature selection in combination with machine learning (ML) algorithms (support vector machine, random forest, and logistic regression) were used to build radiomics signatures for each specific risk group. We evaluated the degree of separation achieved by the identified radiomics signatures using area under curve (AUC), receiver operating characteristic (ROC), and statistical testing. Logistic regression with L1-regularization was the optimal ML model. Compared to conventional imaging indices, radiomics signatures improved the discrimination of risk factor vs. healthy subgroups as assessed by AUC [diabetes: 0.80 vs. 0.70, hypertension: 0.72 vs. 0.69, high cholesterol: 0.71 vs. 0.65, current smoker: 0.68 vs. 0.65, previous smoker: 0.63 vs. 0.60]. Furthermore, we considered clinical interpretation of risk-specific radiomics signatures. For hypertensive individuals and previous smokers, the surface area to volume ratio was smaller in the risk factor vs. healthy subjects; perhaps reflecting a pattern of global concentric hypertrophy in these conditions. In the diabetes subgroup, the most discriminatory radiomics feature was the median intensity of the myocardium at end-systole, which suggests a global alteration at the myocardial tissue level. This study confirms the feasibility and potential of CMR radiomics for deeper image phenotyping of cardiovascular health and disease. We demonstrate such analysis may have utility beyond conventional CMR metrics for improved detection and understanding of the early effects of cardiovascular risk factors on cardiac structure and tissue.

Intravoxel incoherent motion (IVIM) 3 T MRI for orbital lesion characterization

OBJECTIVES

To determine the diagnostic accuracy of MRI intravoxel incoherent motion (IVIM) when characterizing orbital lesions, which is challenging due to a wide range of locations and histologic types.

METHODS

This IRB-approved prospective single-center study enrolled participants presenting with an orbital lesion undergoing a 3-T MRI prior to surgery from December 2015 to July 2019. An IVIM sequence with 15 b values ranging from 0 to 2000 s/mm² was performed. Two neuroradiologists, blinded to clinical data, individually analyzed morphological MRIs. They drew one region of interest inside each orbital lesion, providing apparent diffusion coefficient (ADC), true diffusion coefficient (D), perfusion fraction (f), and pseudodiffusion coefficient (D*) values. T test, Mann-Whitney U test, and receiver operating characteristic curve analyses were performed to discriminate between orbital lesions and to determine the diagnostic accuracy of the IVIM parameters.

RESULTS

One hundred fifty-six participants (84 women and 72 men, mean age 54.4 ± 17.5 years) with 167 orbital lesions (98/167 [59%] benign lesions including 54 orbital inflammations and 69/167 [41%] malignant lesions including 32 lymphomas) were included in the study. ADC and D were significantly lower in malignant than in benign lesions: 0.8 × 10^-3 mm²/s [0.45] versus 1.04 × 10^-3 mm²/s [0.33], p < 0.001, and 0.75 × 10^-3 mm²/s [0.40] versus 0.98 × 10^-3 mm²/s [0.42], p < 0.001, respectively. D* was significantly higher in malignant lesions than in benign ones: 12.8 × 10^-3 mm²/s [20.17] versus 7.52 × 10^-3 mm²/s [7.57], p = 0.005. Area under curve was of 0.73, 0.74, 0.72, and 0.81 for ADC, D, D*, and a combination of D, f, and D*, respectively.

CONCLUSIONS

Our study showed that IVIM might help better characterize orbital lesions.

KEY POINTS

• Intravoxel incoherent motion (IVIM) helps clinicians to assess patients with orbital lesions. • Intravoxel incoherent motion (IVIM) helps clinicians to characterize orbital lymphoma versus orbital inflammation. • Management of patients becomes more appropriate.

Radiomics in diffusion data: a test-retest, inter- and intra-reader DWI phantom study

AIM

The aim of this study was to evaluate the robustness of radiomics features of a MRI (magnetic resonance imaging) phantom in quantitative diffusion-weighted imaging (DWI) and depending on the image resolution.

MATERIALS AND METHODS

Scanning of an in-house developed DWI phantom was performed at a 1.5 T MRI scanner (Magnetom AERA, Siemens, Erlangen, Germany) using an echo planar imaging (EPI) DWI sequence (b=0,500,1,000 s/mm²) with low (3×3 mm²) and high (2×2 mm²) image resolutions. Scans were repeated after phantom repositioning to evaluate retest reliability. Radiomics features were extracted after semi-automatic segmentation and standardised pre-processing. Intra-/interobserver reproducibility and test-retest robustness were assessed using intraclass correlation coefficients (ICC). Differences were tested with non-parametric Wilcoxon's signed-rank and Friedman's test (p < 0.05) with Dunn's post-hoc analysis.

RESULTS

Test-retest ICC was overall high with >0.90 for 39/46 radiomics features in all sequences/resolutions. Decreased test-retest ICCs were pronounced for conventional Min-value (overall ICC=0.817), and grey-level zone length matrix (GLZLM) features Short-Zone Emphasis (SZE) and Short-Zone Low Grey-level Emphasis (SZLGE) (for both overall ICC=0.927). Test-retest reproducibility was significantly different between b=500, 1,000 and apparent diffusion coefficient (ADC) (mean 0.975±0.050, 0.974±0.051 and 0.966±0.063), which remained significant after post-hoc analysis between b=1,000 and ADC (p = 0.022). ICCs were not significantly different between resolutions of 2×2 and 3×3 mm² regarding b=500 (mean: 0.977±0.052 and 0.974±0.049, p = 0.612), b=1,000 (mean: 0.973±0.059 and 0.974±0.054, p = 0.516), and ADC (mean: 0.972±0.049 and 0.955±0.101, p = 0.851). Inter- and intra-observer reliability was consistently high for all sequences (overall mean 0.992±0.021 and 0.990±0.028).

CONCLUSION

Under ex-vivo conditions, DWI provided robust radiomics features with those from ADC being slightly less robust than from raw DWI (b=500, 1,000 s/mm²). No significant difference was detected for different resolutions. Although, ex-vivo reliability of DWI radiomics features was high, no implications can be made regarding in-vivo analyses.

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Radiomics relies on the extraction of a wide variety of quantitative image-based features to provide decision support. Magnetic resonance imaging (MRI) contributes to the personalization of patient care but suffers from being highly dependent on acquisition and reconstruction parameters. Today, there are no guidelines regarding the optimal pre-processing of MR images in the context of radiomics, which is crucial for the generalization of published image-based signatures. This study aims to assess the impact of three different intensity normalization methods (Nyul, WhiteStripe, Z-Score) typically used in MRI together with two methods for intensity discretization (fixed bin size and fixed bin number). The impact of these methods was evaluated on first- and second-order radiomics features extracted from brain MRI, establishing a unified methodology for future radiomics studies. Two independent MRI datasets were used. The first one (DATASET1) included 20 institutional patients with WHO grade II and III gliomas who underwent post-contrast 3D axial T1-weighted (T1w-gd) and axial T2-weighted fluid attenuation inversion recovery (T2w-flair) sequences on two different MR devices (1.5 T and 3.0 T) with a 1-month delay. Jensen–Shannon divergence was used to compare pairs of intensity histograms before and after normalization. The stability of first-order and second-order features across the two acquisitions was analysed using the concordance correlation coefficient and the intra-class correlation coefficient. The second dataset (DATASET2) was extracted from the public TCIA database and included 108 patients with WHO grade II and III gliomas and 135 patients with WHO grade IV glioblastomas. The impact of normalization and discretization methods was evaluated based on a tumour grade classification task (balanced accuracy measurement) using five well-established machine learning algorithms. Intensity normalization highly improved the robustness of first-order features and the performances of subsequent classification models. For the T1w-gd sequence, the mean balanced accuracy for tumour grade classification was increased from 0.67 (95% CI 0.61–0.73) to 0.82 (95% CI 0.79–0.84, P = .006), 0.79 (95% CI 0.76–0.82, P = .021) and 0.82 (95% CI 0.80–0.85, P = .005), respectively, using the Nyul, WhiteStripe and Z-Score normalization methods compared to no normalization. The relative discretization makes unnecessary the use of intensity normalization for the second-order radiomics features. Even if the bin number for the discretization had a small impact on classification performances, a good compromise was obtained using the 32 bins considering both T1w-gd and T2w-flair sequences. No significant improvements in classification performances were observed using feature selection. A standardized pre-processing pipeline is proposed for the use of radiomics in MRI of brain tumours. For models based on first- and second-order features, we recommend normalizing images with the Z-Score method and adopting an absolute discretization approach. For second-order feature-based signatures, relative discretization can be used without prior normalization. In both cases, 32 bins for discretization are recommended. This study may pave the way for the multicentric development and validation of MR-based radiomics biomarkers.

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.

Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma

To investigate the effect of image preprocessing, in respect to intensity inhomogeneity correction and noise filtering, on the robustness and reproducibility of the radiomics features extracted from the Glioblastoma (GBM) tumor in multimodal MR images (mMRI). In this study, for each patient 1461 radiomics features were extracted from GBM subregions (i.e., edema, necrosis, enhancement, and tumor) of mMRI (i.e., FLAIR, T1, T1C, and T2) volumes for five preprocessing combinations (in total 116 880 radiomics features). The robustness and reproducibility of the radiomics features were assessed under four comparisons: (a) Baseline versus modified bias field; (b) Baseline versus modified bias field followed by noise filtering; (c) Baseline versus modified noise, and (d) Baseline versus modified noise followed bias field correction. The concordance correlation coefficient (CCC), dynamic range (DR), and interclass correlation coefficient (ICC) were used as metrics. Shape features and subsequently, local binary pattern (LBP) filtered images were highly stable and reproducible against bias field correction and noise filtering in all measurements. In all MRI modalities, necrosis regions (NC: n ® ~449/1461, 30%) had the highest number of highly robust features, with CCC and DR >= 0.9, in comparison with edema (ED: n ® ~296/1461, 20%), enhanced (EN: n ® ~ 281/1461, 19%) and active‐tumor regions (TM: n ® ~254/1461, 17%). The necrosis regions (NC: n¯ ~ 449/1461, 30%) had a higher number of highly robust features (CCC and DR >= 0.9) than edema (ED: n¯ ~ 296/1461, 20%), enhanced (EN: n¯ ~ 281/1461, 19%) and active‐tumor (TM: n¯ ~ 254/1461, 17%) regions across all modalities. Furthermore, our results identified that the percentage of high reproducible features with ICC >= 0.9 after bias field correction (23.2%), and bias field correction followed by noise filtering (22.4%) were higher in contrast with noise smoothing and also noise smoothing follow by bias correction. These preliminary findings imply that preprocessing sequences can also have a significant impact on the robustness and reproducibility of mMRI‐based radiomics features and identification of generalizable and consistent preprocessing algorithms is a pivotal step before imposing radiomics biomarkers into the clinic for GBM patients.

Robustness of radiomic features in magnetic resonance imaging: review and a phantom study

Radiomic analysis has exponentially increased the amount of quantitative data that can be extracted from a single image. These imaging biomarkers can aid in the generation of prediction models aimed to further personalized medicine. However, the generalizability of the model is dependent on the robustness of these features. The purpose of this study is to review the current literature regarding robustness of radiomic features on magnetic resonance imaging. Additionally, a phantom study is performed to systematically evaluate the behavior of radiomic features under various conditions (signal to noise ratio, region of interest delineation, voxel size change and normalization methods) using intraclass correlation coefficients. The features extracted in this phantom study include first order, shape, gray level cooccurrence matrix and gray level run length matrix. Many features are found to be non-robust to changing parameters. Feature robustness assessment prior to feature selection, especially in the case of combining multi-institutional data, may be warranted. Further investigation is needed in this area of research.

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.