Artificial intelligence-based, semi-automated segmentation for the extraction of ultrasound-derived radiomics features in breast cancer: a prospective multicenter study.

PURPOSE: To investigate the feasibility of an artificial intelligence (AI)-based semi-automated segmentation for the extraction of ultrasound (US)-derived radiomics features in the characterization of focal breast lesions (FBLs). MATERIAL AND METHODS: Two expert radiologists classified according to US BI-RADS criteria 352 FBLs detected in 352 patients (237 at Center A and 115 at Center B). An AI-based semi-automated segmentation was used to build a machine learning (ML) model on the basis of B-mode US of 237 images (center A) and then validated on an external cohort of B-mode US images of 115 patients (Center B). RESULTS: A total of 202 of 352 (57.4%) FBLs were benign, and 150 of 352 (42.6%) were malignant. The AI-based semi-automated segmentation achieved a success rate of 95.7% for one reviewer and 96% for the other, without significant difference (p = 0.839). A total of 15 (4.3%) and 14 (4%) of 352 semi-automated segmentations were not accepted due to posterior acoustic shadowing at B-Mode US and 13 and 10 of them corresponded to malignant lesions, respectively. In the validation cohort, the characterization made by the expert radiologist yielded values of sensitivity, specificity, PPV and NPV of 0.933, 0.9, 0.857, 0.955, respectively. The ML model obtained values of sensitivity, specificity, PPV and NPV of 0.544, 0.6, 0.416, 0.628, respectively. The combined assessment of radiologists and ML model yielded values of sensitivity, specificity, PPV and NPV of 0.756, 0.928, 0.872, 0.855, respectively. CONCLUSION: AI-based semi-automated segmentation is feasible, allowing an instantaneous and reproducible extraction of US-derived radiomics features of FBLs. The combination of radiomics and US BI-RADS classification led to a potential decrease of unnecessary biopsy but at the expense of a not negligible increase of potentially missed cancers.

MR-guided focused ultrasound-induced blood-brain barrier opening for brain metastasis: a review.

Although the therapeutic armamentarium for brain metastases (BMs) has been expanded from innovative surgical techniques and radiotherapy to include targeted therapies and immunotherapy, the prognosis of BMs remains poor. Despite the proven efficacy of numerous compounds in preclinical studies, the limited penetration of promising therapeutic agents across the blood-brain barrier (BBB) remains an unaddressed issue. Recently, low-intensity magnetic resonance-guided focused ultrasound (MRgFUS) in combination with microbubbles has been shown to overcome vascular and cellular transport barriers in the brain and tumor microenvironment, resulting in increased drug diffusion and preliminary effective results. Preclinical studies have investigated the increased penetration of many therapeutic agents including doxorubicin, trastuzumab, and ipilimumab into the CNS with promising results. Furthermore, anticancer drugs combined with MRgFUS-induced BBB opening have been demonstrated to improve animal survival and slow tumor progression. Accordingly, the first clinical trial has recently been launched and hopefully the results will provide evidence for the safety and efficacy of drug delivery enhanced by MRgFUS-induced BBB opening in BMs. This review aims to provide an overview of transcranial low-intensity MRgFUS application for BBB disruption and a comprehensive overview of the most relevant evidence in the treatment of BMs.

New microvascular ultrasound techniques: abdominal applications.

Microvascular ultrasound (MVUS) is a new ultrasound technique that allows the detection of slow-velocity flow, providing the visualization of the blood flow in small vessels without the need of intravenous contrast agent administration. This technology has been integrated in the most recent ultrasound equipment and applied for the assessment of vascularization. Compared to conventional color Doppler and power Doppler imaging, MVUS provides higher capability to detect intralesional flow. A growing number of studies explored the potential applications in hepatobiliary, genitourinary, and vascular pathologies. Different flow patterns can be observed in hepatic and renal focal lesions providing information on tumor vascularity and improving the differential diagnosis. This article aims to provide a detailed review on the current evidences and applications of MVUS in abdominal imaging.

Diagnostic performance of 2D-shear wave elastography in the diagnosis of breast cancer: a clinical appraisal of cutoff values.

PURPOSE: To assess the role of 2D-shear wave elastography (2D-SWE) in differentiating benign from malignant focal breast lesions (FBLs), providing new vendor-specific cutoff values. METHODS: 158 FBLs (size: 3.5-50 mm) detected in 151 women (age: 21-87 years) were prospectively evaluated by means 2D-SWE. For each lesion, an expert radiologist assessed US BI-RADS category and calculated the following four 2D-SWE parameters: (1) elasticity maximum (Emax); (2) mean elasticity (Emean); (3) minimum elasticity (Emin); (4) elasticity ratio (Eratio). US-guided core-biopsy was considered as standard of reference for all the FBLs classified as BI-RADS 4 or 5. For each 2D-SWE parameter, the optimal cutoff value for a diagnostic test was calculated using the Youden method. Diagnostic performance of the US BI-RADS and 2D-SWE parameters was calculated accordingly. RESULTS: 83/158 (52.5%) FBLs were benign and 75/158 (47.5%) were malignant. Statistically significant higher stiffness values were observed in malignant FBLs for all 2D-SWE parameters than in benign ones (p < 0.001). 2D-SWE cutoff values were 82.6 kPa, 66.0 kPa and 53.6 kPa, respectively, for Emax, Emean, Emin and 330.8% for Eratio. The 2D-SWE parameter showing the best diagnostic accuracy was Emax (85.44%). Considering US BI-RADS 3 (n = 60) and 4a (n = 32) FBLs, Emax and Emean showed the best diagnostic accuracy (85.87% for both), without a statistically significant decrease in sensitivity (p = 0.7003 and p = 1, respectively). CONCLUSION: Our study provides new vendor-specific cutoff values for 2D-SWE, suggesting its possible clinical use in the adjunctive assessment of category US-BI-RADS 3 and 4a breast masses.

Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients.

OBJECTIVE: The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging. MATERIAL AND METHODS: Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M). RESULTS: In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%. CONCLUSION: This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes. KEY POINTS: • Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.

Assessment of morphological CT imaging features for the prediction of risk stratification, mutations, and prognosis of gastrointestinal stromal tumors.

OBJECTIVES: To investigate the correlation between CT imaging features and risk stratification of gastrointestinal stromal tumors (GISTs), prediction of mutation status, and prognosis. METHODS: This retrospective dual-institution study included patients with pathologically proven GISTs meeting the following criteria: (i) preoperative contrast-enhanced CT performed between 2008 and 2019; (ii) no treatments before imaging; (iii) available pathological analysis. Tumor risk stratification was determined according to the National Institutes of Health (NIH) 2008 criteria. Two readers evaluated the CT features, including enhancement patterns and tumor characteristics in a blinded fashion. The differences in distribution of CT features were assessed using univariate and multivariate analyses. Survival analyses were performed by using the Cox proportional hazard model, Kaplan-Meier method, and log-rank test. RESULTS: The final population included 88 patients (59 men and 29 women, mean age 60.5 ± 11.1 years) with 45 high-risk and 43 low-to-intermediate-risk GISTs (median size 6.3 cm). At multivariate analysis, lesion size ≥ 5 cm (OR: 10.52, p = 0.009) and enlarged feeding vessels (OR: 12.08, p = 0.040) were independently associated with the high-risk GISTs. Hyperenhancement was significantly more frequent in PDGFRα-mutated/wild-type GISTs compared to GISTs with KIT mutations (59.3% vs 23.0%, p = 0.004). Ill-defined margins were associated with shorter progression-free survival (HR 9.66) at multivariate analysis, while ill-defined margins and hemorrhage remained independently associated with shorter overall survival (HR 44.41 and HR 30.22). Inter-reader agreement ranged from fair to almost perfect (k: 0.32-0.93). CONCLUSIONS: Morphologic contrast-enhanced CT features are significantly different depending on the risk status or mutations and may help to predict prognosis. KEY POINTS: • Lesions size ≥ 5 cm (OR: 10.52, p = 0.009) and enlarged feeding vessels (OR: 12.08, p = 0.040) are independent predictors of high-risk GISTs. • PDGFRα-mutated/wild-type GISTs demonstrate more frequently hyperenhancement compared to GISTs with KIT mutations (59.3% vs 23.0%, p = 0.004). • Ill-defined margins (hazard ratio 9.66) were associated with shorter progression-free survival at multivariate analysis, while ill-defined margins (hazard ratio 44.41) and intralesional hemorrhage (hazard ratio 30.22) were independently associated with shorter overall survival.

Ultrasonographic Detection of Vascularity of Focal Breast Lesions: Microvascular Imaging Versus Conventional Color and Power Doppler Imaging.

To compare microvascular flow imaging (MVFI) to conventional Color-Doppler (CDI) and Power-Doppler (PDI) imaging in the detection of vascularity of Focal Breast Lesions (FBLs). A total of 180 solid FBLs (size: 3.5-45.2 mm) detected in 180 women (age: 21-87 years) were evaluated by means of CDI, PDI, and MVFI. Two blinded reviewers categorized lesion vascularity in absent or present, and vascularity pattern as (a) internal; (b) vessels in rim; (c) combined. The presence of a "penetrating vessel" was assessed separately. Differences in vascularization patterns (chi2 test) and intra- and inter-observer agreement (Fleiss method) were calculated. ROC analysis was performed to assess performance of each technique in differentiating benign from malignant lesions. About 103/180 (57.2%) FBLs were benign and 77/180 (42.8%) were malignant. A statistically significant (p < .001) increase in blood flow detection was observed for both readers with MVFI in comparison to either CDI or PDI. Benign FBLs showed mainly absence of vascularity (p = .02 and p = .01 for each reader, respectively), rim pattern (p < .001 for both readers) or combined pattern (p = .01 and p = .04). Malignant lesions showed a statistically significant higher prevalence of internal flow pattern (p < .001 for both readers). The prevalence of penetrating vessels was significantly higher with MVFI in comparison to either CDI or PDI (p < .001 for both readers) and in the malignant FBLs (p < .001). ROC analysis showed MVFI (AUC = 0.70, 95%CI = [0.64-0.77]) more accurate than CDI (AUC = 0.67, 95%CI = [0.60-0.74]) and PDI (AUC = 0.67, 95%CI = [0.60-0.74]) though not significantly (p = .5436). Sensitivity/Specificity values for MVFI, PDI, and CDI were 76.6%/64.1%, 59.7%/73.8% and 58.4%/74.8%, respectively. Inter-reader agreement with MVFI was always very good (k-score 0.85-0.96), whereas with CDI and PDI evaluation ranged from good to very good. No differences in intra-observer agreement were noted. MVFI showed a statistically significant increase in the detection of the vascularization of FBLs in comparison to Color and Power-Doppler.

Intraoperative imaging findings in transcranial MR imaging-guided focused ultrasound treatment at 1.5T may accurately detect typical lesional findings correlated with sonication parameters.

OBJECTIVES: To assess the intraoperative neuroimaging findings in patients treated with transcranial MR-guided focused ultrasound (tcMRgFUS) thalamotomy using 1.5T equipment in comparison with the 48-h follow-up. METHODS: Fifty prospectively enrolled patients undergoing unilateral tcMRgFUS thalamotomy for either medication-refractory essential tremor (n = 39) or Parkinson tremor (n = 11) were included. Two radiologists evaluated the presence and size of concentric lesional zones (zone I, zone II, and zone III) on 2D T2-weighted sequences acquired intraoperatively after the last high-energy sonication and at 48 h. Sonication parameters including number of sonications, delivered energy, and treatment temperatures were also recorded. Differences in lesion pattern and size were assessed using the McNemar test and paired t test, respectively. RESULTS: Zones I, II, and III were visualized in 34 (68%), 50 (100%), and 44 (88%) patients, and 31 (62%), 50 (100%), and 45 (90%) patients after the last high-energy sonication for R1 and R2, respectively. All three concentric zones were visualized intraoperatively in 56-58% of cases. Zone I was significantly more commonly visualized at 48 h (p < 0.001). Diameter of zones I and II and the thickness of zone III significantly increased at 48 h (p < 0.001). Diameters of zones I and II measured intraoperatively demonstrated significant correlation with thermal map temperatures (p ≤ 0.001). Maximum temperature significantly correlated with zone III thickness at 48 h. A threshold of 60.5° had a sensitivity of 56.5-66.7% and a specificity of 70.5-75.5% for thickness > 6 mm at 48 h. CONCLUSIONS: Intraoperative imaging may accurately detect typical lesional findings, before completing the treatment. These imaging characteristics significantly correlate with sonication parameters and 48-h follow-up. KEY POINTS: • Intraoperative T2-weighted images allow the visualization of the zone I (coagulation necrosis) in most of the treated patients, while zone II (cytotoxic edema) is always detected. • Lesion size depicted with intraoperative transcranial MRgFUS imaging correlates well with procedure parameters. • Intraoperative transcranial MRgFUS imaging may have a significant added value for treating physicians.

TAVI imaging: over the echocardiography.

Aortic valve stenosis (AS) is a common valvular heart disease. Recently, transcatheter aortic valve implantation (TAVI) has changed the treatment of severe AS in elderly patients with contraindications to traditional surgical replacement. Echocardiography is conventionally used as the first imaging modality to assess the presence and severity of AS and to provide anatomical and functional information. Nowadays, imaging techniques play a crucial role in the planning of TAVI to define suitable candidates. Computed tomography (CT) is essential to display the anatomy of the aortic valve complex (including aortic annulus, Valsalva sinuses, coronary arteries ostia, sinotubular junction), thoracoabdominal aorta, and vascular access. Cardiac CT may also provide the evaluation of coronary arteries in alternative to conventional coronary angiography. Magnetic resonance imaging may be alternative or supplementary in selected cases, providing detailed information of cardiac function and myocardial wall characteristics. More recently, advanced computer modeling image-based techniques can be used to support the evaluation of the feasibility and safety of TAVI procedures.

Preoperative loco-regional staging of invasive lobular carcinoma with contrast-enhanced digital mammography (CEDM).

The aim of our study was to assess the performance of contrast-enhanced digital mammography (CEDM) in the preoperative loco-regional staging of invasive lobular carcinoma (ILC) patients, about the valuation of the extension of disease and in measurement of lesions. Then, we selected retrospectively, among the 1500 patients underwent to CEDM at the Breast Diagnostics Department of the Careggi University Hospital of Florence and the National Cancer Institute of Milan from September 2016 to November 2018, 31 women (mean age 57.1 aa; range 41-78 aa) with a definitive histological diagnosis of ILC. CEDM has proved to be a promising imaging technique, being characterized by a sensitivity of 100% in the detection of the index lesion, and of 84.2% in identifying any adjunctive lesions: It was the presence of a non-mass enhancement (NME) to lower the sensitivity of the technique (25% vs. 100% for mass-like enhancements or a mass closely associated with a NME). Specificity in the characterization of additional lesions was 66.7%, and the diagnosis of the extension of disease was correct in 77.4% of cases: NME also led to a decrease in diagnostic accuracy in the evaluation of disease extension up to 40% versus 85% for masses and 80% for masses associated with NME (M/NME). Moreover, in 12/31 (38.7%), CEDM allowed to correctly identify lesions not shown by mammography + ultrasonography + tomosynthesis: In the half of these (6/12), there was a multicentricity, thus allowing an adequate surgical planning change. CEDM was also very accurate in analyzing the maximum diameter of the masses, while it was much less reliable in the case of the M/NME and pure NME. In conclusion, CEDM is a new promising imaging technique in the loco-regional preoperative staging and in the evaluation of disease extension for ILC, especially in case of mass enhancement lesions.

Urological dysfunctions in patients with Parkinson's disease: clues from clinical and non-invasive urological assessment.

BACKGROUND: Autonomic nervous system dysfunction, common in patients with Parkinson's disease (PD), causes significant morbidity and it is correlated with poor quality of life. To assess frequency of urinary symptoms in patients with PD, without conditions known to interfere with urinary function. METHODS: Non-demented PD patients were consecutively enrolled from the outpatients clinic of our department. Scales investigating motor and non-motor symptoms were carried out. Evaluation of urinary dysfunctions was carried out using the AUTonomic Scale for Outcomes in Parkinson's disease (SCOPA-AUT) questionnaire. Patients underwent noninvasive urological studies (nUS), including uroflowmetry and ultrasound of the urinary tract. RESULTS: Forty-eight (20 women, 42%) out of 187 PD patients met the inclusion criteria and were enrolled in the study. Mean SCOPA-AUT score was 14.1 ± 6.9 (urinary symptoms subscore 5.2 ± 3.8). Among those evaluated by the SCOPA-AUT scale, the urinary symptoms were among the most common complaints (93.8%). At nUS mean maximum flow rate (Qmax) was 17.9 ± 9.1 ml/s, and mean postvoid residual (PVR) urine volume was 24.4 ± 44.1 ml. Ultrasound investigation documented prostate hypertrophy in 12 male patients (42.8%). Urinary items of the SCOPA-AUT (SCOPA-U subscore) correlated with measures of disease severity only in female patients. CONCLUSION: Urinary symptoms and abnormal findings in nUS are common in PD. Though nigrostriatal degeneration might be responsible for urinary symptoms also in the early-intermediate stage of the disease, when urinary dysfunction occurs other medical conditions need to be excluded.

Preliminary experience with a transcranial magnetic resonance-guided focused ultrasound surgery system integrated with a 1.5-T MRI unit in a series of patients with essential tremor and Parkinson's disease.

OBJECTIVE Transcranial magnetic resonance-guided focused ultrasound surgery (tcMRgFUS) is one of the emerging noninvasive technologies for the treatment of neurological disorders such as essential tremor (ET), idiopathic asymmetrical tremor-dominant Parkinson's disease (PD), and neuropathic pain. In this clinical series the authors present the preliminary results achieved with the world's first tcMRgFUS system integrated with a 1.5-T MRI unit. METHODS The authors describe the results of tcMRgFUS in a sample of patients with ET and with PD who underwent the procedure during the period from January 2015 to September 2017. A monolateral ventralis intermedius nucleus (VIM) thalamic ablation was performed in both ET and PD patients. In all the tcMRgFUS treatments, a 1.5-T MRI scanner was used for both planning and monitoring the procedure. RESULTS During the study period, a total of 26 patients underwent tcMRgFUS thalamic ablation for different movement disorders. Among these patients, 18 were diagnosed with ET and 4 were affected by PD. All patients with PD were treated using tcMRgFUS thalamic ablation and all completed the procedure. Among the 18 patients with ET, 13 successfully underwent tcMRgFUS, 4 aborted the procedure during ultrasound delivery, and 1 did not undergo the tcMRgFUS procedure after stereotactic frame placement. Two patients with ET were not included in the results because of the short follow-up duration at the time of this study. A monolateral VIM thalamic ablation in both ET and PD patients was performed. All the enrolled patients were evaluated before the treatment and 2 days after, with a clinical control of the treatment effectiveness using the graphic items of the Fahn-Tolosa-Marin tremor rating scale. A global reevaluation was performed 3 months (17/22 patients) and 6 months (11/22 patients) after the treatment; the reevaluation consisted of clinical questionnaires, neurological tests, and video recordings of the tests. All the ET and PD treated patients who completed the procedure showed an immediate amelioration of tremor severity, with no intra- or posttreatment severe permanent side effects. CONCLUSIONS Although this study reports on a small number of patients with a short follow-up duration, the tcMRgFUS procedure using a 1.5-T MRI unit resulted in a safe and effective treatment option for motor symptoms in patients with ET and PD. To the best of the authors' knowledge, this is the first clinical series in which thalamotomy was performed using tcMRgFUS integrated with a 1.5-T magnet.

Role of Cardiac Computed Tomography in the Evaluation of Coronary Artery Stenosis in Patients With Ascending Aorta Aneurysm Detected at Transthoracic Echocardiography.

OBJECTIVE: The aim of our study was to evaluate the diagnostic performance of cardiac computed tomography (CCT) in the evaluation of coronary artery stenosis in patients with ascending aorta aneurysm detected at transthoracic echocardiography. METHODS: We conducted a retrospective analysis of patients with an aneurysm 45 mm or greater at transthoracic echocardiography who underwent CCT from 2012 to 2014 in our hospital. We calculated the sensitivity, specificity, and positive and negative predictive values of CCT for the assessment of coronary artery stenosis (<50% or ≥50% stenosis) in patients who underwent conventional coronary angiography. RESULTS: We included 104 patients (73 men, aged 64 [SD, 10.8] years) in our study. Obstructive coronary artery disease was found in 22.1% of patients. Sensitivity, specificity, and positive and negative predictive values of CCT for detecting significant stenoses were 100%, 98%, and 82% and 100% on a segment-by-segment analysis and 100%, 83%, and 65% and 100% on a per-patient analysis, respectively. CONCLUSIONS: Cardiac computed tomography provides a comprehensive evaluation of ascending aorta aneurysms and coronary artery tree.

Recurrence of hepatocellular carcinoma after liver transplantation: an update.

Liver transplantation is the only curative alternative for selected patients with hepatocellular carcinoma (HCC) who are not eligible for resection and/or with decompensated cirrhosis. According to Milan criteria the 5-year survival rate is 70-85%, with a recurrence-free survival of 75%. However, HCC recurrence rate after liver transplantation remains a significant problem in the clinical practice. The prognosis in patients with HCC recurrence is poor. The treatment of choice for HCC recurrence is surgery, but it seems that a systemic treatment based on combination of an mTOR inhibitor with sorafenib can be used. Data on safety and efficacy are limited, clinical monitoring is necessary. The aim of this review is to underline the main concerns, pitfalls and warnings for these patients.

3D versus 2D contrast-enhanced sonography in the evaluation of therapeutic response of hepatocellular carcinoma after locoregional therapies: preliminary findings.

OBJECTIVE: To investigate diagnostic performance of 3D contrast-enhanced ultrasound (CEUS) compared with 2D CEUS in the assessment of therapeutic response of hepatocellular carcinoma (HCC) treated with locoregional therapies (LRT). MATERIALS AND METHODS: Twenty-three consecutive patients (13 men and 10 women; mean age 65.5 years) with 23 HCCs (size range 1.2-7.2 cm; mean size 2.9 ± 1.4 cm) treated by means of radiofrequency ablation (RFA n = 9), transarterial chemoembolization (TACE n = 8), combined RFA and TACE (n = 3), percutaneous alcoholization (n = 2), and wedge resection (n = 1) underwent 2D and 3D CEUS 1 month (30 ± 2 days) after treatment. Magnetic resonance (n = 17) and computed tomography (n = 6) acted as standard of reference (SOR). Two radiologists assessed the absence (complete response CR) or presence (residual tumor RT) of any nodular arterially enhancing area within or along the margin of the treated HCC. RESULTS: Both 2D and 3D CEUS observed CR in 10/23 (43.5 %) HCCs and RT in 11/23 (47.8 %) HCCs. In 1/23 (4.3 %) HCC, RT was documented by SOR and 2D CEUS, but it was not appreciable at 3D CEUS. In 1/23 (4.3 %) HCC, the presence of peripheral residual tumor was suspected by both 2D and 3D CEUS, but it was not confirmed by SOR. No statistically significant difference between 2D and 3D CEUS in depicting either CR or RT was found (p > 0.05). Sensitivity, specificity, positive and negative predictive values, and accuracy of 3D CEUS were 91.7 % [95 % confidence interval (CI) 0.760-1.073], 90.9 % (95 % CI 0.739-1.079), 91.7, 90.9, and 91.3 %, respectively. CONCLUSION: 2D and 3D CEUS provided similar diagnostic performance in the assessment of therapeutic response of HCC treated with LRT.

Imaging findings of hepatic focal nodular hyperplasia in men and women: are they really different?

PURPOSE: This study was undertaken to compare the imaging findings of focal nodular hyperplasia (FNH) in men and women, as seen on multidetector computed tomography (MDCT), magnetic resonance imaging (MRI) and contrast-enhanced ultrasound (CEUS). MATERIALS AND METHODS: Two radiologists reviewed 195 imaging studies (17 MDCT, 81 MRI and 97 CEUS examinations) pertaining to 111 FNHs (mean size 3 cm) in 91 patients (mean age 39 years). For each lesion, the readers assessed size, location, echogenicity, attenuation, or signal intensity in comparison with adjacent liver parenchyma on both unenhanced and postcontrast images. RESULTS: Eighty-nine FNHs (mean size 3.1 cm) were observed in 73 women (mean age 37.9 years) and 22 FNHs (mean size 2.7 cm) in 18 men (mean age 41.2 years). No statistically significant differences were found between men and women in terms of age, FNH lesions per patient (1.22 and 1.21, respectively), size, baseline and enhancement pattern on MRI, CEUS and MDCT (p < 0.05). A central scar in FNHs was depicted in 4/18 (22.2%) men and 16/63 (25.4%) women on MRI (p < 0.05), and in 1/2 (50%) men and 7/15 (46.7%) women on MDCT (p < 0.05), whereas a spoke-wheel pattern, central scar, and/or feeding vessel were seen in 5/17 (29.4%) men and 22/80 (27.5%) women on CEUS (p < 0.05). CONCLUSIONS: Our results did not show any differences in imaging features, age of occurrence and size of FNH between men and women.

MRI Insights in Breast Imaging.

In the world, breast cancer is the most commonly diagnosed cancer among women. Currently, MRI is the most sensitive breast imaging method for detecting breast cancer, although false positive rates are still an issue. To date, the accuracy of breast MRI is widely recognized across various clinical scenarios, in particular, staging of known cancer, screening for breast cancer in high-risk women, and evaluation of response to neoadjuvant chemotherapy. Since technical development and further clinical indications have expanded over recent years, dedicated breast radiologists need to constantly update their knowledge and expertise to remain confident and maintain high levels of diagnostic performance in breast MRI. This review aims to detail current and future applications of breast MRI, from technological requirements and advances to new multiparametric and abbreviated protocols, and ultrafast imaging, as well as current and future indications.

A mutation-based radiomics signature predicts response to imatinib in Gastrointestinal Stromal Tumors (GIST).

Objectives: To develop a mutation-based radiomics signature to predict response to imatinib in Gastrointestinal Stromal Tumors (GISTs). Methods: Eighty-two patients with GIST were enrolled in this retrospective study, including 52 patients from one center that were used to develop the model, and 30 patients from a second center to validate it. Reference standard was the mutational status of tyrosine-protein kinase (KIT) and platelet-derived growth factor α (PDGFRA). Patients were dichotomized in imatinib sensitive (group 0 - mutation in KIT or PDGFRA, different from exon 18-D842V), and imatinib non-responsive (group 1 - PDGFRA exon 18-D842V mutation or absence of mutation in KIT/PDGFRA). Initially, 107 texture features were extracted from the tumor masks of baseline computed tomography scans. Different machine learning methods were then implemented to select the best combination of features for the development of the radiomics signature. Results: The best performance was obtained with the 5 features selected by the ANOVA model and the Bayes classifier, using a threshold of 0.36. With this setting the radiomics signature had an accuracy and precision for sensitive patients of 82 % (95 % CI:60-95) and 90 % (95 % CI:73-97), respectively. Conversely, a precision of 80 % (95 % CI:34-97) was obtained in non-responsive patients using a threshold of 0.9. Indeed, with the latter setting 4 patients out of 5 were correctly predicted as non-responders. Conclusions: The results are a first step towards using radiomics to improve the management of patients with GIST, especially when tumor tissue is unavailable for molecular analysis or when molecular profiling is inconclusive.

Splenic hemangiomas: contrast-enhanced sonographic findings.

OBJECTIVES: The purpose of this study was to illustrate the baseline appearance and enhancement patterns of splenic hemangiomas on contrast-enhanced sonography. METHODS: Two experienced radiologists retrospectively reviewed by consensus baseline and contrast-enhanced sonographic examinations of 27 patients (14 women and 13 men; mean age, 58.7 years) with 27 splenic hemangiomas (mean size, 2 cm) confirmed by splenectomy, biopsy, computed tomography, and magnetic resonance imaging and follow-up. RESULTS: On baseline sonography, 77.8% of the lesions showed a homogeneous echo texture that was mainly hyperechoic. Color Doppler imaging did not show any signal in 81.5% of the cases. After contrast agent injection, 59.2% of the splenic hemangiomas showed different degrees of contrast enhancement in the arterial phase followed by isoenhancement in the late parenchymal phase. Among these, 2 hemangiomas showed peripheral globular enhancement in the arterial phase, followed by progressive centripetal fill-in. In 29.6% of the cases, some degree of contrast enhancement was appreciable, but the hemangiomas remained substantially hypoechoic throughout the contrast-enhanced sonographic examinations, whereas in 11.1%, the combination of contrast enhancement in the arterial phase followed by wash-out in the late parenchymal phase was evident. CONCLUSIONS: Isoechogenicity to spleen parenchyma in all phases is the most frequent typical enhancement pattern of splenic hemangiomas observed on contrast-enhanced sonography. Nevertheless, these lesions may show atypical contrast enhancement patterns; therefore, further assessment with cross-sectional techniques is needed.