Editorial for “Preoperative MRI ‐Based Radiomic Machine‐Learning Nomogram May Accurately Distinguish Between Benign and Malignant Soft Tissue Lesions: A Two‐Center Study”

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.

Multi-parametric arterial spin labeling and diffusion-weighted imaging of paranasal sinuses masses

PURPOSE

To evaluate arterial spin labeling (ASL) and diffusion-weighted imaging (DWI) in discrimination of benign from malignant paranasal sinus (PNS) tumors.

MATERIAL AND METHODS

A prospective study was done upon 42 cases of PNS masses that underwent magnetic resonance ASL and DWI of the head. Tumor blood flow (TBF) and apparent diffusion coefficient (ADC) of the masses were calculated by two observers. The pathological diagnosis was malignant (n = 28) and benign (n = 14) cases.

RESULTS

For both observers, the malignant PNS masses had significantly higher TBF (P < 0.001, 0.001) and lower ADC (P < 0.001, 0.001) than in benign masses. The ROC curve analysis of TBF, The threshed TBF was (121.45, 122.68 mL/100 g/min) used for differentiation between benign and malignant PNS masses, revealed sensitivity (92.9%, 89.3%), specificity (85.7%, 85.7%), accuracy (90.5%, 88.1%) and the AUC was 0.87 and 0.86 by both observers. the ROC curve analysis of ADC, The threshold ADC (1.215, 1.205 X10^-3mm2/s) was used for differentiation between benign and malignant PNS masses, revealed sensitivity (96.4%, 89.3%), specificity (78.6%, 78.6%), accuracy of (90.5%, 85.7%) and the AUC was 0.93 and 0.92 by both observers. Combined analysis of TBF and ADC used for differentiation between benign and malignant PNS masses had revealed sensitivity (96.4%, 89.3%), specificity (92.9%, 85.7%) accuracy of (95.2%, 88.1%) and AUC. (0.995, 0.985) for both observers.

CONCLUSION

Combined using of TBF and ADC have a role in differentiation malignant from benign PNS masses.

Diffusion tensor imaging of dorsal stream language areas in patients with post-stroke aphasia

Background

Aphasia complicating stroke occurs due to language deficits that decrease communication abilities and functional independence. Our study aims to assess fractional anisotropy (FA) and mean diffusivity (MD) parameters of diffusion tensor imaging (DTI) of the dorsal stream language areas in patients with post-stroke aphasia. It was conducted on 27 patients with post-stroke aphasia and 27 age- and sex-matched controls who underwent DTI of the brain. FA and MD values of Broca's area (BA), Wernick's area (WA), superior longitudinal fasciculus (SLF), and arcuate fasciculus (AF), and number of tract fibers (TF) of AF and SLF were calculated. Results were correlated with National Institutes of Health Stroke Scale (NIHSS), Arabic version of Comprehensive Aphasia Test (Arabic CAT), and Mansoura Arabic Screening Aphasia Test (MASAT).

Results

FA of AF and SLF in patients was significantly lower (P = 0.001) than controls. MD of AF and SLF in patients was significantly higher (P = 0.001) than controls. The mean volume TF of AF and SLF in patients was significantly (P = 0.001) lower than the mean volume in controls for AF and SLF. FA cutoff for AF was 0.34 and for SLF, it was 0.35 with sensitivity, specificity, and accuracy (85.2%, 62.1%, 73.2%) for AF, (74.1%, 69%, 71.4%) for SLF, respectively. MD cutoff value for AF was 0.87, and 0.84 for SLF with sensitivity, specificity, and accuracy (63%, 72.4%, 67.8%) for AF, (81.5%, 79.3%, 80.4%) for SLF, respectively. Cutoff TF of AF was 1728 and for SLF it was 601 with sensitivity, specificity, and accuracy (88.9%, 72.4%, 80.4%) for AF and (85.2%, 85.2%, 78.6%) for SLF, respectively.

Conclusions

DTI is a non-invasive promising method that can be used to assess language areas in patients with post-stroke aphasia.

Can radiomic analysis of a single-phase dual-energy CT improve the diagnostic accuracy of differentiating enhancing from non-enhancing small renal lesions?

BACKGROUND

The value of dual-energy computed tomography (DECT)-based radiomics in renal lesions is unknown.

PURPOSE

To develop DECT-based radiomic models and assess their incremental values in comparison to conventional measurements for differentiating enhancing from non-enhancing small renal lesions.

MATERIAL AND METHODS

A total of 349 patients with 519 small renal lesions (390 non-enhancing, 129 enhancing) who underwent contrast-enhanced nephrographic phase DECT examinations between June 2013 and January 2020 on multiple DECT platforms were retrospectively recruited. Cohort A included all lesions, while cohort B included Bosniak II-IV and solid enhancing renal lesions. Radiomic models were built with features selected by the least absolute shrinkage and selection operator regression (LASSO). ROC analyses were performed to compare the diagnostic accuracy among conventional and radiomic models for predicting enhancing renal lesions.

RESULTS

The individual iodine concentration (IC), normalized IC, mean attenuation on 75-keV images, radiomic model of iodine images, 75-keV images and a combined model integrating all the above-mentioned features all demonstrated high AUCs for predicting renal lesion enhancement in cohort A (AUCs = 0.934-0.979) as well as in the test dataset (AUCs = 0.892-0.962) of cohort B (P values with Bonferroni correction >0.003). The AUC (0.864) of mean attenuation on 75-keV images was significantly lower than those of other models (all P values ≤0.001) except the radiomic model of 75-keV images (P = 0.038) in the training dataset of cohort B.

CONCLUSION

No incremental value was found by adding radiomic and machine learning analyses to iodine images for differentiating enhancing from non-enhancing renal lesions.

Diffusion Tensor Imaging in Characterization of Mediastinal Lymphadenopathy

OBJECTIVE

To determine the efficacy of diffusion-weighted MRI (DWI) and diffusion tensor imaging (DTI) in the characterization of mediastinal lymphadenopathy and the differentiation between malignant and benign lymph nodes (LNs).

METHODS

a retrospective evaluation of 58 patients with mediastinal lymphadenopathy that underwent DWI and DTI with calculation of apparent diffusion coefficient (ADC), fractional anisotropy (FA), and mean diffusivity (MD) values of LNs. Final diagnosis was made by the histopathology and proved metastatic (n = 21), lymphomatous (n = 14), granulomatous (n = 11) and reactive (n = 12) LNs.

RESULTS

Malignant mediastinal LNs had remarkably lower ADC and MD; (p = 0.001) and higher FA; (p = 0.001) than in benign LNs. The threshold of ADC, MD, and FA at (1.48, 1.32 × 10^-3 mm²/s), (1.31, 1.33 × 10^-3 mm²/s), (0.62, 0.52) to differentiate malignant from benign LNs has AUC of (0.89, 0.94), (0.96, 0.95), (0.72, 0.82), accuracy of (87%, 86%), (89%, 86%), (70%, 72%) by both observers respectively. The threshold of ADC, MD, and FA at (1.47, 1.32 × 10^-3 mm²/s), (1.31, 1.3 × 10^-3 mm²/s), (0.62, 0.67) used to differentiate metastatic from reactive LNs revealed AUC of (0.90, 0.94), (0.96, 0.96), (0.73, 0.77), accuracy of (87%, 81%), (87%, 81%), (72%, 66%) by both observers respectively. The mean ADC and MD values of metastatic LNs were statistically significant (p = 0.001) and (p = 0.002, 0.02) respectively when compared with that of lymphoma. The threshold of ADC, and MD (0.94, 0.97 × 10^-3 mm²/s) and (0.87, 0.91 × 10^-3 mm²/s) used to differentiates metastatic from lymphomatous nodes revealed AUC of (0.90, 0.91), (0.81, 0.74), an accuracy of (85%, 91%), (71%, 71%), by both observers respectively. The inter-class correlation between two observers for all nodes for ADC, MD and FA was r= 0.931, 0.956 and 0.885 respectively.

CONCLUSION

Using ADC, MD, and FA can help in the characterization of mediastinal lymphadenopathy noninvasively.

Role of MR Imaging in Head and Neck Squamous Cell Carcinoma

Routine and advanced MR imaging sequences are used for locoregional spread, nodal, and distant staging of head and neck squamous cell carcinoma, aids treatment planning, predicts treatment response, differentiates recurrence for postradiation changes, and monitors patients after chemoradiotherapy.

Coronary artery disease imaging reporting and data system (CAD-RADS): what radiologists need to know?

The aim of this work is to review Coronary Artery Disease Imaging Reporting and Data System (CAD-RADS) that was designed to standardize reporting language and improve the communication of data among radiologists and clinicians. Stenotic lesions are graded into 5 grades ranging from 0 (no stenosis) to 5 (total occlusion), where the highest grade represents the final score. The expert consensus platform has added 4 special modifiers (non-diagnostic, stent, graft, and vulnerability) to aid patient management through linking these scores with decision algorithm and treatment plan. Adherence to standard imaging protocol; knowledge of normal, variant, and anomalous anatomy; and skillful evaluation of stenosis are important for proper utilization of this reporting system. Lastly, radiologists should be aware of the inherited benefits, limitations, and common pitfalls of this classification system.

Diffusion tensor imaging of renal cortex in lupus nephritis

PURPOSE

To evaluate the diagnostic value of diffusion tensor imaging (DTI) of renal cortex in assessment of lupus nephritis (LN) and prediction of its pathological subtypes.

METHODS

Prospective study was performed upon 39 female patients with pathologically proven LN and 16 sex- and age-matched healthy controls. Patients and controls underwent DTI of kidney. Mean diffusivity (MD) and fractional anisotropy (FA) of renal cortex were calculated by two radiologists. LN patients were pathologically classified into either non-proliferative (n = 15) or proliferative (n = 24).

RESULTS

Mean MD of renal cortex in LN was significantly lower (p = 0.001) than that of controls with cut-off (2.16 and 2.2 X10^-3mm²/s), area under curve (AUC) of (0.92, 0.94) and accuracy of (91%, 89%) for both observers. Mean FA of renal cortex in LN was significantly higher (p = 0.001) than that of controls with cut-off (0.20, 0.21), AUC of (0.86, 0.82) and accuracy of (86%, 84%) for both observers. Renal cortex MD and FA in non-proliferative LN were significantly different (p = 0.001) from that of proliferative LN for both observers. There was excellent inter-observer agreement of MD and FA (ICC = 0.96 and 0.81).

CONCLUSION

MD and FA of renal cortex may help to assess renal affection in LN patients and predict its pathological subtypes.

A novel radiomics-platelet nomogram for the prediction of gastroesophageal varices needing treatment in cirrhotic patients

BACKGROUND AND AIMS

Highly accurate noninvasive methods for predicting gastroesophageal varices needing treatment (VNT) are desired. Radiomics is a newly emerging technology of image analysis. This study aims to develop and validate a novel noninvasive method based on radiomics for predicting VNT in cirrhosis.

METHODS

In this retrospective-prospective study, a total of 245 cirrhotic patients were divided as the training set, internal validation set and external validation set. Radiomics features were extracted from portal-phase computed tomography (CT) images of each patient. A radiomics signature (Rad score) was constructed with the least absolute shrinkage and selection operator algorithm and tenfold cross-validation in the training set. Combined with independent risk factors, a radiomics nomogram was built with a multivariate logistic regression model.

RESULTS

The Rad score, consisting of 14 features from the gastroesophageal region and 5 from the splenic hilum region, was effective for VNT classification. The diagnostic performance was further improved by combining the Rad score with platelet counts, achieving an AUC of 0.987 (95% CI 0.969-1.00), 0.973 (95% CI 0.939-1.00) and 0.947 (95% CI 0.876-1.00) in the training set, internal validation set and external validation set, respectively. In efficacy and safety assessment, the radiomics nomogram could spare more than 40% of endoscopic examinations with a low risk of missing VNT (< 5%), and no more than 8.3% of unnecessary endoscopic examinations still be performed.

CONCLUSIONS

In this study, we developed and validated a novel, diagnostic radiomics-based nomogram which is a reliable and noninvasive method to predict VNT in cirrhotic patients.

CLINICAL TRIALS REGISTRATION

NCT04210297.

Diffusion tensor imaging of vertebral bone marrow in children with Gaucher's disease type I and III: Pre- and post-therapy

PURPOSE

To assess diffusion tensor imaging (DTI) of the vertebral bone marrow (BM) in children with Gaucher's disease (GD) types I and III before and after therapy.

METHODS

Prospective study was conducted upon 25 children with GD type I (n = 17) and III (n = 8) and 13 age and sex-matched controls underwent DTI of vertebral BM. Mean diffusivity (MD) and fractional anisotropy (FA) of vertebral BM was calculated and correlated with genotyping, chitotriosidase, hemoglobin (HB) and, platelet count.

RESULTS

There was a statistically significant difference in MD and FA of BM between patients and controls (P = 0.001 and 0.02). The area under the curve (AUC) of MD and FA used to differentiate untreated patients from controls was 0.902 and 0.68 with sensitivity, specificity, and, accuracy 92%, 84.6%, and, 89.5% respectively. There was a significant difference in MD and FA of BM between untreated and treated patients (P = 0.001 and 0.02). AUC of MD and FA used to differentiate untreated from treated patients was 0.93 and 0.649 with sensitivity, specificity, and accuracy of 92%, 80%, and 86% respectively. There was a significant difference in MD and FA (P = 0.03, 0.001 respectively) of BM in GD with homozygous L444P mutation (n = 9) and other mutations (n = 14). Chiotriptase, HB and platelet count of patients was correlated with MD (r = -0.36, 0.42, -0.41) and FA (r = -0.47, -0.37, -0.46) respectively.

CONCLUSION

DTI of vertebral BM can help in diagnosis and monitoring patients with GD after therapy and correlated with genotyping, and hematological biomarkers of GD.

Prostate Imaging Reporting and Data System (PI-RADS): What the radiologists need to know?

We aim to review the new modifications in MR imaging technique, image interpretation, lexicon, and scoring system of the last version of Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) in a simple and practical way. This last version of PI-RADS v2.1 describes the new technical modifications in the protocol of Multiparametric MRI (MpMRI) including T2, diffusion-weighted imaging (DWI), and dynamic contrast enhancement (DCE) parameters. It includes also; new guidelines in the image interpretation specifications in new locations (lesions located in the central zone and anterior fibromuscular stroma), clarification of T2 scoring of lesions of the transition zone, the distinction between DWI score 2 and 3 lesions in the transition zone and peripheral zone, as well as between positive and negative enhancement in DCE. Biparametric MRI (BpMRI) along with simplified PI-RADS is gaining more acceptances in the assessment of clinically significant prostatic cancer.

Diffusion tensor imaging of the spleen in prediction and grading of esophageal varices in cirrhotic children with portal hypertension

PURPOSE

To assess diffusion tensor imaging (DTI) of spleen in prediction and grading of esophageal varices (OV) in cirrhotic children.

METHODS

This prospective study was conducted upon 30 children with cirrhotic children with OV and 10 age-gender matched controls that underwent DTI of abdomen. Mean diffusivity (MD) and fractional anisotropy (FA) of spleen were calculated and matched with the grading of OV at endoscopy and laboratory biomarkers of portal hypertension.

RESULTS

Mean ADC of spleen in patient was significantly different (p = 0.001) from that of controls by both reviewers respectively. The cutoff ADC measurement of the spleen used for prediction of OV was ≥ 0.75 and ≥ 0.76 × 10^-3mm²/s with AUC was 0.993 and 0.997 for both reviewers respectively. The FA of the spleen in patient was different (p = 0.01) from of controls of both reviewers respectively. Cutoff FA of spleen used for prediction of OV was ≤ 0.35 and ≤ 0.36 for both observers respectively. ADC and FA of spleen was correlated with platelets count (r =  - 0.713, 0.392; p = 0.001, 0.012) and prothrombin time (r = 0.518, - 0.380; p = 0.001, 0.016).

CONCLUSION

DTI metrics of spleen can predict and grade OV and correlated with laboratory biomarkers of portal hypertension.

Can perihaematomal radiomics features predict haematoma expansion?

AIM

To evaluate the association between perihaematomal radiomics features and haematoma expansion (HE).

MATERIALS AND METHODS

Clinical and radiological data were collected retrospectively. The 1:1 propensity score matching (PSM) method was used to balance the difference of baseline characteristics between patients with and without HE. Radiomics features were extracted from the intra- and perihaematomal regions. Top HE-associated features were selected using the minimum redundancy, maximum relevancy algorithm. Support vector machine models were used to predict HE. Predictive performance of radiomics features from different regions was evaluated by receiver operating characteristic curve and confusion matrix-derived metrics.

RESULTS

A total of 1,062 patients were enrolled. After PSM analysis, the propensity score-matched cohort (PSM cohort) included 314 patients (HE: n=157; non-HE: n=157). The PSM cohort was distributed into the training (n=218) and the validation cohorts (n=96). The predictive performance of intra- and perihaematomal features were comparable in the training (area under the receiver operating characteristic curve [AUC], 0.751 versus 0.757; p=0.867) and the validation cohorts (AUC, 0.724 versus 0.671; p=0.454). By incorporating intra- and perihaematomal features, the combined model outperformed the single intrahaematomal model in the training cohort (AUC, 0.872 versus 0.751; p<0.001). Decision curve analysis (DCA) further confirmed the clinical usefulness of the combined model.

CONCLUSION

Perihaematomal radiomics features can predict HE. The integration of intra- and perihaematomal signatures may provide additional benefit to the prediction of HE.

Validity and reliability of smartphone applications for measurement of hip rotation, compared with three-dimensional motion analysis

BACKGROUND

Measurement of hip rotation is a crucial clinical parameter for the identification of hip problems and the monitoring of symptoms. The objective of this study was to determine whether the use of two smartphone applications is valid and reliable for the measurement of hip rotation.

METHODS

An experimental, cross-sectional study was undertaken to assess passive hip internal and external rotation in three positions by two examiners. The hip rotational angles were measured by a smartphone clinometer application in the sitting and prone positions, and by a smartphone compass application in the supine position; their results were compared with those of the standard, three-dimensional, motion analysis system. The validities and inter-rater and intra-rater reliabilities of the smartphone applications were evaluated.

RESULTS

The study involved 24 participants. The validities were good to excellent for the internal rotation angles in all positions (ICC 0.81-0.94), good for the external rotation angles in the prone position (ICC 0.79), and fair for the sitting and supine positions (ICC 0.70-0.73). The measurement of the hip internal rotation in the supine position had the highest ICC value of 0.94 (0.91, 0.96). The two smartphone applications showed good-to-excellent intra-rater reliability, but good-to-excellent inter-rater reliability for only three of the six positions (two other positions had fair reliability, while one position demonstrated poor reliability).

CONCLUSIONS

The two smartphone applications have good-to-excellent validity and intra-rater reliability, but only fair-to-good inter-rater reliability for the measurement of the hip rotational angle. The most valid hip rotational position in this study was the supine IR angle measurement, while the lowest validity was the ER angle measurement in the sitting position. The smartphone application is one of the practical measurements in hip rotational angles.

TRIAL REGISTRATION

Number 20181022003 at the Thai Clinical Trials Registry ( http://www.clinicaltrials.in.th ) which was retrospectively registered at 2018-10-18 15:30:29.