Radiology Community Research Articles

Adherence to MRI Protocol Consensus Guidelines in Multiple Sclerosis Patients at Taif Hospitals

Background: multiple sclerosis (MS) is a chronic inflammatory disease that affects the central nervous system (CNS). Its diagnosis is characterized by foci of demyelination, disseminated over time and anatomical space, both clinically and radiologically. Consensus guidelines for the diagnosis of MS have been established to identify the proper sequences and imaging technique. Objective: this study aims to investigate the adherence of Taif hospitals to these consensus guidelines. Method: data were collected from the radiology departments of 3 main hospitals in Taif (King Abdul-Aziz Specialist Hospital, King Faisal Medical Complex, and Al-Hada Hospital for Armed Forces). The standard magnetic resonance imaging (MRI) protocol for MS in each hospital was reviewed using the picture archiving and communication system (PACS). The comparisons were based on the strength of the magnetic field, slice thickness, slice orientation, coverage, and the MR core sequences used. Results: each Taif hospital has its own protocol, which differ from consensus guidelines. The main difference is the hospitals’ lack of 3D sequences. Another difference is the lack of inversion recovery prepared T1 sequences. Finally, for follow-up patients, no contrast administration exists in Taif hospitals. Conclusion: this study shows some major differences in the MS protocols among Taif hospitals. This is probably due to poor awareness of the guidelines in the radiology community. Neuroradiologists at Taif hospitals should ensure the recommended protocol is followed.

Imaging of sarcopenia: old evidence and new insights.

To date, sarcopenia is considered a patient-specific imaging biomarker able to predict clinical outcomes. Several imaging modalities, including dual-energy X-ray absorptiometry (DXA), computed tomography (CT), magnetic resonance (MR), and ultrasound (US), can be used to assess muscle mass and quality and to achieve the diagnosis of sarcopenia. With different extent, all these modalities can provide quantitative data, being thus reproducible and comparable over time. DXA is the one most commonly used in clinical practice, with the advantages of being accurate and widely available, and also being the only radiological tool with accepted cutoff values to diagnose sarcopenia. CT and MR are considered the reference standards, allowing the evaluation of muscle quality and fatty infiltration, but their application is so far mostly limited to research. US has been always regarded as a minor tool in sarcopenia and has never gained enough space. To date, CT is probably the easiest and most promising modality, although limited by the long time needed for muscle segmentation. Also, the absence of validated thresholds for CT measurements of myosteatosis requires that future studies should focus on this point. Radiologists have the great potential of becoming pivotal in the context of sarcopenia. We highly master imaging modalities and know perfectly how to apply them to different organs and clinical scenarios. Similarly, radiologists should master the culture of sarcopenia, and its clinical aspects and relevant implications for patient care. The medical and scientific radiological community should promote specific educational course to spread awareness among professionals. KEY POINTS: • DXA is an accurate, reproducible, and widely available imaging modality to evaluate body composition, being the most commonly used radiological tool to diagnose sarcopenia in clinical practice • CT and MR are the gold standard imaging modalities to assess muscle mass and quality, but no clear cutoff values have been reported to identify sarcopenia, limiting the application of these modalities to research purposes • US has shown to be accurate in the evaluation of muscle trophism, especially in the thigh, but its current application in sarcopenia is limited.

Update of national diagnostic reference levels for adult CT in Switzerland and assessment of radiation dose reduction since 2010.

To update the national diagnostic reference levels (DRLs) for adult CT in Switzerland using dose management software and to compare them to the previous Swiss DRLs from 2010. CT dose data from 14 radiological institutes with a total of 50 CT scanners were collected with locally installed dose management software between 2014 and 2017. Data were assigned to 15 defined master protocols. Data cleaning steps were developed and adjusted individually for each participating institute and protocol. The DRLs for each master protocol were calculated as the 75th percentile of the distribution of the median volume computed tomography dose index (CTDIvol) and dose-length product (DLP) values per CT scanner. In total, 220,269 CT exams were available after data cleaning. Updated DRLs showed a clear trend towards lower doses compared with previous DRLs. The average relative change in the DRLs for CTDIvol was - 30% (0 to - 47%) and - 22% for DLP (+ 20 to - 40%). The largest relative decrease in the DRL for DLP was observed for the cervical spine protocol (- 40%), the two chest protocols (chest, - 37%; and exclusion of pulmonary embolism, - 33%), and the two neck protocols (neck, - 32%; and carotid angiography, - 28%). The DRLs for other protocols, for example the head and the abdomen-pelvis protocol, showed smaller relative changes (- 11% and - 17%). The updated national DRLs are substantially lower than the previous values from 2010, demonstrating technological progress and the efforts of the radiological community to lower CT radiation exposure. • Dose management software allows the establishment of DRLs based on big data. • Updated Swiss DRLs for adult CT are substantially lower compared with those from 2010. • Swiss DRLs are low compared with other national DRLs.

Looking Ahead

HomeRadiology: Artificial IntelligenceVol. 1, No. 6 Next EditorialFree AccessLooking AheadCharles E. Kahn, Jr Charles E. Kahn, Jr Author Affiliations(e-mail: [email protected])Charles E. Kahn, Jr Published Online:Nov 27 2019https://doi.org/10.1148/ryai.2019194003MoreSectionsPDF ToolsImage ViewerAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookTwitterLinked InEmail An investment in knowledge pays the best interest.Benjamin FranklinAs this journal completes its first year of publication, it’s truly a joy to reflect on our progress and to chart our course forward.I’m extremely grateful to our Deputy Editors—William Hsu, PhD, Jayashree Kalpathy-Cramer, PhD, Despina Kontos, PhD, and Ronnie A. Sebro, MD, PhD—for their outstanding guidance in setting the standards for this journal and overseeing the scientific review process. These individuals have given freely of their time to advance the journal. Together with our other Editorial Board members (https://pubs.rsna.org/page/ai/edboard), they have brought thoughtful and wide-ranging scholarship to the task of reviewing the journal’s submitted manuscripts.We have two noteworthy additions to our Editorial Board.Dania Daye, MD, PhD, has joined us as Associate Editor for Social Media. She brings a keen understanding of the power and nuances of various “SoMe” platforms and is working to develop ways to enhance the content and reach of the journal’s social-media offerings.Judy W. Gichoya, MBChB, MS, has joined the journal as Associate Editor and Program Director of our new Trainee Editorial Board. Dr Gichoya will lead the program and provide mentorship to these trainees.The Trainee Editorial Board (TEB) is a new venture for Radiology: Artificial Intelligence, and a new venture for the RSNA, as well. Although RSNA has offered distinguished journalism fellowship programs, our journal sought to do something a little different, and we’re grateful to the RSNA Board and to Dr Jeffrey Klein, our Board Liaison for Publications, for their support.In October, we invited applications from residents and fellows in diagnostic radiology, interventional radiology, and radiation oncology, and from graduate students and postdoctoral fellows in related scientific disciplines (such as medical physics, biomedical informatics, biomedical engineering, and computer science). We’re very proud to announce the inaugural members of the journal’s TEB (https://pubs.rsna.org/page/ai/teb), selected from among more than 80 highly qualified applicants.TEB members will learn about peer review, biostatistics, research design, and journalistic ethics. They’ll review up to six manuscripts per year and receive guidance from Dr Gichoya and from a faculty mentor at their own institution. They’ll also have an opportunity to learn from the other reviews on assigned manuscripts. TEB members will receive recognition on the journal’s masthead, participate in our annual Editorial Board meeting, and join in quarterly teleconferences with the Editor. They’ll also contribute to the journal’s activities such as the editor’s blog, social media, and journal club.We view the TEB as an opportunity to build capacity and to build community. We’ll work to increase the number of members of the radiology and AI communities who have the background and skills to think critically about scientific contributions at the intersection of machine learning and medical imaging. The TEB also provides a venue for our future colleagues to share ideas and get to know one another.On behalf of the entire Editorial Board, I extend our sincere gratitude to the authors, reviewers, and readers of Radiology: Artificial Intelligence and to the dedicated RSNA Publications staff. We extend a warm welcome to the TEB as the newest members of our journal family and will continue to invest in building our profession’s knowledge of AI in radiology.Article HistoryPublished online: Nov 27 2019 FiguresReferencesRelatedDetailsRecommended Articles Congratulations to the 2018 Editorial FellowsRadiology2018Volume: 289Issue: 1pp. 1-2Congratulations to the 2018 Editorial FellowsRadioGraphics2018Volume: 38Issue: 5pp. 1287-1288Diagnosis Please Certificates of Recognition Awarded to Three Individuals and to International and North American Radiology Resident GroupsRadiology2017Volume: 285Issue: 2pp. 336-339RadioGraphics 2021: Continuing the Path of ExcellenceRadioGraphics2021Volume: 41Issue: 1pp. 1-4Diagnosis Please Certificates of Recognition Awarded to Five Individuals and to International and North American Radiology Resident GroupsRadiology2016Volume: 281Issue: 2pp. 329-332See More RSNA Education Exhibits Interventional Radiology Educational Pathways: A 2017 Update, Including Review of 2017 Match Statistics and Key Ways for Students to Maximize Their Exposure to IRDigital Posters2017Incorporating Interventional Radiology into Medical School Curriculum: Report on Year 2 of Establishing a Longitudinal StudyDigital Posters2019Engaging Medical Students in Interventional Radiology: In the Era of the New Integrated IR ResidencyDigital Posters2018 RSNA Case Collection Pulmonary Arteriovenous MalformationRSNA Case Collection2021"Cold" Sentinel Lymph Node in Cutaneous Melanoma RSNA Case Collection2020Autosomal recessive polycystic kidney diseaseRSNA Case Collection2021 Recommended Articles Society of Abdominal Radiology Is Created by a Merger of the Society of Gastrointestinal Radiologists and the Society of Uroradiology: Form Follows FunctionRadiology2012Volume: 265Issue: 2pp. 336-338The RSNA Editorial Fellows: Then and NowRadiology2015Volume: 276Issue: 3pp. 624-631Congratulations to the 2018 Editorial FellowsRadiology2018Volume: 289Issue: 1pp. 1-2 Vol. 1, No. 6 Metrics Downloaded 241 times Altmetric Score

Prospects for the reduction of the patient doses based on the optimization of the CT abdomen protocols for the different types of malignancies

Reducing radiation exposure in computed tomography is a relevant medical task due to the growing number of studies and the lack of generally accepted approaches to their conduct in the radiological community. One way to reduce the effective dose in contrast-enhanced computed tomography of the abdomen is to optimize the protocol of examination, which can include four scans: in the native, arterial, venous and delayed phases. However while providing repeated studies in patients with oncological diseases, it is possible to confine one or two phases, which will allow the radiologist to visualize observed pathological changes and to evaluate the response to the treatment, as well as detect the recurrence in case of the monitoring of the patients. In the present study, two groups were formed on the basis of a sample of 514 patients. In group 1 (control), CTB was performed according to a three- or four-phase protocol. In group 2, the same patients with an interval from 1 to 5.5 months were performed with computed tomography -OBP according to a single or two-phase protocol depending on the degree of vascularization of the tumor tissue and the clinical situation. At the same time, a decrease in the average effective dose in patients in group 2 compared with group 1 was demonstrated by 63% (p<0.05). In all cases, the various pathological changes that characterize the oncological process and were diagnosed with a three- or four-phase protocol were visualized with a single- or two-phase protocol. Thus, the informative value of computed tomography examination did not decrease.

Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement

This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. AI has great potential to increase efficiency and accuracy throughout radiology, but it also carries inherent pitfalls and biases. Widespread use of AI-based intelligent and autonomous systems in radiology can increase the risk of systemic errors with high consequence and highlights complex ethical and societal issues. Currently, there is little experience using AI for patient care in diverse clinical settings. Extensive research is needed to understand how to best deploy AI in clinical practice. This statement highlights our consensus that ethical use of AI in radiology should promote well-being, minimize harm, and ensure that the benefits and harms are distributed among stakeholders in a just manner. We believe AI should respect human rights and freedoms, including dignity and privacy. It should be designed for maximum transparency and dependability. Ultimate responsibility and accountability for AI remains with its human designers and operators for the foreseeable future. The radiology community should start now to develop codes of ethics and practice for AI that promote any use that helps patients and the common good and should block use of radiology data and algorithms for financial gain without those two attributes.

Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement

This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. AI has great potential to increase efficiency and accuracy throughout radiology, but it also carries inherent pitfalls and biases. Widespread use of AI-based intelligent and autonomous systems in radiology can increase the risk of systemic errors with high consequence and highlights complex ethical and societal issues. Currently, there is little experience using AI for patient care in diverse clinical settings. Extensive research is needed to understand how to best deploy AI in clinical practice. This statement highlights our consensus that ethical use of AI in radiology should promote well-being, minimize harm, and ensure that the benefits and harms are distributed among stakeholders in a just manner. We believe AI should respect human rights and freedoms, including dignity and privacy. It should be designed for maximum transparency and dependability. Ultimate responsibility and accountability for AI remains with its human designers and operators for the foreseeable future. The radiology community should start now to develop codes of ethics and practice for AI that promote any use that helps patients and the common good and should block use of radiology data and algorithms for financial gain without those two attributes.

Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement.

This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. AI has great potential to increase efficiency and accuracy throughout radiology, but it also carries inherent pitfalls and biases. Widespread use of AI-based intelligent and autonomous systems in radiology can increase the risk of systemic errors with high consequence and highlights complex ethical and societal issues. Currently, there is little experience using AI for patient care in diverse clinical settings. Extensive research is needed to understand how to best deploy AI in clinical practice. This statement highlights our consensus that ethical use of AI in radiology should promote well-being, minimize harm, and ensure that the benefits and harms are distributed among stakeholders in a just manner. We believe AI should respect human rights and freedoms, including dignity and privacy. It should be designed for maximum transparency and dependability. Ultimate responsibility and accountability for AI remains with its human designers and operators for the foreseeable future. The radiology community should start now to develop codes of ethics and practice for AI that promote any use that helps patients and the common good and should block use of radiology data and algorithms for financial gain without those two attributes. This article is a simultaneous joint publication in Radiology, Journal of the American College of Radiology, Canadian Association of Radiologists Journal, and Insights into Imaging. Published under a CC BY-NC-ND 4.0 license. Online supplemental material is available for this article.

Artificial intelligence and breast screening: French Radiology Community position paper

The objective of this article was to evaluate the evidence currently available about the clinical value of artificial intelligence (AI) in breast imaging. Nine experts from the disciplines involved in breast disease management – including physicists and radiologists – convened a meeting on June 3, 2019 to discuss the evidence for the use of this technology in plenary and focused sessions. Prior to the meeting, the group performed a literature review on predefined topics. This paper presents the consensus reached by this working group on recommendations for the future use of AI in breast screening and related research topics.

Radiologic Considerations and Standardization of Malignant Pleural Mesothelioma Imaging Within Clinical Trials: Consensus Statement from the NCI Thoracic Malignancy Steering Committee – International Association for the Study of Lung Cancer – Mesothelioma Applied Research Foundation Clinical Trials Planning Meeting

Detailed guidelines pertaining to radiological assessment of malignant pleural mesothelioma are currently lacking due to the rarity of the disease, complex morphology, propensity to invade multiple planes simultaneously, and lack of specific recommendations within the radiology community about assessment, reporting, and follow-up. In March 2017, a multidisciplinary meeting of mesothelioma experts was co-sponsored by the National Cancer Institute Thoracic Malignancy Steering Committee, International Association for the Study of Lung Cancer, and the Mesothelioma Applied Research Foundation. One of the outcomes of this conference was the foundation of detailed, multidisciplinary consensus imaging and management guidelines. Here, we present the recommendations for radiologic assessment of malignant pleural mesothelioma in the setting of clinical trial enrollment. We discuss optimization of imaging parameters across modalities, standardized reporting, and response assessment within clinical trials.

Readability of Patient Education Materials From RadiologyInfo.org: Has There Been Progress Over the Past 5 Years?

OBJECTIVE. As patients increasingly turn to the Internet for healthcare information, it is imperative that patient educational materials be written at an appropriate readability level. Although RadiologyInfo.org, a patient education library sponsored by the American College of Radiology (ACR) and Radiological Society of North America, was shown in 2012 to be written at levels too high for the average patient to adequately comprehend, it is unclear if there has been progress made in the past 5 years. The purpose of this study was to provide a 5-year update on the readability of patient education materials from RadiologyInfo.org. MATERIALS AND METHODS. All patient education articles available in 2017 from the ACR and RSNA-sponsored RadiologyInfo.org patient education library were reviewed. We assessed each article for readability using 6 quantitative readability scales: the Flesch-Kincaid (FK) grade level, Flesch Reading Ease, Gunnin-Fog Index, Coleman-Liau Index, Automated Readability Index, and the Simple Measure of Gobbledygook (SMOG). The number of articles with readability ≤ the 8th grade level (average reading ability of US adults) and the 6th-grade level (NIH-recommended level for patient materials) were determined. RESULTS. 131 patient education articles were reviewed. The mean readability grade level was greater than the 11th grade reading level for all readability scales. None of the articles were written at less than the 8th-grade or the 6th-grade levels. CONCLUSION. Although there has been an increasing awareness of the issue of readability of patient educational materials within the radiological community, the patient educational materials within the ACR and RSNA-sponsored RadiologyInfo.org website are still written at levels too high for the average patient. Future efforts should be made to improve the readability of those patient education materials.

Bending the Artificial Intelligence Curve for Radiology: Informatics Tools From ACR and RSNA

Artificial intelligence (AI) will reshape radiology over the coming years. The radiology community has a strong history of embracing new technology for positive change, and AI is no exception. As with any new technology, rapid, successful implementation faces several challenges that will require creation and adoption of new integration technology. Use cases important to real-world application of AI are described, including clinical registries, AI research, AI product validation, and computer assistance for radiology reporting. Furthermore, the informatics technologies required for successful implementation of the use cases are described, including open Computer-Assisted Radiologist Decision Support, ACR Assist, ACR Data Science Institute use cases, common data elements (radelement.org), RadLex (radlex.org), LOINC/RSNA RadLex Playbook (loinc.org), and Radiology Report Templates (radreport.org).

Moving a National Medical Meeting in Response to California’s Anti–Lesbian, Gay, Bisexual, and Transgender Discrimination Travel Ban

As our political landscape becomes more polarized with states creating conflicting laws intended to uphold citizen rights, medical organizations may find themselves involved in conversations and decision making far removed from their professional society missions. Because the Association of University Radiologists (AUR) was in such a position this year, our narrative may benefit other medical organizations, inside and outside of the field of imaging. The AUR mission statement is “to inspire and educate the academic radiology community through collaboration and innovation in teaching, research, management, and leadership.” The AUR’s aspirational vision statement is “We will be an agile, inclusive, collaborative, and creative organization bringing value to patients and their care by enabling radiologists to advance innovation in academic medicine and scholarship.” Although organizations may rarely think about their mission and vision statements once they are created, familiarity with these statements may be highly beneficial when debating the best course for an organization to pursue, particularly when there are competing interests expressed within the group. Inclusion by Exclusion: Response to: “Moving a National Medical Meeting in Response to California’s Anti–Lesbian, Gay, Bisexual, and Transgender Discrimination Travel Ban”Journal of the American College of RadiologyVol. 16Issue 9PreviewThe Association of University Radiologists (AUR) response [1] to the edict forbidding California’s physician scientists from sharing knowledge in jurisdictions with differing viewpoints seems particularly ironic. Full-Text PDF

Use of the Implicit Association Test to Improve Diversity in Radiology

Radiology has a diversity problem. An often cited 2010 study comparing the diversity of radiology residents to the diversity of trainees in other specialties revealed that radiology ranked 17th out of 20 for its representation of women, and 20th out of 20 for its representation of minorities that are underrepresented in medicine [1]. The reasons for gender and racial disparity in radiology are likely multifactorial, and the radiology community has been active recently in trying to determine ways to increase interest in the field among underrepresented groups, particularly women [2-4].

Artificial Intelligence May Cause a Significant Disruption to the Radiology Workforce

The increasingly realistic prospect of artificial intelligence (AI) playing an important role in radiology has been welcomed with a mixture of enthusiasm and anxiousness. A consensus has arisen that AI will support radiologists in the interpretation of less challenging cases, which will give the radiologists more time to focus on the challenging tasks as well as interactions with patients and other clinicians. The possibility of AI replacing a large number of radiologists is generally dismissed by the radiology community. The common arguments include the following: (1) AI will never be able to match radiologists’ performance; (2) radiologists do more than interpret images; (3) even if AI takes over a large portion of the reading tasks, the radiologists’ effort will be shifted toward interactions with patients and other physicians; (4) the FDA would never agree to let machines do the work of radiologist; (5) the issues of legal liability would be insurmountable; and (6) patients would never put complete trust in computer algorithms. In this article, I analyze these arguments in detail. I find a certain level of validity to some of them. However, I conclude that none of the arguments provide sufficient support for the claim that AI will not create a significant disruption in the radiology workforce. Such disruption is a real possibility. Although the radiology specialty has shown an astonishing ability to adapt to the changing technology, the future is uncertain, and an honest, in-depth discussion is needed to guide development of the field.

Practical recommendations for the application of DE 59/2013.

The changes introduced with Council Directive 2013/59/Euratom will require European Member States adapt their regulations, procedures and equipment to the new high standards of radiation safety. These new requirements will have an impact, in particular, on the radiology community (including medical physics experts) and on industry. Relevant changes include new definitions, a new dose limit for the eye lens, non-medical imaging exposures, procedures in asymptomatic individuals, the use and regular review of diagnostic reference levels (including interventional procedures), dosimetric information in imaging systems and its transfer to the examination report, new requirements on responsibilities, the registry and analysis of accidental or unintended exposure and population dose evaluation (based on age and gender distribution). Furthermore, the Directive emphasises the need for justification of medical exposure (including asymptomatic individuals), introduces requirements concerning patient information and strengthens those for recording and reporting doses from radiological procedures, the use of diagnostic reference levels, the availability of dose-indicating devices and the improved role and support of the medical physics experts in imaging.

Pediatric CT radiation exposure: where we were, and where we are now.

Since the turn of the last millennium, the pediatric radiology community has blazed a patient-quality and safety trail in helping to effectively address the public and the news media's concerns about the implications of ionizing radiation from CT scanners in children. As such, this article (1) reviews the potential deleterious effects of ionizing radiation, (2) discusses why limiting radiation exposure in children is so important, (3) tells the history of pediatric CT radiation exposure concerns, (4) explains the interventions that took place to address these concerns and (5) touches on the current school of thought on pediatric CT dose reduction.

Radtools: R utilities for convenient extraction of medical image metadata

The radiology community has adopted several widely used standards for medical image files, including the popular DICOM (Digital Imaging and Communication in Medicine) and NIfTI (Neuroimaging Informatics Technology Initiative) standards. These file formats include image intensities as well as potentially extensive metadata. The NIfTI standard specifies a particular set of header fields describing the image and minimal information about the scan. DICOM headers can include any of >4,000 available metadata attributes spanning a variety of topics. NIfTI files contain all slices for an image series, while DICOM files capture single slices and image series are typically organized into a directory. Each DICOM file contains metadata for the image series as well as the individual image slice. The programming environment R is popular for data analysis due to its free and open code, active ecosystem of tools and users, and excellent system of contributed packages. Currently, many published radiological image analyses are performed with proprietary software or custom unpublished scripts. However, R is increasing in popularity in this area due to several packages for processing and analysis of image files. While these R packages handle image import and processing, no existing package makes image metadata conveniently accessible. Extracting image metadata, combining across slices, and converting to useful formats can be prohibitively cumbersome, especially for DICOM files. We present radtools, an R package for convenient extraction of medical image metadata. Radtools provides simple functions to explore and return metadata in familiar R data structures. For convenience, radtools also includes wrappers of existing tools for extraction of pixel data and viewing of image slices. The package is freely available under the MIT license at GitHub and is easily installable from the Comprehensive R Archive Network.

Deep Learning Convolutional Neural Networks for the Estimation of Liver Fibrosis Severity from Ultrasound Texture.

Diagnosis and staging of liver fibrosis is a vital prognostic marker in chronic liver diseases. Due to the inaccuracies and risk of complications associated with liver core needle biopsy, the current standard for diagnosis, other less invasive methods are sought for diagnosis. One such method that has been shown to correlate well with liver fibrosis is shear wave velocity measured by ultrasound (US) shear wave elastography; however, this technique requires specific software, hardware, and training. A current perspective in the radiology community is that the texture pattern from an US image may be predictive of the stage of liver fibrosis. We propose the use of convolutional neural networks (CNNs), a framework shown to be well suited for real world image interpretation, to test whether the texture pattern in gray scale elastography images (B-mode US with fixed, subject-agnostic acquisition settings) is predictive of the shear wave velocity (SWV). In this study, gray scale elastography images from over 300 patients including 3,500 images with corresponding SWV measurements were preprocessed and used as input to 100 different CNN architectures that were trained to regress shear wave velocity. In this study, even the best performing CNN explained only negligible variation in the shear wave velocity measures. These extensive test results suggest that the gray scale elastography image texture provides little predictive information about shear wave velocity and liver fibrosis.

LI-RADS: a great opportunity not to be missed.

The Liver Imaging Reporting and Data System (LI-RADS) is a widespread comprehensive system for standardising the reporting and data collection of liver imaging to standardise chronic liver disease evaluation. However, the LI-RADS, based on the identification of some categories of lesions by means of a conceptual and nonquantitative probability approach, has many limitations. In fact, recently, the European Association for the Study of the Liver Guidelines regarding the management of hepatocellular carcinoma did not accept the LI-RADS. The aim of this paper was to critically analyse the LI-RADS, focusing on some interesting issues such as the absence of a clear distinction between two different imaging modalities (computed tomography and MRI), the lack of validation of some major features, the assessment of its ancillary features and its complexity. Despite these limitations, the LI-RADS represents a great opportunity for the radiological community. We must not let it escape, but time and experience are necessary for its improvement.