The Current Diagnostic Performance of MRI-Based Radiomics for Glioma Grading: A Meta-Analysis.

BACKGROUND: Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma. METHODS: A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis. RESULTS: In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used. CONCLUSIONS: Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

Combination of fusion guided multiparametric MRI-transrectal US with systematic biopsy of the prostate for the detection of clinically significant prostate cancer: A prospective single-center study.

PURPOSE: To investigate the diagnostic efficacy of fusion guided multiparametric MRI (mpMRI)-transrectal ultrasound (TRUS) biopsy versus systematic biopsy of the prostate in patients with suspicion of prostate cancer. METHODS: A total of 185 patients with PI-RADS 3 lesions or higher underwent fusion guided targeted and systematic prostate biopsy. Histology of samples was correlated with PI-RADS score and biopsy method for each patient. RESULTS: A total of 81/185 (43.8%) cases positive for cancer were detected; 23/81 (28.4%) cases with clinically insignificant prostate cancer-insPCa and 58/81 (71.6%) cases with clinically significant prostate cancer-csPCa. There was a statistically significant difference in the overall detection of adenocarcinomas between methods (p = .035, McNemar test). Moreover, there was a statistically significant difference in the detection of insPCa between the two methods (p = .004, McNemar test). Systematic biopsy detected 13 patients with insPCa more (14.4%) than the targeted biopsy method. However, there is no statistical difference in the detection rate of csPCa between the two methods (p = 1, McNemar test). When both techniques were combined more cases of csPCa were detected. CONCLUSION: The combined implementation of fusion-guided targeted mpMRI-TRUS and systematic biopsy of the prostate provides higher detection number of csPCa, compared to each method alone. The potential of fusion-guided mpMRI-TRUS biopsy of the prostate needs to be further assessed since each method has its limitations; therefore, systematic prostate biopsy still plays an important role in clinical practice.

Automated Analysis vs. Expert Reading in Nuclear Cardiology: Correlations with the Angiographic Score.

Background and Objectives: Myocardial perfusion imaging (MPI) has an important role in the non-invasive investigation of coronary artery disease. The interpretation of MPI studies is mainly based on the visual evaluation of the reconstructed images, while automated quantitation methods may add useful data for each patient. However, little evidence is currently available regarding the actual incremental clinical diagnostic performance of automated MPI analysis. In the present study, we aimed to assess the correlation between automated measurements of Summed Stress Score (SSS), Summed Rest Score (SRS) and Summed Difference Score (SDS), with the corresponding expert reading values, using coronary angiography as the gold standard. Materials and Methods: The study was conducted at the Nuclear Medicine Laboratory of the University Hospital of Larissa, Larissa, Greece, οver an one-year period (January 2019-January 2020). 306 patients, with known or suspected coronary artery disease, were enrolled in the study. Each participant underwent a coronary angiography, prior to or after the scintigraphic study (within a three-month period). Either symptom-limited treadmill test, or pharmacologic testing using adenosine or regadenoson, was performed in all participants, and the scintigraphic studies were carried out using technetium 99m (99mTc) tetrofosmin (one-day stress/rest protocol). Coronary angiographies were scored according to a 4-point scoring system (angiographic score; O: normal study, 1: one-vessel disease, 2: two-vessel disease, 3: three-vessel disease). Moreover, automated measurements of SSS, SRS and SDS were derived by three widely available software packages (Emory Cardiac Toolbox, Myovation, Quantitative Perfusion SPECT). Results: Interclass Correlation Coefficients of SSS, SRS and SDS between expert reading and software packages were moderate to excellent. Visually defined SSS, SRS and SDS were significantly correlated with the corresponding results of all software packages. However, visually defined SSS, SRS and SDS were more strongly correlated with the angiographic score, indicating a better performance of expert reading when compared to automated analysis. Conclusions: Based on our results, visual evaluation continues to have a crucial role for the interpretation of MPI images. Software packages can provide automated measurements of several parameters, particularly contributing to the investigation of cases with ambiguous scintigraphic findings.

Breast Cancer Classification on Multiparametric MRI - Increased Performance of Boosting Ensemble Methods.

Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR images of 140 female patients with mass-like breast lesions (70 benign and 70 malignant), consisting of Dynamic Contrast Enhanced (DCE) and T2-weighted sequences, and the Apparent Diffusion Coefficient (ADC) calculated from the Diffusion Weighted Imaging (DWI) sequence. Tumor masks were manually defined in all consecutive slices of the respective MRI volumes and 3D radiomic features were extracted with the Pyradiomics package. Feature dimensionality reduction was based on statistical tests and the Boruta wrapper. Hierarchical Clustering on Spearman's rank correlation coefficients between features and Random Forest classification for obtaining feature importance, were implemented for selecting the final feature subset. Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) classifiers, were trained and tested with bootstrap validation in differentiating breast lesions. A Support Vector Machine (SVM) classifier was also exploited for comparison. The Receiver Operator Characteristic (ROC) curves and DeLong's test were utilized to evaluate the classification performances. Results: The final feature subset consisted of 5 features derived from the lesion shape and the first order histogram of DCE and ADC images volumes. XGboost and LGBM achieved statistically significantly higher average classification performances [AUC = 0.95 and 0.94 respectively], followed by Adaboost [AUC = 0.90], GB [AUC = 0.89] and SVM [AUC = 0.88]. Conclusion: Overall, the integration of Ensemble Learning methods within mpMRI radiomic analysis can improve the performance of computer-assisted diagnosis of breast cancer lesions.

PCaGuard: A Software Platform to Support Optimal Management of Prostate Cancer.

BACKGROUND AND OBJECTIVE: Prostate cancer (PCa) is a severe public health issue and the most common cancer worldwide in men. Early diagnosis can lead to early treatment and long-term survival. The addition of the multiparametric magnetic resonance imaging in combination with ultrasound (mpMRI-U/S fusion) biopsy to the existing diagnostic tools improved prostate cancer detection. Use of both tools gradually increases in every day urological practice. Furthermore, advances in the area of information technology and artificial intelligence have led to the development of software platforms able to support clinical diagnosis and decision-making using patient data from personalized medicine. METHODS: We investigated the current aspects of implementation, architecture, and design of a health care information system able to handle and store a large number of clinical examination data along with medical images, and produce a risk calculator in a seamless and secure manner complying with data security/accuracy and personal data protection directives and standards simultaneously. Furthermore, we took into account interoperability support and connectivity to legacy and other information management systems. The platform was implemented using open source, modern frameworks, and development tools. RESULTS: The application showed that software platforms supporting patient follow-up monitoring can be effective, productive, and of extreme value, while at the same time, aiding toward the betterment medicine clinical workflows. Furthermore, it removes access barriers and restrictions to specialized care, especially for rural areas, providing the exchange of medical images and patient data, among hospitals and physicians. CONCLUSION: This platform handles data to estimate the risk of prostate cancer detection using current state-of-the-art in eHealth systems and services while fusing emerging multidisciplinary and intersectoral approaches. This work offers the research community an open architecture framework that encourages the broader adoption of more robust and comprehensive systems in standard clinical practice.

Machine Learning in Meningioma MRI: Past to Present. A Narrative Review.

Meningioma is one of the most frequent primary central nervous system tumors. While magnetic resonance imaging (MRI), is the standard radiologic technique for provisional diagnosis and surveillance of meningioma, it nevertheless lacks the prima facie capacity in determining meningioma biological aggressiveness, growth, and recurrence potential. An increasing body of evidence highlights the potential of machine learning and radiomics in improving the consistency and productivity and in providing novel diagnostic, treatment, and prognostic modalities in neuroncology imaging. The aim of the present article is to review the evolution and progress of approaches utilizing machine learning in meningioma MRI-based sementation, diagnosis, grading, and prognosis. We provide a historical perspective on original research on meningioma spanning over two decades and highlight recent studies indicating the feasibility of pertinent approaches, including deep learning in addressing several clinically challenging aspects. We indicate the limitations of previous research designs and resources and propose future directions by highlighting areas of research that remain largely unexplored. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 2.

Incorporating diffusion-weighted imaging in a diagnostic algorithm for multiparametric MR mammography.

BACKGROUND: Apparent diffusion coefficient (ADC) measurements are not incorporated in BI-RADS classification. PURPOSE: To assess the probability of malignancy of breast lesions at magnetic resonance mammography (MRM) at 3 T, by combining ADC measurements with the BI-RADS score, in order to improve the specificity of MRM. MATERIAL AND METHODS: A total of 296 biopsy-proven breast lesions were included in this prospective study. MRM was performed at 3 T, using a standard protocol with dynamic sequence (DCE-MRI) and an extra echo-planar diffusion-weighted sequence. A freehand region of interest was drawn inside the lesion, and ADC values were calculated. Each lesion was categorized according to the BI-RADS classification. Logistic regression analysis was employed to predict the probability of malignancy of a lesion. The model combined the BI-RADS classification and the ADC value. Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were calculated. RESULTS: In total, 153 malignant and 143 benign lesions were analyzed; 257 lesions were masses and 39 lesions were non-mass-like enhancements. The sensitivity and specificity of the combined method were 96% and 86%, respectively, in contrast to 95% and 81% with BI-RADS classification alone. CONCLUSION: We propose a method of assessing the probability of malignancy in breast lesions by combining BI-RADS score and ADC values into a single formula, increasing sensitivity and specificity compared to BI-RADS classification alone.

Detection of Extramedullary Hematopoietic Tissue in a Patient with Beta-Thalassemia Major on Tc99m-Sestamibi Parathyroid Scintigraphy.

A 50-year-old man with beta-thalassemia major underwent Tc-99m sestamibi parathyroid scintigraphy due to elevated parathyroid hormone and calcium serum levels. Single-photon emission computed tomography imaging of neck and thorax revealed a parathyroid adenoma, as well as increased tracer uptake in a paraspinal region in the right hemithorax, where X-ray and computed tomography of the thorax had shown previously a mass compatible with extramedullary hematopoietic tissue.

Evaluation of the Performance of 18F-Fluorothymidine Positron Emission Tomography/Computed Tomography (18F-FLT-PET/CT) in Metastatic Brain Lesions.

18F-fluorothymidine (18F-FLT) is a radiolabeled thymidine analog that has been reported to help monitor tumor proliferation and has been studied in primary brain tumors; however, knowledge about 18F-FLT positron emission tomography/computed tomography (PET/CT) in metastatic brain lesions is limited. The purpose of this study is to evaluate the performance of 18F-FLT-PET/CT in metastatic brain lesions. A total of 20 PET/CT examinations (33 lesions) were included in the study. Semiquantitative analysis was performed: standard uptake value (SUV) with the utilization of SUVmax, tumor-to-background ratio (T/B), SUVpeak, SUV1cm³, SUV0.5cm³, SUV50%, SUV75%, PV50% (volume × SUV50%), and PV75% (volume × SUV75%) were calculated. Sensitivity, specificity, and accuracy for each parameter were calculated. Optimal cutoff values for each parameter were obtained. Using a receiver operating characteristic (ROC) curve analysis, the optimal cutoff values of SUVmax, T/B, and SUVpeak for discriminating active from non-active lesions were found to be 0.615, 4.21, and 0.425, respectively. In an ROC curve analysis, the area under the curve (AUC) is higher for SUVmax (p-value 0.017) compared to the rest of the parameters, while using optimal cutoff T/B shows the highest sensitivity and accuracy. PVs (proliferation × volumes) did not show any significance in discriminating positive from negative lesions. 18F-FLT-PET/CT can detect active metastatic brain lesions and may be used as a complementary tool. Further investigation should be performed.

Diagnostic performance of quantitative diffusion tensor imaging for the differentiation of breast lesions at 3 T MRI.

BACKGROUND: Conventional breast magnetic resonance imaging (MRI), including dynamic contrast-enhanced MR mammography, may lead to ambiguous diagnosis and unnecessary biopsies. PURPOSE: To investigate the contribution of quantitative diffusion tensor imaging (DTI) in the discrimination between benign and malignant breast lesions at 3 T MRI. MATERIAL AND METHODS: The study included a total of 86 lesions (44 benign and 42 malignant) in 58 women (34 with malignant lesions, 23 with benign lesions and 1 with both types of lesions). All patients were examined on a 3 T MRI scanner. Fractional Anisotropy (FA), Mean Diffusivity (MD), Apparent Diffusion Coefficient (ADC), as well as eigenvalues (λ1, λ2, λ3) were calculated and compared between benign and malignant lesions using two different software packages (GE Functool and ExploreDTI). RESULTS: Malignant lesions exhibited significantly lower ADC values compared to benign ones (ADCmal = 1.06 × 10-3 mm2/s, ADCben = 1.54 × 10-3 mm2/s, p-value < 0.0001). FA measurements in carcinomas indicated slightly higher values than those in benign lesions (FAmal = 0.20 ±â€¯0.07, FAben = 0.15 ±â€¯0.05, p-value = 0.0003). Eigenvalues λ1, λ2, λ3, showed significantly lower values in malignant tumors compared to benign lesions and normal breast tissue. ROC curve analysis of ADC and DTI metrics demonstrated that ADC provides high diagnostic performance (AUC = 0.944) while, MD and λ1 showed best discriminative results (AUC = 0.906) for the differentiation of malignant and benign lesions in contrast to other DTI parameters. CONCLUSION: The addition of eigenvalue analysis improves DTI's ability to differentiate between benign and malignant breast lesions.

Application of Radiomics and Decision Support Systems for Breast MR Differential Diagnosis.

Over the years, MR systems have evolved from imaging modalities to advanced computational systems producing a variety of numerical parameters that can be used for the noninvasive preoperative assessment of breast pathology. Furthermore, the combination with state-of-the-art image analysis methods provides a plethora of quantifiable imaging features, termed radiomics that increases diagnostic accuracy towards individualized therapy planning. More importantly, radiomics can now be complemented by the emerging deep learning techniques for further process automation and correlation with other clinical data which facilitate the monitoring of treatment response, as well as the prediction of patient's outcome, by means of unravelling of the complex underlying pathophysiological mechanisms which are reflected in tissue phenotype. The scope of this review is to provide applications and limitations of radiomics towards the development of clinical decision support systems for breast cancer diagnosis and prognosis.

Radiolabeled mAbs as Molecular Imaging and/or Therapy Agents Targeting PSMA.

Molecular imaging and therapy is a rapidly evolving field in research and clinical medicine. The use of the exciting and attractive properties of radioisotopes for imaging and therapy has made Nuclear Medicine very significant when it comes to molecular imaging/therapy. Monoclonal Antibodies (mAbs) on the other hand are very important targeting biomolecules with high affinity that can "carry" the radioisotope of choice. Herein we make a brief overview of the radiolabeled mAbs that target prostate specific membrane antigen (PSMA) and their use in the management of patients with prostate cancer (PCa).

Myocardial perfusion and left ventricular quantitative parameters obtained using gated myocardial SPECT: Comparison of three software packages.

BACKGROUND: The aim of the present study was to compare Emory Cardiac Toolbox, Myovation, and Quantitative Gated SPECT software regarding the automatic measurements of perfusion and functional left ventricular (LV) quantitative parameters, summed stress score (SSS), perfusion defect score, LV ejection fraction (LVEF), end-diastolic volume, and end-systolic volume (ESV). METHODS AND RESULTS: 99mTc-tetrofosmin gated SPECT studies were performed in 634 consecutive patients based on the one-day stress/rest protocol. Participants were divided into subgroups according to heart size (ESV cut-off value: 25 mL), perfusion (SSS >/≤3), and other patient/protocol-related factors. LVEF was categorized as normal (≥50%), mildly moderately impaired (35-49%), and severely abnormal (<35%). The concordance between the packages was good to excellent, in overall population, ESV ≤25 mL, ESV >25 mL, and SSS >3 subgroups (intraclass correlation coefficients, ICCs 0.73-0.93). In SSS ≤3 subgroup, the correlation was excellent for LV functional parameters, but suboptimal for perfusion variables (ICCs 0.30-0.83). LVEF categorization revealed similar variability (discordance 18.1 and 11.1% for stress/rest LVEF values, respectively). Pair comparisons demonstrated considerable differences concerning all parameters for all patient subgroups. The statistical significance of our findings by ESV and SSS classifications was evaluated. CONCLUSIONS: Despite the significant concordance between software packages, considerable differences in mean values of myocardial perfusion and LV functional parameters were demonstrated.

18F-fluorothymidine PET imaging in gliomas: an update.

Brain neoplasms constitute a group of tumors with discrete differentiation grades, and therefore, course of disease and prognosis. Magnetic resonance imaging (MRI) remains the gold standard method for the investigation of central nervous system tumors. However, MRI suffers certain limitations, especially if radiation therapy or chemotherapy has been previously applied. On the other hand, given the development of newer radiopharmaceuticals, positron emission tomography (PET) aims to a better investigation of brain tumors, assisting in the clinical management of the patients. In the present review, the potential contribution of radiolabeled fluorothymidine (FLT) imaging for the evaluation of brain tumors will be discussed. In particular, we will present the role of FLT-PET imaging in the depiction of well and poorly differentiated lesions, the assessment of patient prognosis and treatment response, and the recognition of disease recurrence. Moreover, related semi-quantitative and kinetic parameters will be discussed.

Multimodality-multiparametric brain tumors evaluation.

Brain tumors represent a vast group of lesions, originating from different neuronal cells with different degrees of aggressiveness. Despite some technological advances either pre or post-treatment, these tumors may share similar imaging findings and properties, rendering diagnosis/prognosis, an ambiguous process. Gadolinium-enhanced magnetic resonance imaging remains the gold standard for providing detailed morphologic information, but presents several limitations due to the overlap of findings, in cases such as progressive tumor and post-radiation related effects. Tumor cellularity, vascularity, proliferative activity, metabolic and functional profiles are a few of many characteristics that may further support tumor classification, but cannot be assessed by conventional imaging alone. We review the aforementioned factors and indicate how they improve tumor characterization and grading in order to design the optimal treatment strategy and better evaluate post treatment efficacy.

Magnetic Resonance Spectroscopy and Single-Photon Emission Computed Tomography in the Evaluation of Cerebral Tumors: A Case Report.

In their daily clinical practice, physicians have to confront diagnostic dilemmas which cannot be resolved by the application of only one imaging technique. In this case report, we present a 66-year-old woman who was admitted to our institution for the surgical resection of a recently diagnosed brain tumor. The patient had a history of epileptic seizures and was hospitalized in the past for anti-phospholipid syndrome related to a non-Hodgkin lymphoma in remission. Magnetic resonance imaging (MRI) examination revealed an enhancing right parasagittal lesion with significant edema suggestive of a high grade glioma. Advanced MRI techniques including proton magnetic resonance spectroscopy (1H-MRS) showed findings compatible of glioma. An additional examination was performed as part of a protocol that we are routinely performing in our institution for all brain tumors including not only the gold standard advanced MRI techniques but also single-photon emission computed tomography (SPECT) with technetium-99m (Tc99m). Brain SPECT indicated the presence of a meningioma which was verified by the histopathology of the resected specimen. In conclusion, a multimodality approach for the pre-surgical assessment of brain tumors has significant advantages not only for the diagnosis but also for the evaluation of intracranial tumors histology.

Fast spectroscopic multiple analysis (FASMA) for brain tumor classification: a clinical decision support system utilizing multi-parametric 3T MR data.

INTRODUCTION: A clinical decision support system (CDSS) for brain tumor classification can be used to assist in the diagnosis and grading of brain tumors. A Fast Spectroscopic Multiple Analysis (FASMA) system that uses combinations of multiparametric MRI data sets was developed as a CDSS for brain tumor classification. METHODS: MRI metabolic ratios and spectra, from long and short TE, respectively, as well as diffusion and perfusion data were acquired from the intratumoral and peritumoral area of 126 patients with untreated intracranial tumors. These data were categorized based on the pathology, and different machine learning methods were evaluated regarding their classification performance for glioma grading and differentiation of infiltrating versus non-infiltrating lesions. Additional databases were embedded to the system, including updated literature values of the related MR parameters and typical tumor characteristics (imaging and histological), for further comparisons. Custom Graphical User Interface (GUI) layouts were developed to facilitate classification of the unknown cases based on the user's available MR data. RESULTS: The highest classification performance was achieved with a support vector machine (SVM) using the combination of all MR features. FASMA correctly classified 89 and 79% in the intratumoral and peritumoral area, respectively, for cases from an independent test set. FASMA produced the correct diagnosis, even in the misclassified cases, since discrimination between infiltrative versus non-infiltrative cases was possible. CONCLUSIONS: FASMA is a prototype CDSS, which integrates complex quantitative MR data for brain tumor characterization. FASMA was developed as a diagnostic assistant that provides fast analysis, representation and classification for a set of MR parameters. This software may serve as a teaching tool on advanced MRI techniques, as it incorporates additional information regarding typical tumor characteristics derived from the literature.

Clinical decision support systems for brain tumor characterization using advanced magnetic resonance imaging techniques.

In recent years, advanced magnetic resonance imaging (MRI) techniques, such as magnetic resonance spectroscopy, diffusion weighted imaging, diffusion tensor imaging and perfusion weighted imaging have been used in order to resolve demanding diagnostic problems such as brain tumor characterization and grading, as these techniques offer a more detailed and non-invasive evaluation of the area under study. In the last decade a great effort has been made to import and utilize intelligent systems in the so-called clinical decision support systems (CDSS) for automatic processing, classification, evaluation and representation of MRI data in order for advanced MRI techniques to become a part of the clinical routine, since the amount of data from the aforementioned techniques has gradually increased. Hence, the purpose of the current review article is two-fold. The first is to review and evaluate the progress that has been made towards the utilization of CDSS based on data from advanced MRI techniques. The second is to analyze and propose the future work that has to be done, based on the existing problems and challenges, especially taking into account the new imaging techniques and parameters that can be introduced into intelligent systems to significantly improve their diagnostic specificity and clinical application.