Comparison of Natural Language Processing Rules-based and Machine-learning Systems to Identify Lumbar Spine Imaging Findings Related to Low Back Pain

Publication date: Available online 28 March 2018
Source:Academic Radiology
Author(s): W. Katherine Tan, Saeed Hassanpour, Patrick J. Heagerty, Sean D. Rundell, Pradeep Suri, Hannu T. Huhdanpaa, Kathryn James, David S. Carrell, Curtis P. Langlotz, Nancy L. Organ, Eric N. Meier, Karen J. Sherman, David F. Kallmes, Patrick H. Luetmer, Brent Griffith, David R. Nerenz, Jeffrey G. Jarvik
Rationale and ObjectivesTo evaluate a natural language processing (NLP) system built with open-source tools for identification of lumbar spine imaging findings related to low back pain on magnetic resonance and x-ray radiology reports from four health systems.Materials and MethodsWe used a limited data set (de-identified except for dates) sampled from lumbar spine imaging reports of a prospectively assembled cohort of adults. From N = 178,333 reports, we randomly selected N = 871 to form a reference-standard dataset, consisting of N = 413 x-ray reports and N = 458 MR reports. Using standardized criteria, four spine experts annotated the presence of 26 findings, where 71 reports were annotated by all four experts and 800 were each annotated by two experts. We calculated inter-rater agreement and finding prevalence from annotated data. We randomly split the annotated data into development (80%) and testing (20%) sets. We developed an NLP system from both rule-based and machine-learned models. We validated the system using accuracy metrics such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).ResultsThe multirater annotated dataset achieved inter-rater agreement of Cohen's kappa > 0.60 (substantial agreement) for 25 of 26 findings, with finding prevalence ranging from 3% to 89%. In the testing sample, rule-based and machine-learned predictions both had comparable average specificity (0.97 and 0.95, respectively). The machine-learned approach had a higher average sensitivity (0.94, compared to 0.83 for rules-based), and a higher overall AUC (0.98, compared to 0.90 for rules-based).ConclusionsOur NLP system performed well in identifying the 26 lumbar spine findings, as benchmarked by reference-standard annotation by medical experts. Machine-learned models provided substantial gains in model sensitivity with slight loss of specificity, and overall higher AUC.



from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2GVojdK

ESTRO ACROP guidelines for target volume definition in the treatment of locally advanced non-small cell lung cancer

Publication date: Available online 28 March 2018
Source:Radiotherapy and Oncology
Author(s): Ursula Nestle, Dirk De Ruysscher, Umberto Ricardi, Xavier Geets, Jose Belderbos, Christoph Pöttgen, Rafal Dziadiuszko, Stephanie Peeters, Yolande Lievens, Coen Hurkmans, Ben Slotman, Sara Ramella, Corinne Faivre-Finn, Fiona McDonald, Farkhad Manapov, Paul Martin Putora, Cécile LePéchoux, Paul Van Houtte
Radiotherapy (RT) plays a major role in the curative treatment of locally advanced non-small cell lung cancer (NSCLC). Therefore, the ACROP committee was asked by the ESTRO to provide recommendations on target volume delineation for standard clinical scenarios in definitive (chemo)radiotherapy (RT) and adjuvant RT for locally advanced NSCLC. The guidelines given here are a result of the evaluation of a structured questionnaire followed by a consensus discussion, voting and writing procedure within the committee. Hence, we provide advice for methods and time-points of diagnostics and imaging before the start of treatment planning and for the mandatory and optional imaging to be used for planning itself. Concerning target volumes, recommendations are given for GTV delineation of primary tumour and lymph nodes followed by issues related to the delineation of CTVs for definitive and adjuvant radiotherapy. In the context of PTV delineation, recommendations about the management of geometric uncertainties and target motion are given. We further provide our opinions on normal tissue delineation and organisational and responsibility questions in the process of target volume delineation. This guideline intends to contribute to the standardisation and optimisation of the process of RT treatment planning for clinical practice and prospective studies.



from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2pN7RUH

Practice patterns of image guided particle therapy in Europe: A 2016 survey of the European Particle Therapy Network (EPTN)

Publication date: Available online 28 March 2018
Source:Radiotherapy and Oncology
Author(s): Alessandra Bolsi, Marta Peroni, Dante Amelio, Alexandru Dasu, Markus Stock, Iuliana Toma-Dasu, Petra Witt Nyström, Aswin Hoffmann
Background and purposeImage guidance is critical in achieving accurate and precise radiation delivery in particle therapy, even more than in photon therapy. However, equipment, quality assurance procedures and clinical workflows for image-guided particle therapy (IGPT) may vary substantially between centres due to a lack of standardization. A survey was conducted to evaluate the current practice of IGPT in European particle therapy centres.Material and methodsIn 2016, a questionnaire was distributed among 19 particle therapy centres in 12 European countries. The questionnaire consisted of 30 open and 37 closed questions related to image guidance in the general clinical workflow, for moving targets, current research activities and future perspectives of IGPT.ResultsAll centres completed the questionnaire. The IGPT methods used by the 10 treating centres varied substantially. The 9 non-treating centres were in the process to introduce IGPT. Most centres have developed their own IGPT strategies, being tightly connected to their specific technical implementation and dose delivery methods.ConclusionsInsight into the current clinical practice of IGPT in European particle therapy centres was obtained. A variety in IGPT practices and procedures was confirmed, which underlines the need for harmonisation of practice parameters and consensus guidelines.



from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2J5kraG

Susceptibility-weighted magnetic resonance imaging of cerebrovascular sequelae after radiotherapy for pediatric brain tumors

Publication date: Available online 28 March 2018
Source:Radiotherapy and Oncology
Author(s): Marie A. Neu, Yasemin Tanyildizi, Arthur Wingerter, Nicole Henninger, Khalifa El Malki, Francesca Alt, Barbara Doerr, Heinz Schmidberger, Marcus Stockinger, Wolfgang Wagner, Stefanie Keweloh, Marc A. Brockmann, Alexandra Russo, Joerg Faber
Background and purposeDue to sensitive neuroimaging techniques, cerebrovascular complications such as cerebral microbleeds (CMB) and cerebral cavernous malformations (CCM) are increasingly recognized as considerable late effects after treatment for pediatric brain tumor. The aim of this study was to analyze CMB in a cohort of patients after cranial irradiation therapy for medulloblastoma or other pediatric brain tumors using susceptibility-weighted magnetic resonance imaging (SWI).Materials and methodsForty former pediatric brain tumor patients were enrolled in this prospective cross-sectional study and examined by cranial MRI including SWI sequences. Cerebral microbleeds, clinical symptoms and disability were evaluated.ResultsThirty-six (90%) of the examined individuals (mean follow-up age 22.2 y; mean follow-up time 13.5 y) were affected by CMB. Longer follow-up time and higher craniospinal irradiation doses correlated with higher total lesion count (p < 0.01). Thirteen patients (32.5%) presented with clinical symptoms. Individuals with CMB were more severely disabled than patients without CMB (p < 0.05).ConclusionsCerebrovascular sequelae occur frequently after treatment for pediatric brain tumor. In this study, a remarkable part of pediatric brain tumor patients presents with CMB. As a sign of vascular damage, they can cause clinical symptoms and may correspond to neurocognitive decline. Further studies are needed to standardize MRI protocols and to improve quality of long-term follow-up.



from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2pOQHWK

Is accurate contouring of salivary and swallowing structures necessary to spare them in head and neck VMAT plans?

Publication date: Available online 28 March 2018
Source:Radiotherapy and Oncology
Author(s): Alexander R. Delaney, Max Dahele, Ben J. Slotman, Wilko F.A.R. Verbakel
Background and purposeCurrent standards for organ-at-risk (OAR) contouring encourage anatomical accuracy which can be resource intensive. Certain OARs may be suitable for alternative delineation strategies. We investigated whether simplified salivary and swallowing structure contouring can still lead to good OAR sparing in automated head and neck cancer (HNC) plans.Materials and methodsFor 15 HNC patients, knowledge-based plans (KBPs) using RapidPlan™ were created using: (1) standard clinical contours for all OARs (benchmark-plans), (2) automated knowledge-based contours for the salivary glands, with standard contours for the remaining OARs (SS-plans) and (3) simplified contours (SC-plans) consisting of quick-to-draw tubular structures to account for the oral cavity, salivary glands and swallowing muscles. Individual clinical OAR contours in a RapidPlan™ model were combined to create composite salivary/swallowing structures. These were matched to tube-contours to create SC-plans. All plans were compared based on dose to anatomically accurate clinical OAR contours.ResultsSalivary gland delineation in SS-plans required on average 2 min, compared with 7 min for manual delineation of all tubular-contours. Automated atlas-based contours overlapped with, on average, 71% of clinical salivary gland contours while tube-contours overlapped with 95%/75%/93% of salivary gland/oral cavity/swallowing structure contours. On average, SC-plans were comparable to benchmark-plans and SS-plans, with average differences in composite salivary and swallowing structure dose ≤2 Gy and <1 Gy respectively.ConclusionsSimplified-contours could be created quickly and resulted in clinically acceptable HNC VMAT plans. They can be combined with automated planning to facilitate the implementation of advanced radiotherapy, even when resources are limited.



from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2J5k3sM

The role of shear wave elastography on evaluation of the rigidity changes of corpus cavernosum penis in venogenic erectile dysfunction

Publication date: June 2018
Source:European Journal of Radiology, Volume 103
Author(s): Ailin Cui, Lili Xu, Jingjing Mu, Minghui Tong, Cheng Peng, Tingting Wu
ObjectiveThe goal of this study was to evaluate the effect of shear wave elastography (SWE) on the measurement of rigidity changes of penile erection in venogenic erectile dysfunction (ED) and in rigidity alterations of corpus cavernosum penis with age in normal population.MethodsThe study was a prospective analysis of 81 patients referred to the department of urology with complaints of ED as well as 35 healthy volunteers. SWE was performed on the corpus cavernosum penis (CCP) in the flaccid state of healthy group. The patients were divided into venogenic ED (31 patients) and non-vascular ED (neither arterial insufficiency nor venogenic dysfunction) (36 patients) by performing color doppler ultrasonography in association with intracavernous injection (ICI). SWE measurements were performed in CCP in the flaccid state, after 15–20 min and 25–30 min of ICI in both patients groups. Differences between groups were compared.ResultsAge was significantly negatively associated with SWE values of CCP among three groups (healthy group: r = −0.584, p < 0.05; venogenic ED group: r = −0.468, p < 0.05; non-vascular ED group: r = −0.539, p < 0.05). There was no significant difference between the SWE values of three groups in the flaccid state (p > 0.05). The mean SWE values of CCP were significantly lower in the erectile state (15–20 min after ICI) compared with the flaccid state in two patients groups (p < 0.05). The mean SWE values of CCP after ICI increased with time (from 15–20 min to 25–30 min) in patients with venogenic ED (p < 0.05), while the SWE values of CCP after ICI did not statistically significantly differ with time in patients with non-vascular ED (p > 0.05).ConclusionSWE is expected to be a promising approach in terms of the etiological diagnosis of ED and the quantitative evaluation of alternations of penile structures with age.



from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2usIMnw

Resting-state functional connectivity MRI analysis in Human Immunodeficiency Virus and Hepatitis C Virus co-infected subjects. A pilot study

Publication date: May 2018
Source:European Journal of Radiology, Volume 102
Author(s): Simone Corgiolu, Luigi Barberini, Jasjit S. Suri, Antonella Mandas, Diego Costaggiu, Paola Piano, Fulvio Zaccagna, Pierleone Lucatelli, Antonella Balestrieri, Luca Saba
Background and purposeHepatitis C virus (HCV) co-infection's role on cognitive impairment of human immunodeficiency virus (HIV) positive patients is still debated and functional neuroimaging evaluation on this matter is lacking. To provide further insight about HCV's neuro-effects on HIV associated neurocognitive disorder (HAND), we performed a pilot resting state (RS) functional connectivity magnetic resonance imaging (fcMRI) study to find eventual functional connectivity alteration that could reflect HCV related cognitive performance degradation.MethodsEighteen patients (8 HIV, 10 HIV + HCV), either impaired or not impaired, were assessed with RS fcMRI. A statistic model including cognitive testing results was elaborated during data processing to evaluate brain networks alteration related to actual cognitive status in patients.ResultsStatistically significant different patterns of connectivity were found: HCV co-infection modified 17 ROIs' connectivity with 45 supra-threshold connections (p-FDR min 0.0022, max 0.0497). ROIs most involved were right pallidum, brainstem, vermian lobules 1–2 and right cerebellar lobule 10. Graph theory analysis did not demonstrate significant difference between networks, but HCV related modifications at ROI's local level were found, with particular involvement of ROIs of frontal lobe, basal ganglia and cerebellum. Increased fronto-striatal dysfunctions have been already reported as consequences of HCV infection and could reflect an additive effect. Cerebellar alterations are associated with HIV and HAND, but not with HCV infection, suggesting a synergic effect of HCV.ConclusionOur study demonstrates RS fcMRI can help to understand the interactions between HIV and HCV co-infection, and our preliminary results suggest synergic effects of HCV in HIV-related brain functional modification.

Graphical abstract

from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2Ggtnfr