One of the most promising areas of health innovation is the application of artificial intelligence (AI), primarily in medical imaging. This article provides basic definitions of terms such as “machine/deep learning” and analyses the integration of AI into radiology. Publications on AI have drastically increased from about 100–150 per year in 2007–2008 to 700–800 per year in 2016–2017. Magnetic resonance imaging and computed tomography collectively account for more than 50% of current articles. Neuroradiology appears in about one-third of the papers, followed by musculoskeletal, cardiovascular, breast, urogenital, lung/thorax, and abdomen, each representing 6–9% of articles. With an irreversible increase in the amount of data and the possibility to use AI to identify findings either detectable or not by the human eye, radiology is now moving from a subjective perceptual skill to a more objective science. Radiologists, who were on the forefront of the digital era in medicine, can guide the introduction of AI into healthcare. Yet, they will not be replaced because radiology includes communication of diagnosis, consideration of patient’s values and preferences, medical judgment, quality assurance, education, policy-making, and interventional procedures. The higher efficiency provided by AI will allow radiologists to perform more value-added tasks, becoming more visible to patients and playing a vital role in multidisciplinary clinical teams.
BackgroundIn implant dentistry, three-dimensional (3D) imaging can be realised by dental cone beam computed tomography (CBCT), offering volumetric data on jaw bones and teeth with relatively low radiation doses and costs. The latter may explain why the market has been steadily growing since the first dental CBCT system appeared two decades ago. More than 85 different CBCT devices are currently available and this exponential growth has created a gap between scientific evidence and existing CBCT machines. Indeed, research for one CBCT machine cannot be automatically applied to other systems.MethodsSupported by a narrative review, recommendations for justified and optimized CBCT imaging in oral implant dentistry are provided.ResultsThe huge range in dose and diagnostic image quality requires further optimization and justification prior to clinical use. Yet, indications in implant dentistry may go beyond diagnostics. In fact, the inherent 3D datasets may further allow surgical planning and transfer to surgery via 3D printing or navigation. Nonetheless, effective radiation doses of distinct dental CBCT machines and protocols may largely vary with equivalent doses ranging between 2 to 200 panoramic radiographs, even for similar indications. Likewise, such variation is also noticed for diagnostic image quality, which reveals a massive variability amongst CBCT technologies and exposure protocols. For anatomical model making, the so-called segmentation accuracy may reach up to 200 μm, but considering wide variations in machine performance, larger inaccuracies may apply. This also holds true for linear measures, with accuracies of 200 μm being feasible, while sometimes fivefold inaccuracy levels may be reached. Diagnostic image quality may also be dramatically hampered by patient factors, such as motion and metal artefacts. Apart from radiodiagnostic possibilities, CBCT may offer a huge therapeutic potential, related to surgical guides and further prosthetic rehabilitation. Those additional opportunities may surely clarify part of the success of using CBCT for presurgical implant planning and its transfer to surgery and prosthetic solutions.ConclusionsHence, dental CBCT could be justified for presurgical diagnosis, preoperative planning and peroperative transfer for oral implant rehabilitation, whilst striving for optimisation of CBCT based machine-dependent, patient-specific and indication-oriented variables.
Worldwide interest in artificial intelligence (AI) applications is growing rapidly. In medicine, devices based on machine/deep learning have proliferated, especially for image analysis, presaging new significant challenges for the utility of AI in healthcare. This inevitably raises numerous legal and ethical questions. In this paper we analyse the state of AI regulation in the context of medical device development, and strategies to make AI applications safe and useful in the future. We analyse the legal framework regulating medical devices and data protection in Europe and in the United States, assessing developments that are currently taking place. The European Union (EU) is reforming these fields with new legislation (General Data Protection Regulation [GDPR], Cybersecurity Directive, Medical Devices Regulation, In Vitro Diagnostic Medical Device Regulation). This reform is gradual, but it has now made its first impact, with the GDPR and the Cybersecurity Directive having taken effect in May, 2018. As regards the United States (U.S.), the regulatory scene is predominantly controlled by the Food and Drug Administration. This paper considers issues of accountability, both legal and ethical. The processes of medical device decision-making are largely unpredictable, therefore holding the creators accountable for it clearly raises concerns. There is a lot that can be done in order to regulate AI applications. If this is done properly and timely, the potentiality of AI based technology, in radiology as well as in other fields, will be invaluable.Teaching Points• AI applications are medical devices supporting detection/diagnosis, work-flow, cost-effectiveness.• Regulations for safety, privacy protection, and ethical use of sensitive information are needed.• EU and U.S. have different approaches for approving and regulating new medical devices.• EU laws consider cyberattacks, incidents (notification and minimisation), and service continuity.• U.S. laws ask for opt-in data processing and use as well as for clear consumer consent.
Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. Methods: A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. Results: We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way. Conclusions: Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.
We report the results of a survey conducted among ESR members in November and December 2018, asking for expectations about artificial intelligence (AI) in 5–10 years. Of 24,000 ESR members contacted, 675 (2.8%) completed the survey, 454 males (67%), 555 (82%) working at academic/public hospitals. AI impact was mostly expected (≥ 30% of responders) on breast, oncologic, thoracic, and neuro imaging, mainly involving mammography, computed tomography, and magnetic resonance. Responders foresee AI impact on: job opportunities (375/675, 56%), 218/375 (58%) expecting increase, 157/375 (42%) reduction; reporting workload (504/675, 75%), 256/504 (51%) expecting reduction, 248/504 (49%) increase; radiologist’s profile, becoming more clinical (364/675, 54%) and more subspecialised (283/675, 42%). For 374/675 responders (55%) AI-only reports would be not accepted by patients, for 79/675 (12%) accepted, for 222/675 (33%) it is too early to answer. For 275/675 responders (41%) AI will make the radiologist-patient relation more interactive, for 140/675 (21%) more impersonal, for 259/675 (38%) unchanged. If AI allows time saving, radiologists should interact more with clinicians (437/675, 65%) and/or patients (322/675, 48%). For all responders, involvement in AI-projects is welcome, with different roles: supervision (434/675, 64%), task definition (359/675, 53%), image labelling (197/675, 29%). Of 675 responders, 321 (48%) do not currently use AI, 138 (20%) use AI, 205 (30%) are planning to do it. According to 277/675 responders (41%), radiologists will take responsibility for AI outcome, while 277/675 (41%) suggest shared responsibility with other professionals. To summarise, responders showed a general favourable attitude towards AI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.