Search

Chronic liver diseases, resulting from chronic injuries of various causes, lead to cirrhosis with life-threatening complications including liver failure, portal hypertension, hepatocellular carcinoma. A key unmet medical need is robust non-invasive biomarkers to predict patient outcome, stratify patients for risk of disease progression and monitor response to emerging therapies. Quantitative imaging biomarkers have already been developed, for instance, liver elastography for staging fibrosis or proton density fat fraction on magnetic resonance imaging for liver steatosis. Yet, major improvements, in the field of image acquisition and analysis, are still required to be able to accurately characterize the liver parenchyma, monitor its changes and predict any pejorative evolution across disease progression. Artificial intelligence has the potential to augment the exploitation of massive multi-parametric data to extract valuable information and achieve precision medicine. Machine learning algorithms have been developed to assess non-invasively certain histological characteristics of chronic liver diseases, including fibrosis and steatosis. Although still at an early stage of development, artificial intelligence-based imaging biomarkers provide novel opportunities to predict the risk of progression from early-stage chronic liver diseases toward cirrhosis-related complications, with the ultimate perspective of precision medicine. This review provides an overview of emerging quantitative imaging techniques and the application of artificial intelligence for biomarker discovery in chronic liver disease. journal article review 2022 Jun 2022 02 09 imported

We submit a summary of some of the activities of the IHU-Strasbourg during the initial period of the COVID-19 pandemic. These were presented as part of the coronnavation effort coordinated by Dr Adrian Park. Three initiatives are presented as follows: Protect-Est App, healthcare worker stress, and converted diving mask for ventilation. Two of the 3 projects are still ongoing, and one (Predoict-Est) has been adopted nationally.

The pandemic of COVID-19 is undoubtedly one of the biggest challenges for modern healthcare. From the beginning of the outbreak, new variants have also proven to be even more contagious, accelerating the spread and stressing the healthcare system. In order to analyze the spatio-temporal aspects of the spread of COVID-19, technology has helped us to track, identify and store information regarding positivity and hospitalization, across different levels of municipal entities. In this work, we present a method for predicting positive and hospitalized cases at the department level of France via a novel multi-scale graph neural network, integrating information from fine-scale geographical zones of a few thousand inhabitants. Our model manages to outperform baselines and deep learning models, presenting low errors in both prediction tasks. We specifically point out the importance of our contribution in predicting hospitalization since hospitals became critical infrastructure during the pandemic. To the best of our knowledge, this is the first work to exploit high-resolution spatio-temporal data in a multi-scale manner, incorporating additional knowledge, such as vaccination rates and population mobility data. We believe that our method may improve future estimations of positivity and hospitalization, which is crucial for healthcare planning.

Colorectal surgery has benefited from advances in precision medicine such as total mesorectal resection, and recently, mesocolon resection, fluorescent perfusion imaging, and fluorescent node mapping. However, these advances fail to address the variable quality of mesocolon dissection and the directed extent of vascular dissection (including high ligation) or pre-resection anastomotic perfusion mapping, thereby impacting anastomotic leaks. We propose a new paradigm of precision image-directed colorectal surgery involving 3D preoperative resection modeling and intraoperative fluoroscopic and fluorescence vascular imaging which better defines optimal dissection planes and vascular vs. anatomy-based resection lines according to our hypothesis. Six pigs had preoperative CT with vascular 3D reconstruction allowing for the preoperative planning of vascular-based dissection. Laparoscopic surgery was performed in a hybrid operating room (OR). Superselective arterial catheterization was performed in branches of the superior mesenteric artery (SMA) or the inferior mesenteric artery (IMA). Intraoperative boluses of 0.1 mg/kg or a continuous infusion of indocyanine green (ICG) (0.01 mg/mL) were administered to guide fluorescent-based sigmoid and ileocecal resections. Fluorescence was assessed using proprietary software at several regions of interest (ROI) in the right and left colon. The approach was feasible and safe. Selective catheterization took an average of 43 min. Both bolus and continuous perfusion clearly marked pre-identified vessels (arteries/veins) and the target colon segment, facilitating precise resections based on the visible vascular anatomy. Quantitative software analysis indicated the optimal resection margin for each ROI. Intra-arterial fluorescent mapping allows visualization of major vascular structures and segmental colonic perfusion. This may help to prevent any inadvertent injury to major vascular structures and to precisely determine perfusion-based resection planes and margins. This could enable tailoring of the amount of colon resected, ensure good anastomotic perfusion, and improve oncological outcomes.

MRI is the reference for the diagnosis of arterial cerebral ischemia, but its role in acute mesenteric ischemia (AMI) is poorly known.To assess MRI detection of early ischemic bowel lesions in a porcine model of arterial AMI.Prospective/cohort.Porcine model of arterial AMI obtained by embolization of the superior mesenteric artery (seven pigs).A 5-T. T1 gradient-echo-weighted-imaging (WI), half-Fourier-acquisition-single-shot-turbo-spin-echo, T2 turbo-spin-echo, true-fast-imaging-with-steady-precession (True-FISP), diffusion-weighted-echo-planar (DWI).T1-WI, T2-WI, and DWI were performed before and continuously after embolization for 6 hours. The signal intensity (SI) of the ischemic bowel was assessed visually and quantitatively on all sequences. The apparent diffusion coefficient (ADC) was assessed.Paired Student's t-test or Mann-Whitney U-test, significance at P 0.05.One pig died from non-AMI-related causes. The remaining pigs underwent a median 5 h53 (range 1 h24-6 h01) of ischemia. Visually, the ischemic bowel showed signal hyperintensity on DWI-b800 after a median 85 (57-276) minutes compared to the nonischemic bowel. DWI-b800 SI significantly increased after 2 hours (+19%) and the ADC significant decrease within the first hour (-31%). The ischemic bowel was hyperintense on precontrast T1-WI after a median 87 (70-171) minutes with no significant quantitative changes over time (P = 0.46-0.93). The ischemic bowel was hyperintense on T2-WI in three pigs with a significant SI increase on True-FISP after 1 and 2 hours.Changes in SI and ADC can be seen early after the onset of arterial AMI with DWI. The value of T2-WI appears to be limited.1 TECHNICAL EFFICACY: Stage 2.

Background:To prospectively evaluate the post-therapeutic aspects of the anal canal on MRI using diffusion tensor imaging (DTI) with tractography in healed perianal fistula.Methods:From September 2019 to August 2021, we included 21 patients referred for follow-up MRI of post-therapeutic anal fistulas. All patients were imaged at 3T including an additional DTI sequence. Our cohort was divided between normal and abnormal sphincters based on T2-weighted images. Fractional anisotropy (FA) and apparent diffusion coefficient (ADC) values were measured for four different muscular components. For the qualitative data, interobserver concordance was determined using quadratic Cohen weighted kappa statistics. For quantitative data we used the Mann-Whitney test for two independent groups and Kruskall-Wallis for several independent groups, with a significance level pResults:The quality score of the 3D representation was satisfying with a substantial interobserver concordance. On the 3D color coded representation, we did not observe any disruption of fibers in the abnormal group. The circular configuration of the internal sphincter and puborectalis was clearly demonstrated. In both groups, there was no significant different between internal sphincter and puborectalis/external sphincters, (ADC values (p=0.38 and p=0.24; FA values (p=0.73 and p=0.27), respectively. Similarly, there was no statistically significant difference in terms of DTI values between the normal and abnormal segments.Conclusion:In healed perianal fistula, minor sequalae (on T2-weighted images) did not appear to modify the DTI parameters or the 3D tractography. However, further studies with larger cohorts are required to confirm the potential clinical impact of this new noninvasive imaging method. Trial registration : This study was approved by the National Ethical Committee (CPP 19 04) and the Institutional Review Board of the US National Library of Medicine -ClinicalTrials.gov Identifier : NCT03881436 ; first posted registration date : 19/03/2019

Artificial intelligence (AI) applications aiming to support surgical decision-making processes are generating novel threats to ethical surgical care. To understand and address these threats, we summarize the main ethical issues that may arise from applying AI to surgery, starting from the Ethics Guidelines for Trustworthy Artificial Intelligence framework recently promoted by the European Commission.A modified Delphi process has been employed to achieve expert consensus.The main ethical issues that arise from applying AI to surgery, described in detail here, relate to human agency, accountability for errors, technical robustness, privacy and data governance, transparency, diversity, non-discrimination, and fairness. It may be possible to address many of these ethical issues by expanding the breadth of surgical AI research to focus on implementation science. The potential for AI to disrupt surgical practice suggests that formal digital health education is becoming increasingly important for surgeons and surgical trainees.A multidisciplinary focus on implementation science and digital health education is desirable to balance opportunities offered by emerging AI technologies and respect for the ethical principles of a patient-centric philosophy.

PURPOSE: To determine if the mean curvature of isophotes (MCI), a standard computer vision technique, can be used to improve detection of chronic obstructive pulmonary disease (COPD) at chest CT. MATERIALS AND METHODS: In this retrospective study, chest CT scans were obtained in 243 patients with COPD and 31 controls (among all 274: 151 women [mean age, 70 years; range, 44–90 years] and 123 men [mean age, 71 years; range, 29–90 years]) from two community practices between 2006 and 2019. A convolutional neural network (CNN) architecture was trained on either CT images or CT images transformed through the MCI algorithm. Separately, a linear classification based on a single feature derived from the MCI computation (called hMCI1) was also evaluated. All three models were evaluated with cross-validation, using precision-macro and recall-macro metrics, that is, the mean of per-class precision and recall values, respectively (the latter being equivalent to balanced accuracy). RESULTS: Linear classification based on hMCI1 resulted in a higher recall-macro relative to the CNN trained and applied on CT images (0.85 [95% CI: 0.84, 0.86] vs 0.77 [95% CI: 0.75, 0.79]) but with a similar reduction in precision-macro (0.66 [95% CI: 0.65, 0.67] vs 0.77 [95% CI: 0.75, 0.79]). The CNN model trained and applied on MCI-transformed images had a higher recall-macro (0.85 [95% CI: 0.83, 0.87] vs 0.77 [95% CI: 0.75, 0.79]) and precision-macro (0.85 [95% CI: 0.83, 0.87] vs 0.77 [95% CI: 0.75, 0.79]) relative to the CNN trained and applied on CT images. CONCLUSION: The MCI algorithm may be valuable toward the automated detection and diagnosis of COPD on chest CT scans as part of a CNN-based pipeline or with stand-alone features. Keywords: Chronic Obstructive Pulmonary Disease, Quantification, Lung, CT Supplemental material is available for this article. See also the invited commentary by Vannier in this issue. © RSNA, 2021

PurposeThe objective of this study was to build and validate a radiomic signature to predict early a poor outcome using baseline and 2-month evaluation CT and to compare it to the RECIST1·1 and morphological criteria defined by changes in homogeneity and borders.MethodsThis study is an ancillary study from the PRODIGE-9 multicentre prospective study for which 491 patients with metastatic colorectal cancer (mCRC) treated by 5-fluorouracil, leucovorin and irinotecan (FOLFIRI) and bevacizumab had been analysed. In 230 patients, computed texture analysis was performed on the dominant liver lesion (DLL) at baseline and 2 months after chemotherapy. RECIST1·1 evaluation was performed at 6 months. A radiomic signature (Survival PrEdiction in patients treated by FOLFIRI and bevacizumab for mCRC using contrast-enhanced CT TextuRe Analysis (SPECTRA) Score) combining the significant predictive features was built using multivariable Cox analysis in 120 patients, then locked, and validated in 110 patients. Overall survival (OS) was estimated with the Kaplan-Meier method and compared between groups with the logrank test. An external validation was performed in another cohort of 40 patients from the PRODIGE 20 Trial.ResultsIn the training cohort, the significant predictive features for OS were: decrease in sum of the target liver lesions (STL), (adjusted hasard-ratio(aHR)=13·7, p=1·93×10–7), decrease in kurtosis (ssf=4) (aHR=1·08, p=0·001) and high baseline density of DLL, (aHR=0·98, p0·02 had a lower OS in the training cohort (pConclusionA radiomic signature (combining decrease in STL, density and computed texture analysis of the DLL) at baseline and 2-month CT was able to predict OS, and identify good responders better than RECIST1.1 criteria in patients with mCRC treated by FOLFIRI and bevacizumab as a first-line treatment. This tool should now be validated by further prospective studies.Trial registrationClinicaltrial.gov identifier of the PRODIGE 9 study: NCT00952029.Clinicaltrial.gov identifier of the PRODIGE 20 study: NCT01900717.

Purpose To evaluate the safety and efficacy of percutaneous transarterial embolization (PTAE) for the treatment of spontaneous soft-tissue hematomas (SSTHs) and identify variables predictive of short-term outcome. Materials and Methods Between 2011 and 2017, the outcome was retrospectively analyzed for 112 patients (mean age ± standard deviation, 72 years ± 14; range, 28-92 years), including 65 women (mean age, 73 years ± 12.7; range, 39-92 years) and 47 men (mean age, 70 years ± 14.9; range, 28-91 years), with SSTH treated with PTAE. Thirty-day mortality, technical and clinical success, simplified acute physiology score (SAPS) II, anticoagulation, embolic agent, hematoma volume and location, serum hemoglobin level, hemodynamic instability, and presence of active bleeding at CT and/or angiography were recorded. Clinical success was defined as cessation of bleeding as determined by hemodynamic stability and/or serum hemoglobin level stabilization after PTAE. Univariable and multivariable analyses were performed by using a Cox model to identify variables associated with time to death. Results Mortality rate was 26.8% (30 of 112 patients), angiographic success rate was 95.5% (107 of 112 patients), and clinical success rate was 83% (93 of 112 patients). For surviving patients, mean SAPS II was 19.6 ± 7.1 (range, 13-31) and mean hematoma volume was 862 cm3 ± 618 (range, 238-1887 cm3). For deceased patients, mean SAPS II was 42 ± 13.2 (range, 18-63) and mean hematoma volume was 1419 cm3 ± 788 (range, 251-3492 cm3). SAPS II (P < .001), hematoma volume (P = .01), and retroperitoneal location (P = .01) were independently associated with fatal outcome. Conclusion Percutaneous transarterial embolization is effective for the emergency treatment of spontaneous soft-tissue hematomas. Simplified acute physiology score II, hematoma volume, and retroperitoneal location are predictors of short-term outcome. © RSNA, 2019 Online supplemental material is available for this article.

Background Radiological preoperative assessment of endometrial cancer (EC) is in some cases not precise enough and its performances improvement could lead to a clinical benefit. Radiomics is a recent field of application of artificial intelligence (AI) in radiology. Aims To investigate the contribution of radiomics on the radiological preoperative assessment of patients with EC; and to establish a simple and reproducible AI Quality Score applicable to Machine Learning and Deep Learning studies. Methods We conducted a systematic review of current literature including original articles that studied EC through imaging-based AI techniques. Then, we developed a novel Simplified and Reproducible AI Quality score (SRQS) based on 10 items which ranged to 0 to 20 points in total which focused on clinical relevance, data collection, model design and statistical analysis. SRQS cut-off was defined at 10/20. Results We included 17 articles which studied different radiological parameters such as deep myometrial invasion, lympho-vascular space invasion, lymph nodes involvement, etc. One article was prospective, and the others were retrospective. The predominant technique was magnetic resonance imaging. Two studies developed Deep Learning models, while the others machine learning ones. We evaluated each article with SRQS by 2 independent readers. Finally, we kept only 7 high-quality articles with clinical impact. SRQS was highly reproducible (Kappa = 0.95 IC 95% [0.907–0.988]). Conclusion There is currently insufficient evidence on the benefit of radiomics in EC. Nevertheless, this field is promising for future clinical practice. Quality should be a priority when developing these new technologies.

Objective: To develop consensus definitions of image-guided surgery, computer-assisted surgery, hybrid operating room, and surgical navigation systems. Summary Background Data: The use of minimally invasive procedures has increased tremendously over the past 2 decades, but terminology related to image-guided minimally invasive procedures has not been standardized, which is a barrier to clear communication. Methods: Experts in image-guided techniques and specialized engineers were invited to engage in a systematic process to develop consensus definitions of the key terms listed above. The process was designed following review of common consensus-development methodologies and included participation in 4 online surveys and a post-surveys face-to-face panel meeting held in Strasbourg, France. Results: The experts settled on the terms computer-assisted surgery and intervention, image-guided surgery and intervention, hybrid operating room, and guidance systems and agreed-upon definitions of these terms, with rates of consensus of more than 80% for each term. The methodology used proved to be a compelling strategy to overcome the current difficulties related to data growth rates and technological convergence in this field. Conclusions: Our multidisciplinary collaborative approach resulted in consensus definitions that may improve communication, knowledge transfer, collaboration, and research in the rapidly changing field of image-guided minimally invasive techniques., This study gathered experts with multiple backgrounds and used common consensus-development methodologies in 2 phases (online and panel meeting). It resulted in definitions that may improve communication, knowledge transfer, collaboration, and research in the field of image-guided minimally invasive techniques.

International audience; Research in medical imaging has yet to do to achieve precision oncology. Over the past 30 years, only the simplest imaging biomarkers (RECIST, SUV,…) have become widespread clinical tools. This may be due to our inability to accurately characterize tumors and monitor intratumoral changes in imaging. Artificial intelligence, through machine learning and deep learning, opens a new path in medical research because it can bring together a large amount of heterogeneous data into the same analysis to reach a single outcome. Supervised or unsupervised learning may lead to new paradigms by identifying unrevealed structural patterns across data. Deep learning will provide human-free, undefined upstream, reproducible, and automated quantitative imaging biomarkers. Since tumor phenotype is driven by its genotype and thus indirectly defines tumoral progression, tumor characterization using machine learning and deep learning algorithms will allow us to monitor molecular expression noninvasively, anticipate therapeutic failure, and lead therapeutic management. To follow this path, quality standards have to be set: standardization of imaging acquisition as it has been done in the field of biology, transparency of the model development as it should be reproducible by different institutions, validation, and testing through a high-quality process using large and complex open databases and better interpretability of these algorithms.

Purpose To compare changes in inferior vena cava (IVC) filter positional parameters from insertion to removal and examine how they affect retrievability amongst various filter types. Materials and methods A total of 447 patients (260 men, 187 women) with a mean age of 55 years (range: 13–91 years) who underwent IVC filter retrieval between 2007–2014 were retrospectively included. Post-insertion and pre-retrieval angiographic studies were assessed for filter tilt, migration, strut wall penetration and retrieval outcomes. ANCOVA and multiple logistic regression models were used to analyze factors affecting retrieval success. Pairwise comparisons between filter types were performed. Results Of 488 IVC filter retrieval attempts, 94.1% were ultimately successful. The ALN filter had the highest mean absolute value of tilt (5.6 degrees), the Optease filter demonstrated the largest mean migration (−8.0 mm) and the Bard G2 filter showed highest mean penetration (5.2 mm). Dwell time of 0–90 days (OR, 11.1; P = 0.01) or 90–180 days (OR, 2.6; P = 0.02), net tilt of 10–15 degrees (OR 8.9; P = 0.05), caudal migration of −10 to 0 mm (OR, 3.46; P = 0.03) and penetration less than 3 mm (OR, 2.6; P = 0.01) were positive predictors of successful retrievability. Higher odds of successful retrieval were obtained for the Bard G2X, Bard G2 and Cook Celect when compared to the ALN and Cordis Optease filters. Conclusion Shorter dwell time, lower mean tilt, caudal migration and less caval wall penetration are positive predictors of successful IVC filter retrieval.

Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada.

Background Negative-margin status is a prognostic indicator for long-term survival following curative intent resection for pancreatic adenocarcinoma. Patients at increased risk for positive-margin resections may benefit from neoadjuvant chemotherapy prior to resection. Methods We retrospectively analyzed preoperative computed-tomography (CT) scans in 108 consecutive patients that underwent curative intent resection for a resectable pancreatic ductal adenocarcinoma from 2009 to 2016 in two academic hospitals. Two radiologists independently staged the tumor, including tumor location, size, and tumor-to-superior mesenteric/portal vein (SMV/PV) contact. Uni and multivariate analysis were performed to identify independent predictors of an R1 resection. Results Twenty-nine patients had an R1 resection (26.9%). Tumor size, location, and presence of tumor-to-SMV/PV contact were significantly associated with an R1 resection. In multivariate analysis, the independent parameters associated with resection status were: tumor size (R2 = 9.7), and tumor location (neck R2 = 6.6; pancreaticoduodenal interface R2 = 4.4; uncinate process R2 = 4.1), but not tumor-to-SMV/PV contact (R2 = 0.1, p = 0.7). A simple CT score was built based on tumor size and location. Patients with an R0 resectability score ≥3, i.e. patients with tumor size ≥30 mm (except when tumor location is at the pancreatico-duodenal interface) or patients with tumor size ≥20 mm AND tumor located in the uncinate process or neck, were at high-risk of an R1 resection (AUC, 0.82; sensitivity, 79%; specificity, 76%). This score also showed good diagnostic performances for predicting an R1 resection involving the medial resection margin only (AUC, 0.85). Conclusions A simple score based on tumor location and size can accurately predict patients at high-risk of an R1 resection.

Backgrounds Patients with a pancreatic cancer amenable to surgery still have a poor prognosis and high risk of post-operative recurrence. We aimed to assess the value of quantitative imaging biomarkers using computed-tomography (CT) texture analysis to evaluate the pathologic tumor aggressiveness and predict disease-free survival (DFS) in patients with resectable pancreatic adenocarcinoma. Methods We retrospectively performed attenuation measurements and texture analysis on the portal-venous phase of the pre-operative CT scan of 99 patients that underwent resection of a pancreatic ductal adenocarcinoma in two university hospitals. Tumor attenuation parameters included: mean attenuation value of the whole tumor (WHOLE-AV), and of the most hypoattenuating area within the tumor (CENTRAL-AV). Tumor heterogeneity parameters included: standard deviation, entropy, skewness, and kurtosis. Results Tumor attenuation parameters showed significant association with the tumor differentiation grade (CENTRAL-AV, Odds ratio (OR) 0.968, 95% confidence interval (CI) 0.94–0.998) and lymph node invasion (WHOLE-AV, OR 0.886, CI 0.823–0.955). Variables associated with early-recurrence were: lymph node ratio (R2 = 0.15), kurtosis (R2 = 0.08), and CENTRAL-AV (R2 = 0.04). Lymph node ratio (Hazard ratio (HR) 1.02), and CENTRAL-AV (HR 0.98) were independently associated with shorter DFS. Patients with CENTRAL-AV Conclusion Tumors that are more hypoattenuating on the portal-venous phase on CT scan are potentially more aggressive with higher tumor grade, greater lymph node invasion, and shorter DFS.

The current unprecedented coronavirus 2019 (COVID-19) crisis has accelerated and enhanced e-learning solutions. During the so-called transition phase, efforts were made to reorganize surgical services, reschedule elective surgical procedures, surgical research, academic education, and careers to optimize results. The intention to switch to e-learning medical education is not a new concern. However, the current crisis triggered an alarm to accelerate the transition. Efforts to consider e-learning as a teaching and training method for medical education have proven to be efficient. For image-guided therapies, the challenge requires more effort since surgical skills training is combined with image interpretation training, thus the challenge is to cover quality educational content with a balanced combination of blended courses (online/onsite). Several e-resources are currently available in the surgical scenario; however, further efforts to enhance the current system are required by accelerating the creation of new learning solutions to optimize complex surgical education needs in the current disrupted environment.

Background & Aims Primary sclerosing cholangitis (PSC) has a variable, often progressive, course. Magnetic resonance cholangiography (MRC) is used in the diagnosis of PSC. Magnetic resonance risk scoring systems, called Anali without and with gadolinium, are used to predict disease progression, determined by radiologic factors. We aimed to assess the prognostic value of Anali scores in patients with PSC and validate our findings in a separate cohort. Methods We performed a retrospective study of patients with large-duct PSC (internal cohort, 119 patients in France; external cohort, 119 patients in Canada, Italy, and the United Kingdom). All the first-available MRC results were reviewed by 2 radiologists and the Anali scores were calculated as follows: Anali without gadolinium = (1× dilatation of intrahepatic bile ducts) + (2× dysmorphy) + (1× portal hypertension); Anali with gadolinium = (1× dysmorphy) + (1× parenchymal enhancement heterogeneity). The primary end point was survival without liver transplantation or cirrhosis decompensation. The prognostic value of Anali scores was assessed by Cox regression modeling. Results During a total of 549 patient-years for the internal cohort and 497 patient-years for the external cohort, we recorded 2 and 8 liver transplantations, 4 and 3 liver-related deaths, and 26 and 25 cirrhosis decompensations, respectively. In the univariate analysis, factors associated with survival without liver transplantation or cirrhosis decompensation in the internal cohort were as follows: serum levels of bilirubin, aspartate aminotransferase, alanine aminotransferase, γ-glutamyl transferase, alkaline phosphatase, albumin, and Anali scores. Anali scores without and with gadolinium identified patients' survival without liver transplantation or cirrhosis decompensation with a c-statistic of 0.89 (95% CI, 0.84–0.95) and 0.75 (95% CI, 0.64–0.87), respectively. Independent prognostic factors identified by multivariate analysis were Anali scores and bilirubinemia. The prognostic value of Anali scores was confirmed in the external cohort. Conclusions In internal and external cohorts, we found that Anali scores, determined from MRC, were associated with outcomes of patients with PSC. These scores might be used as prognostic factors.

Background Response Evaluation Criteria in Solid Tumors (RECIST) are used to assess tumour shrinkage after cytotoxic chemotherapy, but may be inadequate for efficacy evaluation of anti-angiogenic therapies. Aims This study aimed to identify novel radiologic tumour response criteria based on early changes in tumour size and density, observed on computed tomography (CT), in patients with colorectal liver metastases (CRLM) treated with bevacizumab-containing chemotherapy. Methods CT of 71 and 68 CRLM patients treated with bevacizumab and non-bevacizumab-based regimens, respectively, were retrospectively reviewed. Tumour size, tumour density, and tumour-to-liver density (TTLD) ratio were determined at baseline and at first restaging. We tested their correlation with progression-free (PFS) and overall survival (OS) using the log-rank test. Results In the bevacizumab group, neither RECIST response nor tumour density variation was correlated with PFS or OS. In contrast, PFS and OS were significantly longer in patients with tumour size reduction ≥15% (RECIST−15%) and/or decrease in TTLD ratio not exceeding −10% (TTLD−10%) than in patients who did not reach any of those criteria, in univariate and multivariate analysis. Only size-response criteria predicted clinical outcome in the non-bevacizumab group. Conclusions This study highlights new quantitative CT criteria that may early predict the efficacy of bevacizumab in CRLM patients.

OBJECTIVE. The objective of our study was to evaluate whether shear wave elastography (SWE) can differentiate benign from malignant microcalcifications of the breast when detected on ultrasound (US). SUBJECTS AND METHODS. Between February 9, and June 23, 2016, 74 patients with mammographically detected suspicious microcalcifications underwent breast US. When microcalcifications were identified on US, stiffness was assessed using SWE. Biopsy was subsequently performed under US guidance using a 10-gauge vacuum-assisted needle. Qualitative and quantitative elastography results were compared between benign and malignant calcifications as well as between pure ductal carcinoma in situ and lesions with invasive components using the Mann-Whitney U test. ROC curves were created to assess the performance of SWE in detecting malignancy and invasive components. RESULTS. Twenty-nine groups of microcalcifications in 29 patients were identified on US. At pathology, 16 groups were benign and 13 were malignant. Stiffness of malignant calcifications was significantly higher than that of the benign ones (p = 0.0004). The AUC, sensitivity, specificity, negative predictive value, positive predictive value, and accuracy of SWE for the diagnosis of malignancy were 0.89, 69%, 100%, 80%, 100%, and 86%, respectively, and for detection of an invasive component were 0.93, 75%, 100%, 75%, 100%, and 85%. CONCLUSION. SWE has the potential to differentiate benign from malignant micro-calcifications of the breast when detected on US with high specificity.

BackgroundInnovation in healthcare is the practical application of new concepts, ideas, processes or technologies into clinical practice. Despite its necessity and potential to improve care in measurable ways, there are several issues related to patient safety, high costs, high failure rates and limited adoption by end-users. This mixed-method study aims to explore the role of simulation as a potential testbed for diminishing the risks, pitfalls and resources associated with development and implementation of medical innovations.MethodsSubject-matter experts consisting of physicians, engineers, scientists and industry leaders participated in four semistructured teleconferences each lasting up to 2 hours each. Verbal data were transcribed verbatim, coded and categorised according to themes using grounded theory, and subsequently synthesised into a conceptual framework. Panelists were then invited to complete an online survey, ranking the (1) current use and (2) potential effectiveness of simulation-based technologies and techniques for evaluating and facilitating the product life cycle pathway. This was performed for each theme of the previously generated conceptual framework using a Likert scale of 1 (no effectiveness) to 9 (highest possible effectiveness) and then segregated according to various forms of simulation.ResultsOver 100 hours of data were collected and analysed. After 7 rounds of inductive data analysis, a conceptual framework of the product life cycle was developed. This framework helped to define and characterise the product development pathway. Agreement between reviewers for inclusion of items after the final round of analysis was 100%. A total of 7 themes were synthesised and categorised into 3 phases of the pathway: ‘design and development’, ‘implementation and value creation’ and ‘product launch’. Strong discrepancies were identified between the current and potential roles of simulation in each phase. Simulation was felt to have the strongest potential role for early prototyping, testing for safety and product quality and testing for product effectiveness and ergonomics.ConclusionsSimulation has great potential to fulfil several unmet needs in healthcare innovation. This framework can be used to help guide innovators and channel resources appropriately. The ultimate goal is a structured, well-defined process that will result in a product development outcome that has the greatest potential to succeed.

International audience; BACKGROUND:Severe spontaneous soft tissue hematomas (SSTH) are usually treated with transcatheter arterial embolization (TAE) although only limited retrospective studies exist evaluating this treatment option. The aim of this study was to systematically assess the efficacy and safety of TAE for the management of SSTH.METHODS:Medline, EMBASE, PubMed and Cochrane Library were searched from inception to July 2017 using MeSH headings and a combination of keywords. Eligibility was restricted to original studies with patients suffering from SSTH treated with TAE. Patients with traumatic hematomas or who were treated with solely conservative or surgical management were excluded. For each publication, clinical success based on the control of the bleed, rebleeding rates and complications (including mortality) was collected, as well as technical details.RESULTS:Sixty-three studies met the inclusion criteria, with an aggregate total of 267 patients. Follow-up extended from 1 day to 10 years. Bleeding was mainly localized to the iliopsoas (n = 113/267, 42.3%) and anterior abdominal wall (n = 145/266, 54.7%). When information was available, 81.0% (n = 158/195) of patients were on anticoagulant therapy prior to the bleeding episode. Initial stabilization with control of the bleed was obtained in 93.1% (n = 242 patients, n = 60 studies). The most common embolic materials were coils (n = 129, 54.4%). Rebleeding was reported in 25 patients (9.4%). Only two embolization complications were reported (0.7%). The 30-day mortality was 22.7% (n = 42/1857).CONCLUSION:TAE represents a safe and effective procedure in the management of SSTH. We present a management algorithm based on these data, but further studies are needed to address the knowledge gap.

Radiomics is an emerging field which extracts quantitative radiology data from medical images and explores their correlation with clinical outcomes in a non-invasive manner. This review aims to assess whether radiomics is a useful and reproducible method for clinical management of hepatocellular carcinoma (HCC) by reviewing the strengths and weaknesses of current radiomics literature pertaining specifically to HCC. From an initial set of 48 articles recovered through database searches, 23 articles were retained to be included in this review after full screening. Among these 23 studies, 7 used a radiomics approach in magnetic resonance imaging (MRI). Only two studies applied radiomics to positron emission tomography-computed tomography (PET-CT). In the remaining 14 articles, a radiomics analysis was performed on computed tomography (CT). Eight studies dealt with the relationship between biological signatures and imaging findings, and can be classified as radiogenomic studies. For each study included in our review, we computed a Radiomics Quality Score (RQS) as proposed by Lambin et al. We found that the RQS (mean +/- standard deviation) was 8.35 +/- 5.38 (out of a possible maximum value of 36). Although these scores are fairly low, and radiomics has not yet reached clinical utility in HCC, it is important to underscore the fact that these early studies pave the way for the radiomics field with a focus on HCC. Radiomics is still a very young field, and is far from being mature, but it remains a very promising technology for the future for developing adequate personalized treatment as a non-invasive approach, for complementing or replacing tumor biopsies, as well as for developing novel prognostic biomarkers in HCC patients.

This Editorial comment refers to the article "Medical students' attitude towards artificial intelligence: a multicenter survey," Pinto Dos Santos D, et al Eur Radiol 2018. KEY POINTS: • Medical students are not well informed of the potential consequences of AI in radiology. • The fundamental principles of AI-as well as its application in medicine-must be taught in medical schools. • The radiologist specialty must actively reflect on how to validate, approve, and integrate AI algorithms into our clinical practices.

The last few decades have witnessed tremendous technological developments in image-based biomarkers for tumor quantification and characterization. Initially limited to manual one- and two-dimensional size measurements, image biomarkers have evolved to harness developments not only in image acquisition technology but also in image processing and analysis algorithms. At the same time, clinical validation remains a major challenge for the vast majority of these novel techniques, and there is still a major gap between the latest technological developments and image biomarkers used in everyday clinical practice. Currently, the imaging biomarker field is attracting increasing attention not only because of the tremendous interest in cutting-edge therapeutic developments and personalized medicine but also because of the recent progress in the application of artificial intelligence (AI) algorithms to large-scale datasets. Thus, the goal of the present article is to review the current state of the art for image biomarkers and their use for characterization and predictive quantification of solid tumors. Beginning with an overview of validated imaging biomarkers in current clinical practice, we proceed to a review of AI-based methods for tumor characterization, such as radiomics-based approaches and deep learning.Key Points• Recent years have seen tremendous technological developments in image-based biomarkers for tumor quantification and characterization.• Image-based biomarkers can be used on an ongoing basis, in a non-invasive (or mildly invasive) way, to monitor the development and progression of the disease or its response to therapy.• We review the current state of the art for image biomarkers, as well as the recent developments in artificial intelligence (AI) algorithms for image processing and analysis.

International audience; Purpose: To assess the usefulness of a second biopsy when the first one was inconclusive in patients with a liver nodule found during the follow-up for chronic liver disease.Materials and methods: Among 381 patients (544 nodules) included in a prospective study designed to evaluate the accuracy of imaging for the diagnosis of small hepatocellular carcinoma (HCC) in chronic liver disease, 254 nodules were biopsied. The following histological results were considered as conclusive: HCC, dysplastic or regenerative nodule, and other identified tumors (benign or malignant). For nodules with inconclusive results (e.g. fibrosis or no definite focal lesion), a second biopsy was suggested, but was not mandatory.Results: A total of 242 patients (194 men, 48 women; mean age, 61.9 +/- 9.5 [SD]; range: 40.2-89.0years) with 254 nodules underwent a first biopsy. Mean nodule diameter was 19.2 +/- 5.4mm (range: 10-33mm). The first biopsy was conclusive in 189/254 nodules (74.4%): 157 HCCs (83.1%), 11 regenerative nodules (5.8%), 10 dysplastic nodules (5.3%), 3 cholangiocarcinomas (1.6%), and 8 other tumors (4.2%). Among the 65 nodules for which the first biopsy was inconclusive, a second biopsy was performed for 17 nodules in 16 patients within 6 months of the first one. It was conclusive in 13/17 nodules (76.5%): 10 HCCs (76.9%), 2 dysplastic nodules (15.4%), and 1 other tumor (7.7%). In 4/17 nodules (23.5%), no definitive diagnosis could be provided.Conclusion: The diagnostic yield of a second biopsy of a suspicious lesion suggestive of HCC in chronic liver disease is not decreased compared to the first one. Repeated biopsy after a first negative one could be an alternative option to the follow-up of patients with chronic liver disease. (C) 2018 Societe francaise de radiologie

Summary Purpose To evaluate whether enhancement of breast cancer on pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) as evaluated semi-quantitatively using computer-aided detection (CAD) is associated with response to neo-adjuvant chemotherapy. Materials and methods A total of 84 women, (mean age, 51 ± 10 [SD] years; range: 30–73 years) with 84 breast cancers who underwent MRI before neo-adjuvant chemotherapy were included in this retrospective study. The proportion of each type of signal intensity-time curve (SITC) (type 1: persistent; type 2: plateau; Type 3: washout) within the tumor volume was quantified semi-automatically using a CAD system (Aegis®, Sentinelle medical, Toronto, Canada) and was compared to histological features of the tumors and to pathological response to neo-adjuvant chemotherapy. Results Pathological complete response was obtained in 29 patients (35%). Proportion of SITC type 1 was greater in non-responders (P = 0.019) while proportion of SITC type 3 was greater in responders (P = 0.04). Sensitivity, specificity, and accuracy of proportion of SITC type 1 for the identification of incomplete response on pathology were 42% (95% CI: 29%–56%), 90% (95% CI: 73%–98%), and 59% (95% CI: 48%–70%), respectively. Conclusion Proportion of SITC type 1 (persistent) in breast cancers on pre-treatment MRI as semi-automatically quantified using a CAD system is associated with absence of pathological complete response to neo-adjuvant chemotherapy with good specificity.

Purpose To evaluate whether features from texture analysis of breast cancers were associated with pathologic complete response (pCR) after neoadjuvant chemotherapy and to explore the association between texture features and tumor subtypes at pretreatment magnetic resonance (MR) imaging. Materials and Methods Institutional review board approval was obtained. This retrospective study included 85 patients with 85 breast cancers who underwent breast MR imaging before neoadjuvant chemotherapy between April 10, 2008, and March 12, 2015. Two-dimensional texture analysis was performed by using software at T2-weighted MR imaging and contrast material-enhanced T1-weighted MR imaging. Quantitative parameters were compared between patients with pCR and those with non-pCR and between patients with triple-negative breast cancer and those with non-triple-negative cancer. Multiple logistic regression analysis was used to determine independent parameters. Results Eighteen tumors (22%) were triple-negative breast cancers. pCR was achieved in 30 of the 85 tumors (35%). At univariate analysis, mean pixel intensity with spatial scaling factor (SSF) of 2 and 4 on T2-weighted images and kurtosis on contrast-enhanced T1-weighted images showed a significant difference between triple-negative breast cancer and non-triple-negative breast cancer (P = .009, .003, and .001, respectively). Kurtosis (SSF, 2) on T2-weighted images showed a significant difference between pCR and non-pCR (P = .015). At multiple logistic regression, kurtosis on T2-weighted images was independently associated with pCR in non-triple-negative breast cancer (P = .033). A multivariate model incorporating T2-weighted and contrast-enhanced T1-weighted kurtosis showed good performance for the identification of triple-negative breast cancer (area under the receiver operating characteristic curve, 0.834). Conclusion At pretreatment MR imaging, kurtosis appears to be associated with pCR to neoadjuvant chemotherapy in non-triple-negative breast cancer and may be a promising biomarker for the identification of triple-negative breast cancer. © RSNA, 2017.

Background Percutaneous cholecystostomy (PC) is an alternative among high-risk surgical patients or those with multiple comorbidities, but its indications have not been clearly established in the literature. The aim of this paper is to provide the reader with an updated review of the literature summarizing what is known on this topic. Data sources We reviewed articles from 1979 to 2016 using the PubMed/Medline Database on PC and especially those evaluating this option as a bridge to surgery. Conclusions There remains a paucity of randomized control trials to ascertain the use of PC as a definitive treatment for acute cholecystitis. In most studies, more than 50% of patients underwent PC as a definite treatment without subsequent cholecystectomy. A newer avenue of endoscopic ultrasound is also discussed, which requires rigorous trials to determine its appropriate applications.

Purpose To evaluate the associations among mathematical modeling with the use of magnetic resonance (MR) imaging-based texture features and deep myometrial invasion (DMI), lymphovascular space invasion (LVSI), and histologic high-grade endometrial carcinoma. Materials and Methods Institutional review board approval was obtained for this retrospective study. This study included 137 women with endometrial carcinomas measuring greater than 1 cm in maximal diameter who underwent 1.5-T MR imaging before hysterectomy between January 2011 and December 2015. Texture analysis was performed with commercial research software with manual delineation of a region of interest around the tumor on MR images (T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced images and apparent diffusion coefficient maps). Areas under the receiver operating characteristic curve and diagnostic performance of random forest models determined by using a subset of the most relevant texture features were estimated and compared with those of independent and blinded visual assessments by three subspecialty radiologists. Results A total of 180 texture features were extracted and ultimately limited to 11 features for DMI, 12 for LVSI, and 16 for high-grade tumor for random forest modeling. With random forest models, areas under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were estimated at 0.84, 79.3%, 82.3%, 81.0%, 76.7%, and 84.4% for DMI; 0.80, 80.9%, 72.5%, 76.6%, 74.3%, and 79.4% for LVSI; and 0.83, 81.0%, 76.8%, 78.1%, 60.7%, and 90.1% for high-grade tumor, respectively. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of visual assessment for DMI were 84.5%, 82.3%, 83.2%, 77.7%, and 87.8% (reader 3). Conclusion The mathematical models that incorporated MR imaging-based texture features were associated with the presence of DMI, LVSI, and high-grade tumor and achieved equivalent accuracy to that of subspecialty radiologists for assessment of DMI in endometrial cancers larger than 1 cm. However, these preliminary results must be interpreted with caution until they are validated with an independent data set, because the small sample size relative to the number of features extracted may have resulted in overfitting of the models.

Objectives Liver volumetry has emerged as an important tool in clinical practice. Liver volume is assessed primarily via organ segmentation of computed tomography (CT) and magnetic resonance imaging (MRI) images. The goal of this paper is to provide an accessible overview of liver segmentation targeted at radiologists and other healthcare professionals. Methods Using images from CT and MRI, this paper reviews the indications for liver segmentation, technical approaches used in segmentation software and the developing roles of liver segmentation in clinical practice. Results Liver segmentation for volumetric assessment is indicated prior to major hepatectomy, portal vein embolisation, associating liver partition and portal vein ligation for staged hepatectomy (ALPPS) and transplant. Segmentation software can be categorised according to amount of user input involved: manual, semi-automated and fully automated. Manual segmentation is considered the “gold standard” in clinical practice and research, but is tedious and time-consuming. Increasingly automated segmentation approaches are more robust, but may suffer from certain segmentation pitfalls. Emerging applications of segmentation include surgical planning and integration with MRI-based biomarkers. Conclusions Liver segmentation has multiple clinical applications and is expanding in scope. Clinicians can employ semi-automated or fully automated segmentation options to more efficiently integrate volumetry into clinical practice. Teaching points • Liver volume is assessed via organ segmentation on CT and MRI examinations. • Liver segmentation is used for volume assessment prior to major hepatic procedures. • Segmentation approaches may be categorised according to the amount of user input involved. • Emerging applications include surgical planning and integration with MRI-based biomarkers. Electronic supplementary material The online version of this article (doi:10.1007/s13244-017-0558-1) contains supplementary material, which is available to authorised users.

Lymphadenopathy continues to be a common problem to radiologists and treating physicians because of the difficulty in confidently categorizing a node as being benign or malignant using standard diagnostic techniques. The goal of our research was to assess whether magnetic resonance (MR) spectroscopy contains the necessary information to allow differentiation of benign from malignant lymph nodes in an in-vitro approach using a modern pattern recognition method. Tissue samples from a tissue bank were analyzed on a nuclear magnetic resonance (NMR) spectrometer. A total of 69 samples were studied. The samples included a wide variety of malignant and benign etiologies. Using 45 samples, we initially created a model which was able to predict if a certain spectrum originates from benign or malignant lymph nodes using a pattern-recognition technique which takes into account the entire magnetic spectrum rather than single peaks alone. The remaining 24 samples were blindly loaded in the model to assess its performance. We obtained an excellent accuracy in differentiating benign and malignant lymphadenopathy using the model. It correctly differentiated as malignant or benign, in a blinded fashion, all of the malignant samples (13 of 13) and 10 out of the 11 benign samples. We thus showed that magnetic spectroscopy is able to differentiate benign from malignant causes of lymphadenopathy. Additional experiments were performed to verify that the differentiating abilities of our model were not due to differential tissue decay in between benign and malignant tissues. If future experiments demonstrate that a similar approach could be executed with standard MR imaging, this technique could be useful as a problem-solving tool when assessing lymphadenopathy in general. Alternatively, our in-vitro technique could also be useful to pathologists faced with indeterminate pathologies of the lymph nodes after validating our results with a larger sample size.

Background Adverse events (AEs) in acute care hospitals are frequent and associated with significant morbidity, mortality, and costs. Measuring AEs is necessary for quality improvement and benchmarking purposes, but current detection methods lack in accuracy, efficiency, and generalizability. The growing availability of electronic health records (EHR) and the development of natural language processing techniques for encoding narrative data offer an opportunity to develop potentially better methods. The purpose of this study is to determine the accuracy and generalizability of using automated methods for detecting three high-incidence and high-impact AEs from EHR data: a) hospital-acquired pneumonia, b) ventilator-associated event and, c) central line-associated bloodstream infection. Methods This validation study will be conducted among medical, surgical and ICU patients admitted between 2013 and 2016 to the Centre hospitalier universitaire de Sherbrooke (CHUS) and the McGill University Health Centre (MUHC), which has both French and English sites. A random 60% sample of CHUS patients will be used for model development purposes (cohort 1, development set). Using a random sample of these patients, a reference standard assessment of their medical chart will be performed. Multivariate logistic regression and the area under the curve (AUC) will be employed to iteratively develop and optimize three automated AE detection models (i.e., one per AE of interest) using EHR data from the CHUS. These models will then be validated on a random sample of the remaining 40% of CHUS patients (cohort 1, internal validation set) using chart review to assess accuracy. The most accurate models developed and validated at the CHUS will then be applied to EHR data from a random sample of patients admitted to the MUHC French site (cohort 2) and English site (cohort 3)—a critical requirement given the use of narrative data –, and accuracy will be assessed using chart review. Generalizability will be determined by comparing AUCs from cohorts 2 and 3 to those from cohort 1. Discussion This study will likely produce more accurate and efficient measures of AEs. These measures could be used to assess the incidence rates of AEs, evaluate the success of preventive interventions, or benchmark performance across hospitals.

Purpose: To evaluate rectal cancer volumetry in predicting initial neoadjuvant chemotherapy response. Materials and Methods: Sixteen consecutive patients who underwent neoadjuvant chemotherapy (CX) before chemoradiotherapy (CRT) and surgery were enrolled in this retrospective study. Tumor volume was evaluated at the first magnetic resonance imaging (MRI), after CX and after CRT. Tumor volume regression (TVR) and downstaging were compared with histological results according to Tumor Regression Grade (TRG) to assess CX and CRT response, respectively. Results: The mean tumor volume was 132 cm3 ± 166 before and 56 cm3 ± 71 after CX. TVR after CX was significantly different between patients with poor histologic response (TRG1/2) and those with good histologic response (TRG3/4) (P = 0.001). An optimal cutoff of TVR >68% (area under the curve [AUC]: 0.9, 95% confidence interval [CI]: 0.65–0.98, P = 0.0001) to predict good histology response after CX was assessed by receiver operating characteristic curve. According to previous data and this study, we defined 70% as the best cutoff values according to sensitivity (86%), specificity (100%) of TVR for predicting good histology response. In contradistinction, MRI downstaging was associated with TRG only after CRT (P = 0.04). Conclusion: Our pilot study showed that MRI volumetry can predict early histological response after CX and before CRT. MRI volumetry could help the clinician to distinguish early responders in order to aid appropriate individually tailored therapies. J. Magn. Reson. Imaging 2013;38:726–732. © 2012 Wiley Periodicals, Inc.