Search

Introduction: The recognition and therapy of patients with stroke is becoming progressively intricate as additional treatment choices become accessible and new associations between disease characteristics and treatment response are incessantly uncovered. Therefore, clinicians must regularly learn new skill, stay up to date with the literature and integrate advances into daily practice. The application of artificial intelligence (AI) to assist clinical decision making could diminish inter-rater variation in routine clinical practice and accelerate the mining of vital data that could expand recognition of patients with stroke, forecast of treatment responses and patient outcomes.Areas covered: In this review, the authors provide an up-to-date review of AI in stroke, analyzing the latest papers on this subject. These have been divided in two main groups: stroke diagnosis and outcome prediction.Expert opinion: The highest value of AI is its capability to merge, select and condense a large amount of clinical and imaging features of a single patient and to associate these with fitted models that have gone through robust assessment and optimization with large cohorts of data to support clinical decision making.

Purpose: To explore the association between carotid artery length and tortuosity, and the occurrence of stroke. Material and Methods: In this retrospective study, IRB approved, 411 consecutive patients (males: 245; median age: 56 ± 12 years, age range: 21-93 years) with anterior circulation ischemic stroke were included. Only patients that underwent CTA within 7 days were considered and stroke caused by cardiac embolism and thoracic aorta embolism were excluded. For each patient, both carotid arteries were considered, and the ICA, CCA-ICA length and tortuosity were calculated. Inter-observer analysis was quantified with the Bland-Altman test. Mann-Whitney test and logistic regression analysis were also calculated to test the association between length and tortuosity with the occurrence of stroke. Results: In the final analysis, 166 patients (males: 72; median age: 54 ± 12 years, age range: 24-89 years) with anterior circulation ischemic stroke that were admitted to our hospital between February 2008 and December 2013 were included. The results showed a good concordance for the length of the vessels with a mean variation of 0.7% and 0.5% for CCA-ICA and ICA length respectively an for the tortuosity with a mean variation of 0.2% and -0.4% for CCA-ICA and ICA respectively. The analysis shows a statistically significant association between the tortuosity index of the ICA and CCA-ICA sides with stroke ( P value = 0.0001 in both cases) and these findings were confirmed also with the logistic regression analysis. Conclusion: Results of this study suggest that tortuosity index is associated with the presence of stroke whereas the length of the carotid arteries does not play a significant role.

Four-dimensional (4D) flow sequences are an innovative type of MR sequences based upon phase contrast (PC) sequences which are a type of application of Angio-MRI together with the Time of Flight (TOF) sequences and Contrast-Enhanced Magnetic Resonance Acquisition (CE-MRA). They share the basic principles of PC, but unlike PC sequences, 4D flow has velocity encoding along all three flow directions and three-dimensional (3D) anatomic coverage. They guarantee the analysis of flow with multiplanarity on a post-processing level, which is a unique feature among MR sequences. Furthermore, this technique provides a completely new level to the in vivo flow analysis as it allows measurements in never studied districts such as intracranial applications or some parts of the heart never studied with echo-color-doppler, which is its sonographic equivalent. Furthermore, this technique provides a completely new level to the in vivo flow analysis as it allows accurate measurement of the flows in different districts (e.g., intracranial, cardiac) that are usually studied with echo-color-doppler, which is its sonographic equivalent. Of note, the technique has proved to be affected by less inter and intra-observer variability in several application. 4D-flow basic principles, advantages, limitations, common pitfalls and artefacts are described. This review will outline the basis of the formation of PC image, the construction of a 4D-flow and the huge impact the technique is having on the cardiovascular non-invasive examination. It will be then studied how this technique has had a huge impact on cardiovascular examinations especially on a central heart level.

Purpose: The lack of standardization in quantitative radiomic measures of tumors seen on computed tomography (CT) scans is generally recognized as an unresolved issue. To develop reliable clinical applications, radiomics must be robust across different CT scan modes, protocols, software, and systems. We demonstrate how custom-designed phantoms, imprinted with human-derived patterns, can provide a straightforward approach to validating longitudinally stable radiomic signature values in a clinical setting. Approach: Described herein is a prototype process to design an anatomically informed 3D-printed radiomic phantom. We used a multimaterial, ultra-high-resolution 3D printer with voxel printing capabilities. Multiple tissue regions of interest (ROIs), from four pancreas tumors, one lung tumor, and a liver background, were extracted from digital imaging and communication in medicine (DICOM) CT exam files and were merged together to develop a multipurpose, circular radiomic phantom (18 cm diameter and 4 cm width). The phantom was scanned 30 times using standard clinical CT protocols to test repeatability. Features that have been found to be prognostic for various diseases were then investigated for their repeatability and reproducibility across different CT scan modes. Results: The structural similarity index between the segment used from the patients’ DICOM image and the phantom CT scan was 0.71. The coefficient variation for all assessed radiomic features was ± 15 % . Conclusions: Previously discovered prognostic and popular radiomic features are variable in practice and need to be interpreted with caution or excluded from clinical implementation. Voxel-based 3D printing can reproduce tissue morphology seen on CT exams. We believe that this is a flexible, yet practical, way to design custom phantoms to validate and compare radiomic metrics longitudinally, over time, and across systems.

To develop and optimize a rapid magnetic resonance imaging (MRI) screening protocol for pancreatic cancer to be performed in conjunction with breast MRI screening in breast cancer susceptibility gene (BRCA)–positive individuals. An IRB-approved prospective study was conducted. The rapid screening pancreatic MR protocol was designed to be less than 10 min to be performed after a standard breast MRI protocol. Protocol consisted of coronal NT T2 SSFSE, axial NT T2 SSFSE and axial NT rFOV FOCUS DWI, and axial T1. Images were acquired with the patient in the same prone position of breast MRI using the built-in body coil. Image quality was qualitatively assessed by two radiologists with 12 and 13 years of MRI experience, respectively. The imaging protocol was modified until an endpoint of five consecutive patients with high-quality diagnostic images were achieved. Signal-to-noise ratio and contrast-to-noise ratio were assessed. The rapid pancreas MR protocol was successfully completed in all patients. Diagnostic image quality was achieved for all patients. Excellent image quality was achieved for low b values; however, image quality at higher b values was more variable. In one patient, a pancreatic neuroendocrine tumor was found and the patient was treated surgically. In four patients, small pancreatic cystic lesions were detected. In one subject, a hepatic mass was identified and confirmed as adenoma by liver MRI. Rapid MR protocol for pancreatic cancer screening is feasible and has the potential to play a role in screening BRCA patients undergoing breast MRI. • Develop and optimize a rapid magnetic resonance imaging (MRI) screening protocol for pancreatic cancer to be performed in conjunction with breast MRI screening in BRCA mutation positive individuals.

Artificial intelligence (AI) has been successful at solving numerous problems in machine perception. In radiology, AI systems are rapidly evolving and show progress in guiding treatment decisions, diagnosing, localizing disease on medical images, and improving radiologists' efficiency. A critical component to deploying AI in radiology is to gain confidence in a developed system's efficacy and safety. The current gold standard approach is to conduct an analytical validation of performance on a generalization dataset from one or more institutions, followed by a clinical validation study of the system's efficacy during deployment. Clinical validation studies are time-consuming, and best practices dictate limited re-use of analytical validation data, so it is ideal to know ahead of time if a system is likely to fail analytical or clinical validation. In this paper, we describe a series of sanity tests to identify when a system performs well on development data for the wrong reasons. We illustrate the sanity tests' value by designing a deep learning system to classify pancreatic cancer seen in computed tomography scans.

Introduction: Oncologic patients who develop chemotherapy-associated liver injury (CALI) secondary to chemotherapy treatment tend to have worse outcomes. Biopsy remains the gold standard for the diagnosis of hepatic steatosis. The purpose of this article is to compare 2 alternatives: Proton-Density-Fat-Fraction (PDFF) MRI and MultiMaterial-Decomposition (MMD) DECT. Materials and Methods: 49 consecutive oncologic patients treated with Chemotherapy underwent abdominal DECT and abdominal MRI within 2 weeks of each other. Two radiologists tracked Regions of Interest independently both in the PDFF fat maps and in the MMD DECT fat maps. Non-parametric exact Wilcoxon signed rank test and Cohen’s K were used to compare the 2 sequences and to evaluate the agreement. Results: There was no statistically significant difference in the fat fraction measured as a continuous value between PDFF and DECT between 2 readers. Within the same imaging method (PDFF) the degree of agreement based on the k coefficient between reader 1 and reader 2 is 0.88 (p-value < 0.05). Similarly, for single-source DECT(ssDECT) the degree of agreement based on the k coefficient between reader 1 and reader 2 is 0.97 (p-value < 0.05). Conclusions: The results of this study demonstrate that the hepatic fat fraction of ssDECT with MMD are not significantly different from PDFF. This could be an advantage in an oncological population that undergoes serial CT scans for follow up of chemotherapy response.

Texture analysis has arisen as a tool to explore the amount of data contained in images that cannot be explored by humans visually. Radiomics is a method that extracts a large number of features from radiographic medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover disease characteristics. The goal of both radiomics and texture analysis is to go beyond size or human-eye based semantic descriptors, to enable the non-invasive extraction of quantitative radiological data to correlate them with clinical outcomes or pathological characteristics. In the latest years there has been a flourishing sub-field of radiology where texture analysis and radiomics have been used in many settings. It is difficult for the clinical radiologist to cope with such amount of data in all the different radiological sub-fields and to identify the most significant papers. The aim of this review is to provide a tool to better understand the basic principles underlining texture analysis and radiological data mining and a summary of the most significant papers of the latest years.

Introduction Chemotherapy prolongs the survival of patients with advanced and metastatic tumors. Since the liver plays an active role in the metabolism of chemotherapy agents, hepatic injury is a common adverse effect. The purpose of this study is to compare a novel quantitative chemical shift encoded magnetic resonance imaging (CSE-MRI) method with conventional T1-weighted In and Out of phase (T1 IOP) MR for evaluating the reproducibility of the methods in an oncologic population exposed to chemotherapy. Materials and methods This retrospective study was approved by the institutional review board with a waiver for informed consent. The study included patients who underwent chemotherapy, no suspected liver iron overload, and underwent upper abdomen MRI. Two radiologists independently draw circular ROIsin the liver parenchyma. The fat fraction was calculated from IOP imaging and measured from IDEAL-IQ fat fraction maps. Two different equations were used to estimate fat with IOP sequences. Intra-class correlation coefficient and repeatability coefficient were estimated to evaluate agreement between two readers on iron level and fat fraction measurement. Results CSE-MRI showed a higher reliability in fat quantification compared with both IOP methods, with a substantially higher inter-reader agreement (0.961 vs 0.372). This has important clinical implications. Conclusion The novel CSE-MRI method described here provides increased reproducibility and confidence in diagnosing hepatic steatosis in a oncologic clinical setting. IDEAL-IQ has been proved to be more reproducible than conventional IOP imaging.

PURPOSE: To investigate the value of second-opinion interpretation of cross-sectional images by subspecialized radiologists to diagnose recurrent pancreatic cancer after surgery. METHODS: The IRB approved and issued a waiver of informed consent for this retrospective study. Initial and second-opinion interpretations of 69 consecutive submitted MRI or CT follow up after pancreatic cancer resection between January 1, 2009 and December 31, 2013 were evaluated by one oncologic imaging radiologist, who was blinded to patient’s clinical details and histopathologic data. The reviewer was asked to classify each interpretation in reference of the diagnosis of PDAC recurrence. It was also recorded if the radiologic interpretation recommended additional imaging studies to confirm recurrence. The diagnosis of recurrence was determined by pathology when available, otherwise by imaging follow up, clinical or laboratory assessments. Cohen’s kappa statistic was used to assess agreement between initial and second-opinion interpretations. The differences between the initial and second-opinion interpretations were examined using McNemar test or Bowker’s test of symmetry. RESULTS: Disagreement on recurrence between the initial report and the second-opinion interpretation was observed in 32% of cases (22/69; k=0.44). Second-opinion interpretations had a higher sensitivity and a higher specificity on recurrence compared to the initial interpretations (0.93 vs 0.75 and 0.90 vs 0.68, respectively), and the difference in specificity was significant (p=0.016). Additional imaging studies were recommended more frequently in the initial interpretation (22% vs 6%, p=0.006). CONCLUSIONS: Our study shows the second-opinion interpretation by subspecialized radiologists improves the detection of pancreatic cancer recurrence after surgical resection.

Rationale and Objectives To determine the impact of second-opinion assessment on cancer staging and patient management in patients with pancreatic ductal adenocarcinoma. Methods and Materials This retrospective study was approved by our institutional review board with a waiver of informed consent. Second-opinion reports between January 1, 2009 and December 31, 2013, alongside outside reports for 65 consecutive cases of biopsy-proven pancreatic adenocarcinomas, were presented in random order to two experienced abdominal surgeons who independently reviewed them blinded to the origin of the report, images of the examinations, and patient identifier. Each surgeon filled in a questionnaire for each report recommending cancer staging and patient management. Recommended patient management and staging were evaluated against reference standards (actual patient management at 6 months following second-opinion assessment, and pathology or other clinical and imaging reference standards at 6 months or longer, respectively) using Cohen kappa. Results Cancer staging differed in 13% (9 of 65) of cases for surgeon 1 and in 18.4% (12 of 65) for surgeon 2. Patient management changed in 38.4% (25 of 65) of cases for surgeon 1 and in 20% (13 of 65) for surgeon 2. When compared to the pathologic staging gold standard, second opinion was correct in 85.7% (six of seven) of the time for both surgeons. Recommended patient management from second-opinion reports showed good agreement with the reference standard (weighted k = 0.6467 [0.4014–0.892] and weighted k = 0.6262 [0.3954–0.857] for surgeon 2). Conclusion Second-opinion review by subspecialized oncologic radiologists can impact patient care, specifically in terms of management decision.

OBJECTIVE To evaluate the accuracy of single-source dual-energy computed tomography (ssDECT) in iodine quantification using various segmentation methods in an ex vivo model. METHODS Ten sausages, injected with variable quantities of iodinated contrast, were inserted into 2 livers and scanned with ssDECT. Material density iodine images were reconstructed. Three radiologists segmented each sausage. Iodine concentration, volume, and absolute quantity were measured. Agreement between the measured and injected iodine was assessed with the concordance correlation coefficient (CCC). Intrareader agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS Air bubbles were observed in sausage (IX). Sausage (X) was within the same view as hyper-attenuating markers used for localization. With IX and X excluded, CCC and ICC were greater than 0.98 and greater than 0.88. When included, CCC and ICC were greater than 0.94 and greater than 0.79. CONCLUSIONS Iodine quantification was reproducible and precise. However, accuracy reduced in sausages consisting of air filled cavities and within the same view as hyperattenuating markers.

PurposeThis study investigates the robustness of quantitative radiomic features derived from computed tomography (CT) images of a novel patient informed 3-D printed phantom, which captures the morphological heterogeneity of tumors and normal tissue observed on CT scans.MethodsUsing a novel voxel-based multi-material three-dimensional (3D) printer, an anthropomorphic phantom that was modeled after diseased tissue seen on 6 patient CT scans was manufactured. Four patients presented with pancreatic adenocarcinoma tumors (PDAC), 1 with non-small cell lung carcinoma (NSCLC) and 1 with advanced stage hepatic cirrhosis. The 5 tumors were segmented, extracted and then imbedded into CT images of the heterogenous portion of the cirrhotic liver. The composite scan of the implanted tumor within the background cirrhotic liver was then 3D printed. The resultant phantom was scanned sequentially, 30 times with a clinical CT scanner using a reference CT protocol. One hundred and four quantitative radiomic features were then extracted from images of each lesion to determine their repeatability. Repeatability of each radiomic feature was evaluated using the within subject coefficient of variation (wCV, %). A feature with a wCV (%) > 10% was considered as being unrepeatable. A subset of the repeatable features that were also found to be prognostic for lung and pancreatic cancers were then assessed for their percent deviation (pDV, %) from reference values. The reference values were those derived from the repeatability portion of this study. The assessment was conducted by re-scanning the phantom with 11 different clinically relevant sets of scanning parameters. Deviation of radiomic features derived from images of each tumor across all sets of scanning parameters was assessed using the percent deviation relative to the reference values.ResultsTwenty nine of the 104 features presented with wCV (%) > 10%. The lack of repeatability was found to depend on tumor type. The only class of radiomic features with a wCV (%) < 10% were those calculated using the neighboring grey level dependence-based matrices (NGLDM). Notably, skewness, first information correlation, cluster shade, Haralick correlation, autocorrelation, busyness, complexity, high gray level zone emphasis, small area high gray level emphasis, large area low gray level emphasis, large area high gray level emphasis, short run high grey level emphasis, and valley radiomic features had wCV (%) values > 10% for select tumors within the phantom. Two radiomic features prognostic for NSCLC, energy and grey level non-uniformity, had pDV’s (%) that exceeded 30% across all scanning techniques. The pDV (%) for the 4 radiomic features prognostic for PDAC tumors depended on tumor type and selected scanning parameter. Application of the lung kernel caused the largest pDV’s (%). Scans acquired with the reduced tube current of 100 mA and reconstructed with the bone kernel yielded pDV’s (%) within ± 10%.ConclusionWe demonstrated the feasibility with which patient informed 3D printed phantoms can be manufactured directly from lesions seen on CT scans, and demonstrate their potential use for the assessment of robust quantitative radiomic features.

RATIONALE AND OBJECTIVES The purpose of this study is to compare image quality, presence and grade of artifacts, signal-to-noise ratio, and apparent diffusion coefficient (ADC) values in pancreatic tissue between high-resolution navigator-triggered (NT) restricted field of view (rFOV) FOCUS single-shot (SS) echo-planar imaging (EPI) diffusion-weighted imaging (DWI) and NT large FOV SS-EPI DWI. MATERIALS AND METHODS Magnetic resonance imaging examinations were performed with GE 3-T systems using a 32-channel body array coil. Seventeen consecutive patients were imaged. A 5-point scale semiquantitative grading system was used to evaluate image quality and general artifacts. Signal-to-noise ratio and ADC were measured in the head, body, and tail of the pancreas. Statistical analysis was performed using Student t test and Wilcoxon signed rank test, with differences considered significant for P value less than 0.05. RESULTS More artifacts were present on large FOV compared with rFOV FOCUS SS-EPI DW images (P < 0.01). Restricted field of view image quality was subjectively better (P < 0.01). No difference in the signal-to-noise ratio was demonstrated between the 2 image datasets. Apparent diffusion coefficient values were significantly lower (P < 0.01) when calculated from rFOV images than large FOV images. CONCLUSIONS Our results demonstrate better image quality and reduced artifacts in rFOV images compared with large FOV DWI. Measurements from ADC maps derived from rFOV DWI show significantly lower ADC values when compared with ADC maps derived from large FOV DWI.

Rationale: Hepatic epithelioid hemangioendothelioma (EHE) is a rare malignant vascular tumor of endothelial origin with a highly variable clinical presentation and natural history. Given its vascular origin, new therapies with inhibitors of vascular endothelial growth factor (VEGF) have been introduced in the treatment of these patients and have shown promising results. Few reports have described the role of 18F-Fluorodeoxyglucose positron emission tomography/contrast-enhanced computed tomography (18F-FDG PET/CT) in the evaluation of this tumor after treatment with anti-angiogenic agents. Our case reports how 18F-FDG PET-CT scan was critical in the assessment of this tumor after treatment with an anti-angiogenic agent, Pazopanib, demonstrating complete metabolic response. Patient concerns: A 30-year-old man with no previous significant medical history presented with pain in the right upper quadrant for over a year. Diagnoses: Multiple hepatic masses were found on abdominal ultrasound. Liver biopsy confirmed the diagnosis of epithelioid hemangioendothelioma. 18F-FDG PET/CT was performed for staging. Multiple FDG-avid hepatic, splenic, and lymph nodes lesions were detected on 18F-FDG PET/CT. A subsequent spleen biopsy confirmed splenic involvement. Immunohistochemistry was positive for CD31, CD34, and ERG, supporting the diagnosis of epithelioid hemangioendothelioma. Interventions: A 1-year cyclophosphamide treatment was provided followed by Pazopanib for 17 months. Outcomes: Six years after the first 18F-FDG PET/CT, 18F-FDG PET/CT performed for restaging demonstrated complete metabolic response to therapy. Follow-up CT demonstrated no interval changes in size of some of the treated lesions. Lesson: 18F-FDG PET/CT is useful for baseline assessment and posttreatment follow-up of this rare cancer.

Background Gastroenteropancreatic neuroendocrine tumors (NETs) are rare entities arising from neuroendocrine cells in the gastroenteric tract and pancreas. The purpose of this article is to present four cases of gastroenteropancreatic NETs that featured a challenging diagnosis. Case presentation We report a case series of four NETs, each with different features. All NETs were suspected based on clinical and biochemical data. The workup of the abnormalities was performed with CT, PET or MRI. Conclusion The diagnosis of NETs is challenging and generally based on clinical manifestations, blood biochemical tests, imaging techniques, and pathology.

A previously healthy 4-year-old girl presented with petechial rash and low platelet count. There were no other symptoms. On abdominal ultrasound, a 4.7-cm heterogeneous mass was demonstrated anterior to the left kidney. An abdominal MRI subsequently performed demonstrated a heterogeneously enhancing mass at the same location extending to the pancreas and spleen. A surgical biopsy of the mass was obtained. Pathology reported a malignant epithelioid neoplasm consistent with pancreatoblastoma. The mass demonstrated intense FDG uptake on PET and an FDG avid retrocaval lymph node.

Rationale Mediastinal nonseminomatous germ cell tumor (NSGCT) is an uncommon entity. Metastatic hepatic sarcomatous transformation is rare. Patient concerns We report a 24-year-old man with no previous related medical history presented with chest pain and left arm numbness. Diagnoses The x-ray showed an anterior mediastinal mass. The chest computed tomography (CT) confirmed the presence of a mildly enhancing mass in the same location, without invasion of any vascular structure. A CT-guided biopsy was performed, revealing a primary mediastinal nonseminomatous germ cell tumor (NSGCT), yolk sac histology, with areas of somatic transformation to malignant nerve sheath tumor. After surgery patient was followed-up with imaging. Two years later a CT scan showed a new hepatic hyper vascular lesion, confirmed by a subsequent magnetic resonance imaging (MRI) and positron emission tomography (PET) scan. A CT-guided biopsy revealed a hepatic metastatic transformation to angiosarcoma of the primitive NSGCT. Interventions The patient went on to received palliative chemotherapy. Outcomes The patient is being followed-up regularly at the outpatient department. Lessons Because of the potential of metastatic sarcoma arising from germ cell tumors, these patients should undergo periodical follow-up, with periodical scans. PET\CT scan might have a role in the follow-up of these patients.

Rationale:Glucagonoma is an uncommon disease but it has been associated with a pattern of symptoms defined as glucagonoma syndrome. These symptoms, if promptly recognized, could help to speed up the diagnosing process.Patient concerns:We report a case of a 68-year-old woman with a pancreatic