Search

Purpose To assess a radiomic machine learning (ML) model in classifying solid adrenal lesions (ALs) without fat signal drop on chemical shift (CS) as benign or malignant. Method 55 indeterminate ALs (21 lipid poor adenomas, 15 benign pheocromocytomas, 1 oncocytoma, 12 metastases, 6 primary tumors) showing no fat signal drop on CS were retrospectively included. Manual 3D segmentation on T2-weighted and CS images was performed for subsequent radiomic feature extraction. After feature stability testing and an 80–20% train-test split, the train set was balanced via oversampling. Following a multi-step feature selection, an Extra Trees model was tuned with 5-fold stratified cross-validation in the train set and then tested on the hold-out test set. Results A total of 3396 features were extracted from each AL, of which 133 resulted unstable while none had low variance (< 0.01). Highly correlated (r > 0.8) features were also excluded, leaving 440 parameters. Among these, Support Vector Machine 5-fold stratified cross-validated recursive feature elimination selected a subset of 6 features. ML obtained a cross-validation accuracy of 0.94 on the train and 0.91 on the test sets. Precision, recall and F1 score were respectively 0.92, 0.91 and 0.91. Conclusions Our MRI handcrafted radiomics and ML pipeline proved useful to characterize benign and malignant solid indeterminate adrenal lesions.

We present a case of a middle-age male who presented in emergency room with nonspecific abdominal pain. A contrast-enhanced computer tomography (ceCT) scan showed a reduced perfusion of both adrenal glands. The clinical examinations and the laboratory tests were negative for an adrenal pathological process. To reassess the adrenal ischemia, a second ceCT scan was performed 5 days later showing an acute bilateral adrenal hemorrhage. These findings demonstrated that the previous adrenal hypoperfusion represented the prodromal manifestation of a hemorrhagic intraglandular process. This case suggests that adrenal hypoperfusion detected on tomographic imaging dictates a prompt clinical management finalized to strictly monitor the potential evolution towards a more aggressive pathological condition and confirms the pivotal role of imaging in the diagnosis of such uncommon disorder.

Objective The identification of deep myometrial invasion (DMI) represents a fundamental aspect in patients with endometrial cancer (EC) for accurate disease staging. It can be detected on MRI using T2-weighted (T2-w), diffusion weighted (DWI) and dynamic contrast enhanced sequences (DCE). Aim of the study was to perform a multi-reader evaluation of such sequences to identify the most accurate and its reliability for the best protocol. Methods In this multicenter retrospective study, MRI were independently evaluated by 4 radiologists (2 senior and 2 novice) with a sequence-based approach to identify DMI. The performance of the entire protocol was also evaluated. A comparison between the different sequences assessed by the same reader was performed using receiver operating curve and post-hoc analysis. Intraclass Correlation Coefficient (ICC) was used to assess inter- and intra-observer variability. Results A total of 92 patients were included. The performance of the readers did not show significant differences among DWI, DCE and the entire protocol. For only one senior radiologist, who reached the highest diagnostic accuracy with the entire protocol (82,6 %), both DWI (p = 0,0197) and entire protocol (p = 0,0039) were found significantly superior to T2-w. The highest inter-observer agreement was obtained with the entire protocol by expert readers (ICC = 0,77). Conclusions For the detection of DMI, the performances of DWI and DCE alone and that of a complete protocol do not significantly differ, even though the latter ensures the highest reliability particularly for expert readers. In cases in which T2-w and DWI are consistent, an unenhanced protocol could be proposed.

Pheochromocytomas may show atypical imaging findings leading to diagnostic pitfalls. We correlated the results of magnetic resonance imaging (MRI) with those of radionuclide studies in patients with pheochromocytomas. T2-weighted (-w), T1-w chemical-shift and T1-w dynamic contrast enhanced (DCE) MRI sequences were evaluated to assess tumor structure. 131Iodine metaiodobenzylguanidine (MIBG) scintigraphy, 18fluoro (F) deoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) or FDG PET/MRI were evaluated for direct comparison. Of a total of 80 adrenal lesions in 73 patients, 20 in 18 patients were pheochromocytomas. More than half (55%) of the pheochromocytomas (n = 11) had the typical increased signal intensity on T2-w and T1-w DCE, while the remaining (n = 9) lesions showed atypical findings, of these nine latter atypical lesions, seven (35%) were cystic (two totally, three predominantly and two partially) and two (10%) were hemorrhagic on MRI. In these atypical lesions, MIBG scintigraphy (n = 5), FDG PET/CT (n = 6) or FDG PET/MRI (n = 2) showed inhomogeneous tracer uptake in the residual viable tissue providing tumor characterization, however, one predominantly cystic pheochromocytoma showed false negative MIBG scan. Our preliminary results show that cystic degeneration may be frequent in pheochromocytoma being so marked that only a thin rim of viable cells may residue to disclose the true nature of the tumor. MRI findings together with those of correlative planar/hybrid radionuclide images are helpful to characterize these atypical pheochromocytomas. In particular, tumor accumulation of MIBG and/or FDG is able to classify these lesions as not simple cysts, in detail, the presence of partial MIBG uptake allows the diagnosis of pheochromocytomas, while the presence of partial FDG uptake generically reflects the presence of viable solid tissue of such cystic tumors.

Purpose: To perform an intra-patient comparison between a single-pass protocol (SP) and a portal venous phase (PVP) by means of both quantitative and qualitative analysis of image quality. Methods: Forty patients (31 M; 9F; aged 20–77 years; BMI 23 ± 4 Kg/m2) underwent both a SP and a PVP using a 64-rows multi-detector CT with a median interval time of 56 days (range 5–903). All patients underwent i.v. bolus injection (2.0 cc/sec) of 1.7 cc/Kg of a non ionic iodinated contrast-media (370 mgI/ml) with scan delays of 67 ± 8 and 90 s for the SP and the PVP, respectively. Signal- (SNR) and contrast-to-noise ratios (CNR) were calculated for most visceral organs and for both abdominal aorta (AA) and main portal vein (MPV). For qualitative analysis, reproduction of abdominal viscera and vascular structures was blindly evaluated and inter-observer agreement calculated by the weighted Cohen k-analysis. Results: Attenuation values (H.U.) of AA (232 ± 53 vs 180 ± 36) and MPV (215 ± 39 vs 187 ± 42) were significantly (p < 0.001) higher in the SP than in PVP, respectively. At qualitative analysis, reproduction of most abdominal viscera was also significantly sharper (p < 0.001) with the SP than the PVP with inter-observer agreement scores (k) ranging from 0.60 to 0.88 for all but one imaging criteria. Conclusions: As the SP resulted in a significantly higher vascular enhancement and in a sharper reproduction of most abdominal viscera, it may be better suited than a PVP for the CT evaluation of non traumatic acute abdomen.

Background: MRI is a useful imaging modality to assess the presence of pancreatic neuroendocrine tumors (PNETs), allowing repeat monitoring examinations in multiple endocrine neoplasia type 1 (MEN-1) patients. Objectives: We aimed to compare the diagnostic accuracy of conventional MRI sequences to identify which sequence better depicts the presence of PNETs in MEN-1 patients. Method: We performed a retrospective analysis of consecutive MEN-1 patients who underwent a conventional MRI protocol to monitor previously proven PNETs. MRI sequences T1-w chemical shift (CS), T2-w HASTE, fat-suppressed (FS) T2-w HASTE, diffusion-weighted imaging (DWI), and pre- and post-contrast FS T1-w sequences were independently analyzed by 2 experienced radiologists using a 3-grade score (no lesion, uncertain lesion, and certain lesion); lesion size and signal intensity were recorded. A Friedman ANOVA and a Wilcoxon pairwise test for the post hoc analysis were used. The sensitivity of each sequence was measured, and the results were analyzed with the χ2 test. Results: We included 21 patients with a total of 45 PNETs proven by histology, endoscopic ultrasonography-guided fine-needle aspiration, CT, and nuclear medicine studies. A statistically significant (p < 0.01) difference was observed in the detection performance of each MRI sequence, particularly between DWI (91%) and T2-w FS (85%) sequences in comparison to the others (T1-w CS, T2-w, and pre- and post-contrast FS T1-w, ≤56% for all); no significant (p = 0.5) difference was found between the detection performance of DWI and T2-w FS sequences. No correlation was observed between the qualitative score of each sequence and lesion tumor size. Conclusions: DWI and T2-w FS sequences proved to be the most accurate in the detection of PNETs, thus suggesting a role for an abbreviated MRI protocol without contrast medium administration for monitoring MEN-1 patients.

Angiomyolipomas (AMLs) are among the most common benign renal tumors, typically consisting of varying proportions of 3 components: blood vessels (angio), smooth muscle cells (myo), and fatty tissue (lipoma), and are thus called triphasic. Occasionally, AMLs may present atypical histologic features consisting almost exclusively of one component (monophasic) or containing numerous epithelioid muscle cells with small amount of fat, as in the rare epithelioid variant (E-AMLs). AMLs occur as a sporadic entity in 80% of cases; more rarely, they are related to hereditary diseases such as tuberous sclerosis complex (TSC). Hereditary AMLs can reach huge dimensions and may present unusual imaging features determining diagnostic pitfalls. Few cases of giant sporadic AMLs are reported in literature, and even fewer regarding the epithelioid variant. We present a case of a 36-year-old man suffering from anemia and fever, whose contrast-enhanced computed tomography (CT) depicted the presence of a huge (14 x 21 x 30 cm) retroperitoneal fat-containing mass.