Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI

In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa.

CT Coronary Angiography: Technical Approach and Atherosclerotic Plaque Characterization

Coronary computed tomography angiography (CCTA) currently represents a robust imaging technique for the detection, quantification and characterization of coronary atherosclerosis. However, CCTA remains a challenging task requiring both high spatial and temporal resolution to provide motion-free images of the coronary arteries. Several CCTA features, such as low attenuation, positive remodeling, spotty calcification, napkin-ring and high pericoronary fat attenuation index have been proved as associated to high-risk plaques. This review aims to explore the role of CCTA in the characterization of high-risk atherosclerotic plaque and the recent advancements in CCTA technologies with a focus on radiomics plaque analysis.

Radiomics for the identification of extraprostatic extension with prostate MRI: a systematic review and meta-analysis

OBJECTIVES

Extraprostatic extension (EPE) of prostate cancer (PCa) is predicted using clinical nomograms. Incorporating MRI could represent a leap forward, although poor sensitivity and standardization represent unsolved issues. MRI radiomics has been proposed for EPE prediction. The aim of the study was to systematically review the literature and perform a meta-analysis of MRI-based radiomics approaches for EPE prediction.

MATERIALS AND METHODS

Multiple databases were systematically searched for radiomics studies on EPE detection up to June 2022. Methodological quality was appraised according to Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool and radiomics quality score (RQS). The area under the receiver operating characteristic curves (AUC) was pooled to estimate predictive accuracy. A random-effects model estimated overall effect size. Statistical heterogeneity was assessed with I2 value. Publication bias was evaluated with a funnel plot. Subgroup analyses were performed to explore heterogeneity.

RESULTS

Thirteen studies were included, showing limitations in study design and methodological quality (median RQS 10/36), with high statistical heterogeneity. Pooled AUC for EPE identification was 0.80. In subgroup analysis, test-set and cross-validation-based studies had pooled AUC of 0.85 and 0.89 respectively. Pooled AUC was 0.72 for deep learning (DL)-based and 0.82 for handcrafted radiomics studies and 0.79 and 0.83 for studies with multiple and single scanner data, respectively. Finally, models with the best predictive performance obtained using radiomics features showed pooled AUC of 0.82, while those including clinical data of 0.76.

CONCLUSION

MRI radiomics-powered models to identify EPE in PCa showed a promising predictive performance overall. However, methodologically robust, clinically driven research evaluating their diagnostic and therapeutic impact is still needed.

CLINICAL RELEVANCE STATEMENT

Radiomics might improve the management of prostate cancer patients increasing the value of MRI in the assessment of extraprostatic extension. However, it is imperative that forthcoming research prioritizes confirmation studies and a stronger clinical orientation to solidify these advancements.

KEY POINTS

• MRI radiomics deserves attention as a tool to overcome the limitations of MRI in prostate cancer local staging. • Pooled AUC was 0.80 for the 13 included studies, with high heterogeneity (84.7%, p < .001), methodological issues, and poor clinical orientation. • Methodologically robust radiomics research needs to focus on increasing MRI sensitivity and bringing added value to clinical nomograms at patient level.

Emerging Role of Nuclear Medicine in Prostate Cancer: Current State and Future Perspectives

Prostate cancer is the most frequent epithelial neoplasia after skin cancer in men starting from 50 years and prostate-specific antigen (PSA) dosage can be used as an early screening tool. Prostate cancer imaging includes several radiological modalities, ranging from ultrasonography, computed tomography (CT), and magnetic resonance to nuclear medicine hybrid techniques such as single-photon emission computed tomography (SPECT)/CT and positron emission tomography (PET)/CT. Innovation in radiopharmaceutical compounds has introduced specific tracers with diagnostic and therapeutic indications, opening the horizons to targeted and very effective clinical care for patients with prostate cancer. The aim of the present review is to illustrate the current knowledge and future perspectives of nuclear medicine, including stand-alone diagnostic techniques and theragnostic approaches, in the clinical management of patients with prostate cancer from initial staging to advanced disease.

R0 surgical resection of giant dedifferentiated retroperitoneal liposarcomas in the COVID era with and without nephrectomy: A case report

Retroperitoneal sarcomas (RPSs) are rare findings that can grow into large masses without eliciting severe symptoms. At present, surgical resection is the only radical therapy, whenever it can be performed with the aim to achieve a complete removal of the tumor. The present report describes two consecutive cases of RPSs that resulted in dedifferentiated liposarcomas (DDLPSs) and these patients underwent R0 surgical resection with and without a nephron-sparing procedure. The diagnostic workup, the surgical approach, the impact of late surgical management due to the COVID pandemic and the latest literature on the topic are discussed and analyzed. The patients, who refused to undergo any medical examination during the prior 2 years due to the COVID pandemic, were admitted to Federico II University Hospital (Naples, Italy) complaining about weight loss and general abdominal discomfort. In the first case, a primitive giant abdominal right neoplasm of retroperitoneal origin enveloping and medializing the right kidney was observed. The second patient had a similar primitive retroperitoneal giant left neoplasm, which did not affect the kidney. Given the characteristics of the masses and the absence of distant metastases, after a multidisciplinary discussion, radical surgical removal was carried out for both patients. The lesions appeared well-defined from the surrounding tissues, and markedly compressed all the adjacent organs, without signs of infiltration. In the first patient, the right kidney was surrounded and undetachable from the tumor and it was removed en bloc with the mass. The second patient benefited from a nephron-sparing resection, due to the existence of a clear cleavage plane. The postoperative courses were uneventful. Both the histological examinations were oriented towards a DDLPS and both patients benefited from adjuvant chemotherapy. In conclusion, the treatment of giant RPS is still challenging and requires multidisciplinary treatment as well as, when possible, radical surgical removal. The lack of tissue infiltration and the avoidance of excision or reconstruction of major organs (including the kidney) could lead to an easier postoperative course and an improved prognosis. When possible, surgical management of recurrences or incompletely resected masses must be pursued. Since the COVID pandemic caused limited medicalization of a number of population groups and delayed diagnosis of other oncologic diseases, an increased number of DDLPSs could be expected in the near future.

MR image quality in local staging of prostate cancer: Role of PI-QUAL in the detection of extraprostatic extension

PURPOSE

To assess the impact of prostate MRI image quality by means of the Prostate Imaging Quality (PI-QUAL) score, on the identification of extraprostatic extension of disease (EPE), predicted using the EPE Grade Score, Likert Scale Score (LSS) and a clinical nomogram (MSKCCn).

METHODS

We retrospectively included 105 patients with multiparametric prostate MRI prior to prostatectomy. Two radiologists evaluated image quality using PI-QUAL (≥4 was considered high quality) in consensus. All cases were also scored using the EPE Grade, the LSS, and the MSKCCn (dichotomized). Inter-rater reproducibility for each score was also assessed. Accuracy was calculated for the entire population and by image quality, considering two thresholds for EPE Grade (≥2 and = 3) and LSS (≥3 and ≥ 4) and using McNemar's test for comparison.

RESULTS

Overall, 66 scans achieved high quality. The accuracy of EPE Grade ranged from 0.695 to 0.743, while LSS achieved values between 0.705 and 0.733. Overall sensitivity for the radiological scores (range = 0.235-0.529) was low irrespective of the PI-QUAL score, while specificity was higher (0.775-0.986). The MSKCCn achieved an AUC of 0.76, outperforming EPE Grade (=3 threshold) in studies with suboptimal image quality (0.821 vs 0.564, p = 0.016). EPE Grade (=3 threshold) accuracy was also better in high image quality studies (0.849 vs 0.564, p = 0.001). Reproducibility was good to excellent overall (95 % Confidence Interval range = 0.782-0.924).

CONCLUSION

Assessing image quality by means of PI-QUAL is helpful in the evaluation of EPE, as a scan of low quality makes its performance drop compared to clinical staging tools.

Advanced CMR Techniques in Anderson-Fabry Disease: State of the Art

Anderson-Fabry disease (AFD) is a rare multisystem X-linked lysosomal storage disorder caused by α-galactosidase A enzyme deficiency. Long-term cardiac involvement in AFD results in left ventricular hypertrophy and myocardial fibrosis, inducing several complications, mainly arrhythmias, valvular dysfunction, and coronary artery disease. Cardiac magnetic resonance (CMR) represents the predominant noninvasive imaging modality for the assessment of cardiac involvement in the AFD, being able to comprehensively assess cardiac regional anatomy, ventricular function as well as to provide tissue characterization. This review aims to explore the role of the most advanced CMR techniques, such as myocardial strain, T1 and T2 mapping, perfusion and hybrid imaging, as diagnostic and prognostic biomarkers.

Diagnosis and Clinical Implication of Left Ventricular Aneurysm in Hypertrophic Cardiomyopathy

Hypertrophic cardiomyopathy (HCM) is a genetic disease with heterogeneous clinical presentation and prognosis. Within the broad phenotypic expression of HCM, there is a subgroup of patients with a left ventricular (LV) apical aneurysm, which has an estimated prevalence between 2% and 5%. LV apical aneurysm is characterized by an area of apical dyskinesis or akinesis, often associated with regional scarring. To date, the most accepted pathomechanism of this complication is, in absence of coronary artery disease, the high systolic intra-aneurysmal pressure, which, combined with impaired diastolic perfusion from lower stroke volume, results in supply-demand ischemia and myocardial injury. Apical aneurysm is increasingly recognized as a poor prognostic marker; however, the efficacy of prophylactic anticoagulation and/or intracardiac cardioverted defibrillator (ICD) in improving morbidity and mortality is not yet clearly demonstrated. This review aims to elucidate the mechanism, diagnosis and clinical implication of LV aneurysm in patients with HCM.

Beyond diagnosis: is there a role for radiomics in prostate cancer management?

The role of imaging in pretreatment staging and management of prostate cancer (PCa) is constantly evolving. In the last decade, there has been an ever-growing interest in radiomics as an image analysis approach able to extract objective quantitative features that are missed by human eye. However, most of PCa radiomics studies have been focused on cancer detection and characterisation. With this narrative review we aimed to provide a synopsis of the recently proposed potential applications of radiomics for PCa with a management-based approach, focusing on primary treatments with curative intent and active surveillance as well as highlighting on recurrent disease after primary treatment. Current evidence is encouraging, with radiomics and artificial intelligence appearing as feasible tools to aid physicians in planning PCa management. However, the lack of external independent datasets for validation and prospectively designed studies casts a shadow on the reliability and generalisability of radiomics models, delaying their translation into clinical practice.Key points• Artificial intelligence solutions have been proposed to streamline prostate cancer radiotherapy planning.• Radiomics models could improve risk assessment for radical prostatectomy patient selection.• Delta-radiomics appears promising for the management of patients under active surveillance.• Radiomics might outperform current nomograms for prostate cancer recurrence risk assessment.• Reproducibility of results, methodological and ethical issues must still be faced before clinical implementation.

Dual-Energy CT of the Heart: A Review

Dual-energy computed tomography (DECT) represents an emerging imaging technique which consists of the acquisition of two separate datasets utilizing two different X-ray spectra energies. Several cardiac DECT applications have been assessed, such as virtual monoenergetic images, virtual non-contrast reconstructions, and iodine myocardial perfusion maps, which are demonstrated to improve diagnostic accuracy and image quality while reducing both radiation and contrast media administration. This review will summarize the technical basis of DECT and review the principal cardiac applications currently adopted in clinical practice, exploring possible future applications.

Insights into Myocardial Perfusion PET Imaging: the Coronary Flow Capacity

Purpose of Review

The present work summarizes the clinical relevance of coronary flow capacity (CFC) with an eye on future perspectives.

Recent findings

CFC concept has been recently introduced providing a comprehensive framework for coronary physiology evaluation.

Summary

It has been widely demonstrated that coronary artery disease (CAD) is a complex disease with a multifactorial etiology resulting from different pathogenic mechanisms. Cardiac positron emission tomography (PET) currently represents the gold standard for CAD assessment, providing absolute myocardial perfusion data including coronary flow reserve (CFR), calculated as the ratio of hyperemic to rest absolute myocardial blood flows. CFC can be obtained from dynamic PET images by plotting the primary stress perfusion data and CFR values for each pixel on a graph of predefined exact ranges. The routine evaluation of this parameter may add diagnostic and prognostic value to clinical and conventional imaging data.

Intramedullary Spinal Cord Metastases from Differentiated Thyroid Cancer, a Case Report

Intramedullary spinal cord metastases (ISCM) are uncommon metastases of the spinal cord. Magnetic resonance (MR) plays an important role in surgical planning when ISCM is suspected in the differential diagnosis. The incidence of ISCM is expected to increase due to the longer survival of cancer patients as well as the widespread use of MR in the diagnosis of neurological syndromes. The management of these patients is controversial because of the multiple clinical presentations and lack of controlled studies on the efficacy of different therapeutic approaches. Increased awareness of this rare entity may lead to an earlier diagnosis with novel imaging approaches at a stage when neurological deficits are reversible. A case of ISCM in a 49-year-old patient with differentiated thyroid cancer is reported.

Multimodality imaging approach to Fabry cardiomyopathy: Any role for nuclear cardiology?

Anderson-Fabry disease (AFD) is a multisystem X-linked disorder of lipid metabolism frequently associated with progressive glycosphingolipid accumulation in cardiac, renal, and nervous cells. The diagnosis of AFD is usually assessed by enzyme assay and genetic tests, but advanced cardiac imaging can be useful in detecting early signs of the disease. Echocardiography and cardiac magnetic resonance are the first-line imaging modalities to investigate cardiac involvement in AFD, but the recent introduction of new molecular and hybrid imaging techniques opens to a wider range of diagnostic applications. This article aims to provide an overview of nuclear cardiology techniques in diagnosis and clinical management of AFD.

Cardiovascular magnetic resonance native T1 mapping in Anderson-Fabry disease: a systematic review and meta-analysis

BACKGROUND

T1 mapping is an established cardiovascular magnetic resonance (CMR) technique that can characterize myocardial tissue. We aimed to determine the weighted mean native T1 values of Anderson-Fabry disease (AFD) patients and the standardized mean differences (SMD) as compared to healthy control subjects.

METHODS

A comprehensive literature search of the PubMed, Scopus and Web of Science databases was conducted according to the PRISMA statement to retrieve original studies reporting myocardial native T1 values in AFD patients and healthy controls. A random effects model was used to calculate SMD, and meta-regression analysis was conducted to explore heterogeneity sources. Subgroup analysis was also performed according to scanner field strength and sequence type.

RESULTS

From a total of 151 items, 14 articles were included in the final analysis accounting for a total population of 982 subjects. Overall, the weighted mean native T1 values was 984 ± 47 ms in AFD patients and 1016 ± 26 ms in controls (P < 0.0001) with a pooled SMD of - 2.38. In AFD patients there was an inverse correlation between native T1 values and male gender (P = 0.002) and left ventricular hypertrophy (LVH) (P < 0.001). Subgroup analyses confirmed lower T1 values in AFD patients compared to controls with a pooled SMD of -  2.54,  -  2.28, -   2.46 for studies performed on 1.5T with modified Look-Locker inversion recovery (MOLLI), shortened MOLLI and saturation-recovery single-shot acquisition, respectively and of -  2.41 for studies conducted on 3T.

CONCLUSIONS

Our findings confirm a reduction of native T1 values in AFD patients compared to healthy controls and point out that the degree of T1 shortening in AFD is influenced by gender and LVH. Although T1 mapping is useful in proving cardiac involvement in AFD patients, there is need to standardize shreshold values according to imaging equipment and protocols.

Cardiac CT and MRI radiomics: systematic review of the literature and radiomics quality score assessment

OBJECTIVE

To systematically review and evaluate the methodological quality of studies using magnetic resonance imaging (MRI) and computed tomography (CT) radiomics for cardiac applications.

METHODS

Multiple medical literature archives (PubMed, Web of Science, and EMBASE) were systematically searched to retrieve original studies focused on cardiac MRI and CT radiomics applications. Two researchers in consensus assessed each investigation using the radiomics quality score (RQS). Subgroup analyses were performed to assess whether the total RQS varied according to study aim, journal quartile, imaging modality, and first author category.

RESULTS

From a total of 1961 items, 53 articles were finally included in the analysis. Overall, the studies reached a median total RQS of 7 (IQR, 4-12), corresponding to a percentage score of 19.4% (IQR, 11.1-33.3%). Item scores were particularly low due to lack of prospective design, cost-effectiveness analysis, and open science. Median RQS percentage score was significantly higher in papers where the first author was a medical doctor and in those published on first quartile journals.

CONCLUSIONS

The overall methodological quality of radiomics studies in cardiac MRI and CT is still lacking. A higher degree of standardization of the radiomics workflow and higher publication standards for studies are required to allow its translation into clinical practice.

KEY POINTS

• RQS has been recently proposed for the overall assessment of the methodological quality of radiomics-based studies. • The 53 included studies on cardiac MRI and CT radiomics applications reached a median total RQS of 7 (IQR, 4-12), corresponding to a percentage of 19.4% (IQR, 11.1-33.3%). • A more standardized methodology in the radiomics workflow is needed, especially in terms of study design, validation, and open science, in order to translate the results to clinical applications.

MRI radiomics-based machine learning classification of atypical cartilaginous tumour and grade II chondrosarcoma of long bones

Background

Atypical cartilaginous tumour (ACT) and grade II chondrosarcoma (CS2) of long bones are respectively managed with watchful waiting or curettage and wide resection. Preoperatively, imaging diagnosis can be challenging due to interobserver variability and biopsy suffers from sample errors. The aim of this study is to determine diagnostic performance of MRI radiomics-based machine learning in differentiating ACT from CS2 of long bones.

Methods

One-hundred-fifty-eight patients with surgically treated and histology-proven cartilaginous bone tumours were retrospectively included at two tertiary bone tumour centres. The training cohort consisted of 93 MRI scans from centre 1 (n=74 ACT; n=19 CS2). The external test cohort consisted of 65 MRI scans from centre 2 (n=45 ACT; n=20 CS2). Bidimensional segmentation was performed on T1-weighted MRI. Radiomic features were extracted. After dimensionality reduction and class balancing in centre 1, a machine-learning classifier (Extra Trees Classifier) was tuned on the training cohort using 10-fold cross-validation and tested on the external test cohort. In centre 2, its performance was compared with an experienced musculoskeletal oncology radiologist using McNemar's test.

Findings

After tuning on the training cohort (AUC=0.88), the machine-learning classifier had 92% accuracy (60/65, AUC=0.94) in identifying the lesions in the external test cohort. Its accuracies in correctly classifying ACT and CS2 were 98% (44/45) and 80% (16/20), respectively. The radiologist had 98% accuracy (64/65) with no difference compared to the classifier (p=0.134).

Interpretation

Machine learning showed high accuracy in classifying ACT and CS2 of long bones based on MRI radiomic features.

Funding

ESSR Young Researchers Grant.

Cystadenoma of the seminal vesicle – Potential diagnostic pitfall: A case report and literature review

Background:

Cystadenomas of the seminal vesicles are benign cystic tumours, currently classified into the group of mixed epithelial-stromal tumours (MEST). Primary tumours arising in the seminal vesicles are quite rare, benign tumours being rarer than malignant ones, with only a few cases reported in the English literature since 1944. Cystadenomas represent a potential diagnostic pitfall, as they can be clinically confused with malignant neoplasms and histologically with non-neoplastic inflammatory lesions or other cystic tumours, even malignant.

Objective and methods:

We report a case of a 23-year-old man presenting with a cystic mass of the seminal vesicle, clinically suspected to be a malignant neoplasm. On pathological examination, a diagnosis of cystadenoma was made. Diagnostic criteria to make a diagnosis of this tumour are questionable. Therefore, we carried out a literature review in attempt to compare clinico-pathological findings of 28 cases reported in the English literature as cystadenomas of the seminal vesicle.

Results:

Only 28 cases of cystadenomas of seminal vesicles were reported in the English literature. The available data show the difficulty to rule out malignancy preoperatively in a patient with a solid-cystic mass in the pelvic region, and that morphological findings observed were often reported incompletely.

Conclusions:

The current classification appears debatable, as well as histopathological criteria to diagnose a cystadenoma of the seminal vesicle. For the proper management of these lesions, a multidisciplinary approach is mandatory.

Level of evidence:

Not applicable

Prostate Health Index and Multiparametric MRI: Partners in Crime Fighting Overdiagnosis and Overtreatment in Prostate Cancer

Simple Summary

In the last decades, the widespread use of PSA as the standard tool for prostate cancer diagnosis led to a high rate of overdiagnosis and overtreatment. More recently, multiparametric magnetic resonance imaging (mpMRI) became part of the diagnostic pathway, and several next-generation PSA-based tests (PHI, PHI density, 4Kscore, STHLM3) have been proposed. The multivariable approach promises to help with a better stratification of PCa patients at initial diagnosis. In this study, we evaluated the performance of the prostate health index (PHI) and mpMRI for the prediction of positive biopsy and of high-grade PCa at radical prostatectomy (RP). Our findings suggested that PHI had a better ability than mpMRI to predict positive biopsy, whereas a comparable performance in the identification of pathological aggressive PCa was pointed out. Notably, PHI and PHI density might represent useful biomarkers to recognize high-grade PCa in patients with low or uncertain PI-RADS scores on mpMRI.

Abstract

Widespread use of PSA as the standard tool for prostate cancer (PCa) diagnosis led to a high rate of overdiagnosis and overtreatment. In this study, we evaluated the performance of the prostate health index (PHI) and multiparametric magnetic resonance imaging (mpMRI) for the prediction of positive biopsy and of high-grade PCa at radical prostatectomy (RP). To this end, we prospectively enrolled 196 biopsy-naïve patients who underwent mpMRI. A subgroup of 116 subjects with biopsy-proven PCa underwent surgery. We found that PHI significantly outperformed both PI-RADS score (difference in AUC: 0.14; p < 0.001) and PHI density (difference in AUC: 0.08; p = 0.002) in the ability to predict positive biopsy with a cut-off value of 42.7 as the best threshold. Conversely, comparing the performance in the identification of clinically significant prostate cancer (csPCa) at RP, we found that PHI ≥ 61.68 and PI-RADS score ≥ 4 were able to identify csPCa (Gleason score ≥ 7 (3 + 4)) both alone and added to a base model including age, PSA, fPSA-to-tPSA ratio and prostate volume. In conclusion, PHI had a better ability than PI-RADS score to predict positive biopsy, whereas it had a comparable performance in the identification of pathological csPCa.

Role of serial cardiac 18F-FDG PET-MRI in Anderson-Fabry disease: a pilot study

Aim

We investigated the value of serial cardiac ¹⁸F-FDG PET-MRI in Anderson–Fabry disease (AFD) and the potential relationship of imaging results with FASTEX score.

Methods and results

Thirteen AFD patients underwent cardiac ¹⁸F-FDG PET-MRI at baseline and follow-up. Coefficient of variation (COV) of FDG uptake and FASTEX score were assessed. At baseline, 9 patients were enzyme replacement therapy (ERT) naïve and 4 patients were under treatment. Two patients presented a FASTEX score of 0 indicating stable disease and did not show any imaging abnormality at baseline and follow-up PET-MRI. Eleven patients had a FASTEX score > 20% indicating disease worsening. Four of these patients without late gadolinium enhancement (LGE) and with normal COV at baseline and follow-up had a FASTEX score of 35%. Three patients without LGE and with abnormal COV at baseline and follow-up had a FASTEX score ranging from 30 to 70%. Three patients with LGE and abnormal COV at baseline and follow-up had a FASTEX score between 35 and 75%. Finally, one patient with LGE and normal COV had a FASTEX score of 100%. Of the 12 patients on ERT at follow-up, FASTEX score was significantly higher in those 4 showing irreversible cardiac injury at baseline compared to 8 with negative LGE (66 ± 24 vs. 32 ± 21, p = 0.03).

Conclusion

¹⁸F-FDG PET-MRI may be effective to monitor cardiac involvement in AFD.

Effects of Interobserver Variability on 2D and 3D CT- and MRI-Based Texture Feature Reproducibility of Cartilaginous Bone Tumors

This study aims to investigate the influence of interobserver manual segmentation variability on the reproducibility of 2D and 3D unenhanced computed tomography (CT)- and magnetic resonance imaging (MRI)-based texture analysis. Thirty patients with cartilaginous bone tumors (10 enchondromas, 10 atypical cartilaginous tumors, 10 chondrosarcomas) were retrospectively included. Three radiologists independently performed manual contour-focused segmentation on unenhanced CT and T1-weighted and T2-weighted MRI by drawing both a 2D region of interest (ROI) on the slice showing the largest tumor area and a 3D ROI including the whole tumor volume. Additionally, a marginal erosion was applied to both 2D and 3D segmentations to evaluate the influence of segmentation margins. A total of 783 and 1132 features were extracted from original and filtered 2D and 3D images, respectively. Intraclass correlation coefficient ≥ 0.75 defined feature stability. In 2D vs. 3D contour-focused segmentation, the rates of stable features were 74.71% vs. 86.57% (p < 0.001), 77.14% vs. 80.04% (p = 0.142), and 95.66% vs. 94.97% (p = 0.554) for CT and T1-weighted and T2-weighted images, respectively. Margin shrinkage did not improve 2D (p = 0.343) and performed worse than 3D (p < 0.001) contour-focused segmentation in terms of feature stability. In 2D vs. 3D contour-focused segmentation, matching stable features derived from CT and MRI were 65.8% vs. 68.7% (p = 0.191), and those derived from T1-weighted and T2-weighted images were 76.0% vs. 78.2% (p = 0.285). 2D and 3D radiomic features of cartilaginous bone tumors extracted from unenhanced CT and MRI are reproducible, although some degree of interobserver segmentation variability highlights the need for reliability analysis in future studies.

Prostate Volume Estimation on MRI: Accuracy and Effects of Ellipsoid and Bullet-Shaped Measurements on PSA Density

RATIONALE AND OBJECTIVES

PSA density (PSAd), an important decision-making parameter for patients with suspected prostate cancer (PCa), is dependent on magnetic resonance imaging prostate volume (PV) estimation. We aimed to compare the accuracy of the ellipsoid and bullet-shaped formulas with manual whole-gland segmentation as reference standard and to evaluate the corresponding PSAd diagnostic accuracy in predicting clinically significant PCa.

MATERIALS AND METHODS

We retrospectively analysed 195 patients with suspected PCa who underwent magnetic resonance imaging and prostate biopsy. Patients with PCa were categorized according to ISUP score. PV and corresponding PSAd were calculated with manual segmentation (mPV and mPSAd) as well as with ellipsoid (ePV and ePSAd) and bullet-shaped (bPV and bPSAd) formulas. Inter and intra-reader reproducibility were assessed with Lin's concordance correlation coefficient and the intraclass correlation coefficient (ICC). A 2-way analysis of variance with post-hoc Bonferroni test was used for assessing PV differences. Predictive values of PSAd calculated with different methods for detecting clinically significant PCa were evaluated by receiver operating characteristic curve analysis and Youden's index.

RESULTS

Both intra (ρ = 0.99, ICC = 0.99) and inter-reader (ρ = 0.98, ICC = 0.98) reproducibility were excellent. No significant difference was found between ePV and reference standard (p = 1.00). bPV was significantly different from both (p = 0.00). PSAd (mPSAd/ePSAd cut-off ≥ 0.15, bPSAd cut-off ≥ 0.12) had sensitivity = 69-70%, specificity = 72-75%, areas under the curve = 0.757-0.760 (p = 0.70-0.88).

CONCLUSIONS

Our work shows that when using bullet-shaped formula, a different PSAd cut-off must be considered to avoid PCa under-diagnosis and inaccurate risk-stratification.

CT and MRI radiomics of bone and soft-tissue sarcomas: a systematic review of reproducibility and validation strategies

Background

Feature reproducibility and model validation are two main challenges of radiomics. This study aims to systematically review radiomic feature reproducibility and predictive model validation strategies in studies dealing with CT and MRI radiomics of bone and soft-tissue sarcomas. The ultimate goal is to promote achieving a consensus on these aspects in radiomic workflows and facilitate clinical transferability.

Results

Out of 278 identified papers, forty-nine papers published between 2008 and 2020 were included. They dealt with radiomics of bone (n = 12) or soft-tissue (n = 37) tumors. Eighteen (37%) studies included a feature reproducibility analysis. Inter-/intra-reader segmentation variability was the theme of reproducibility analysis in 16 (33%) investigations, outnumbering the analyses focused on image acquisition or post-processing (n = 2, 4%). The intraclass correlation coefficient was the most commonly used statistical method to assess reproducibility, which ranged from 0.6 and 0.9. At least one machine learning validation technique was used for model development in 25 (51%) papers, and K-fold cross-validation was the most commonly employed. A clinical validation of the model was reported in 19 (39%) papers. It was performed using a separate dataset from the primary institution (i.e., internal validation) in 14 (29%) studies and an independent dataset related to different scanners or from another institution (i.e., independent validation) in 5 (10%) studies.

Conclusions

The issues of radiomic feature reproducibility and model validation varied largely among the studies dealing with musculoskeletal sarcomas and should be addressed in future investigations to bring the field of radiomics from a preclinical research area to the clinical stage.

Clinical value of radiomics and machine learning in breast ultrasound: a multicenter study for differential diagnosis of benign and malignant lesions

Objectives

We aimed to assess the performance of radiomics and machine learning (ML) for classification of non-cystic benign and malignant breast lesions on ultrasound images, compare ML’s accuracy with that of a breast radiologist, and verify if the radiologist’s performance is improved by using ML.

Methods

Our retrospective study included patients from two institutions. A total of 135 lesions from Institution 1 were used to train and test the ML model with cross-validation. Radiomic features were extracted from manually annotated images and underwent a multistep feature selection process. Not reproducible, low variance, and highly intercorrelated features were removed from the dataset. Then, 66 lesions from Institution 2 were used as an external test set for ML and to assess the performance of a radiologist without and with the aid of ML, using McNemar’s test.

Results

After feature selection, 10 of the 520 features extracted were employed to train a random forest algorithm. Its accuracy in the training set was 82% (standard deviation, SD, ± 6%), with an AUC of 0.90 (SD ± 0.06), while the performance on the test set was 82% (95% confidence intervals (CI) = 70–90%) with an AUC of 0.82 (95% CI = 0.70–0.93). It resulted in being significantly better than the baseline reference (p = 0.0098), but not different from the radiologist (79.4%, p = 0.815). The radiologist’s performance improved when using ML (80.2%), but not significantly (p = 0.508).

Conclusions

A radiomic analysis combined with ML showed promising results to differentiate benign from malignant breast lesions on ultrasound images.

Key Points

• Machine learning showed good accuracy in discriminating benign from malignant breast lesions

• The machine learning classifier’s performance was comparable to that of a breast radiologist

• The radiologist’s accuracy improved with machine learning, but not significantly

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-08009-2.

Machine learning solutions in radiology: does the emperor have no clothes?

KEY POINTS

• Interest in radiomics and machine learning is steadily increasing and is reflected both in research output and number of commercially available solutions.• Currently available commercial products using machine learning are often supported by limited evidence of clinical usefulness and studies are often of low methodological quality.• Ethical and regulatory issues remain open and hinder implementation of machine learning software packages in daily clinical practice.

MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study

Objectives

To build a machine learning (ML) model to detect extraprostatic extension (EPE) of prostate cancer (PCa), based on radiomics features extracted from prostate MRI index lesions.

Methods

Consecutive MRI exams of patients undergoing radical prostatectomy for PCa were retrospectively collected from three institutions. Axial T2-weighted and apparent diffusion coefficient map images were annotated to obtain index lesion volumes of interest for radiomics feature extraction. Data from one institution was used for training, feature selection (using reproducibility, variance and pairwise correlation analyses, and a correlation-based subset evaluator), and tuning of a support vector machine (SVM) algorithm, with stratified 10-fold cross-validation. The model was tested on the two remaining institutions’ data and compared with a baseline reference and expert radiologist assessment of EPE.

Results

In total, 193 patients were included. From an initial dataset of 2436 features, 2287 were excluded due to either poor stability, low variance, or high collinearity. Among the remaining, 14 features were used to train the ML model, which reached an overall accuracy of 83% in the training set. In the two external test sets, the SVM achieved an accuracy of 79% and 74% respectively, not statistically different from that of the radiologist (81–83%, p = 0.39–1) and outperforming the baseline reference (p = 0.001–0.02).

Conclusions

A ML model solely based on radiomics features demonstrated high accuracy for EPE detection and good generalizability in a multicenter setting. Paired to qualitative EPE assessment, this approach could aid radiologists in this challenging task.

Key Points

• Predicting the presence of EPE in prostate cancer patients is a challenging task for radiologists.

• A support vector machine algorithm achieved high diagnostic accuracy for EPE detection, with good generalizability when tested on multiple external datasets.

• The performance of the algorithm was not significantly different from that of an experienced radiologist.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-07856-3.

Focal reduction in left ventricular 123I-metaiodobenzylguanidine uptake and impairment in systolic function in patients with Anderson-Fabry disease

BACKGROUND

Abnormalities of cardiac sympathetic innervation have been demonstrated in Anderson-Fabry disease (AFD). We aimed to investigate the relationship between regional left ventricular (LV) denervation and regional function abnormalities.

METHODS

Twenty-four AFD patients (43.7 ± 12.8 years) were studied by 123I-metaiodobenzylguanidine (MIBG) cardiac imaging and speckle-tracking echocardiography. Segmental tracer uptake was estimated according to 0 to 4 score, and total defect score (TDS) was calculated for each patient.

RESULTS

Segmental longitudinal strain worsened as MIBG uptake score increased (P < 0.001). By ROC analysis, a segmental longitudinal strain > - 16.2% predicted a segmental MIBG uptake score ≥1, with 79.7% sensitivity and 65.3% specificity. Segmental MIBG uptake defects were found in 13 out 24 AFD patients. LV mass index (60.8 ± 10.1 vs. 41.4 ± 9.8 g/h2.7), relative wall thickness (0.51 ± 0.06 vs. 0.40 ± 0.06), systolic pulmonary artery pressure (35.2 ± 6.7 vs. 27.2 ± 4.2 mmHg), and longitudinal strain (- 14.3 ± 2.7 vs. -19.4 ± 1.8%) were significantly higher in patients with segmental defect (all P < 0.01). At multivariate linear regression analysis, global longitudinal strain was independently associated with TDS (B = 3.007, 95% confidence interval 1.384 to 4.630, P = 0.001).

CONCLUSIONS

Reduced cardiac MIBG uptake reflects the severity of cardiac involvement in AFD patients. LV longitudinal function impairment seems to be an earlier disease feature than regional myocardial denervation.

Quality control and whole-gland, zonal and lesion annotations for the PROSTATEx challenge public dataset

PURPOSE

Radiomic features are promising quantitative parameters that can be extracted from medical images and employed to build machine learning predictive models. However, generalizability is a key concern, encouraging the use of public image datasets. We performed a quality assessment of the PROSTATEx training dataset and provide publicly available lesion, whole-gland, and zonal anatomy segmentation masks.

METHOD

Two radiology residents and two experienced board-certified radiologists reviewed the 204 prostate MRI scans (330 lesions) included in the training dataset. The quality of provided lesion coordinate was scored using the following scale: 0 = perfectly centered, 1 = within lesion, 2 = within the prostate without lesion, 3 = outside the prostate. All clearly detectable lesions were segmented individually slice-by-slice on T2-weighted and apparent diffusion coefficient images. With the same methodology, volumes of interest including the whole gland, transition, and peripheral zones were annotated.

RESULTS

Of the 330 available lesion identifiers, 3 were duplicates (1%). From the remaining, 218 received score = 0, 74 score = 1, 31 score = 2 and 4 score = 3. Overall, 299 lesions were verified and segmented. Independently of lesion coordinate score and other issues (e.g., lesion coordinates falling outside DICOM images, artifacts etc.), the whole prostate gland and zonal anatomy were also manually annotated for all cases.

CONCLUSION

While several issues were encountered evaluating the original PROSTATEx dataset, the improved quality and availability of lesion, whole-gland and zonal segmentations will increase its potential utility as a common benchmark in prostate MRI radiomics.

Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset

BACKGROUND

Prostate volume, as determined by magnetic resonance imaging (MRI), is a useful biomarker both for distinguishing between benign and malignant pathology and can be used either alone or combined with other parameters such as prostate-specific antigen.

PURPOSE

This study compared different deep learning methods for whole-gland and zonal prostate segmentation.

STUDY TYPE

Retrospective.

POPULATION

A total of 204 patients (train/test = 99/105) from the PROSTATEx public dataset.

FIELD STRENGTH/SEQUENCE

A 3 T, TSE T₂ -weighted.

ASSESSMENT

Four operators performed manual segmentation of the whole-gland, central zone + anterior stroma + transition zone (TZ), and peripheral zone (PZ). U-net, efficient neural network (ENet), and efficient residual factorized ConvNet (ERFNet) were trained and tuned on the training data through 5-fold cross-validation to segment the whole gland and TZ separately, while PZ automated masks were obtained by the subtraction of the first two.

STATISTICAL TESTS

Networks were evaluated on the test set using various accuracy metrics, including the Dice similarity coefficient (DSC). Model DSC was compared in both the training and test sets using the analysis of variance test (ANOVA) and post hoc tests. Parameter number, disk size, training, and inference times determined network computational complexity and were also used to assess the model performance differences. A P < 0.05 was selected to indicate the statistical significance.

RESULTS

The best DSC (P < 0.05) in the test set was achieved by ENet: 91% ± 4% for the whole gland, 87% ± 5% for the TZ, and 71% ± 8% for the PZ. U-net and ERFNet obtained, respectively, 88% ± 6% and 87% ± 6% for the whole gland, 86% ± 7% and 84% ± 7% for the TZ, and 70% ± 8% and 65 ± 8% for the PZ. Training and inference time were lowest for ENet.

DATA CONCLUSION

Deep learning networks can accurately segment the prostate using T₂ -weighted images.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

DNA methylation impact on Fabry disease

BACKGROUND

Fabry disease (FD) is a rare X-linked disease caused by mutations in GLA gene with consequent lysosomal accumulation of globotriaosylceramide (Gb3). Women with FD often show highly heterogeneous symptoms that can manifest from mild to severe phenotype.

MAIN BODY

The phenotypic variability of the clinical manifestations in heterozygous women with FD mainly depends on the degree and direction of inactivation of the X chromosome. Classical approaches to measure XCI skewness might be not sufficient to explain disease manifestation in women. In addition to unbalanced XCI, allele-specific DNA methylation at promoter of GLA gene may influence the expression levels of the mutated allele, thus impacting the onset and the outcome of FD. In this regard, analyses of DNA methylation at GLA promoter, performed by approaches allowing distinction between mutated and non-mutated allele, may be much more informative. The aim of this review is to critically evaluate recent literature articles addressing the potential role of DNA methylation in the context of FD. Although up to date relatively few works have addressed this point, reviewing all pertinent studies may help to evaluate the importance of DNA methylation analysis in FD and to develop new research and technologies aimed to predict whether the carrier females will develop symptoms.

CONCLUSIONS

Relatively few studies have addressed the complexity of DNA methylation landscape in FD that remains poorly investigated. The hope for the future is that ad hoc and ultradeep methylation analyses of GLA gene will provide epigenetic signatures able to predict whether pre-symptomatic female carriers will develop symptoms thus helping timely interventions.

A Rare Case of Solitary Fibrous Tumour of the Pelvis in an 18-Year-Old Young Man: CT and MRI Features with Pathologic Correlations

Solitary fibrous tumors (SFTs) are mesenchymal neoplasms of fibroblastic origin, even if commonly seen in the pleura, they can occur anywhere in the body. SFT presents as a slow growing, often asymptomatic mass, generally affecting middle-aged adults regardless of the sex. We report a rare case of an 18-year-old man referred to our institution to perform computed tomography (CT) and magnetic resonance imaging (MRI), to investigate a pelvic mass incidentally discovered at abdominal ultrasound examination. A well circumscribed, heterogenous and hypervascular lesion was described at imaging, with absence of calcifications, hemorrhage, necrosis nor cystic degeneration. The mass removal was performed via the Da Vinci-assisted robotic surgery. Histopathological evaluation confirmed the diagnosis of SFT. CT and MRI can aid the identification of SFT, providing useful information which needs to be supported by histopathological analysis.

Cardiac magnetic resonance imaging during the COVID-19 pandemic: A southern Italian single-center experience

Purpose

We aimed to assess the impact of COVID-19 pandemic on cardiac magnetic resonance (CMR) imaging studies performed during the lockdown imposed by the Italian Government from March 2020 to May 2020.

Materials and method

We reviewed the number and the findings of CMR scans performed during the COVID-19 pandemic between March and May 2020 at University of Naples Federico II. The number and the findings of CMR studies acquired in the corresponding months of 2017, 2018 and 2019 were also assessed for direct comparison.

Results

A total of 117 CMR studies was considered, including the procedures performed during the pandemic (n = 18) and those performed in the corresponding months of the prior 3 years (n = 99). The number of CMR studies performed during the COVID-19 pandemic was significantly (P < .01) lower compared to the mean number (n = 33) of the procedures performed in the corresponding months of 2017-2019. The percentage of abnormal CMR studies was similar (P = 0.73) during the pandemic (67 %) compared to that found in the corresponding months of 2017-2019 (70 %) suggesting that many abnormal tests were missed due to the lockdown.

Conclusion

The number of CMR studies was significantly reduced during the COVID-19 pandemic compared to the corresponding period of the previous three years. The lack of difference in the prevalence of abnormal CMR studies between the two study time intervals strongly suggests that many patients with potentially abnormal imaging test have been missed during the pandemic.

The Retinal Vessel Density as a New Vascular Biomarker in Multisystem Involvement in Fabry Disease: An Optical Coherence Tomography Angiography Study

In this study, we evaluated the possible relationship between the changes in retinal vessel density (VD) by optical coherence tomography angiography (OCTA) and the vascular alterations involving renal, cardiovascular and central nervous systems in patients affected by Fabry disease (FD). In 50 FD patients, the retinal superficial capillary plexus (SCP) and deep capillary plexus (DCP) in macular region were evaluated by OCTA examination. The patients also underwent a brain magnetic resonance imaging scan, renal and echocardiographic examinations with quantification of systolic pulmonary arterial pressure (PAPs) and left atrial volume index (LAVi). The VD of SCP and DCP was inversely related with E/e’ ratio, LAVi, interventricular septal thickness, global longitudinal strain (GLS) and PAPs (p < 0.05). No relationship was found, with a multivariate analysis, between OCTA parameters and kidney function and neuroradiological signs of central nervous system involvement. OCTA could be a new vascular biomarker in FD, revealing a strong correlation between retinal capillary damage and myocardial impairment, possibly preceding both renal dysfunction and cerebrovascular involvement.

Attitudes and perceptions towards multiparametric magnetic resonance imaging of the prostate: A national survey among Italian urologists

OBJECTIVE

We aimed to assess the attitudes and perceptions towards multiparametric magnetic resonance imaging (mpMRI) of the prostate among Italian urologists.

MATERIAL AND METHODS

A national, web-based survey was performed. A questionnaire composed of 18 multiple choice questions was e-mailed to 941 currently active urologists, members of the Italian Society of Urology. Preserving anonymity, respondents' demographics were collected (e.g. geographic region, type of workplace, prostate procedures performed) as well as data concerning their attitudes and perceptions towards mpMRI (e.g. indications deemed appropriate, degree of confidence in mpMRI results). Data were expressed as raw numbers and percentages of survey answers.

RESULTS

In total, 98 responses were received (participation rate = 10.4%). Respondents mostly worked in urban areas (96%) and primarily in hospital settings (89%), while 48% of them worked in southern Italy. 97% of respondents considered mpMRI useful to detect Prostate Cancer (PCa) in patients with prior negative biopsy, 64% in biopsy-naïve patients and 60% for PCa pre-operatory staging. About half (42%) of the participants declared that mpMRI results frequently lead them to change PCa management strategy. Standardization of mpMRI acquisition and reporting was partially unsatisfactory. Reported waiting time for mpMRI scans was longer than 4 weeks for 51% of respondents. The major limitation of this survey includes the small number of participants.

CONCLUSIONS

Prostate mpMRI is used by Italian urologists mainly for detection and for pre-operative staging of PCa. Further improvements in terms of mpMRI availability and report standardization are required.

Hybrid positron emission tomography-magnetic resonance imaging for assessing different stages of cardiac impairment in patients with Anderson-Fabry disease: AFFINITY study group

AIMS

Anderson-Fabry disease (AFD) is an X-linked lysosomal storage disorder associated with multi-organ dysfunction. While native myocardial T1 mapping by magnetic resonance (MR) allow non-invasive measurement of myocyte sphingolipid accumulation, 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) and MR are able to identify different pathological patterns of disease progression. We investigated the relationship between T1 mapping and 18F-FDG uptake by hybrid PET-MR cardiac imaging in AFD female patients.

METHODS AND RESULTS

Twenty AFD females without cardiac symptoms underwent cardiac PET-MR using 18F-FDG for glucose uptake. In all patients and in seven age- and sex-matched control subjects, T1 mapping was performed using native T1 Modified Look-Locker Inversion-recovery prototype sequences. 18F-FDG myocardial uptake was quantified by measuring the coefficient of variation (COV) of the standardized uptake value using a 17-segment model. T1 values of AFD patients were lower compared with control subjects (1236 ± 49 ms vs. 1334 ± 27 ms, P < 0.0001). Focal 18F-FDG uptake with COV >0.17 was detected in seven patients. COV was 0.32 ± 0.1 in patients with focal 18F-FDG uptake and 0.12 ± 0.04 in those without (P < 0.001). Patients with COV >0.17 had higher T1 values of lateral segments of the mid ventricular wall, compared with those with COV ≤0.17 (1216 ± 22 ms vs. 1160 ± 59 ms, P < 0.05).

CONCLUSION

In females with AFD, focal 18F-FDG uptake with a trend towards a pseudo-normalization of abnormal T1 mapping values, may represent an intermediate stage before the development of myocardial fibrosis. These findings suggest a potential relationship between progressive myocyte sphingolipid accumulation and inflammation.

Does left ventricular function predict cardiac outcome in Anderson-Fabry disease?

In Anderson–Fabry disease (AFD) the impact of left ventricular (LV) function on cardiac outcome is unknown. Noninvasive LV pressure–strain loop analysis is a new echocardiographic method to estimate myocardial work (MW). We aimed to evaluate whether LV function was associated with outcome and whether MW had a prognostic value in AFD. Ninety-six AFD patients (41.8 ± 14.7 years, 43.7% males) with normal LV ejection fraction were retrospectively evaluated. Inclusion criteria were sinus rhythm and ≥ 2-year follow-up. Standard echocardiography measurements, myocardial mechano-energetic efficiency (MEE) index, global longitudinal strain (GLS) and MW were evaluated. Adverse cardiac events were defined as composite of cardiac death, malignant ventricular tachycardia, atrial fibrillation and severe heart failure development. During a median follow-up of 63 months (interquartile range 37–85), 14 events occurred. Patient age, cardiac biomarkers, LV mass index, left atrium volume, E/Ea ratio, LV ejection fraction, MEE index, GLS and all MW indices were significantly related to adverse outcome at univariate analysis. After adjustment for clinical and echocardiographic parameters, which were significant at univariate analysis, GLS and MW resulted independent predictors of adverse events (p < 0.01). By ROC curve analysis, constructive MW ≤ 1513 mmHg% showed the highest sensitivity and specificity in predicting adverse outcome (92.9% and 86.6%, respectively). MW did not improve the predictive value of a model including clinical data, LV diastolic function and GLS. LV function impairment (both systolic and diastolic) is associated with adverse events in AFD. MW does not provide additive information over clinical features and systolic and diastolic function.

Breast implant associated anaplastic large cell lymphoma (BIA-ALCL): a challenging cytological diagnosis with hybrid PET/MRI staging and follow-up

We report a case of a 55-year-old woman with left breast cosmetic augmentation performed 5 years earlier, showing at ultrasound a left small amount of peri-implant effusion suspicious for an anaplastic large cell lymphoma localization. The final diagnosis was obtained by cytology using a small amount of fluid (6 ml). Subsequently, hybrid 18F-FDG PET/MRI was used for pre-operative staging and follow-up. An appropriate management of BIA-ALCL could be obtained even in cases of a small amount of peri-implant effusion, using a comprehensive approach of clinical and imaging evaluation, including PET/MRI as useful and innovative staging imaging technique.

Association between Left Atrial Deformation and Brain Involvement in Patients with Anderson-Fabry Disease at Diagnosis

Background: Anderson-Fabry disease (AFD) can induce both central nervous system white matter lesions (WMLs) and cardiac abnormalities including left atrial (LA) dysfunction. We sought to evaluate the possible interrelations of LA structure and function impairment with the presence of WMLs in AFD patients. Methods 22 AFD patients and 22 controls, matched for age and sex, underwent an echo-Doppler exam including quantification of peak atrial longitudinal strain (PALS). AFD patients underwent also a 3-T brain magnetic resonance imaging with a visual quantification of WMLs by Fazekas’ score (FS) on 3D FLAIR images. Results AFD patients had significantly higher left ventricular (LV) mass index (LVMi) and relative wall thickness, and lower PALS compared to controls. Among AFD patients, 9 showed a FS = 0, and 13 a FS > 1. AFD patients with FS ≥ 1 showed lower PALS (29.4 ± 6.7 vs. 37.2 ± 3.9%, p = 0.003) than those with FS = 0, without difference in LA volume index and LVMi. In AFD patients, FS was inversely related to PALS (r = −0.49, p < 0.0001), even after adjusting for LVMi (r = −0.43, p < 0.05). Conclusions In the absence of significant alterations in LA size, AFD patients had lower PALS compared to controls. The inverse association between PALS and presence of WMLs indicates a possible parallel early involvement of heart and brain.

Machine learning for the identification of clinically significant prostate cancer on MRI: a meta-analysis

OBJECTIVES

The aim of this study was to systematically review the literature and perform a meta-analysis of machine learning (ML) diagnostic accuracy studies focused on clinically significant prostate cancer (csPCa) identification on MRI.

METHODS

Multiple medical databases were systematically searched for studies on ML applications in csPCa identification up to July 31, 2019. Two reviewers screened all papers independently for eligibility. The area under the receiver operating characteristic curves (AUC) was pooled to quantify predictive accuracy. A random-effects model estimated overall effect size while statistical heterogeneity was assessed with the I² value. A funnel plot was used to investigate publication bias. Subgroup analyses were performed based on reference standard (biopsy or radical prostatectomy) and ML type (deep and non-deep).

RESULTS

After the final revision, 12 studies were included in the analysis. Statistical heterogeneity was high both in overall and in subgroup analyses. The overall pooled AUC for ML in csPCa identification was 0.86, with 0.81-0.91 95% confidence intervals (95%CI). The biopsy subgroup (n = 9) had a pooled AUC of 0.85 (95%CI = 0.79-0.91) while the radical prostatectomy one (n = 3) of 0.88 (95%CI = 0.76-0.99). Deep learning ML (n = 4) had a 0.78 AUC (95%CI = 0.69-0.86) while the remaining 8 had AUC = 0.90 (95%CI = 0.85-0.94).

CONCLUSIONS

ML pipelines using prostate MRI to identify csPCa showed good accuracy and should be further investigated, possibly with better standardisation in design and reporting of results.

KEY POINTS

• Overall pooled AUC was 0.86 with 0.81-0.91 95% confidence intervals. • In the reference standard subgroup analysis, algorithm accuracy was similar with pooled AUCs of 0.85 (0.79-0.91 95% confidence intervals) and 0.88 (0.76-0.99 95% confidence intervals) for studies employing biopsies and radical prostatectomy, respectively. • Deep learning pipelines performed worse (AUC = 0.78, 0.69-0.86 95% confidence intervals) than other approaches (AUC = 0.90, 0.85-0.94 95% confidence intervals).

Identification and typing of cardiac amyloidosis by noninvasive imaging: Two cases for two patterns

Cardiac amyloidosis is a restrictive infiltrative cardiomyopathy burdened by high mortality. The two more common forms are immunoglobulin light-chain amyloidosis and transthyretin-related amyloidosis with different prognoses and treatments. However, distinguishing between them is challenging. Appropriate utilization of the different available imaging techniques in the evaluation of patients with known or suspected cardiac amyloidosis is mandatory. We report two cases with cardiac amyloidosis of different etiology and with distinct imaging patterns. In the first case, the negative 99mTc-diphosphonate imaging was useful to support the diagnosis of cardiac amyloid light-chain; the second case emphasized the utility of whole-body scintigraphy in recognizing transthyretin-related cardiac amyloidosis and the potential role of cadmium-zinc-telluride SPECT imaging for the evaluation of segmental distribution of cardiac disease. Both cases support the growing interest in looking for noninvasive methods to type cardiac amyloidosis in the place of invasive myocardial biopsy highlighting both possibilities and limitations of available imaging techniques in diagnosis and treatment monitoring.

Prostate MRI radiomics: A systematic review and radiomic quality score assessment

BACKGROUND

Radiomics have the potential to further increase the value of MRI in prostate cancer management. However, implementation in clinical practice is still far and concerns have been raised regarding the methodological quality of radiomic studies. Therefore, we aimed to systematically review the literature to assess the quality of prostate MRI radiomic studies using the radiomics quality score (RQS).

METHODS

Multiple medical literature archives (PubMed, Web of Science and EMBASE) were searched to retrieve original investigations focused on prostate MRI radiomic approaches up to the end of June 2019. Three researchers independently assessed each paper using the RQS. Data from the most experienced researcher were used for descriptive analysis. Inter-rater reproducibility was assessed using the intraclass correlation coefficient (ICC) on the total RQS score.

RESULTS

73 studies were included in the analysis. Overall, the average RQS total score was 7.93 ± 5.13 on a maximum of 36 points, with a final average percentage of 23 ± 13%. Among the most critical items, the lack of feature robustness testing strategies and external validation datasets. The ICC resulted poor to moderate, with an average value of 0.57 and 95% Confidence Intervals between 0.44 and 0.69.

CONCLUSIONS

Current studies on prostate MRI radiomics still lack the quality required to allow their introduction in clinical practice.