Search

Splenic hamartoma is a rare benign vascular lesion of the spleen. A splenic mass was incidentally detected in an asymptomatic 65-year-old male during an abdominal ultrasound scan. The workup of the splenic lesion included an abdominal CT angiography (CTA), contrast-enhanced ultrasound (CEUS), and microvascular flow imaging Doppler sonography. The CT scan confirmed that the splenic mass had benign characteristics, and its contrast enhancement was similar to the spleen. The CEUS was able to rule out the possibility of hemangioma. Meanwhile, chronic compression of the celiac trunk and the filling of the splenic artery from collaterals were also detected on CTA. The imaging studies suggested a splenic hamartoma, and the diagnosis was confirmed by the result of a fine needle aspiration biopsy.

Background The nature of input data is an essential factor when training neural networks. Research concerning magnetic resonance imaging (MRI)-based diagnosis of liver tumors using deep learning has been rapidly advancing. Still, evidence to support the utilization of multi-dimensional and multi-parametric image data is lacking. Due to higher information content, three-dimensional input should presumably result in higher classification precision. Also, the differentiation between focal liver lesions (FLLs) can only be plausible with simultaneous analysis of multi-sequence MRI images. Aim To compare diagnostic efficiency of two-dimensional (2D) and three-dimensional (3D)-densely connected convolutional neural networks (DenseNet) for FLLs on multi-sequence MRI. Methods We retrospectively collected T2-weighted, gadoxetate disodium-enhanced arterial phase, portal venous phase, and hepatobiliary phase MRI scans from patients with focal nodular hyperplasia (FNH), hepatocellular carcinomas (HCC) or liver metastases (MET). Our search identified 71 FNH, 69 HCC and 76 MET. After volume registration, the same three most representative axial slices from all sequences were combined into four-channel images to train the 2D-DenseNet264 network. Identical bounding boxes were selected on all scans and stacked into 4D volumes to train the 3D-DenseNet264 model. The test set consisted of 10-10-10 tumors. The performance of the models was compared using area under the receiver operating characteristic curve (AUROC), specificity, sensitivity, positive predictive values (PPV), negative predictive values (NPV), and f1 scores. Results The average AUC value of the 2D model (0.98) was slightly higher than that of the 3D model (0.94). Mean PPV, sensitivity, NPV, specificity and f1 scores (0.94, 0.93, 0.97, 0.97, and 0.93) of the 2D model were also superior to metrics of the 3D model (0.84, 0.83, 0.92, 0.92, and 0.83). The classification metrics of FNH were 0.91, 1.00, 1.00, 0.95, and 0.95 using the 2D and 0.90, 0.90, 0.95, 0.95, and 0.90 using the 3D models. The 2D and 3D networks' performance in the diagnosis of HCC were 1.00, 0.80, 0.91, 1.00, and 0.89 and 0.88, 0.70, 0.86, 0.95, and 0.78, respectively; while the evaluation of MET lesions resulted in 0.91, 1.00, 1.00, 0.95, and 0.95 and 0.75, 0.90, 0.94, 0.85, and 0.82 using the 2D and 3D networks, respectively. Conclusion Both 2D and 3D-DenseNets can differentiate FNH, HCC and MET with good accuracy when trained on hepatocyte-specific contrast-enhanced multi-sequence MRI volumes.

It has been proven in a few early studies that radiomic analysis offers a promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT texture analysis (CTTA) has been receiving significant attention, especially for response evaluation and prognostication of different oncological diagnoses. In this review article, we discuss the unique ability of radiomics and its subfield CTTA to diagnose lesions in the pancreas and kidney. We review studies in which CTTA was used for the classification of histology grades in pancreas and kidney tumors. We also review the role of radiogenomics in the prediction of the molecular and genetic subtypes of pancreatic tumors. Furthermore, we provide a short report on recent advancements of radiomic analysis in predicting prognosis and survival of patients with pancreatic and renal cancers.

Artificial Intelligence and the use of radiomics analysis have been of great interest in the last decade in the field of imaging. CT texture analysis (CTTA) is a new and emerging field in radiomics, which seems promising in the assessment and diagnosis of both focal and diffuse liver lesions. The utilization of CTTA has only been receiving great attention recently, especially for response evaluation and prognostication of different oncological diagnoses. Radiomics, combined with machine learning techniques, offers a promising opportunity to accurately detect or differentiate between focal liver lesions based on their unique texture parameters. In this review article, we discuss the unique ability of radiomics in the diagnostics and prognostication of both focal and diffuse liver lesions. We also provide a brief review of radiogenomics and summarize its potential role of in the non-invasive diagnosis of malignant liver tumors.

PURPOSE Our study aimed to evaluate the technical success rate, interobserver reproducibility, and accuracy of shearwave elastography (SWE) in the staging of hepatitis C virus (HCV)-associated liver fibrosis. METHODS A total of 10 healthy controls and 49 patients with chronic liver disease were enrolled prospectively. Two examiners performed point shearwave elastography (pSWE) and two-dimensional shearwave elastography (2D-SWE) measurements with an RS85A ultrasound scanner using the S-Shearwave application (Samsung Medison, Hongcheon, Korea). The performance of S-Shearwave in the staging (METAVIR F0-F4) of liver fibrosis was compared with prior transient elastography (TE) with receiver operating characteristic (ROC) curve analysis. RESULTS The interobserver reproducibility was excellent with pSWE (ICC = 0.92, 95% CI: 0.86-0.95, P < .001). A very good agreement was found between pSWE and TE measurements (ICC =0.85, 95% CI: 0.78-0.89, P

AIM To retrospectively assess the clinical effectiveness of intra-arterial steroid administration (IASA) treatment in adult patients who developed steroid-refractory gastrointestinal acute graft-versus-host disease (GI-aGvHD) (≥stage II) following haematopoietic stem cell transplantation. MATERIALS AND METHODS Clinical data of 10 consecutive adult patients (age range, 19–61 years; mean age, 42 years) of a single centre with GI-aGvHD (≥stage II) who showed no response to intravenous methylprednisolone and received IASA into the superior (SMA) and/or inferior mesenteric arteries (IMA) were analysed. The severity of aGvHD was determined as the volume of diarrhoea (stages 0–IV) and the Glucksberg grading system before and 12±3 SD, 27±4 and 54±6 days after IASA treatment. Median follow-up was 65 days (range, 22–370 days). RESULTS Six out of 10 patients at 12 days, 8/10 patients at 27 days, 6/10 patients at 54 days after IASA showed gastrointestinal response. Among them, 1/10 patients at 12 days, 4/10 patients at 27 days, and the same 4/10 patients at 54 days showed complete resolution of GI-aGvHD. The 4/10 patients who reached complete resolution of GI-aGvHD at day 12 or 27 showed a sustained symptom-free state. One in 10 patient showed only a temporary response, 5/10 patients died between days 22 and 67. CONCLUSIONS IASA seems to be a potentially useful second-line therapy for intravenous steroid-refractory GI-aGvHD.

To examine the improvement in the visualisation of bladder and ureteric pathologies next to a hip prosthesis with metallic artefact reduction for orthopaedic implants (O-MAR).Thirty-four patients who underwent pelvic computed tomography (CT) for non-prosthesis-related causes were enrolled retrospectively. Portal venous phase scans were reconstructed both with standard iterative reconstruction (ITR) and with O-MAR. The density of the ureters and the bladder was measured at both sides in the plane of the prosthesis. A semi-quantitative score was also used to assess visibility. The R (version 3.4.1) package was used for statistical analysis.The average (μ) density of the 41 prosthesis side ureters was significantly lower on ITR images (μ=-94.76±150.48 [±SD] HU) than on O-MAR images (μ=-13.40±36.37 HU; p0.0004). The difference between the ITR and O-MAR (μ=-138.62±182.64 versus -35.55±40.21 HU; p0.0003) was also significant at the prosthesis side of the bladder. The visibility of the prosthesis side ureters was improved: 53.7% was obscured on ITR series compared to 4.9% on O-MAR. The visibility score was also better across all levels (p0.001) with O-MAR. In four cases (13%), the O-MAR images significantly changed the diagnosis: in two cases ureteric stones, in one case each a bladder stone and a bladder tumour were discovered.O-MAR reconstruction of CT images significantly improves the visibility of the urinary tract adjacent to metallic hip implants. Thus, O-MAR is essential for detecting ureteric and bladder pathologies in patients with a hip prosthesis.

It has been demonstrated recently in several solid tumors that thrombocytosis at diagnosis may correlate with tumor invasion, metastatic progression and worse outcome. Several details of the pathomechanism of the relationship of thrombocytosis and cancer have been elucidated; however, the complete process is not clearly understood. Several hypotheses have been proposed. Recently, it was suggested that in ovarian cancer elevated IL-6 production by the tumor may induce increased megakaryopoiesis via hepatic thrombopoietin production leading to thrombocytosis. The importance of the prognostic power of elevated platelet count is still debated in gastrointestinal cancer. The aims of this review were to evaluate the prognostic significance of thrombocytosis in gastrointestinal tumors, to see whether clinical practice confirmed the hypotheses and to reveal the causes of the inconsistent findings.

To evaluate the prognostic value of pretreatment pelvic magnetic resonance imaging (MRI) features in uterine artery embolisation (UAE) for symptomatic fibroids.MRI characteristics of 109 fibroids (≥3 cm) in 70 patients were analysed retrospectively. Imaging was performed 1.8±1.3 (SD) months before and 6.6±1.8 months after UAE. On pretreatment images, signal intensity (SI) of fibroids was compared with that of the myometrium and skeletal muscle on T1- and T2-weighted sequences; the contrast enhancement pattern and localisation of fibroids were also analysed. Fibroid volume reduction (VR) was assessed by control imaging. The numerical analogue quality-of-life score was obtained before and after UAE. Statistical analysis was performed using the Mann-Whitney U-test, Kruskal-Wallis test, and Wilcoxon signed-rank test.The mean fibroid volume decreased by 51.1±30.8% during the 6.6±1.8 months (p0.001). Mean quality-of-life score improved by 48.2±27.6 points (p0.001). The mean VR of submucosal fibroids (82.1±18.5%) was greater than that of intramural (49.4±30.7%) and subserosal (43±28.3%) fibroids (p0.001 for both). Fibroids that were isointense/hyperintense to myometrium on T2-weighted images showed a better response than hypointense fibroids (63.7±25.8% versus 48.6±31.3%, respectively; p=0.041). On contrast-enhanced images, isointense/hyperintense fibroids showed a better VR than hypointense fibroids (61.3±27.4% versus 47.6±31.6%, respectively; p=0.035). Baseline fibroid volume of50 cmLocalisation, T2 SI, contrast enhancement, and50 cm