Search

The purpose of this study was to assess whether Immune CompleX Predictive Index (iXip) improves diagnostic accuracy of multiparametric prostate MRI (mpMRI) for clinically significant prostate cancer. This study included 72 patients (mean age: 68±8 years) with suspicion of prostate cancer and available iXip score. mpMRI images were evaluated by two radiologists according to the PI-RADS v2.1. Reference standard was based on fusion biopsy and standard transperineal 12-point biopsy. Diagnostic accuracy of iXip, mpMRI and their combination were calculated. Optimal cutoff of iXip with sensitivity and specificity was identified using the Youden index. Patients with clinically significant prostate cancers had significantly higher iXip values compared to patients without clinically significant prostate cancers (median 0.411 vs 0.273; p=0.026). The AUROC for iXip was 0.795 (95% CI 0.579-1.000, p=0.026). Sensitivity and specificity were 75% and 100% respectively for mpMRI alone, and 100% and 80% respectively for mpMRI combined with iXip > 0.375. The combination of mpMRI with a cutoff value of iXip > 0.375 has a very high sensitivity for the diagnosis of prostate cancer and a moderately high specificity.

Purpose The aim of our study was to evaluate the prevalence of early complications after Transcatheter Aortic Valve Implantation (TAVI) and their correlation with the Calcium Score (CS) of the aortic valve, aorta and ilio-femoral arteries derived from pre-procedural computed tomography (CT). Materials and methods We retrospectively reviewed 226 patients (100 males, mean age 79.4 ± 6.7 years) undergoing 64-slice CT for pre-TAVI evaluation from January 2018 to April 2021. The population was divided into CS quartiles. Results Overall, 173 patients underwent TAVI procedure, of whom 61% presented paravalvular leak after the procedure, 28% presented bleeding or vascular complications, 25% presented atrioventricular block, and 8% developed acute kidney injury. The prevalence of paravalvular leak and vascular complications was higher in the upper CS quartiles for aortic valve and ilio-femoral arteries. Conclusions Aortic valve and vascular CS could help to predict post-TAVI early complications.

The volume estimation of retroperitoneal sarcoma (RPS) is often difficult due to its huge dimensions and irregular shape; thus, it often requires manual segmentation, which is time-consuming and operator-dependent. This study aimed to evaluate two fully automated deep learning networks (ENet and ERFNet) for RPS segmentation. This retrospective study included 20 patients with RPS who received an abdominal computed tomography (CT) examination. Forty-nine CT examinations, with a total of 72 lesions, were included. Manual segmentation was performed by two radiologists in consensus, and automatic segmentation was performed using ENet and ERFNet. Significant differences between manual and automatic segmentation were tested using the analysis of variance (ANOVA). A set of performance indicators for the shape comparison (namely sensitivity), positive predictive value (PPV), dice similarity coefficient (DSC), volume overlap error (VOE), and volumetric differences (VD) were calculated. There were no significant differences found between the RPS volumes obtained using manual segmentation and ENet (p-value = 0.935), manual segmentation and ERFNet (p-value = 0.544), or ENet and ERFNet (p-value = 0.119). The sensitivity, PPV, DSC, VOE, and VD for ENet and ERFNet were 91.54% and 72.21%, 89.85% and 87.00%, 90.52% and 74.85%, 16.87% and 36.85%, and 2.11% and −14.80%, respectively. By using a dedicated GPU, ENet took around 15 s for segmentation versus 13 s for ERFNet. In the case of CPU, ENet took around 2 min versus 1 min for ERFNet. The manual approach required approximately one hour per segmentation. In conclusion, fully automatic deep learning networks are reliable methods for RPS volume assessment. ENet performs better than ERFNet for automatic segmentation, though it requires more time.

Although preoperative biopsy of rectal cancer (RC) is an essential step for confirmation of diagnosis, it currently fails to provide prognostic information to the clinician beyond a rough estimation of tumour grade. In this study we used a risk classification to stratified patient in low-risk and high-risk patients in relation to the disease free survival and the overall survival using histopathological post-operative features. The purpose of this study was to evaluate if low-risk and high-risk RC can be distinguished using a CT-based radiomics model. We retrospectively reviewed the preoperative abdominal contrast-enhanced CT of 40 patients with RC. CT portal-venous phase was used for manual RC segmentation by two radiologists. Radiomics parameters were extracted by using PyRadiomics (3.0) software, which automatically obtained a total of 120 radiomics features. An operator-independent statistical hybrid method was adopted for the selection and reduction of features, while discriminant analysis was used to construct the predictive model. Postoperative histopathological report was used as reference standard. Receiver operating characteristics (ROC) and areas under the ROC curve (AUROC) were calculated to evaluate the diagnostic performance of the most dis-criminating selected parameters. Sensitivity, specificity, and accuracy were calculated. In our study cohort, the original_shape_Maximum3DDiameter and origi-nal_shape_MajorAxisLength demonstrated a good performance in the differentiation between preoperative degree of RC, with an AUROC of 0.680%, sensitivity of 74.02%, specificity of 73.45%, positive predictive value of 81.47%, and accuracy of 73.71%. In conclusion, this preliminary analysis showed statistically significant differences in radiomics features between low-risk and high-risk RC.

The purpose of this preliminary study was to evaluate the differences in Magnetic Resonance Imaging (MRI)-based radiomics analysis between cerebellopontine angle neurinomas and schwannomas originating from other locations in the neck spaces. Twenty-six patients with available MRI exams and head and neck schwannomas were included. Lesions were manually segmented on the precontrast and postcontrast T1 sequences. The radiomics features were extracted by using PyRadiomics software, and a total of 120 radiomics features were obtained from each segmented tumor volume. An operator-independent hybrid descriptive‐inferential method was adopted for the selection and reduction of the features, while discriminant analysis was used to construct the predictive model. On precontrast T1 images, the original_glcm_InverseVariance demonstrated a good performance with an area under the receiver operating characteristic (AUROC) of 0.756 (95% C.I. 0.532–0.979; p = 0.026). On postcontrast T1 images, the original_glcm_Idmn provided a good diagnostic performance with an AUROC of 0.779 (95% C.I. 0.572–0.987; p = 0.014). In conclusion, this preliminary analysis showed statistically significant differences in radiomics features between cerebellopontine angle neurinomas and schwannomas of other locations in the neck spaces.

SARS-CoV-2 epidemics has resulted in an unprecedented global health crisis causing a high number of deaths with pneumonia being the most common manifestation. Chest CT is the best imaging modality to identify pulmonary involvement, but unfortunately there are no pathognomonic features for COVID-19 pneumonia, since many other infectious and non-infectious diseases may cause similar alterations. The adoption of artificial intelligence in biomedical imaging has the potential to revolutionize the identification, management, and the patient’s outcome. If adequately validated, it could be used as a support with predictive and prognostic purposes in symptomatic patients but also as a screening test in asymptomatic patients in COVID-19 epidemics. Some studies have already shown the potential adoption of artificial intelligence for detection of COVID-19 infection, or even to differentiate from community-acquired pneumonia, but at present artificial intelligence cannot routinely applied for COVID-19 due to several limitations. This book chapter will first revise the basics of radiomics with a short practical and easy guide for radiologists; then, the main radiological findings of COVID-19 pneumonia will be presented with the most relevant information that are assessed to evaluate extent of the disease; finally, the main current literature on potential clinical application of radiomics and artificial intelligence for COVID-19 will be presented together with limitations and perspectives.

Aim: This systematic review aims to present the available evidence on the use of radiomic features (RFs) extracted from PET imaging in patients with prostate cancer (PCa). Materials and methods: A comprehensive literature search of studies on the utility of PET-derived RFs in patients with PCa was performed in the PubMed/MEDLINE database through February 24th, 2021 using the following search string: [“positron-emission tomography” (MeSh terms) OR “positron emission tomography computed tomography” (MeSh terms) OR “positron-emission tomography” (all fields) OR “positron emission tomography computed tomography” (all fields) OR “PET” (all fields)] AND [“radiomics” (all fields) OR “radiomic” (all fields) OR “radiogenomics” (all fields) OR “radiogenomic”(all fields) OR “machine learning”(all fields) OR “machine learning”(MeSh terms) OR “artificial intelligence”(MeSh terms) OR “artificial intelligence”(all fields)] AND [“prostatic neoplasms” (MeSh terms) OR “prostate cancer”(all fields) OR “prostatic carcinoma” (all fields) OR “prostate carcinoma” (all fields) OR “prostatic tumor” (all fields) OR “prostatic tumour” (all fields)]. The Google scholar database was interrogated to find additional studies. Results: Seven studies were ultimately included in the systematic review and summarized in two relevant clinical sections: (1) primary staging and (2) restaging. In primary staging, RFs, extracted from 68Ga-prostate-specific membrane antigen (PSMA) PET may characterize intraprostatic radiotracer hotspots in patients with high- and intermediate-risk, discriminate between Gleason Score (GS) 7 and ≥ 8 and between pN1 and pN0 disease, and suggest presence of intraprostatic lesions missed at visual PET examination. Machine learning (ML) may help selecting RFs able to predict risk classification (low vs. high), lymph node involvement, presence of nodal or distant metastasis, GS and extracapsular extension. At restaging, PET_Kurtosis may correlate with OS in patients with advanced PCa scheduled for 177Lu-PSMA treatment, whereas ML may assist discrimination of malignant lesions from physiologic/unspecific tracer accumulation, and predict disease progression. Conclusion: To date, although PET literature appears still too narrow to draw definitive conclusions, PET-derived RFs appear promising in PCa. ML seems an important tool that may contribute to the widespread use of radiomics and subsequent implementation in the clinical setting.

Purpose: Aim of this study was to evaluate a fully automated deep learning network named Efficient Neural Network (ENet) for segmentation of prostate gland with median lobe enlargement compared to manual segmentation. Materials and Methods: One-hundred-three patients with median lobe enlargement on prostate MRI were retrospectively included. Ellipsoid formula, manual segmentation and automatic segmentation were used for prostate volume estimation using T2 weighted MRI images. ENet was used for automatic segmentation; it is a deep learning network developed for fast inference and high accuracy in augmented reality and automotive scenarios. Student t-test was performed to compare prostate volumes obtained with ellipsoid formula, manual segmentation, and automated segmentation. To provide an evaluation of the similarity or difference to manual segmentation, sensitivity, positive predictive value (PPV), dice similarity coefficient (DSC), volume overlap error (VOE), and volumetric difference (VD) were calculated. Results: Differences between prostate volume obtained from ellipsoid formula versus manual segmentation and versus automatic segmentation were statistically significant (P < 0.049318 and P < 0.034305, respectively), while no statistical difference was found between volume obtained from manual versus automatic segmentation (P = 0.438045). The performance of ENet versus manual segmentations was good providing a sensitivity of 93.51%, a PPV of 87.93%, a DSC of 90.38%, a VOE of 17.32% and a VD of 6.85%. Conclusion: The presence of median lobe enlargement may lead to MRI volume overestimation when using the ellipsoid formula so that a segmentation method is recommended. ENet volume estimation showed great accuracy in evaluation of prostate volume similar to that of manual segmentation.

Ingestion of caustic substances, whether accidental or for the purpose of suicide, can cause severe lesions of the lips, oral cavity, pharynx, upper gastrointestinal system, and upper airways. In particular, caustic agents could be responsible for severe esophageal injuries resulting in short- and long-term complications. Because of these important clinical implications, timely diagnosis and appropriate management are crucial. In the evaluation of esophageal injuries, thoraco-abdominal computed tomography (CT) is preferable to endoscopy as it avoids the risk of esophageal perforation and allows the evaluation of esophageal injuries as well as of the surrounding tissue. In this review, we report CT findings of esophageal injuries and possible related thoracic complications caused by caustic ingestion.

Congenital cystic lesions of the bile ducts represent a spectrum of liver and biliary system lesions, resulting from abnormal embryologic development of the ductal plate. These disorders include Caroli disease, choledochal cysts, autosomal dominant polycystic liver disease, congenital hepatic fibrosis, and biliary hamartomas. Each disorder carries a peculiar clinical presentation, prognosis, and risk of complications. Knowledge of radiological findings of fibropolycystic liver diseases is crucial for their appropriate detection and for differential diagnosis with other similar hepatic cystic lesions, in order to avoid relevant misdiagnosis. The aim of this review is to provide an illustrative summary of the most relevant imaging findings of these conditions as encountered on ultrasound, computed tomography, and magnetic resonance imaging, and provide pearls for imaging-based differential diagnosis. (c) 2019 Elsevier Inc. All rights reserved.

Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.

Acute pancreatitis (AP) represents a pancreas inflammation of sudden onset that can present different degrees of severity. AP is a frequent cause of acute abdomen and its complications are still a cause of death. Biliary calculosis and alcohol abuse are the most frequent cause of AP. Computed tomography (CT) and magnetic resonance imaging (MRI) are not necessary for the diagnosis of AP but they are fundamental tools for the identification of the cause, degree severity and AP complications. AP severity assessment is in fact one of the most important issue in disease management. Contrast-enhanced CT is preferred in the emergency setting and is considered the gold standard in patients with AP. MRI is comparable to CT for the diagnosis of AP but requires much more time so it is not usually chosen in the emergency scenario. Complications of AP can be distinguished in localized and generalized. Among the localized complications, we can identify: acute peripancreatic fluid collections (APFC), pseudocysts, acute necrotic collections (ANC), walled off pancreatic necrosis (WOPN), venous thrombosis, pseudoaneurysms and haemorrhage. Multiple organ failure syndrome (MOFS) and sepsis are possible generalized complications of AP. In this review, we focus on CT and MRI findings in local complications of AP and when and how to perform CT and MRI. We paid also attention to recent developments in diagnostic classification of AP complications.