Explore the vast range of titles available.

The recent explosion of ‘big data’ has ushered in a new era of artificial intelligence (AI) algorithms in every sphere of technological activity, including medicine, and in particular radiology. However, the recent success of AI in certain flagship applications has, to some extent, masked decades-long advances in computational technology development for medical image analysis. In this article, we provide an overview of the history of AI methods for radiological image analysis in order to provide a context for the latest developments. We review the functioning, strengths and limitations of more classical methods as well as of the more recent deep learning techniques. We discuss the unique characteristics of medical data and medical science that set medicine apart from other technological domains in order to highlight not only the potential of AI in radiology but also the very real and often overlooked constraints that may limit the applicability of certain AI methods. Finally, we provide a comprehensive perspective on the potential impact of AI on radiology and on how to evaluate it not only from a technical point of view but also from a clinical one, so that patients can ultimately benefit from it.Key Points• Artificial intelligence (AI) research in medical imaging has a long history• The functioning, strengths and limitations of more classical AI methods is reviewed, together with that of more recent deep learning methods.• A perspective is provided on the potential impact of AI on radiology and on its evaluation from both technical and clinical points of view.

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones.This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.Key points • The incorporation of artificial intelligence (AI) in radiological practice demands increased monitoring of its utility and safety.• Cooperation between developers, clinicians, and regulators will allow all involved to address ethical issues and monitor AI performance.• AI can fulfil its promise to advance patient well-being if all steps from development to integration in healthcare are rigorously evaluated.

Background Computerized decision support systems (CDSS) are believed to have the potential to improve the quality of health care delivery, although results from high quality studies have been mixed. We conducted a systematic review to evaluate whether certain features of prescribing decision support systems (RxCDSS) predict successful implementation, change in provider behaviour, and change in patient outcomes. Methods A literature search of Medline, EMBASE, CINAHL and INSPEC databases (earliest entry to June 2008) was conducted to identify randomized controlled trials involving RxCDSS. Each citation was independently assessed by two reviewers for outcomes and 28 predefined system features. Statistical analysis of associations between system features and success of outcomes was planned. Results Of 4534 citations returned by the search, 41 met the inclusion criteria. Of these, 37 reported successful system implementations, 25 reported success at changing health care provider behaviour, and 5 noted improvements in patient outcomes. A mean of 17 features per study were mentioned. The statistical analysis could not be completed due primarily to the small number of studies and lack of diversity of outcomes. Descriptive analysis did not confirm any feature to be more prevalent in successful trials relative to unsuccessful ones for implementation, provider behaviour or patient outcomes. Conclusion While RxCDSSs have the potential to change health care provider behaviour, very few high quality studies show improvement in patient outcomes. Furthermore, the features of the RxCDSS associated with success (or failure) are poorly described, thus making it difficult for system design and implementation to improve.

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.

Background Pneumocystis jirovecii pneumonia (PJP) can be challenging to diagnose, often requiring bronchoscopy. Since most patients suspected of PJP undergo imaging, we hypothesized that the findings of these studies could help estimate the probability of disease prior to invasive testing. Methods We created a cohort of patients who underwent bronchoscopy specifically to diagnose PJP and conducted a nested case-control study to compare the radiographic features between patients with ( n  = 72) and without ( n  = 288) pathologically proven PJP. We used multivariable logistic regression to identify radiographic features independently associated with PJP. Results Chest x-ray findings poorly predicted the diagnosis of PJP. However, multivariable analysis of CT scan findings found that “increased interstitial markings” (OR 4.3; 95%CI 2.2–8.2), “ground glass opacities” (OR 3.3; 95%CI 1.2–9.1) and the radiologist’s impression of PJP being “possible” (OR 2.0; 95%CI 1.0–4.1) or “likely” (OR 9.3; 95%CI 3.4–25.3) were independently associated with the final diagnosis (c-statistic 0.75). Conclusions Where there is clinical suspicion of PJP, the use of CT scan can help determine the probability of PJP. Identifying patients at low risk of PJP may enable better use of non-invasive testing to avoid bronchoscopy while higher probability patients could be prioritized.

Approximately a year later, because of persistence of symptoms, an abdominal computed tomography (CT) and plain-film abdominal radiographs were performed at our institution. These 2 studies finally revealed an intrauterine device (IUD) adjacent to the sigmoid colon (Figures 2, 3). On follow-up, the patient was surprised, because she had believed that the IUD fell out years ago. A laparotomy was performed, which found the IUD adherent to the wall of the sigmoid colon and surrounded by densely fibrotic tissue. Fortunately, the colon was found to be intact, wim no evidence of perforation. The operation successfully removed the IUD, and the patient went on to have an uneventful postoperative recovery. Uterine perforation with an IUD, colonic migration, and subsequent sequelae was previously described in the medical literature [3,7-9] and poses a diagnostic challenge to radiologists and clinicians with partial or incomplete clinical information. Ordinarily, a patient who reports a \"missing\" IUD is investigated with pelvic ultrasound to visualize the IUD within the uterus. If found to be missing, then subsequent plain abdominal films with multiple views are taken to localize the radiopaque IUD and aid in operative planning for removal [10]. IUD perforation is usually diagnosed through routine follow-up after placement or reports of a \"missing\" string through the external cervical os by the patient or primary care physician. If the IUD is found to be absent, then further investigation with pelvic ultrasound and plain-film abdominal radiographs is warranted. In female patients with abdominal pain, an unreported IUD perforation should be maintained as a diagnostic possibility, independent of whether suggestive clinical history is provided.

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.

Objectives To determine the incidence of infectious complications following ultrasound-guided musculoskeletal interventions performed with a disinfected uncovered ultrasound transducer footprint. Methods Electronic medical records of all patients who underwent an ultrasound-guided musculoskeletal procedure (including injection, calcific lavage, or ganglion cyst aspiration) performed by any of the 14 interventional musculoskeletal radiologists at our institution between January 2013 and December 2018 were retrospectively reviewed to identify procedure site infections. Biopsies and joint aspirations were excluded. The procedures were performed using a disinfected uncovered transducer footprint. First, an automated chart review identified cases with (1) positive answers to the nurse’s post-procedure call, (2) an International Classification of Diseases (ICD) diagnostic code related to a musculoskeletal infection, or (3) an antibiotic prescription within 30 days post-procedure. Then, these cases were manually reviewed for evidence of procedure site infection. Results In total, 6511 procedures were included. The automated chart review identified 3 procedures (2 patients) in which post-procedural fever was reported during the nurse’s post-procedure call, 33 procedures (28 patients) with an ICD code for a musculoskeletal infection, and 220 procedures (216 patients) with an antibiotic prescription within 30 post-procedural days. The manual chart review of these patients revealed no cases of confirmed infection and 1 case (0.015%) of possible site infection. Conclusions The incidence of infectious complications after an ultrasound-guided musculoskeletal procedure performed with an uncovered transducer footprint is extremely low. This information allows radiologists to counsel their patients more precisely when obtaining informed consent. Key Points • Infectious complications after ultrasound-guided musculoskeletal procedures performed with a disinfected uncovered transducer footprint are extremely rare.

Objectives To examine the natural history of incidentally detected pancreatic cysts and whether a simplified MRI protocol without gadolinium is adequate for lesion follow-up. Methods Over a 10-year period, 301-patients with asymptomatic pancreatic cysts underwent follow-up (45 months ± 30). The magnetic resonance imaging (MRI) protocol included axial, coronal T2-weighted images, MR cholangiopancreatographic and fat suppressed T1-weighted sequences before and after gadolinium. Three radiologists independently reviewed the initial MRI, the follow-up studies using first only unenhanced images, then secondly gadolinium-enhanced-sequences. Lesion changes during follow-up were recorded and the added value of gadolinium-enhanced sequences was determined by classifying the lesions into risk categories. Results Three hundred and one patients (1,174 cysts) constituted the study population. Only 35/301 patients (12 %) showed significant lesion change on follow-up. Using multivariate analysis the only independent factor of lesion growth (OR = 2.4; 95 % CI, 1.7–3.3; P  < 0.001) and mural nodule development (OR = 1.9; 95 % CI, 1.1–3.4, P  = 0.03) during follow-up was initial lesion size. No patient with a lesion initial size less than 2 cm developed cancer during follow-up. Intra-observer agreement with and without gadolinium enhancement ranged from 0.86 to 0.97. After consensus review of discordant cases, gadolinium-enhanced sequences demonstrated no added value. Conclusion Most incidental pancreatic cystic lesions did not demonstrate change during follow-up. The addition of gadolinium-enhanced-sequences had no added-value for risk assignment on serial follow-up. Key points • Significant growth of pancreatic cysts occurred in a minority of patients only. • No lesion <2 cm demonstrated any change during the first year of follow-up. • Intra-observer agreement between MR pancreatic protocols with and without gadolinium was excellent . • Gadolinium application had limited value for follow-up of asymptomatic pancreatic cystic lesions.